{ "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": 56.12763214111328, "learning_rate": 0.0, "loss": 1.1767829656600952, "step": 1 }, { "epoch": 0.0005192107995846313, "grad_norm": 57.369110107421875, "learning_rate": 2.1551724137931035e-08, "loss": 1.0944066047668457, "step": 2 }, { "epoch": 0.000778816199376947, "grad_norm": 63.55313491821289, "learning_rate": 4.310344827586207e-08, "loss": 1.1246483325958252, "step": 3 }, { "epoch": 0.0010384215991692627, "grad_norm": 56.83699417114258, "learning_rate": 6.465517241379311e-08, "loss": 1.1804063320159912, "step": 4 }, { "epoch": 0.0012980269989615785, "grad_norm": 63.08527374267578, "learning_rate": 8.620689655172414e-08, "loss": 1.1267154216766357, "step": 5 }, { "epoch": 0.001557632398753894, "grad_norm": 53.82145690917969, "learning_rate": 1.0775862068965518e-07, "loss": 1.0712288618087769, "step": 6 }, { "epoch": 0.0018172377985462098, "grad_norm": 63.40141677856445, "learning_rate": 1.2931034482758622e-07, "loss": 1.119071364402771, "step": 7 }, { "epoch": 0.0020768431983385254, "grad_norm": 53.909332275390625, "learning_rate": 1.5086206896551727e-07, "loss": 1.149245262145996, "step": 8 }, { "epoch": 0.002336448598130841, "grad_norm": 54.72301483154297, "learning_rate": 1.7241379310344828e-07, "loss": 1.1055127382278442, "step": 9 }, { "epoch": 0.002596053997923157, "grad_norm": 52.17654800415039, "learning_rate": 1.9396551724137932e-07, "loss": 1.156409740447998, "step": 10 }, { "epoch": 0.0028556593977154725, "grad_norm": 48.73526382446289, "learning_rate": 2.1551724137931036e-07, "loss": 1.063295602798462, "step": 11 }, { "epoch": 0.003115264797507788, "grad_norm": 54.148555755615234, "learning_rate": 2.3706896551724138e-07, "loss": 1.041365146636963, "step": 12 }, { "epoch": 0.0033748701973001036, "grad_norm": 54.39642333984375, "learning_rate": 2.5862068965517245e-07, "loss": 1.1423689126968384, "step": 13 }, { "epoch": 0.0036344755970924196, "grad_norm": 47.79109191894531, "learning_rate": 2.801724137931035e-07, "loss": 1.0799610614776611, "step": 14 }, { "epoch": 0.003894080996884735, "grad_norm": 42.12434005737305, "learning_rate": 3.0172413793103453e-07, "loss": 1.0654401779174805, "step": 15 }, { "epoch": 0.004153686396677051, "grad_norm": 37.64540481567383, "learning_rate": 3.2327586206896557e-07, "loss": 0.982224702835083, "step": 16 }, { "epoch": 0.004413291796469367, "grad_norm": 35.11069107055664, "learning_rate": 3.4482758620689656e-07, "loss": 1.00788414478302, "step": 17 }, { "epoch": 0.004672897196261682, "grad_norm": 32.787052154541016, "learning_rate": 3.663793103448276e-07, "loss": 0.9813713431358337, "step": 18 }, { "epoch": 0.004932502596053998, "grad_norm": 36.87429428100586, "learning_rate": 3.8793103448275865e-07, "loss": 0.9762959480285645, "step": 19 }, { "epoch": 0.005192107995846314, "grad_norm": 29.375904083251953, "learning_rate": 4.094827586206897e-07, "loss": 0.9345088005065918, "step": 20 }, { "epoch": 0.005451713395638629, "grad_norm": 27.418033599853516, "learning_rate": 4.3103448275862073e-07, "loss": 0.8883498907089233, "step": 21 }, { "epoch": 0.005711318795430945, "grad_norm": 41.07191467285156, "learning_rate": 4.5258620689655177e-07, "loss": 0.9153745174407959, "step": 22 }, { "epoch": 0.005970924195223261, "grad_norm": 58.78077697753906, "learning_rate": 4.7413793103448276e-07, "loss": 0.9257931709289551, "step": 23 }, { "epoch": 0.006230529595015576, "grad_norm": 45.06435012817383, "learning_rate": 4.956896551724138e-07, "loss": 0.8757412433624268, "step": 24 }, { "epoch": 0.006490134994807892, "grad_norm": 46.13261413574219, "learning_rate": 5.172413793103449e-07, "loss": 0.9285770654678345, "step": 25 }, { "epoch": 0.006749740394600207, "grad_norm": 40.79570388793945, "learning_rate": 5.387931034482759e-07, "loss": 0.8356306552886963, "step": 26 }, { "epoch": 0.007009345794392523, "grad_norm": 55.78379440307617, "learning_rate": 5.60344827586207e-07, "loss": 0.7671315670013428, "step": 27 }, { "epoch": 0.007268951194184839, "grad_norm": 23.281293869018555, "learning_rate": 5.81896551724138e-07, "loss": 0.7845706343650818, "step": 28 }, { "epoch": 0.007528556593977154, "grad_norm": 37.595924377441406, "learning_rate": 6.034482758620691e-07, "loss": 0.8437960147857666, "step": 29 }, { "epoch": 0.00778816199376947, "grad_norm": 19.812557220458984, "learning_rate": 6.25e-07, "loss": 0.8211421966552734, "step": 30 }, { "epoch": 0.008047767393561786, "grad_norm": 24.464649200439453, "learning_rate": 6.465517241379311e-07, "loss": 0.8539906740188599, "step": 31 }, { "epoch": 0.008307372793354102, "grad_norm": 25.212980270385742, "learning_rate": 6.68103448275862e-07, "loss": 0.7998757362365723, "step": 32 }, { "epoch": 0.008566978193146417, "grad_norm": 29.691871643066406, "learning_rate": 6.896551724137931e-07, "loss": 0.74427330493927, "step": 33 }, { "epoch": 0.008826583592938734, "grad_norm": 32.41645812988281, "learning_rate": 7.112068965517242e-07, "loss": 0.7662654519081116, "step": 34 }, { "epoch": 0.009086188992731049, "grad_norm": 27.347801208496094, "learning_rate": 7.327586206896552e-07, "loss": 0.7835115194320679, "step": 35 }, { "epoch": 0.009345794392523364, "grad_norm": 24.39205551147461, "learning_rate": 7.543103448275863e-07, "loss": 0.8760180473327637, "step": 36 }, { "epoch": 0.00960539979231568, "grad_norm": 23.65860366821289, "learning_rate": 7.758620689655173e-07, "loss": 0.8508461713790894, "step": 37 }, { "epoch": 0.009865005192107996, "grad_norm": 19.655126571655273, "learning_rate": 7.974137931034484e-07, "loss": 0.7646362781524658, "step": 38 }, { "epoch": 0.010124610591900311, "grad_norm": 14.602331161499023, "learning_rate": 8.189655172413794e-07, "loss": 0.824042797088623, "step": 39 }, { "epoch": 0.010384215991692628, "grad_norm": 19.533180236816406, "learning_rate": 8.405172413793105e-07, "loss": 0.6725217700004578, "step": 40 }, { "epoch": 0.010643821391484943, "grad_norm": 17.35113525390625, "learning_rate": 8.620689655172415e-07, "loss": 0.7098663449287415, "step": 41 }, { "epoch": 0.010903426791277258, "grad_norm": 12.126578330993652, "learning_rate": 8.836206896551724e-07, "loss": 0.7396062612533569, "step": 42 }, { "epoch": 0.011163032191069575, "grad_norm": 27.805156707763672, "learning_rate": 9.051724137931035e-07, "loss": 0.7784627676010132, "step": 43 }, { "epoch": 0.01142263759086189, "grad_norm": 16.87905502319336, "learning_rate": 9.267241379310346e-07, "loss": 0.6987231969833374, "step": 44 }, { "epoch": 0.011682242990654205, "grad_norm": 18.10316276550293, "learning_rate": 9.482758620689655e-07, "loss": 0.654620885848999, "step": 45 }, { "epoch": 0.011941848390446522, "grad_norm": 18.666994094848633, "learning_rate": 9.698275862068966e-07, "loss": 0.6703775525093079, "step": 46 }, { "epoch": 0.012201453790238837, "grad_norm": 21.910228729248047, "learning_rate": 9.913793103448276e-07, "loss": 0.6952446699142456, "step": 47 }, { "epoch": 0.012461059190031152, "grad_norm": 11.424211502075195, "learning_rate": 1.0129310344827586e-06, "loss": 0.6862825155258179, "step": 48 }, { "epoch": 0.01272066458982347, "grad_norm": 20.637399673461914, "learning_rate": 1.0344827586206898e-06, "loss": 0.7090197801589966, "step": 49 }, { "epoch": 0.012980269989615784, "grad_norm": 12.04622745513916, "learning_rate": 1.0560344827586208e-06, "loss": 0.5988951325416565, "step": 50 }, { "epoch": 0.0132398753894081, "grad_norm": 14.262478828430176, "learning_rate": 1.0775862068965518e-06, "loss": 0.6203463077545166, "step": 51 }, { "epoch": 0.013499480789200415, "grad_norm": 11.28053092956543, "learning_rate": 1.0991379310344828e-06, "loss": 0.5593292713165283, "step": 52 }, { "epoch": 0.013759086188992731, "grad_norm": 14.986948013305664, "learning_rate": 1.120689655172414e-06, "loss": 0.5909141302108765, "step": 53 }, { "epoch": 0.014018691588785047, "grad_norm": 16.949548721313477, "learning_rate": 1.142241379310345e-06, "loss": 0.7122017741203308, "step": 54 }, { "epoch": 0.014278296988577362, "grad_norm": 22.012622833251953, "learning_rate": 1.163793103448276e-06, "loss": 0.7256337404251099, "step": 55 }, { "epoch": 0.014537902388369679, "grad_norm": 14.750531196594238, "learning_rate": 1.185344827586207e-06, "loss": 0.6556919813156128, "step": 56 }, { "epoch": 0.014797507788161994, "grad_norm": 18.829668045043945, "learning_rate": 1.2068965517241381e-06, "loss": 0.7798358201980591, "step": 57 }, { "epoch": 0.015057113187954309, "grad_norm": 29.86578369140625, "learning_rate": 1.2284482758620691e-06, "loss": 0.8214295506477356, "step": 58 }, { "epoch": 0.015316718587746626, "grad_norm": 21.798738479614258, "learning_rate": 1.25e-06, "loss": 0.5696253776550293, "step": 59 }, { "epoch": 0.01557632398753894, "grad_norm": 20.015850067138672, "learning_rate": 1.271551724137931e-06, "loss": 0.6652724742889404, "step": 60 }, { "epoch": 0.015835929387331256, "grad_norm": 15.268033981323242, "learning_rate": 1.2931034482758623e-06, "loss": 0.6687959432601929, "step": 61 }, { "epoch": 0.016095534787123573, "grad_norm": 11.465410232543945, "learning_rate": 1.3146551724137933e-06, "loss": 0.5621124505996704, "step": 62 }, { "epoch": 0.016355140186915886, "grad_norm": 11.002583503723145, "learning_rate": 1.336206896551724e-06, "loss": 0.6158288717269897, "step": 63 }, { "epoch": 0.016614745586708203, "grad_norm": 23.351486206054688, "learning_rate": 1.3577586206896553e-06, "loss": 0.6900712251663208, "step": 64 }, { "epoch": 0.01687435098650052, "grad_norm": 19.239316940307617, "learning_rate": 1.3793103448275862e-06, "loss": 0.6904399394989014, "step": 65 }, { "epoch": 0.017133956386292833, "grad_norm": 8.982855796813965, "learning_rate": 1.4008620689655172e-06, "loss": 0.5500361919403076, "step": 66 }, { "epoch": 0.01739356178608515, "grad_norm": 10.42712116241455, "learning_rate": 1.4224137931034484e-06, "loss": 0.5941383242607117, "step": 67 }, { "epoch": 0.017653167185877467, "grad_norm": 13.277571678161621, "learning_rate": 1.4439655172413794e-06, "loss": 0.7626602053642273, "step": 68 }, { "epoch": 0.01791277258566978, "grad_norm": 11.641759872436523, "learning_rate": 1.4655172413793104e-06, "loss": 0.5581159591674805, "step": 69 }, { "epoch": 0.018172377985462097, "grad_norm": 12.384684562683105, "learning_rate": 1.4870689655172416e-06, "loss": 0.5750356912612915, "step": 70 }, { "epoch": 0.018431983385254414, "grad_norm": 12.690411567687988, "learning_rate": 1.5086206896551726e-06, "loss": 0.5319701433181763, "step": 71 }, { "epoch": 0.018691588785046728, "grad_norm": 10.662824630737305, "learning_rate": 1.5301724137931034e-06, "loss": 0.5427800416946411, "step": 72 }, { "epoch": 0.018951194184839044, "grad_norm": 19.095687866210938, "learning_rate": 1.5517241379310346e-06, "loss": 0.6233627200126648, "step": 73 }, { "epoch": 0.01921079958463136, "grad_norm": 12.89486312866211, "learning_rate": 1.5732758620689656e-06, "loss": 0.6487718820571899, "step": 74 }, { "epoch": 0.019470404984423675, "grad_norm": 11.958884239196777, "learning_rate": 1.5948275862068968e-06, "loss": 0.5092940330505371, "step": 75 }, { "epoch": 0.01973001038421599, "grad_norm": 9.644646644592285, "learning_rate": 1.6163793103448278e-06, "loss": 0.5453559160232544, "step": 76 }, { "epoch": 0.01998961578400831, "grad_norm": 16.251482009887695, "learning_rate": 1.6379310344827587e-06, "loss": 0.6846215724945068, "step": 77 }, { "epoch": 0.020249221183800622, "grad_norm": 12.237055778503418, "learning_rate": 1.65948275862069e-06, "loss": 0.5398324728012085, "step": 78 }, { "epoch": 0.02050882658359294, "grad_norm": 9.08665943145752, "learning_rate": 1.681034482758621e-06, "loss": 0.659212589263916, "step": 79 }, { "epoch": 0.020768431983385256, "grad_norm": 10.898070335388184, "learning_rate": 1.7025862068965517e-06, "loss": 0.6317132115364075, "step": 80 }, { "epoch": 0.02102803738317757, "grad_norm": 10.96983814239502, "learning_rate": 1.724137931034483e-06, "loss": 0.5344484448432922, "step": 81 }, { "epoch": 0.021287642782969886, "grad_norm": 8.71694564819336, "learning_rate": 1.745689655172414e-06, "loss": 0.5043845772743225, "step": 82 }, { "epoch": 0.021547248182762203, "grad_norm": 27.129955291748047, "learning_rate": 1.7672413793103449e-06, "loss": 0.6784875988960266, "step": 83 }, { "epoch": 0.021806853582554516, "grad_norm": 10.170581817626953, "learning_rate": 1.788793103448276e-06, "loss": 0.5735191702842712, "step": 84 }, { "epoch": 0.022066458982346833, "grad_norm": 10.8073148727417, "learning_rate": 1.810344827586207e-06, "loss": 0.6046783328056335, "step": 85 }, { "epoch": 0.02232606438213915, "grad_norm": 16.003704071044922, "learning_rate": 1.831896551724138e-06, "loss": 0.670263409614563, "step": 86 }, { "epoch": 0.022585669781931463, "grad_norm": 14.035204887390137, "learning_rate": 1.8534482758620693e-06, "loss": 0.5671132802963257, "step": 87 }, { "epoch": 0.02284527518172378, "grad_norm": 20.562623977661133, "learning_rate": 1.8750000000000003e-06, "loss": 0.6119136214256287, "step": 88 }, { "epoch": 0.023104880581516097, "grad_norm": 13.668643951416016, "learning_rate": 1.896551724137931e-06, "loss": 0.5238128900527954, "step": 89 }, { "epoch": 0.02336448598130841, "grad_norm": 8.811748504638672, "learning_rate": 1.9181034482758622e-06, "loss": 0.5545532703399658, "step": 90 }, { "epoch": 0.023624091381100727, "grad_norm": 20.551401138305664, "learning_rate": 1.9396551724137932e-06, "loss": 0.6199004650115967, "step": 91 }, { "epoch": 0.023883696780893044, "grad_norm": 10.208572387695312, "learning_rate": 1.9612068965517242e-06, "loss": 0.603948712348938, "step": 92 }, { "epoch": 0.024143302180685357, "grad_norm": 8.470540046691895, "learning_rate": 1.982758620689655e-06, "loss": 0.49160143733024597, "step": 93 }, { "epoch": 0.024402907580477674, "grad_norm": 18.488231658935547, "learning_rate": 2.004310344827586e-06, "loss": 0.5283989906311035, "step": 94 }, { "epoch": 0.02466251298026999, "grad_norm": 15.914358139038086, "learning_rate": 2.025862068965517e-06, "loss": 0.5142050385475159, "step": 95 }, { "epoch": 0.024922118380062305, "grad_norm": 11.770125389099121, "learning_rate": 2.0474137931034486e-06, "loss": 0.5142949819564819, "step": 96 }, { "epoch": 0.02518172377985462, "grad_norm": 17.857479095458984, "learning_rate": 2.0689655172413796e-06, "loss": 0.5444283485412598, "step": 97 }, { "epoch": 0.02544132917964694, "grad_norm": 15.205316543579102, "learning_rate": 2.0905172413793106e-06, "loss": 0.5781108140945435, "step": 98 }, { "epoch": 0.02570093457943925, "grad_norm": 9.835127830505371, "learning_rate": 2.1120689655172416e-06, "loss": 0.5041610598564148, "step": 99 }, { "epoch": 0.02596053997923157, "grad_norm": 14.009139060974121, "learning_rate": 2.1336206896551725e-06, "loss": 0.5114507675170898, "step": 100 }, { "epoch": 0.026220145379023882, "grad_norm": 12.934613227844238, "learning_rate": 2.1551724137931035e-06, "loss": 0.5125044584274292, "step": 101 }, { "epoch": 0.0264797507788162, "grad_norm": 12.63524055480957, "learning_rate": 2.1767241379310345e-06, "loss": 0.5749733448028564, "step": 102 }, { "epoch": 0.026739356178608516, "grad_norm": 11.484814643859863, "learning_rate": 2.1982758620689655e-06, "loss": 0.5696791410446167, "step": 103 }, { "epoch": 0.02699896157840083, "grad_norm": 15.73495864868164, "learning_rate": 2.219827586206897e-06, "loss": 0.5140605568885803, "step": 104 }, { "epoch": 0.027258566978193146, "grad_norm": 10.089570045471191, "learning_rate": 2.241379310344828e-06, "loss": 0.6113229990005493, "step": 105 }, { "epoch": 0.027518172377985463, "grad_norm": 19.400663375854492, "learning_rate": 2.262931034482759e-06, "loss": 0.5675051212310791, "step": 106 }, { "epoch": 0.027777777777777776, "grad_norm": 12.63032054901123, "learning_rate": 2.28448275862069e-06, "loss": 0.4986203610897064, "step": 107 }, { "epoch": 0.028037383177570093, "grad_norm": 6.296806812286377, "learning_rate": 2.306034482758621e-06, "loss": 0.44755011796951294, "step": 108 }, { "epoch": 0.02829698857736241, "grad_norm": 6.265273571014404, "learning_rate": 2.327586206896552e-06, "loss": 0.47970661520957947, "step": 109 }, { "epoch": 0.028556593977154723, "grad_norm": 31.346519470214844, "learning_rate": 2.349137931034483e-06, "loss": 0.7029252648353577, "step": 110 }, { "epoch": 0.02881619937694704, "grad_norm": 13.082422256469727, "learning_rate": 2.370689655172414e-06, "loss": 0.7016382217407227, "step": 111 }, { "epoch": 0.029075804776739357, "grad_norm": 15.209015846252441, "learning_rate": 2.392241379310345e-06, "loss": 0.6071974039077759, "step": 112 }, { "epoch": 0.02933541017653167, "grad_norm": 10.814181327819824, "learning_rate": 2.4137931034482762e-06, "loss": 0.6505585312843323, "step": 113 }, { "epoch": 0.029595015576323987, "grad_norm": 19.420440673828125, "learning_rate": 2.4353448275862072e-06, "loss": 0.5632834434509277, "step": 114 }, { "epoch": 0.029854620976116304, "grad_norm": 11.203591346740723, "learning_rate": 2.4568965517241382e-06, "loss": 0.5796357989311218, "step": 115 }, { "epoch": 0.030114226375908618, "grad_norm": 15.619573593139648, "learning_rate": 2.4784482758620692e-06, "loss": 0.6278386116027832, "step": 116 }, { "epoch": 0.030373831775700934, "grad_norm": 12.246647834777832, "learning_rate": 2.5e-06, "loss": 0.5041946172714233, "step": 117 }, { "epoch": 0.03063343717549325, "grad_norm": 12.385438919067383, "learning_rate": 2.521551724137931e-06, "loss": 0.6298964023590088, "step": 118 }, { "epoch": 0.030893042575285565, "grad_norm": 11.970782279968262, "learning_rate": 2.543103448275862e-06, "loss": 0.6216919422149658, "step": 119 }, { "epoch": 0.03115264797507788, "grad_norm": 8.128572463989258, "learning_rate": 2.5646551724137936e-06, "loss": 0.4878144860267639, "step": 120 }, { "epoch": 0.0314122533748702, "grad_norm": 13.90795612335205, "learning_rate": 2.5862068965517246e-06, "loss": 0.6712855100631714, "step": 121 }, { "epoch": 0.03167185877466251, "grad_norm": 8.121232986450195, "learning_rate": 2.6077586206896556e-06, "loss": 0.535862922668457, "step": 122 }, { "epoch": 0.031931464174454825, "grad_norm": 13.665836334228516, "learning_rate": 2.6293103448275866e-06, "loss": 0.5112475156784058, "step": 123 }, { "epoch": 0.032191069574247146, "grad_norm": 10.209010124206543, "learning_rate": 2.6508620689655175e-06, "loss": 0.5192108750343323, "step": 124 }, { "epoch": 0.03245067497403946, "grad_norm": 17.21038055419922, "learning_rate": 2.672413793103448e-06, "loss": 0.6961323618888855, "step": 125 }, { "epoch": 0.03271028037383177, "grad_norm": 6.000017166137695, "learning_rate": 2.69396551724138e-06, "loss": 0.4714090824127197, "step": 126 }, { "epoch": 0.03296988577362409, "grad_norm": 17.659652709960938, "learning_rate": 2.7155172413793105e-06, "loss": 0.6186486482620239, "step": 127 }, { "epoch": 0.033229491173416406, "grad_norm": 9.56258487701416, "learning_rate": 2.7370689655172415e-06, "loss": 0.5229357481002808, "step": 128 }, { "epoch": 0.03348909657320872, "grad_norm": 7.855279922485352, "learning_rate": 2.7586206896551725e-06, "loss": 0.572293758392334, "step": 129 }, { "epoch": 0.03374870197300104, "grad_norm": 8.887450218200684, "learning_rate": 2.7801724137931035e-06, "loss": 0.522781252861023, "step": 130 }, { "epoch": 0.03400830737279335, "grad_norm": 10.954737663269043, "learning_rate": 2.8017241379310345e-06, "loss": 0.4858476221561432, "step": 131 }, { "epoch": 0.03426791277258567, "grad_norm": 16.121471405029297, "learning_rate": 2.823275862068966e-06, "loss": 0.6021642088890076, "step": 132 }, { "epoch": 0.03452751817237799, "grad_norm": 10.39312744140625, "learning_rate": 2.844827586206897e-06, "loss": 0.5368252992630005, "step": 133 }, { "epoch": 0.0347871235721703, "grad_norm": 8.382211685180664, "learning_rate": 2.866379310344828e-06, "loss": 0.4851570725440979, "step": 134 }, { "epoch": 0.035046728971962614, "grad_norm": 22.806591033935547, "learning_rate": 2.887931034482759e-06, "loss": 0.5503276586532593, "step": 135 }, { "epoch": 0.035306334371754934, "grad_norm": 12.693863868713379, "learning_rate": 2.90948275862069e-06, "loss": 0.5966099500656128, "step": 136 }, { "epoch": 0.03556593977154725, "grad_norm": 5.192198753356934, "learning_rate": 2.931034482758621e-06, "loss": 0.5861632823944092, "step": 137 }, { "epoch": 0.03582554517133956, "grad_norm": 5.360598087310791, "learning_rate": 2.9525862068965522e-06, "loss": 0.4907028079032898, "step": 138 }, { "epoch": 0.03608515057113188, "grad_norm": 7.478189945220947, "learning_rate": 2.9741379310344832e-06, "loss": 0.4952141046524048, "step": 139 }, { "epoch": 0.036344755970924195, "grad_norm": 16.71737289428711, "learning_rate": 2.9956896551724142e-06, "loss": 0.5930260419845581, "step": 140 }, { "epoch": 0.03660436137071651, "grad_norm": 18.61660385131836, "learning_rate": 3.017241379310345e-06, "loss": 0.6942348480224609, "step": 141 }, { "epoch": 0.03686396677050883, "grad_norm": 6.4927496910095215, "learning_rate": 3.0387931034482758e-06, "loss": 0.5085504651069641, "step": 142 }, { "epoch": 0.03712357217030114, "grad_norm": 16.52231216430664, "learning_rate": 3.0603448275862068e-06, "loss": 0.49431079626083374, "step": 143 }, { "epoch": 0.037383177570093455, "grad_norm": 18.24912452697754, "learning_rate": 3.081896551724138e-06, "loss": 0.5593111515045166, "step": 144 }, { "epoch": 0.037642782969885775, "grad_norm": 7.936757564544678, "learning_rate": 3.103448275862069e-06, "loss": 0.48822128772735596, "step": 145 }, { "epoch": 0.03790238836967809, "grad_norm": 6.831502437591553, "learning_rate": 3.125e-06, "loss": 0.4800247550010681, "step": 146 }, { "epoch": 0.0381619937694704, "grad_norm": 16.872541427612305, "learning_rate": 3.146551724137931e-06, "loss": 0.6584337949752808, "step": 147 }, { "epoch": 0.03842159916926272, "grad_norm": 12.880175590515137, "learning_rate": 3.168103448275862e-06, "loss": 0.6354821920394897, "step": 148 }, { "epoch": 0.038681204569055036, "grad_norm": 10.929549217224121, "learning_rate": 3.1896551724137935e-06, "loss": 0.46939319372177124, "step": 149 }, { "epoch": 0.03894080996884735, "grad_norm": 9.854819297790527, "learning_rate": 3.2112068965517245e-06, "loss": 0.5201865434646606, "step": 150 }, { "epoch": 0.03920041536863967, "grad_norm": 12.379501342773438, "learning_rate": 3.2327586206896555e-06, "loss": 0.5397966504096985, "step": 151 }, { "epoch": 0.03946002076843198, "grad_norm": 13.8975830078125, "learning_rate": 3.2543103448275865e-06, "loss": 0.649648904800415, "step": 152 }, { "epoch": 0.0397196261682243, "grad_norm": 10.382563591003418, "learning_rate": 3.2758620689655175e-06, "loss": 0.48398616909980774, "step": 153 }, { "epoch": 0.03997923156801662, "grad_norm": 8.734719276428223, "learning_rate": 3.2974137931034485e-06, "loss": 0.4740087389945984, "step": 154 }, { "epoch": 0.04023883696780893, "grad_norm": 8.701436042785645, "learning_rate": 3.31896551724138e-06, "loss": 0.5029703378677368, "step": 155 }, { "epoch": 0.040498442367601244, "grad_norm": 7.4113383293151855, "learning_rate": 3.340517241379311e-06, "loss": 0.5004898309707642, "step": 156 }, { "epoch": 0.040758047767393564, "grad_norm": 11.692047119140625, "learning_rate": 3.362068965517242e-06, "loss": 0.528872013092041, "step": 157 }, { "epoch": 0.04101765316718588, "grad_norm": 10.1122465133667, "learning_rate": 3.383620689655173e-06, "loss": 0.5972768068313599, "step": 158 }, { "epoch": 0.04127725856697819, "grad_norm": 4.650244235992432, "learning_rate": 3.4051724137931034e-06, "loss": 0.46740883588790894, "step": 159 }, { "epoch": 0.04153686396677051, "grad_norm": 5.490291118621826, "learning_rate": 3.4267241379310344e-06, "loss": 0.507111668586731, "step": 160 }, { "epoch": 0.041796469366562825, "grad_norm": 6.462915897369385, "learning_rate": 3.448275862068966e-06, "loss": 0.44573110342025757, "step": 161 }, { "epoch": 0.04205607476635514, "grad_norm": 9.800371170043945, "learning_rate": 3.469827586206897e-06, "loss": 0.5781997442245483, "step": 162 }, { "epoch": 0.04231568016614746, "grad_norm": 8.227819442749023, "learning_rate": 3.491379310344828e-06, "loss": 0.49378859996795654, "step": 163 }, { "epoch": 0.04257528556593977, "grad_norm": 4.281506538391113, "learning_rate": 3.512931034482759e-06, "loss": 0.4816921353340149, "step": 164 }, { "epoch": 0.042834890965732085, "grad_norm": 8.513190269470215, "learning_rate": 3.5344827586206898e-06, "loss": 0.5991846323013306, "step": 165 }, { "epoch": 0.043094496365524405, "grad_norm": 7.231751918792725, "learning_rate": 3.5560344827586208e-06, "loss": 0.5615875720977783, "step": 166 }, { "epoch": 0.04335410176531672, "grad_norm": 10.550736427307129, "learning_rate": 3.577586206896552e-06, "loss": 0.56041020154953, "step": 167 }, { "epoch": 0.04361370716510903, "grad_norm": 8.747481346130371, "learning_rate": 3.599137931034483e-06, "loss": 0.5747597813606262, "step": 168 }, { "epoch": 0.04387331256490135, "grad_norm": 8.821013450622559, "learning_rate": 3.620689655172414e-06, "loss": 0.6302136182785034, "step": 169 }, { "epoch": 0.044132917964693666, "grad_norm": 9.58485221862793, "learning_rate": 3.642241379310345e-06, "loss": 0.6243805289268494, "step": 170 }, { "epoch": 0.04439252336448598, "grad_norm": 8.298470497131348, "learning_rate": 3.663793103448276e-06, "loss": 0.5062118768692017, "step": 171 }, { "epoch": 0.0446521287642783, "grad_norm": 16.431337356567383, "learning_rate": 3.685344827586207e-06, "loss": 0.7254905700683594, "step": 172 }, { "epoch": 0.04491173416407061, "grad_norm": 5.928415298461914, "learning_rate": 3.7068965517241385e-06, "loss": 0.5001013278961182, "step": 173 }, { "epoch": 0.045171339563862926, "grad_norm": 16.009807586669922, "learning_rate": 3.7284482758620695e-06, "loss": 0.495943158864975, "step": 174 }, { "epoch": 0.04543094496365525, "grad_norm": 14.812080383300781, "learning_rate": 3.7500000000000005e-06, "loss": 0.5225613117218018, "step": 175 }, { "epoch": 0.04569055036344756, "grad_norm": 3.2337920665740967, "learning_rate": 3.771551724137931e-06, "loss": 0.44838079810142517, "step": 176 }, { "epoch": 0.045950155763239874, "grad_norm": 12.479637145996094, "learning_rate": 3.793103448275862e-06, "loss": 0.6242549419403076, "step": 177 }, { "epoch": 0.046209761163032194, "grad_norm": 7.243624687194824, "learning_rate": 3.8146551724137935e-06, "loss": 0.48405060172080994, "step": 178 }, { "epoch": 0.04646936656282451, "grad_norm": 10.3535737991333, "learning_rate": 3.8362068965517245e-06, "loss": 0.5400301218032837, "step": 179 }, { "epoch": 0.04672897196261682, "grad_norm": 6.659900665283203, "learning_rate": 3.857758620689656e-06, "loss": 0.5442554950714111, "step": 180 }, { "epoch": 0.04698857736240914, "grad_norm": 14.14492130279541, "learning_rate": 3.8793103448275865e-06, "loss": 0.6581616401672363, "step": 181 }, { "epoch": 0.047248182762201454, "grad_norm": 12.333831787109375, "learning_rate": 3.900862068965518e-06, "loss": 0.4803241193294525, "step": 182 }, { "epoch": 0.04750778816199377, "grad_norm": 17.161312103271484, "learning_rate": 3.9224137931034484e-06, "loss": 0.5621408224105835, "step": 183 }, { "epoch": 0.04776739356178609, "grad_norm": 4.353350639343262, "learning_rate": 3.94396551724138e-06, "loss": 0.45356786251068115, "step": 184 }, { "epoch": 0.0480269989615784, "grad_norm": 6.690971851348877, "learning_rate": 3.96551724137931e-06, "loss": 0.542668342590332, "step": 185 }, { "epoch": 0.048286604361370715, "grad_norm": 5.107015132904053, "learning_rate": 3.987068965517242e-06, "loss": 0.46338796615600586, "step": 186 }, { "epoch": 0.048546209761163035, "grad_norm": 6.174976348876953, "learning_rate": 4.008620689655172e-06, "loss": 0.4634787142276764, "step": 187 }, { "epoch": 0.04880581516095535, "grad_norm": 6.406347751617432, "learning_rate": 4.030172413793104e-06, "loss": 0.460099458694458, "step": 188 }, { "epoch": 0.04906542056074766, "grad_norm": 4.627748966217041, "learning_rate": 4.051724137931034e-06, "loss": 0.46749967336654663, "step": 189 }, { "epoch": 0.04932502596053998, "grad_norm": 12.376349449157715, "learning_rate": 4.073275862068966e-06, "loss": 0.483662486076355, "step": 190 }, { "epoch": 0.049584631360332296, "grad_norm": 4.18363618850708, "learning_rate": 4.094827586206897e-06, "loss": 0.42710548639297485, "step": 191 }, { "epoch": 0.04984423676012461, "grad_norm": 5.502525806427002, "learning_rate": 4.116379310344828e-06, "loss": 0.5186187028884888, "step": 192 }, { "epoch": 0.05010384215991693, "grad_norm": 15.101107597351074, "learning_rate": 4.137931034482759e-06, "loss": 0.5561249852180481, "step": 193 }, { "epoch": 0.05036344755970924, "grad_norm": 6.884454727172852, "learning_rate": 4.15948275862069e-06, "loss": 0.5138318538665771, "step": 194 }, { "epoch": 0.050623052959501556, "grad_norm": 4.8271708488464355, "learning_rate": 4.181034482758621e-06, "loss": 0.45588722825050354, "step": 195 }, { "epoch": 0.05088265835929388, "grad_norm": 7.043482780456543, "learning_rate": 4.2025862068965526e-06, "loss": 0.5324005484580994, "step": 196 }, { "epoch": 0.05114226375908619, "grad_norm": 9.631487846374512, "learning_rate": 4.224137931034483e-06, "loss": 0.47907784581184387, "step": 197 }, { "epoch": 0.0514018691588785, "grad_norm": 5.316957473754883, "learning_rate": 4.2456896551724145e-06, "loss": 0.4695828855037689, "step": 198 }, { "epoch": 0.051661474558670824, "grad_norm": 7.6390275955200195, "learning_rate": 4.267241379310345e-06, "loss": 0.5515874028205872, "step": 199 }, { "epoch": 0.05192107995846314, "grad_norm": 6.314497947692871, "learning_rate": 4.288793103448276e-06, "loss": 0.5900042057037354, "step": 200 }, { "epoch": 0.05218068535825545, "grad_norm": 5.306649684906006, "learning_rate": 4.310344827586207e-06, "loss": 0.5116796493530273, "step": 201 }, { "epoch": 0.052440290758047764, "grad_norm": 11.506986618041992, "learning_rate": 4.3318965517241385e-06, "loss": 0.5312507152557373, "step": 202 }, { "epoch": 0.052699896157840084, "grad_norm": 9.019251823425293, "learning_rate": 4.353448275862069e-06, "loss": 0.5241291522979736, "step": 203 }, { "epoch": 0.0529595015576324, "grad_norm": 5.495859146118164, "learning_rate": 4.3750000000000005e-06, "loss": 0.48742103576660156, "step": 204 }, { "epoch": 0.05321910695742471, "grad_norm": 8.972434043884277, "learning_rate": 4.396551724137931e-06, "loss": 0.5912078619003296, "step": 205 }, { "epoch": 0.05347871235721703, "grad_norm": 5.9770588874816895, "learning_rate": 4.4181034482758624e-06, "loss": 0.4464493989944458, "step": 206 }, { "epoch": 0.053738317757009345, "grad_norm": 9.319690704345703, "learning_rate": 4.439655172413794e-06, "loss": 0.5856052041053772, "step": 207 }, { "epoch": 0.05399792315680166, "grad_norm": 10.969439506530762, "learning_rate": 4.461206896551724e-06, "loss": 0.5415751338005066, "step": 208 }, { "epoch": 0.05425752855659398, "grad_norm": 7.401954174041748, "learning_rate": 4.482758620689656e-06, "loss": 0.5576952695846558, "step": 209 }, { "epoch": 0.05451713395638629, "grad_norm": 4.676854610443115, "learning_rate": 4.504310344827586e-06, "loss": 0.4780375361442566, "step": 210 }, { "epoch": 0.054776739356178605, "grad_norm": 7.839669704437256, "learning_rate": 4.525862068965518e-06, "loss": 0.5884494781494141, "step": 211 }, { "epoch": 0.055036344755970926, "grad_norm": 6.92739200592041, "learning_rate": 4.547413793103448e-06, "loss": 0.5465302467346191, "step": 212 }, { "epoch": 0.05529595015576324, "grad_norm": 8.222253799438477, "learning_rate": 4.56896551724138e-06, "loss": 0.5350728631019592, "step": 213 }, { "epoch": 0.05555555555555555, "grad_norm": 9.507868766784668, "learning_rate": 4.590517241379311e-06, "loss": 0.44773563742637634, "step": 214 }, { "epoch": 0.05581516095534787, "grad_norm": 6.1381144523620605, "learning_rate": 4.612068965517242e-06, "loss": 0.4967676103115082, "step": 215 }, { "epoch": 0.056074766355140186, "grad_norm": 10.123889923095703, "learning_rate": 4.633620689655173e-06, "loss": 0.5243629217147827, "step": 216 }, { "epoch": 0.0563343717549325, "grad_norm": 6.188157558441162, "learning_rate": 4.655172413793104e-06, "loss": 0.46838635206222534, "step": 217 }, { "epoch": 0.05659397715472482, "grad_norm": 5.154716491699219, "learning_rate": 4.676724137931034e-06, "loss": 0.44646069407463074, "step": 218 }, { "epoch": 0.05685358255451713, "grad_norm": 11.15829849243164, "learning_rate": 4.698275862068966e-06, "loss": 0.6884605288505554, "step": 219 }, { "epoch": 0.05711318795430945, "grad_norm": 8.001893043518066, "learning_rate": 4.719827586206897e-06, "loss": 0.5129959583282471, "step": 220 }, { "epoch": 0.05737279335410177, "grad_norm": 6.527271747589111, "learning_rate": 4.741379310344828e-06, "loss": 0.47755593061447144, "step": 221 }, { "epoch": 0.05763239875389408, "grad_norm": 6.239192008972168, "learning_rate": 4.762931034482759e-06, "loss": 0.4607839286327362, "step": 222 }, { "epoch": 0.057892004153686394, "grad_norm": 7.187161445617676, "learning_rate": 4.78448275862069e-06, "loss": 0.5175713896751404, "step": 223 }, { "epoch": 0.058151609553478714, "grad_norm": 8.13447380065918, "learning_rate": 4.806034482758621e-06, "loss": 0.4860948622226715, "step": 224 }, { "epoch": 0.05841121495327103, "grad_norm": 8.027262687683105, "learning_rate": 4.8275862068965525e-06, "loss": 0.5002280473709106, "step": 225 }, { "epoch": 0.05867082035306334, "grad_norm": 9.666559219360352, "learning_rate": 4.849137931034483e-06, "loss": 0.6050724983215332, "step": 226 }, { "epoch": 0.05893042575285566, "grad_norm": 6.681295871734619, "learning_rate": 4.8706896551724145e-06, "loss": 0.5408742427825928, "step": 227 }, { "epoch": 0.059190031152647975, "grad_norm": 6.850449085235596, "learning_rate": 4.892241379310345e-06, "loss": 0.5287983417510986, "step": 228 }, { "epoch": 0.05944963655244029, "grad_norm": 5.235950469970703, "learning_rate": 4.9137931034482765e-06, "loss": 0.5082547068595886, "step": 229 }, { "epoch": 0.05970924195223261, "grad_norm": 4.515280723571777, "learning_rate": 4.935344827586207e-06, "loss": 0.446138471364975, "step": 230 }, { "epoch": 0.05996884735202492, "grad_norm": 9.580804824829102, "learning_rate": 4.9568965517241384e-06, "loss": 0.46111860871315, "step": 231 }, { "epoch": 0.060228452751817235, "grad_norm": 14.123738288879395, "learning_rate": 4.97844827586207e-06, "loss": 0.5456571578979492, "step": 232 }, { "epoch": 0.060488058151609556, "grad_norm": 10.264272689819336, "learning_rate": 5e-06, "loss": 0.5233131647109985, "step": 233 }, { "epoch": 0.06074766355140187, "grad_norm": 11.79328727722168, "learning_rate": 4.99999980112576e-06, "loss": 0.5916544198989868, "step": 234 }, { "epoch": 0.06100726895119418, "grad_norm": 8.580262184143066, "learning_rate": 4.999999204503072e-06, "loss": 0.5206959247589111, "step": 235 }, { "epoch": 0.0612668743509865, "grad_norm": 13.771783828735352, "learning_rate": 4.999998210132044e-06, "loss": 0.5200749635696411, "step": 236 }, { "epoch": 0.061526479750778816, "grad_norm": 9.708440780639648, "learning_rate": 4.999996818012849e-06, "loss": 0.5324063897132874, "step": 237 }, { "epoch": 0.06178608515057113, "grad_norm": 2.7194809913635254, "learning_rate": 4.999995028145735e-06, "loss": 0.4947490096092224, "step": 238 }, { "epoch": 0.06204569055036345, "grad_norm": 12.529326438903809, "learning_rate": 4.999992840531019e-06, "loss": 0.6445401906967163, "step": 239 }, { "epoch": 0.06230529595015576, "grad_norm": 6.439173698425293, "learning_rate": 4.999990255169086e-06, "loss": 0.5492210388183594, "step": 240 }, { "epoch": 0.06256490134994808, "grad_norm": 5.375085830688477, "learning_rate": 4.999987272060394e-06, "loss": 0.5186984539031982, "step": 241 }, { "epoch": 0.0628245067497404, "grad_norm": 7.444694519042969, "learning_rate": 4.999983891205471e-06, "loss": 0.4727640151977539, "step": 242 }, { "epoch": 0.0630841121495327, "grad_norm": 6.853529930114746, "learning_rate": 4.999980112604912e-06, "loss": 0.5544508695602417, "step": 243 }, { "epoch": 0.06334371754932502, "grad_norm": 5.400933742523193, "learning_rate": 4.999975936259389e-06, "loss": 0.5348935127258301, "step": 244 }, { "epoch": 0.06360332294911734, "grad_norm": 7.3853960037231445, "learning_rate": 4.9999713621696375e-06, "loss": 0.5849200487136841, "step": 245 }, { "epoch": 0.06386292834890965, "grad_norm": 5.368354797363281, "learning_rate": 4.999966390336466e-06, "loss": 0.49673426151275635, "step": 246 }, { "epoch": 0.06412253374870197, "grad_norm": 6.852190017700195, "learning_rate": 4.999961020760754e-06, "loss": 0.5422779321670532, "step": 247 }, { "epoch": 0.06438213914849429, "grad_norm": 13.783917427062988, "learning_rate": 4.999955253443451e-06, "loss": 0.5471408367156982, "step": 248 }, { "epoch": 0.0646417445482866, "grad_norm": 8.88382339477539, "learning_rate": 4.999949088385577e-06, "loss": 0.6348952054977417, "step": 249 }, { "epoch": 0.06490134994807892, "grad_norm": 9.713522911071777, "learning_rate": 4.9999425255882205e-06, "loss": 0.5833041667938232, "step": 250 }, { "epoch": 0.06516095534787124, "grad_norm": 9.525135040283203, "learning_rate": 4.999935565052543e-06, "loss": 0.5271466970443726, "step": 251 }, { "epoch": 0.06542056074766354, "grad_norm": 7.078178405761719, "learning_rate": 4.999928206779774e-06, "loss": 0.578914225101471, "step": 252 }, { "epoch": 0.06568016614745587, "grad_norm": 6.571529388427734, "learning_rate": 4.999920450771214e-06, "loss": 0.5580006837844849, "step": 253 }, { "epoch": 0.06593977154724819, "grad_norm": 10.402029037475586, "learning_rate": 4.999912297028235e-06, "loss": 0.6068065762519836, "step": 254 }, { "epoch": 0.06619937694704049, "grad_norm": 4.190751552581787, "learning_rate": 4.999903745552278e-06, "loss": 0.5434763431549072, "step": 255 }, { "epoch": 0.06645898234683281, "grad_norm": 6.394086837768555, "learning_rate": 4.9998947963448554e-06, "loss": 0.62064528465271, "step": 256 }, { "epoch": 0.06671858774662513, "grad_norm": 11.793587684631348, "learning_rate": 4.999885449407547e-06, "loss": 0.5236709117889404, "step": 257 }, { "epoch": 0.06697819314641744, "grad_norm": 19.985754013061523, "learning_rate": 4.999875704742009e-06, "loss": 0.6068195700645447, "step": 258 }, { "epoch": 0.06723779854620976, "grad_norm": 10.459057807922363, "learning_rate": 4.99986556234996e-06, "loss": 0.5712143182754517, "step": 259 }, { "epoch": 0.06749740394600208, "grad_norm": 16.725513458251953, "learning_rate": 4.999855022233195e-06, "loss": 0.5209740996360779, "step": 260 }, { "epoch": 0.06775700934579439, "grad_norm": 17.664823532104492, "learning_rate": 4.999844084393577e-06, "loss": 0.5929869413375854, "step": 261 }, { "epoch": 0.0680166147455867, "grad_norm": 14.777020454406738, "learning_rate": 4.99983274883304e-06, "loss": 0.540290892124176, "step": 262 }, { "epoch": 0.06827622014537903, "grad_norm": 8.9825439453125, "learning_rate": 4.999821015553586e-06, "loss": 0.4702712595462799, "step": 263 }, { "epoch": 0.06853582554517133, "grad_norm": 11.614644050598145, "learning_rate": 4.999808884557291e-06, "loss": 0.4747675657272339, "step": 264 }, { "epoch": 0.06879543094496365, "grad_norm": 10.105212211608887, "learning_rate": 4.9997963558463e-06, "loss": 0.5333774089813232, "step": 265 }, { "epoch": 0.06905503634475597, "grad_norm": 9.218629837036133, "learning_rate": 4.999783429422826e-06, "loss": 0.45735931396484375, "step": 266 }, { "epoch": 0.06931464174454828, "grad_norm": 8.050702095031738, "learning_rate": 4.999770105289155e-06, "loss": 0.5476728081703186, "step": 267 }, { "epoch": 0.0695742471443406, "grad_norm": 9.071940422058105, "learning_rate": 4.999756383447642e-06, "loss": 0.5722087025642395, "step": 268 }, { "epoch": 0.06983385254413292, "grad_norm": 7.5676679611206055, "learning_rate": 4.999742263900714e-06, "loss": 0.5902025699615479, "step": 269 }, { "epoch": 0.07009345794392523, "grad_norm": 3.7243242263793945, "learning_rate": 4.9997277466508654e-06, "loss": 0.4307483434677124, "step": 270 }, { "epoch": 0.07035306334371755, "grad_norm": 5.856462478637695, "learning_rate": 4.9997128317006625e-06, "loss": 0.5765952467918396, "step": 271 }, { "epoch": 0.07061266874350987, "grad_norm": 7.2907586097717285, "learning_rate": 4.999697519052743e-06, "loss": 0.46289390325546265, "step": 272 }, { "epoch": 0.07087227414330217, "grad_norm": 9.929651260375977, "learning_rate": 4.999681808709814e-06, "loss": 0.5641341805458069, "step": 273 }, { "epoch": 0.0711318795430945, "grad_norm": 7.2935075759887695, "learning_rate": 4.999665700674651e-06, "loss": 0.5745533108711243, "step": 274 }, { "epoch": 0.07139148494288682, "grad_norm": 7.695417881011963, "learning_rate": 4.999649194950103e-06, "loss": 0.5827292203903198, "step": 275 }, { "epoch": 0.07165109034267912, "grad_norm": 10.851717948913574, "learning_rate": 4.999632291539088e-06, "loss": 0.5143301486968994, "step": 276 }, { "epoch": 0.07191069574247144, "grad_norm": 7.368400573730469, "learning_rate": 4.999614990444594e-06, "loss": 0.5030809640884399, "step": 277 }, { "epoch": 0.07217030114226376, "grad_norm": 8.858487129211426, "learning_rate": 4.999597291669679e-06, "loss": 0.5935959815979004, "step": 278 }, { "epoch": 0.07242990654205607, "grad_norm": 8.814509391784668, "learning_rate": 4.99957919521747e-06, "loss": 0.47866612672805786, "step": 279 }, { "epoch": 0.07268951194184839, "grad_norm": 5.9628190994262695, "learning_rate": 4.9995607010911696e-06, "loss": 0.5588573813438416, "step": 280 }, { "epoch": 0.07294911734164071, "grad_norm": 3.4742164611816406, "learning_rate": 4.999541809294045e-06, "loss": 0.41693732142448425, "step": 281 }, { "epoch": 0.07320872274143302, "grad_norm": 6.178086280822754, "learning_rate": 4.999522519829435e-06, "loss": 0.43742477893829346, "step": 282 }, { "epoch": 0.07346832814122534, "grad_norm": 5.6690673828125, "learning_rate": 4.999502832700752e-06, "loss": 0.47355061769485474, "step": 283 }, { "epoch": 0.07372793354101766, "grad_norm": 5.096330165863037, "learning_rate": 4.999482747911475e-06, "loss": 0.4572702646255493, "step": 284 }, { "epoch": 0.07398753894080996, "grad_norm": 4.457252502441406, "learning_rate": 4.999462265465154e-06, "loss": 0.4066341817378998, "step": 285 }, { "epoch": 0.07424714434060228, "grad_norm": 6.169216156005859, "learning_rate": 4.99944138536541e-06, "loss": 0.4209744334220886, "step": 286 }, { "epoch": 0.0745067497403946, "grad_norm": 3.454883337020874, "learning_rate": 4.999420107615935e-06, "loss": 0.43474164605140686, "step": 287 }, { "epoch": 0.07476635514018691, "grad_norm": 4.178854942321777, "learning_rate": 4.9993984322204905e-06, "loss": 0.46666795015335083, "step": 288 }, { "epoch": 0.07502596053997923, "grad_norm": 6.272046089172363, "learning_rate": 4.999376359182906e-06, "loss": 0.4610603451728821, "step": 289 }, { "epoch": 0.07528556593977155, "grad_norm": 5.4195942878723145, "learning_rate": 4.999353888507086e-06, "loss": 0.4439009428024292, "step": 290 }, { "epoch": 0.07554517133956386, "grad_norm": 3.594836711883545, "learning_rate": 4.999331020197002e-06, "loss": 0.4869612753391266, "step": 291 }, { "epoch": 0.07580477673935618, "grad_norm": 6.227189064025879, "learning_rate": 4.999307754256696e-06, "loss": 0.5629096031188965, "step": 292 }, { "epoch": 0.0760643821391485, "grad_norm": 3.4425275325775146, "learning_rate": 4.999284090690282e-06, "loss": 0.42326006293296814, "step": 293 }, { "epoch": 0.0763239875389408, "grad_norm": 9.097262382507324, "learning_rate": 4.999260029501942e-06, "loss": 0.6065998077392578, "step": 294 }, { "epoch": 0.07658359293873312, "grad_norm": 8.643491744995117, "learning_rate": 4.999235570695931e-06, "loss": 0.44442349672317505, "step": 295 }, { "epoch": 0.07684319833852545, "grad_norm": 3.0241944789886475, "learning_rate": 4.9992107142765715e-06, "loss": 0.4261346459388733, "step": 296 }, { "epoch": 0.07710280373831775, "grad_norm": 8.033190727233887, "learning_rate": 4.999185460248257e-06, "loss": 0.49502748250961304, "step": 297 }, { "epoch": 0.07736240913811007, "grad_norm": 5.691076755523682, "learning_rate": 4.999159808615453e-06, "loss": 0.41723889112472534, "step": 298 }, { "epoch": 0.07762201453790239, "grad_norm": 6.070134162902832, "learning_rate": 4.999133759382693e-06, "loss": 0.5311443209648132, "step": 299 }, { "epoch": 0.0778816199376947, "grad_norm": 3.7701733112335205, "learning_rate": 4.999107312554583e-06, "loss": 0.4382491111755371, "step": 300 }, { "epoch": 0.07814122533748702, "grad_norm": 4.783874988555908, "learning_rate": 4.9990804681358e-06, "loss": 0.46694791316986084, "step": 301 }, { "epoch": 0.07840083073727934, "grad_norm": 7.223684310913086, "learning_rate": 4.999053226131084e-06, "loss": 0.5969036817550659, "step": 302 }, { "epoch": 0.07866043613707165, "grad_norm": 5.3418474197387695, "learning_rate": 4.9990255865452565e-06, "loss": 0.4592551589012146, "step": 303 }, { "epoch": 0.07892004153686397, "grad_norm": 6.772636413574219, "learning_rate": 4.9989975493832005e-06, "loss": 0.44608163833618164, "step": 304 }, { "epoch": 0.07917964693665629, "grad_norm": 11.6766939163208, "learning_rate": 4.998969114649873e-06, "loss": 0.5876092910766602, "step": 305 }, { "epoch": 0.0794392523364486, "grad_norm": 3.950498104095459, "learning_rate": 4.9989402823503006e-06, "loss": 0.5384328365325928, "step": 306 }, { "epoch": 0.07969885773624091, "grad_norm": 6.726335525512695, "learning_rate": 4.9989110524895795e-06, "loss": 0.4955541789531708, "step": 307 }, { "epoch": 0.07995846313603323, "grad_norm": 4.100427150726318, "learning_rate": 4.998881425072879e-06, "loss": 0.5137687921524048, "step": 308 }, { "epoch": 0.08021806853582554, "grad_norm": 3.150749683380127, "learning_rate": 4.998851400105433e-06, "loss": 0.42349404096603394, "step": 309 }, { "epoch": 0.08047767393561786, "grad_norm": 7.014369487762451, "learning_rate": 4.998820977592553e-06, "loss": 0.5707464218139648, "step": 310 }, { "epoch": 0.08073727933541018, "grad_norm": 7.427856922149658, "learning_rate": 4.998790157539615e-06, "loss": 0.48474282026290894, "step": 311 }, { "epoch": 0.08099688473520249, "grad_norm": 6.741508960723877, "learning_rate": 4.998758939952068e-06, "loss": 0.5975462794303894, "step": 312 }, { "epoch": 0.08125649013499481, "grad_norm": 6.187541484832764, "learning_rate": 4.998727324835429e-06, "loss": 0.46996477246284485, "step": 313 }, { "epoch": 0.08151609553478713, "grad_norm": 7.6486687660217285, "learning_rate": 4.998695312195289e-06, "loss": 0.46912190318107605, "step": 314 }, { "epoch": 0.08177570093457943, "grad_norm": 8.799538612365723, "learning_rate": 4.998662902037306e-06, "loss": 0.481076180934906, "step": 315 }, { "epoch": 0.08203530633437175, "grad_norm": 4.616541385650635, "learning_rate": 4.998630094367209e-06, "loss": 0.4655141830444336, "step": 316 }, { "epoch": 0.08229491173416408, "grad_norm": 4.802173614501953, "learning_rate": 4.998596889190799e-06, "loss": 0.4353707730770111, "step": 317 }, { "epoch": 0.08255451713395638, "grad_norm": 2.800426483154297, "learning_rate": 4.998563286513944e-06, "loss": 0.4638857841491699, "step": 318 }, { "epoch": 0.0828141225337487, "grad_norm": 4.82088565826416, "learning_rate": 4.998529286342585e-06, "loss": 0.5165430903434753, "step": 319 }, { "epoch": 0.08307372793354102, "grad_norm": 8.128887176513672, "learning_rate": 4.998494888682734e-06, "loss": 0.6205308437347412, "step": 320 }, { "epoch": 0.08333333333333333, "grad_norm": 6.683003902435303, "learning_rate": 4.99846009354047e-06, "loss": 0.4981082081794739, "step": 321 }, { "epoch": 0.08359293873312565, "grad_norm": 5.618592262268066, "learning_rate": 4.998424900921944e-06, "loss": 0.5476319789886475, "step": 322 }, { "epoch": 0.08385254413291797, "grad_norm": 5.181295871734619, "learning_rate": 4.998389310833378e-06, "loss": 0.512939453125, "step": 323 }, { "epoch": 0.08411214953271028, "grad_norm": 5.041267395019531, "learning_rate": 4.998353323281063e-06, "loss": 0.44203323125839233, "step": 324 }, { "epoch": 0.0843717549325026, "grad_norm": 4.018551826477051, "learning_rate": 4.998316938271361e-06, "loss": 0.4744490683078766, "step": 325 }, { "epoch": 0.08463136033229492, "grad_norm": 5.759253025054932, "learning_rate": 4.998280155810704e-06, "loss": 0.4971356689929962, "step": 326 }, { "epoch": 0.08489096573208722, "grad_norm": 6.209257125854492, "learning_rate": 4.998242975905593e-06, "loss": 0.5283785462379456, "step": 327 }, { "epoch": 0.08515057113187954, "grad_norm": 6.394739627838135, "learning_rate": 4.998205398562603e-06, "loss": 0.5111987590789795, "step": 328 }, { "epoch": 0.08541017653167186, "grad_norm": 3.575739860534668, "learning_rate": 4.998167423788375e-06, "loss": 0.43048685789108276, "step": 329 }, { "epoch": 0.08566978193146417, "grad_norm": 8.729154586791992, "learning_rate": 4.998129051589624e-06, "loss": 0.6183044910430908, "step": 330 }, { "epoch": 0.08592938733125649, "grad_norm": 2.9350500106811523, "learning_rate": 4.998090281973131e-06, "loss": 0.4489804208278656, "step": 331 }, { "epoch": 0.08618899273104881, "grad_norm": 2.995389461517334, "learning_rate": 4.99805111494575e-06, "loss": 0.464781254529953, "step": 332 }, { "epoch": 0.08644859813084112, "grad_norm": 7.591894626617432, "learning_rate": 4.9980115505144065e-06, "loss": 0.5175775289535522, "step": 333 }, { "epoch": 0.08670820353063344, "grad_norm": 3.422516345977783, "learning_rate": 4.997971588686093e-06, "loss": 0.45676666498184204, "step": 334 }, { "epoch": 0.08696780893042576, "grad_norm": 6.0763092041015625, "learning_rate": 4.9979312294678745e-06, "loss": 0.5668925046920776, "step": 335 }, { "epoch": 0.08722741433021806, "grad_norm": 4.167880535125732, "learning_rate": 4.997890472866885e-06, "loss": 0.5038737654685974, "step": 336 }, { "epoch": 0.08748701973001038, "grad_norm": 4.36902379989624, "learning_rate": 4.99784931889033e-06, "loss": 0.5280246734619141, "step": 337 }, { "epoch": 0.0877466251298027, "grad_norm": 3.4477357864379883, "learning_rate": 4.997807767545485e-06, "loss": 0.43364572525024414, "step": 338 }, { "epoch": 0.08800623052959501, "grad_norm": 6.510862827301025, "learning_rate": 4.9977658188396935e-06, "loss": 0.4572657346725464, "step": 339 }, { "epoch": 0.08826583592938733, "grad_norm": 4.491781711578369, "learning_rate": 4.997723472780373e-06, "loss": 0.44301334023475647, "step": 340 }, { "epoch": 0.08852544132917965, "grad_norm": 4.919832706451416, "learning_rate": 4.997680729375008e-06, "loss": 0.42126548290252686, "step": 341 }, { "epoch": 0.08878504672897196, "grad_norm": 9.152565956115723, "learning_rate": 4.997637588631156e-06, "loss": 0.5370042324066162, "step": 342 }, { "epoch": 0.08904465212876428, "grad_norm": 6.329803466796875, "learning_rate": 4.997594050556443e-06, "loss": 0.427659809589386, "step": 343 }, { "epoch": 0.0893042575285566, "grad_norm": 3.7586588859558105, "learning_rate": 4.9975501151585635e-06, "loss": 0.49239760637283325, "step": 344 }, { "epoch": 0.0895638629283489, "grad_norm": 7.028627395629883, "learning_rate": 4.997505782445286e-06, "loss": 0.474162220954895, "step": 345 }, { "epoch": 0.08982346832814123, "grad_norm": 4.088550090789795, "learning_rate": 4.997461052424447e-06, "loss": 0.49671506881713867, "step": 346 }, { "epoch": 0.09008307372793355, "grad_norm": 6.399348258972168, "learning_rate": 4.997415925103955e-06, "loss": 0.5055777430534363, "step": 347 }, { "epoch": 0.09034267912772585, "grad_norm": 6.53875732421875, "learning_rate": 4.997370400491786e-06, "loss": 0.46737515926361084, "step": 348 }, { "epoch": 0.09060228452751817, "grad_norm": 9.43808364868164, "learning_rate": 4.997324478595987e-06, "loss": 0.5434072017669678, "step": 349 }, { "epoch": 0.0908618899273105, "grad_norm": 6.428090572357178, "learning_rate": 4.997278159424678e-06, "loss": 0.4902229607105255, "step": 350 }, { "epoch": 0.0911214953271028, "grad_norm": 12.499608039855957, "learning_rate": 4.997231442986047e-06, "loss": 0.5568786263465881, "step": 351 }, { "epoch": 0.09138110072689512, "grad_norm": 10.651397705078125, "learning_rate": 4.997184329288351e-06, "loss": 0.5766294002532959, "step": 352 }, { "epoch": 0.09164070612668744, "grad_norm": 5.472596168518066, "learning_rate": 4.99713681833992e-06, "loss": 0.5410800576210022, "step": 353 }, { "epoch": 0.09190031152647975, "grad_norm": 10.665688514709473, "learning_rate": 4.99708891014915e-06, "loss": 0.5386850237846375, "step": 354 }, { "epoch": 0.09215991692627207, "grad_norm": 5.215460777282715, "learning_rate": 4.997040604724514e-06, "loss": 0.46369490027427673, "step": 355 }, { "epoch": 0.09241952232606439, "grad_norm": 7.269367218017578, "learning_rate": 4.9969919020745485e-06, "loss": 0.4199228882789612, "step": 356 }, { "epoch": 0.0926791277258567, "grad_norm": 4.827279567718506, "learning_rate": 4.996942802207866e-06, "loss": 0.4414736032485962, "step": 357 }, { "epoch": 0.09293873312564901, "grad_norm": 6.884330749511719, "learning_rate": 4.996893305133142e-06, "loss": 0.5703909397125244, "step": 358 }, { "epoch": 0.09319833852544133, "grad_norm": 4.02549409866333, "learning_rate": 4.996843410859129e-06, "loss": 0.41511666774749756, "step": 359 }, { "epoch": 0.09345794392523364, "grad_norm": 3.859698534011841, "learning_rate": 4.996793119394648e-06, "loss": 0.4342956840991974, "step": 360 }, { "epoch": 0.09371754932502596, "grad_norm": 4.296453952789307, "learning_rate": 4.996742430748587e-06, "loss": 0.4514685273170471, "step": 361 }, { "epoch": 0.09397715472481828, "grad_norm": 5.000412464141846, "learning_rate": 4.996691344929909e-06, "loss": 0.636665940284729, "step": 362 }, { "epoch": 0.09423676012461059, "grad_norm": 8.623202323913574, "learning_rate": 4.996639861947643e-06, "loss": 0.4895521104335785, "step": 363 }, { "epoch": 0.09449636552440291, "grad_norm": 6.561052322387695, "learning_rate": 4.99658798181089e-06, "loss": 0.52446049451828, "step": 364 }, { "epoch": 0.09475597092419523, "grad_norm": 5.947225570678711, "learning_rate": 4.996535704528823e-06, "loss": 0.48671770095825195, "step": 365 }, { "epoch": 0.09501557632398754, "grad_norm": 8.202113151550293, "learning_rate": 4.996483030110682e-06, "loss": 0.5412723422050476, "step": 366 }, { "epoch": 0.09527518172377986, "grad_norm": 5.622419834136963, "learning_rate": 4.996429958565779e-06, "loss": 0.4232691526412964, "step": 367 }, { "epoch": 0.09553478712357218, "grad_norm": 12.598993301391602, "learning_rate": 4.996376489903495e-06, "loss": 0.5062035322189331, "step": 368 }, { "epoch": 0.09579439252336448, "grad_norm": 4.895508289337158, "learning_rate": 4.996322624133284e-06, "loss": 0.44736891984939575, "step": 369 }, { "epoch": 0.0960539979231568, "grad_norm": 3.979123830795288, "learning_rate": 4.996268361264666e-06, "loss": 0.4172593951225281, "step": 370 }, { "epoch": 0.09631360332294912, "grad_norm": 5.797790050506592, "learning_rate": 4.996213701307235e-06, "loss": 0.4536728262901306, "step": 371 }, { "epoch": 0.09657320872274143, "grad_norm": 13.94966983795166, "learning_rate": 4.9961586442706525e-06, "loss": 0.6315829753875732, "step": 372 }, { "epoch": 0.09683281412253375, "grad_norm": 3.858624219894409, "learning_rate": 4.9961031901646524e-06, "loss": 0.5524418950080872, "step": 373 }, { "epoch": 0.09709241952232607, "grad_norm": 6.552168369293213, "learning_rate": 4.996047338999037e-06, "loss": 0.5428586006164551, "step": 374 }, { "epoch": 0.09735202492211838, "grad_norm": 4.128238201141357, "learning_rate": 4.99599109078368e-06, "loss": 0.4654802680015564, "step": 375 }, { "epoch": 0.0976116303219107, "grad_norm": 2.951348304748535, "learning_rate": 4.995934445528524e-06, "loss": 0.46354082226753235, "step": 376 }, { "epoch": 0.09787123572170302, "grad_norm": 5.0861711502075195, "learning_rate": 4.995877403243584e-06, "loss": 0.48380717635154724, "step": 377 }, { "epoch": 0.09813084112149532, "grad_norm": 1.9964491128921509, "learning_rate": 4.995819963938942e-06, "loss": 0.43185704946517944, "step": 378 }, { "epoch": 0.09839044652128764, "grad_norm": 3.5721664428710938, "learning_rate": 4.995762127624753e-06, "loss": 0.4263012409210205, "step": 379 }, { "epoch": 0.09865005192107996, "grad_norm": 3.1556589603424072, "learning_rate": 4.995703894311242e-06, "loss": 0.4406569004058838, "step": 380 }, { "epoch": 0.09890965732087227, "grad_norm": 4.981197834014893, "learning_rate": 4.995645264008701e-06, "loss": 0.5394615530967712, "step": 381 }, { "epoch": 0.09916926272066459, "grad_norm": 4.420776844024658, "learning_rate": 4.995586236727496e-06, "loss": 0.48902076482772827, "step": 382 }, { "epoch": 0.09942886812045691, "grad_norm": 4.273446083068848, "learning_rate": 4.995526812478061e-06, "loss": 0.6177826523780823, "step": 383 }, { "epoch": 0.09968847352024922, "grad_norm": 5.749030590057373, "learning_rate": 4.995466991270903e-06, "loss": 0.44224250316619873, "step": 384 }, { "epoch": 0.09994807892004154, "grad_norm": 5.101156711578369, "learning_rate": 4.9954067731165945e-06, "loss": 0.45356419682502747, "step": 385 }, { "epoch": 0.10020768431983386, "grad_norm": 3.1944947242736816, "learning_rate": 4.995346158025781e-06, "loss": 0.41644054651260376, "step": 386 }, { "epoch": 0.10046728971962617, "grad_norm": 2.9493019580841064, "learning_rate": 4.995285146009179e-06, "loss": 0.44571858644485474, "step": 387 }, { "epoch": 0.10072689511941849, "grad_norm": 4.0340352058410645, "learning_rate": 4.995223737077573e-06, "loss": 0.6060078740119934, "step": 388 }, { "epoch": 0.1009865005192108, "grad_norm": 4.919320583343506, "learning_rate": 4.9951619312418196e-06, "loss": 0.4332171082496643, "step": 389 }, { "epoch": 0.10124610591900311, "grad_norm": 4.920609474182129, "learning_rate": 4.995099728512843e-06, "loss": 0.48712432384490967, "step": 390 }, { "epoch": 0.10150571131879543, "grad_norm": 5.441844940185547, "learning_rate": 4.995037128901642e-06, "loss": 0.4576793909072876, "step": 391 }, { "epoch": 0.10176531671858775, "grad_norm": 4.493037223815918, "learning_rate": 4.99497413241928e-06, "loss": 0.4561532139778137, "step": 392 }, { "epoch": 0.10202492211838006, "grad_norm": 5.856847763061523, "learning_rate": 4.994910739076895e-06, "loss": 0.6028748750686646, "step": 393 }, { "epoch": 0.10228452751817238, "grad_norm": 3.271965265274048, "learning_rate": 4.994846948885693e-06, "loss": 0.4742409884929657, "step": 394 }, { "epoch": 0.1025441329179647, "grad_norm": 10.380974769592285, "learning_rate": 4.99478276185695e-06, "loss": 0.5299404859542847, "step": 395 }, { "epoch": 0.102803738317757, "grad_norm": 2.4686119556427, "learning_rate": 4.994718178002013e-06, "loss": 0.4107514023780823, "step": 396 }, { "epoch": 0.10306334371754933, "grad_norm": 3.4382729530334473, "learning_rate": 4.9946531973323005e-06, "loss": 0.43483981490135193, "step": 397 }, { "epoch": 0.10332294911734165, "grad_norm": 2.692878246307373, "learning_rate": 4.9945878198592975e-06, "loss": 0.44049811363220215, "step": 398 }, { "epoch": 0.10358255451713395, "grad_norm": 6.0905442237854, "learning_rate": 4.994522045594563e-06, "loss": 0.5086922645568848, "step": 399 }, { "epoch": 0.10384215991692627, "grad_norm": 4.821905612945557, "learning_rate": 4.9944558745497236e-06, "loss": 0.4658876657485962, "step": 400 }, { "epoch": 0.1041017653167186, "grad_norm": 4.138703346252441, "learning_rate": 4.9943893067364765e-06, "loss": 0.4860210120677948, "step": 401 }, { "epoch": 0.1043613707165109, "grad_norm": 4.59815788269043, "learning_rate": 4.99432234216659e-06, "loss": 0.49128779768943787, "step": 402 }, { "epoch": 0.10462097611630322, "grad_norm": 4.004542827606201, "learning_rate": 4.994254980851901e-06, "loss": 0.4425760507583618, "step": 403 }, { "epoch": 0.10488058151609553, "grad_norm": 5.567637920379639, "learning_rate": 4.994187222804319e-06, "loss": 0.47559189796447754, "step": 404 }, { "epoch": 0.10514018691588785, "grad_norm": 6.161932468414307, "learning_rate": 4.99411906803582e-06, "loss": 0.4967007040977478, "step": 405 }, { "epoch": 0.10539979231568017, "grad_norm": 3.8937578201293945, "learning_rate": 4.994050516558454e-06, "loss": 0.4565598964691162, "step": 406 }, { "epoch": 0.10565939771547248, "grad_norm": 3.7667715549468994, "learning_rate": 4.993981568384339e-06, "loss": 0.46240657567977905, "step": 407 }, { "epoch": 0.1059190031152648, "grad_norm": 4.313129425048828, "learning_rate": 4.993912223525661e-06, "loss": 0.5068934559822083, "step": 408 }, { "epoch": 0.10617860851505712, "grad_norm": 4.248948097229004, "learning_rate": 4.993842481994683e-06, "loss": 0.5244277119636536, "step": 409 }, { "epoch": 0.10643821391484942, "grad_norm": 4.199985980987549, "learning_rate": 4.99377234380373e-06, "loss": 0.5335643291473389, "step": 410 }, { "epoch": 0.10669781931464174, "grad_norm": 8.12460994720459, "learning_rate": 4.9937018089652024e-06, "loss": 0.5818942785263062, "step": 411 }, { "epoch": 0.10695742471443406, "grad_norm": 4.00601053237915, "learning_rate": 4.99363087749157e-06, "loss": 0.49700433015823364, "step": 412 }, { "epoch": 0.10721703011422637, "grad_norm": 9.90966510772705, "learning_rate": 4.993559549395369e-06, "loss": 0.5948454141616821, "step": 413 }, { "epoch": 0.10747663551401869, "grad_norm": 2.385650634765625, "learning_rate": 4.993487824689211e-06, "loss": 0.4501389265060425, "step": 414 }, { "epoch": 0.10773624091381101, "grad_norm": 4.449684143066406, "learning_rate": 4.993415703385776e-06, "loss": 0.41034919023513794, "step": 415 }, { "epoch": 0.10799584631360332, "grad_norm": 2.5131313800811768, "learning_rate": 4.99334318549781e-06, "loss": 0.41693374514579773, "step": 416 }, { "epoch": 0.10825545171339564, "grad_norm": 2.6677849292755127, "learning_rate": 4.993270271038136e-06, "loss": 0.42568445205688477, "step": 417 }, { "epoch": 0.10851505711318796, "grad_norm": 3.141993761062622, "learning_rate": 4.993196960019642e-06, "loss": 0.4593856930732727, "step": 418 }, { "epoch": 0.10877466251298026, "grad_norm": 5.402771949768066, "learning_rate": 4.993123252455288e-06, "loss": 0.4990957975387573, "step": 419 }, { "epoch": 0.10903426791277258, "grad_norm": 3.1906869411468506, "learning_rate": 4.993049148358103e-06, "loss": 0.43776464462280273, "step": 420 }, { "epoch": 0.1092938733125649, "grad_norm": 3.3023149967193604, "learning_rate": 4.992974647741188e-06, "loss": 0.41643890738487244, "step": 421 }, { "epoch": 0.10955347871235721, "grad_norm": 5.418334484100342, "learning_rate": 4.992899750617712e-06, "loss": 0.5188839435577393, "step": 422 }, { "epoch": 0.10981308411214953, "grad_norm": 17.61301040649414, "learning_rate": 4.9928244570009165e-06, "loss": 0.4297912120819092, "step": 423 }, { "epoch": 0.11007268951194185, "grad_norm": 5.931271553039551, "learning_rate": 4.99274876690411e-06, "loss": 0.42543360590934753, "step": 424 }, { "epoch": 0.11033229491173416, "grad_norm": 3.528001546859741, "learning_rate": 4.992672680340675e-06, "loss": 0.44461604952812195, "step": 425 }, { "epoch": 0.11059190031152648, "grad_norm": 6.358506202697754, "learning_rate": 4.9925961973240595e-06, "loss": 0.3941733241081238, "step": 426 }, { "epoch": 0.1108515057113188, "grad_norm": 4.244649887084961, "learning_rate": 4.992519317867784e-06, "loss": 0.4490964114665985, "step": 427 }, { "epoch": 0.1111111111111111, "grad_norm": 9.47954273223877, "learning_rate": 4.992442041985442e-06, "loss": 0.4783027768135071, "step": 428 }, { "epoch": 0.11137071651090343, "grad_norm": 4.258228302001953, "learning_rate": 4.9923643696906915e-06, "loss": 0.4205884337425232, "step": 429 }, { "epoch": 0.11163032191069575, "grad_norm": 4.22894287109375, "learning_rate": 4.992286300997263e-06, "loss": 0.45681366324424744, "step": 430 }, { "epoch": 0.11188992731048805, "grad_norm": 3.7759501934051514, "learning_rate": 4.992207835918959e-06, "loss": 0.5205523371696472, "step": 431 }, { "epoch": 0.11214953271028037, "grad_norm": 4.188932418823242, "learning_rate": 4.99212897446965e-06, "loss": 0.42231807112693787, "step": 432 }, { "epoch": 0.11240913811007269, "grad_norm": 2.6179375648498535, "learning_rate": 4.992049716663274e-06, "loss": 0.432325541973114, "step": 433 }, { "epoch": 0.112668743509865, "grad_norm": 3.403902053833008, "learning_rate": 4.991970062513845e-06, "loss": 0.42542627453804016, "step": 434 }, { "epoch": 0.11292834890965732, "grad_norm": 4.138727188110352, "learning_rate": 4.991890012035444e-06, "loss": 0.5517829656600952, "step": 435 }, { "epoch": 0.11318795430944964, "grad_norm": 68.35316467285156, "learning_rate": 4.991809565242221e-06, "loss": 0.5385382771492004, "step": 436 }, { "epoch": 0.11344755970924195, "grad_norm": 12.58847427368164, "learning_rate": 4.991728722148398e-06, "loss": 0.45991051197052, "step": 437 }, { "epoch": 0.11370716510903427, "grad_norm": 4.740567207336426, "learning_rate": 4.991647482768265e-06, "loss": 0.5399333238601685, "step": 438 }, { "epoch": 0.11396677050882659, "grad_norm": 5.028296947479248, "learning_rate": 4.991565847116184e-06, "loss": 0.511888861656189, "step": 439 }, { "epoch": 0.1142263759086189, "grad_norm": 6.521610260009766, "learning_rate": 4.991483815206586e-06, "loss": 0.45697760581970215, "step": 440 }, { "epoch": 0.11448598130841121, "grad_norm": 3.8660433292388916, "learning_rate": 4.991401387053973e-06, "loss": 0.427493691444397, "step": 441 }, { "epoch": 0.11474558670820353, "grad_norm": 6.5271501541137695, "learning_rate": 4.991318562672917e-06, "loss": 0.48384320735931396, "step": 442 }, { "epoch": 0.11500519210799584, "grad_norm": 5.17435359954834, "learning_rate": 4.991235342078058e-06, "loss": 0.472913920879364, "step": 443 }, { "epoch": 0.11526479750778816, "grad_norm": 3.915404796600342, "learning_rate": 4.9911517252841066e-06, "loss": 0.414094477891922, "step": 444 }, { "epoch": 0.11552440290758048, "grad_norm": 7.414904594421387, "learning_rate": 4.991067712305848e-06, "loss": 0.6394424438476562, "step": 445 }, { "epoch": 0.11578400830737279, "grad_norm": 3.6802620887756348, "learning_rate": 4.9909833031581294e-06, "loss": 0.44983941316604614, "step": 446 }, { "epoch": 0.11604361370716511, "grad_norm": 3.9253342151641846, "learning_rate": 4.990898497855876e-06, "loss": 0.5043781995773315, "step": 447 }, { "epoch": 0.11630321910695743, "grad_norm": 7.357441425323486, "learning_rate": 4.990813296414077e-06, "loss": 0.5536998510360718, "step": 448 }, { "epoch": 0.11656282450674973, "grad_norm": 7.424095630645752, "learning_rate": 4.990727698847796e-06, "loss": 0.5095422267913818, "step": 449 }, { "epoch": 0.11682242990654206, "grad_norm": 4.101597309112549, "learning_rate": 4.990641705172163e-06, "loss": 0.5054322481155396, "step": 450 }, { "epoch": 0.11708203530633438, "grad_norm": 6.140098571777344, "learning_rate": 4.99055531540238e-06, "loss": 0.5410080552101135, "step": 451 }, { "epoch": 0.11734164070612668, "grad_norm": 6.645506381988525, "learning_rate": 4.99046852955372e-06, "loss": 0.5242952704429626, "step": 452 }, { "epoch": 0.117601246105919, "grad_norm": 6.761953830718994, "learning_rate": 4.990381347641524e-06, "loss": 0.40787750482559204, "step": 453 }, { "epoch": 0.11786085150571132, "grad_norm": 5.316078186035156, "learning_rate": 4.9902937696812034e-06, "loss": 0.3780360817909241, "step": 454 }, { "epoch": 0.11812045690550363, "grad_norm": 4.452262878417969, "learning_rate": 4.99020579568824e-06, "loss": 0.49903202056884766, "step": 455 }, { "epoch": 0.11838006230529595, "grad_norm": 5.226681232452393, "learning_rate": 4.990117425678186e-06, "loss": 0.4459652006626129, "step": 456 }, { "epoch": 0.11863966770508827, "grad_norm": 4.417540550231934, "learning_rate": 4.990028659666663e-06, "loss": 0.44444137811660767, "step": 457 }, { "epoch": 0.11889927310488058, "grad_norm": 7.4588212966918945, "learning_rate": 4.989939497669363e-06, "loss": 0.4421077072620392, "step": 458 }, { "epoch": 0.1191588785046729, "grad_norm": 4.8512678146362305, "learning_rate": 4.989849939702047e-06, "loss": 0.49545592069625854, "step": 459 }, { "epoch": 0.11941848390446522, "grad_norm": 4.571129322052002, "learning_rate": 4.989759985780548e-06, "loss": 0.42855215072631836, "step": 460 }, { "epoch": 0.11967808930425752, "grad_norm": 4.793543815612793, "learning_rate": 4.989669635920767e-06, "loss": 0.46311116218566895, "step": 461 }, { "epoch": 0.11993769470404984, "grad_norm": 5.658203601837158, "learning_rate": 4.989578890138676e-06, "loss": 0.3824612498283386, "step": 462 }, { "epoch": 0.12019730010384216, "grad_norm": 1.7833009958267212, "learning_rate": 4.989487748450318e-06, "loss": 0.4166397452354431, "step": 463 }, { "epoch": 0.12045690550363447, "grad_norm": 9.162005424499512, "learning_rate": 4.9893962108718015e-06, "loss": 0.6399606466293335, "step": 464 }, { "epoch": 0.12071651090342679, "grad_norm": 4.3770599365234375, "learning_rate": 4.989304277419311e-06, "loss": 0.5730549097061157, "step": 465 }, { "epoch": 0.12097611630321911, "grad_norm": 8.151185989379883, "learning_rate": 4.989211948109099e-06, "loss": 0.5726807117462158, "step": 466 }, { "epoch": 0.12123572170301142, "grad_norm": 8.096189498901367, "learning_rate": 4.989119222957483e-06, "loss": 0.535588264465332, "step": 467 }, { "epoch": 0.12149532710280374, "grad_norm": 5.3171000480651855, "learning_rate": 4.98902610198086e-06, "loss": 0.5635818243026733, "step": 468 }, { "epoch": 0.12175493250259606, "grad_norm": 7.807260513305664, "learning_rate": 4.988932585195688e-06, "loss": 0.5921921133995056, "step": 469 }, { "epoch": 0.12201453790238836, "grad_norm": 3.169217348098755, "learning_rate": 4.988838672618499e-06, "loss": 0.41780662536621094, "step": 470 }, { "epoch": 0.12227414330218069, "grad_norm": 10.762792587280273, "learning_rate": 4.988744364265896e-06, "loss": 0.5438511371612549, "step": 471 }, { "epoch": 0.122533748701973, "grad_norm": 4.050555229187012, "learning_rate": 4.988649660154551e-06, "loss": 0.4996591806411743, "step": 472 }, { "epoch": 0.12279335410176531, "grad_norm": 8.634578704833984, "learning_rate": 4.988554560301203e-06, "loss": 0.4942517876625061, "step": 473 }, { "epoch": 0.12305295950155763, "grad_norm": 8.848898887634277, "learning_rate": 4.988459064722664e-06, "loss": 0.3556513786315918, "step": 474 }, { "epoch": 0.12331256490134995, "grad_norm": 3.72186017036438, "learning_rate": 4.988363173435818e-06, "loss": 0.48734456300735474, "step": 475 }, { "epoch": 0.12357217030114226, "grad_norm": 7.204815864562988, "learning_rate": 4.9882668864576135e-06, "loss": 0.5066211223602295, "step": 476 }, { "epoch": 0.12383177570093458, "grad_norm": 6.3965325355529785, "learning_rate": 4.988170203805074e-06, "loss": 0.4699963331222534, "step": 477 }, { "epoch": 0.1240913811007269, "grad_norm": 6.484414577484131, "learning_rate": 4.9880731254952885e-06, "loss": 0.444282591342926, "step": 478 }, { "epoch": 0.1243509865005192, "grad_norm": 4.442004203796387, "learning_rate": 4.987975651545421e-06, "loss": 0.40129682421684265, "step": 479 }, { "epoch": 0.12461059190031153, "grad_norm": 6.731329917907715, "learning_rate": 4.9878777819727e-06, "loss": 0.42712539434432983, "step": 480 }, { "epoch": 0.12487019730010385, "grad_norm": 4.707566738128662, "learning_rate": 4.9877795167944285e-06, "loss": 0.4443056583404541, "step": 481 }, { "epoch": 0.12512980269989615, "grad_norm": 8.242801666259766, "learning_rate": 4.987680856027976e-06, "loss": 0.50754714012146, "step": 482 }, { "epoch": 0.12538940809968846, "grad_norm": 6.1576995849609375, "learning_rate": 4.987581799690785e-06, "loss": 0.5149681568145752, "step": 483 }, { "epoch": 0.1256490134994808, "grad_norm": 2.911613941192627, "learning_rate": 4.987482347800365e-06, "loss": 0.3871539235115051, "step": 484 }, { "epoch": 0.1259086188992731, "grad_norm": 4.447214603424072, "learning_rate": 4.987382500374298e-06, "loss": 0.61224764585495, "step": 485 }, { "epoch": 0.1261682242990654, "grad_norm": 9.29373836517334, "learning_rate": 4.987282257430234e-06, "loss": 0.5661545395851135, "step": 486 }, { "epoch": 0.12642782969885774, "grad_norm": 3.040036916732788, "learning_rate": 4.987181618985893e-06, "loss": 0.5064644813537598, "step": 487 }, { "epoch": 0.12668743509865005, "grad_norm": 2.9151430130004883, "learning_rate": 4.987080585059068e-06, "loss": 0.4260159134864807, "step": 488 }, { "epoch": 0.12694704049844235, "grad_norm": 6.606950283050537, "learning_rate": 4.9869791556676175e-06, "loss": 0.48735836148262024, "step": 489 }, { "epoch": 0.1272066458982347, "grad_norm": 2.758770704269409, "learning_rate": 4.986877330829472e-06, "loss": 0.4269605278968811, "step": 490 }, { "epoch": 0.127466251298027, "grad_norm": 3.1296162605285645, "learning_rate": 4.986775110562632e-06, "loss": 0.44720959663391113, "step": 491 }, { "epoch": 0.1277258566978193, "grad_norm": 6.147182464599609, "learning_rate": 4.9866724948851685e-06, "loss": 0.5239644050598145, "step": 492 }, { "epoch": 0.12798546209761164, "grad_norm": 5.636440753936768, "learning_rate": 4.98656948381522e-06, "loss": 0.45152294635772705, "step": 493 }, { "epoch": 0.12824506749740394, "grad_norm": 4.43963098526001, "learning_rate": 4.986466077370998e-06, "loss": 0.43977832794189453, "step": 494 }, { "epoch": 0.12850467289719625, "grad_norm": 8.292168617248535, "learning_rate": 4.9863622755707815e-06, "loss": 0.5616459846496582, "step": 495 }, { "epoch": 0.12876427829698858, "grad_norm": 2.5528979301452637, "learning_rate": 4.986258078432921e-06, "loss": 0.4561668038368225, "step": 496 }, { "epoch": 0.1290238836967809, "grad_norm": 7.400587558746338, "learning_rate": 4.986153485975835e-06, "loss": 0.5669654011726379, "step": 497 }, { "epoch": 0.1292834890965732, "grad_norm": 3.437511444091797, "learning_rate": 4.986048498218014e-06, "loss": 0.4876917004585266, "step": 498 }, { "epoch": 0.12954309449636553, "grad_norm": 5.485934734344482, "learning_rate": 4.985943115178018e-06, "loss": 0.5901495218276978, "step": 499 }, { "epoch": 0.12980269989615784, "grad_norm": 4.5830183029174805, "learning_rate": 4.985837336874475e-06, "loss": 0.4475491940975189, "step": 500 }, { "epoch": 0.13006230529595014, "grad_norm": 4.488611698150635, "learning_rate": 4.985731163326084e-06, "loss": 0.5706274509429932, "step": 501 }, { "epoch": 0.13032191069574248, "grad_norm": 4.243246555328369, "learning_rate": 4.985624594551616e-06, "loss": 0.4759644567966461, "step": 502 }, { "epoch": 0.13058151609553478, "grad_norm": 3.8463335037231445, "learning_rate": 4.985517630569908e-06, "loss": 0.39586377143859863, "step": 503 }, { "epoch": 0.1308411214953271, "grad_norm": 3.456817150115967, "learning_rate": 4.98541027139987e-06, "loss": 0.4323771595954895, "step": 504 }, { "epoch": 0.13110072689511942, "grad_norm": 4.629668712615967, "learning_rate": 4.98530251706048e-06, "loss": 0.5264617204666138, "step": 505 }, { "epoch": 0.13136033229491173, "grad_norm": 3.571604013442993, "learning_rate": 4.9851943675707864e-06, "loss": 0.4570789933204651, "step": 506 }, { "epoch": 0.13161993769470404, "grad_norm": 5.187135219573975, "learning_rate": 4.985085822949908e-06, "loss": 0.4276350736618042, "step": 507 }, { "epoch": 0.13187954309449637, "grad_norm": 5.701794624328613, "learning_rate": 4.984976883217032e-06, "loss": 0.4968237578868866, "step": 508 }, { "epoch": 0.13213914849428868, "grad_norm": 3.1850290298461914, "learning_rate": 4.984867548391418e-06, "loss": 0.4125601053237915, "step": 509 }, { "epoch": 0.13239875389408098, "grad_norm": 4.560277938842773, "learning_rate": 4.984757818492393e-06, "loss": 0.4184044599533081, "step": 510 }, { "epoch": 0.13265835929387332, "grad_norm": 2.366057872772217, "learning_rate": 4.984647693539355e-06, "loss": 0.40925508737564087, "step": 511 }, { "epoch": 0.13291796469366562, "grad_norm": 1.6031137704849243, "learning_rate": 4.984537173551772e-06, "loss": 0.407886803150177, "step": 512 }, { "epoch": 0.13317757009345793, "grad_norm": 3.6763949394226074, "learning_rate": 4.98442625854918e-06, "loss": 0.4935030937194824, "step": 513 }, { "epoch": 0.13343717549325027, "grad_norm": 4.221203804016113, "learning_rate": 4.984314948551187e-06, "loss": 0.4823238253593445, "step": 514 }, { "epoch": 0.13369678089304257, "grad_norm": 5.3972978591918945, "learning_rate": 4.98420324357747e-06, "loss": 0.4897490441799164, "step": 515 }, { "epoch": 0.13395638629283488, "grad_norm": 5.019381046295166, "learning_rate": 4.984091143647777e-06, "loss": 0.5635701417922974, "step": 516 }, { "epoch": 0.1342159916926272, "grad_norm": 4.818643093109131, "learning_rate": 4.983978648781923e-06, "loss": 0.4595264196395874, "step": 517 }, { "epoch": 0.13447559709241952, "grad_norm": 4.758942127227783, "learning_rate": 4.983865758999795e-06, "loss": 0.487060546875, "step": 518 }, { "epoch": 0.13473520249221183, "grad_norm": 2.923048257827759, "learning_rate": 4.98375247432135e-06, "loss": 0.39177680015563965, "step": 519 }, { "epoch": 0.13499480789200416, "grad_norm": 4.112105369567871, "learning_rate": 4.983638794766613e-06, "loss": 0.47005388140678406, "step": 520 }, { "epoch": 0.13525441329179647, "grad_norm": 4.818210601806641, "learning_rate": 4.9835247203556815e-06, "loss": 0.5198639035224915, "step": 521 }, { "epoch": 0.13551401869158877, "grad_norm": 3.493656873703003, "learning_rate": 4.9834102511087205e-06, "loss": 0.4024009704589844, "step": 522 }, { "epoch": 0.1357736240913811, "grad_norm": 4.751536846160889, "learning_rate": 4.983295387045965e-06, "loss": 0.5635366439819336, "step": 523 }, { "epoch": 0.1360332294911734, "grad_norm": 2.8217861652374268, "learning_rate": 4.98318012818772e-06, "loss": 0.3929491639137268, "step": 524 }, { "epoch": 0.13629283489096572, "grad_norm": 3.0487725734710693, "learning_rate": 4.983064474554362e-06, "loss": 0.42114683985710144, "step": 525 }, { "epoch": 0.13655244029075805, "grad_norm": 5.345431804656982, "learning_rate": 4.9829484261663355e-06, "loss": 0.5700342655181885, "step": 526 }, { "epoch": 0.13681204569055036, "grad_norm": 6.034809589385986, "learning_rate": 4.982831983044155e-06, "loss": 0.38292890787124634, "step": 527 }, { "epoch": 0.13707165109034267, "grad_norm": 3.71313738822937, "learning_rate": 4.982715145208405e-06, "loss": 0.42444926500320435, "step": 528 }, { "epoch": 0.137331256490135, "grad_norm": 3.297471761703491, "learning_rate": 4.982597912679739e-06, "loss": 0.3965129852294922, "step": 529 }, { "epoch": 0.1375908618899273, "grad_norm": 5.7637038230896, "learning_rate": 4.9824802854788825e-06, "loss": 0.5132381916046143, "step": 530 }, { "epoch": 0.1378504672897196, "grad_norm": 5.202768325805664, "learning_rate": 4.982362263626629e-06, "loss": 0.39122554659843445, "step": 531 }, { "epoch": 0.13811007268951195, "grad_norm": 3.324673891067505, "learning_rate": 4.9822438471438404e-06, "loss": 0.4078780710697174, "step": 532 }, { "epoch": 0.13836967808930425, "grad_norm": 4.122550964355469, "learning_rate": 4.982125036051452e-06, "loss": 0.40936771035194397, "step": 533 }, { "epoch": 0.13862928348909656, "grad_norm": 4.698622703552246, "learning_rate": 4.982005830370466e-06, "loss": 0.5052698850631714, "step": 534 }, { "epoch": 0.1388888888888889, "grad_norm": 6.716699600219727, "learning_rate": 4.981886230121956e-06, "loss": 0.49213463068008423, "step": 535 }, { "epoch": 0.1391484942886812, "grad_norm": 2.914647340774536, "learning_rate": 4.981766235327062e-06, "loss": 0.44230303168296814, "step": 536 }, { "epoch": 0.1394080996884735, "grad_norm": 5.271180629730225, "learning_rate": 4.981645846007e-06, "loss": 0.41681310534477234, "step": 537 }, { "epoch": 0.13966770508826584, "grad_norm": 4.77512264251709, "learning_rate": 4.98152506218305e-06, "loss": 0.5200923681259155, "step": 538 }, { "epoch": 0.13992731048805815, "grad_norm": 4.884916305541992, "learning_rate": 4.981403883876564e-06, "loss": 0.5001978874206543, "step": 539 }, { "epoch": 0.14018691588785046, "grad_norm": 3.8458945751190186, "learning_rate": 4.981282311108964e-06, "loss": 0.4093615412712097, "step": 540 }, { "epoch": 0.1404465212876428, "grad_norm": 8.845970153808594, "learning_rate": 4.98116034390174e-06, "loss": 0.5361051559448242, "step": 541 }, { "epoch": 0.1407061266874351, "grad_norm": 3.8765554428100586, "learning_rate": 4.981037982276456e-06, "loss": 0.46769657731056213, "step": 542 }, { "epoch": 0.1409657320872274, "grad_norm": 5.188159942626953, "learning_rate": 4.980915226254739e-06, "loss": 0.4382452368736267, "step": 543 }, { "epoch": 0.14122533748701974, "grad_norm": 3.4234397411346436, "learning_rate": 4.980792075858291e-06, "loss": 0.42352360486984253, "step": 544 }, { "epoch": 0.14148494288681204, "grad_norm": 3.8816747665405273, "learning_rate": 4.9806685311088834e-06, "loss": 0.4568791687488556, "step": 545 }, { "epoch": 0.14174454828660435, "grad_norm": 2.5859553813934326, "learning_rate": 4.980544592028354e-06, "loss": 0.40890276432037354, "step": 546 }, { "epoch": 0.14200415368639668, "grad_norm": 4.172756195068359, "learning_rate": 4.980420258638615e-06, "loss": 0.41402357816696167, "step": 547 }, { "epoch": 0.142263759086189, "grad_norm": 4.5434417724609375, "learning_rate": 4.980295530961643e-06, "loss": 0.4435521364212036, "step": 548 }, { "epoch": 0.1425233644859813, "grad_norm": 4.88698673248291, "learning_rate": 4.980170409019488e-06, "loss": 0.4357866644859314, "step": 549 }, { "epoch": 0.14278296988577363, "grad_norm": 5.166161060333252, "learning_rate": 4.980044892834269e-06, "loss": 0.3909970223903656, "step": 550 }, { "epoch": 0.14304257528556594, "grad_norm": 3.266367197036743, "learning_rate": 4.979918982428174e-06, "loss": 0.5007011890411377, "step": 551 }, { "epoch": 0.14330218068535824, "grad_norm": 6.698180675506592, "learning_rate": 4.9797926778234615e-06, "loss": 0.43079856038093567, "step": 552 }, { "epoch": 0.14356178608515058, "grad_norm": 3.524786949157715, "learning_rate": 4.9796659790424595e-06, "loss": 0.40056151151657104, "step": 553 }, { "epoch": 0.14382139148494288, "grad_norm": 2.3861610889434814, "learning_rate": 4.979538886107565e-06, "loss": 0.40527230501174927, "step": 554 }, { "epoch": 0.1440809968847352, "grad_norm": 3.0946412086486816, "learning_rate": 4.979411399041244e-06, "loss": 0.4169374108314514, "step": 555 }, { "epoch": 0.14434060228452752, "grad_norm": 3.129420280456543, "learning_rate": 4.979283517866036e-06, "loss": 0.44289126992225647, "step": 556 }, { "epoch": 0.14460020768431983, "grad_norm": 6.024947643280029, "learning_rate": 4.979155242604545e-06, "loss": 0.5026830434799194, "step": 557 }, { "epoch": 0.14485981308411214, "grad_norm": 4.883155822753906, "learning_rate": 4.979026573279447e-06, "loss": 0.49079644680023193, "step": 558 }, { "epoch": 0.14511941848390447, "grad_norm": 2.680999755859375, "learning_rate": 4.97889750991349e-06, "loss": 0.40493452548980713, "step": 559 }, { "epoch": 0.14537902388369678, "grad_norm": 3.5142505168914795, "learning_rate": 4.978768052529488e-06, "loss": 0.48949673771858215, "step": 560 }, { "epoch": 0.14563862928348908, "grad_norm": 7.532229900360107, "learning_rate": 4.978638201150327e-06, "loss": 0.46807023882865906, "step": 561 }, { "epoch": 0.14589823468328142, "grad_norm": 4.466492652893066, "learning_rate": 4.9785079557989605e-06, "loss": 0.4595901072025299, "step": 562 }, { "epoch": 0.14615784008307373, "grad_norm": 5.659477233886719, "learning_rate": 4.978377316498414e-06, "loss": 0.47865015268325806, "step": 563 }, { "epoch": 0.14641744548286603, "grad_norm": 1.9787251949310303, "learning_rate": 4.97824628327178e-06, "loss": 0.4029911756515503, "step": 564 }, { "epoch": 0.14667705088265837, "grad_norm": 3.475024938583374, "learning_rate": 4.978114856142224e-06, "loss": 0.43051302433013916, "step": 565 }, { "epoch": 0.14693665628245067, "grad_norm": 3.2974472045898438, "learning_rate": 4.977983035132977e-06, "loss": 0.44740334153175354, "step": 566 }, { "epoch": 0.14719626168224298, "grad_norm": 5.043542861938477, "learning_rate": 4.977850820267346e-06, "loss": 0.45235276222229004, "step": 567 }, { "epoch": 0.1474558670820353, "grad_norm": 3.7615468502044678, "learning_rate": 4.9777182115686995e-06, "loss": 0.4339011311531067, "step": 568 }, { "epoch": 0.14771547248182762, "grad_norm": 3.188081741333008, "learning_rate": 4.977585209060481e-06, "loss": 0.4662698209285736, "step": 569 }, { "epoch": 0.14797507788161993, "grad_norm": 5.139828681945801, "learning_rate": 4.977451812766203e-06, "loss": 0.5621873140335083, "step": 570 }, { "epoch": 0.14823468328141226, "grad_norm": 4.057642936706543, "learning_rate": 4.977318022709445e-06, "loss": 0.5402652621269226, "step": 571 }, { "epoch": 0.14849428868120457, "grad_norm": 3.519535541534424, "learning_rate": 4.977183838913862e-06, "loss": 0.4160043001174927, "step": 572 }, { "epoch": 0.14875389408099687, "grad_norm": 8.645358085632324, "learning_rate": 4.97704926140317e-06, "loss": 0.473563015460968, "step": 573 }, { "epoch": 0.1490134994807892, "grad_norm": 2.782449960708618, "learning_rate": 4.9769142902011615e-06, "loss": 0.4703660309314728, "step": 574 }, { "epoch": 0.14927310488058151, "grad_norm": 6.71249532699585, "learning_rate": 4.9767789253316964e-06, "loss": 0.4835863709449768, "step": 575 }, { "epoch": 0.14953271028037382, "grad_norm": 5.629760265350342, "learning_rate": 4.976643166818704e-06, "loss": 0.44052886962890625, "step": 576 }, { "epoch": 0.14979231568016615, "grad_norm": 4.701119422912598, "learning_rate": 4.976507014686183e-06, "loss": 0.5660954713821411, "step": 577 }, { "epoch": 0.15005192107995846, "grad_norm": 2.35831356048584, "learning_rate": 4.976370468958201e-06, "loss": 0.4142773151397705, "step": 578 }, { "epoch": 0.15031152647975077, "grad_norm": 7.111921787261963, "learning_rate": 4.976233529658898e-06, "loss": 0.4206070303916931, "step": 579 }, { "epoch": 0.1505711318795431, "grad_norm": 7.895639419555664, "learning_rate": 4.9760961968124815e-06, "loss": 0.455823689699173, "step": 580 }, { "epoch": 0.1508307372793354, "grad_norm": 3.1066548824310303, "learning_rate": 4.975958470443228e-06, "loss": 0.39855682849884033, "step": 581 }, { "epoch": 0.15109034267912771, "grad_norm": 4.775622367858887, "learning_rate": 4.9758203505754845e-06, "loss": 0.4940792918205261, "step": 582 }, { "epoch": 0.15134994807892005, "grad_norm": 5.355891704559326, "learning_rate": 4.975681837233668e-06, "loss": 0.40516898036003113, "step": 583 }, { "epoch": 0.15160955347871236, "grad_norm": 4.851274013519287, "learning_rate": 4.975542930442263e-06, "loss": 0.4326617121696472, "step": 584 }, { "epoch": 0.15186915887850466, "grad_norm": 5.3988213539123535, "learning_rate": 4.975403630225827e-06, "loss": 0.5612162947654724, "step": 585 }, { "epoch": 0.152128764278297, "grad_norm": 4.879323959350586, "learning_rate": 4.975263936608984e-06, "loss": 0.35481542348861694, "step": 586 }, { "epoch": 0.1523883696780893, "grad_norm": 2.1441991329193115, "learning_rate": 4.975123849616429e-06, "loss": 0.4090525507926941, "step": 587 }, { "epoch": 0.1526479750778816, "grad_norm": 4.785078525543213, "learning_rate": 4.974983369272925e-06, "loss": 0.37846630811691284, "step": 588 }, { "epoch": 0.15290758047767394, "grad_norm": 7.9185099601745605, "learning_rate": 4.9748424956033076e-06, "loss": 0.4877920150756836, "step": 589 }, { "epoch": 0.15316718587746625, "grad_norm": 2.8863744735717773, "learning_rate": 4.9747012286324784e-06, "loss": 0.38130488991737366, "step": 590 }, { "epoch": 0.15342679127725856, "grad_norm": 3.9749937057495117, "learning_rate": 4.9745595683854115e-06, "loss": 0.4304489493370056, "step": 591 }, { "epoch": 0.1536863966770509, "grad_norm": 5.521031379699707, "learning_rate": 4.974417514887148e-06, "loss": 0.49033135175704956, "step": 592 }, { "epoch": 0.1539460020768432, "grad_norm": 5.037997245788574, "learning_rate": 4.9742750681628e-06, "loss": 0.4792112112045288, "step": 593 }, { "epoch": 0.1542056074766355, "grad_norm": 2.270946979522705, "learning_rate": 4.97413222823755e-06, "loss": 0.41485488414764404, "step": 594 }, { "epoch": 0.15446521287642784, "grad_norm": 7.642820358276367, "learning_rate": 4.973988995136648e-06, "loss": 0.5208946466445923, "step": 595 }, { "epoch": 0.15472481827622014, "grad_norm": 4.2401227951049805, "learning_rate": 4.9738453688854145e-06, "loss": 0.42350295186042786, "step": 596 }, { "epoch": 0.15498442367601245, "grad_norm": 3.885835886001587, "learning_rate": 4.973701349509238e-06, "loss": 0.4684147238731384, "step": 597 }, { "epoch": 0.15524402907580478, "grad_norm": 2.8638851642608643, "learning_rate": 4.973556937033579e-06, "loss": 0.3765237629413605, "step": 598 }, { "epoch": 0.1555036344755971, "grad_norm": 3.2166833877563477, "learning_rate": 4.973412131483966e-06, "loss": 0.41516759991645813, "step": 599 }, { "epoch": 0.1557632398753894, "grad_norm": 4.753665924072266, "learning_rate": 4.973266932885999e-06, "loss": 0.4058469831943512, "step": 600 }, { "epoch": 0.15602284527518173, "grad_norm": 6.858180046081543, "learning_rate": 4.973121341265343e-06, "loss": 0.4961075782775879, "step": 601 }, { "epoch": 0.15628245067497404, "grad_norm": 4.421675205230713, "learning_rate": 4.9729753566477376e-06, "loss": 0.49924153089523315, "step": 602 }, { "epoch": 0.15654205607476634, "grad_norm": 4.023726940155029, "learning_rate": 4.972828979058988e-06, "loss": 0.5430727005004883, "step": 603 }, { "epoch": 0.15680166147455868, "grad_norm": 3.7027971744537354, "learning_rate": 4.972682208524971e-06, "loss": 0.4281099736690521, "step": 604 }, { "epoch": 0.15706126687435099, "grad_norm": 3.3810036182403564, "learning_rate": 4.972535045071632e-06, "loss": 0.4100213050842285, "step": 605 }, { "epoch": 0.1573208722741433, "grad_norm": 2.9549918174743652, "learning_rate": 4.972387488724986e-06, "loss": 0.4362281560897827, "step": 606 }, { "epoch": 0.15758047767393563, "grad_norm": 3.925501585006714, "learning_rate": 4.972239539511119e-06, "loss": 0.4453914761543274, "step": 607 }, { "epoch": 0.15784008307372793, "grad_norm": 2.8403472900390625, "learning_rate": 4.9720911974561835e-06, "loss": 0.40518221259117126, "step": 608 }, { "epoch": 0.15809968847352024, "grad_norm": 6.974108695983887, "learning_rate": 4.971942462586403e-06, "loss": 0.46630972623825073, "step": 609 }, { "epoch": 0.15835929387331257, "grad_norm": 5.298018455505371, "learning_rate": 4.971793334928071e-06, "loss": 0.39844489097595215, "step": 610 }, { "epoch": 0.15861889927310488, "grad_norm": 9.629158020019531, "learning_rate": 4.9716438145075505e-06, "loss": 0.54801344871521, "step": 611 }, { "epoch": 0.1588785046728972, "grad_norm": 8.626191139221191, "learning_rate": 4.971493901351272e-06, "loss": 0.48875245451927185, "step": 612 }, { "epoch": 0.15913811007268952, "grad_norm": 2.9213368892669678, "learning_rate": 4.971343595485736e-06, "loss": 0.5618195533752441, "step": 613 }, { "epoch": 0.15939771547248183, "grad_norm": 4.805420398712158, "learning_rate": 4.971192896937516e-06, "loss": 0.4650375545024872, "step": 614 }, { "epoch": 0.15965732087227413, "grad_norm": 2.330608367919922, "learning_rate": 4.97104180573325e-06, "loss": 0.39627525210380554, "step": 615 }, { "epoch": 0.15991692627206647, "grad_norm": 10.789729118347168, "learning_rate": 4.970890321899647e-06, "loss": 0.47701096534729004, "step": 616 }, { "epoch": 0.16017653167185877, "grad_norm": 3.5172083377838135, "learning_rate": 4.970738445463488e-06, "loss": 0.5249626040458679, "step": 617 }, { "epoch": 0.16043613707165108, "grad_norm": 4.061378479003906, "learning_rate": 4.9705861764516195e-06, "loss": 0.49836504459381104, "step": 618 }, { "epoch": 0.16069574247144341, "grad_norm": 7.9369049072265625, "learning_rate": 4.97043351489096e-06, "loss": 0.4159799814224243, "step": 619 }, { "epoch": 0.16095534787123572, "grad_norm": 5.135136127471924, "learning_rate": 4.970280460808495e-06, "loss": 0.5212286710739136, "step": 620 }, { "epoch": 0.16121495327102803, "grad_norm": 5.842394828796387, "learning_rate": 4.970127014231283e-06, "loss": 0.39218753576278687, "step": 621 }, { "epoch": 0.16147455867082036, "grad_norm": 5.428141117095947, "learning_rate": 4.969973175186449e-06, "loss": 0.4774446487426758, "step": 622 }, { "epoch": 0.16173416407061267, "grad_norm": 5.151580333709717, "learning_rate": 4.969818943701189e-06, "loss": 0.45472967624664307, "step": 623 }, { "epoch": 0.16199376947040497, "grad_norm": 3.6495003700256348, "learning_rate": 4.969664319802766e-06, "loss": 0.40642279386520386, "step": 624 }, { "epoch": 0.1622533748701973, "grad_norm": 4.733207702636719, "learning_rate": 4.9695093035185154e-06, "loss": 0.42266416549682617, "step": 625 }, { "epoch": 0.16251298026998962, "grad_norm": 3.914456367492676, "learning_rate": 4.96935389487584e-06, "loss": 0.3745306134223938, "step": 626 }, { "epoch": 0.16277258566978192, "grad_norm": 4.844422340393066, "learning_rate": 4.969198093902212e-06, "loss": 0.4796900153160095, "step": 627 }, { "epoch": 0.16303219106957426, "grad_norm": 3.22635817527771, "learning_rate": 4.969041900625174e-06, "loss": 0.43351566791534424, "step": 628 }, { "epoch": 0.16329179646936656, "grad_norm": 4.4425764083862305, "learning_rate": 4.968885315072338e-06, "loss": 0.45028936862945557, "step": 629 }, { "epoch": 0.16355140186915887, "grad_norm": 4.35629415512085, "learning_rate": 4.968728337271383e-06, "loss": 0.450461745262146, "step": 630 }, { "epoch": 0.1638110072689512, "grad_norm": 4.7446160316467285, "learning_rate": 4.968570967250061e-06, "loss": 0.40362146496772766, "step": 631 }, { "epoch": 0.1640706126687435, "grad_norm": 5.060612678527832, "learning_rate": 4.9684132050361896e-06, "loss": 0.43406087160110474, "step": 632 }, { "epoch": 0.16433021806853582, "grad_norm": 4.878486156463623, "learning_rate": 4.968255050657658e-06, "loss": 0.4562380313873291, "step": 633 }, { "epoch": 0.16458982346832815, "grad_norm": 4.8465118408203125, "learning_rate": 4.968096504142426e-06, "loss": 0.47121548652648926, "step": 634 }, { "epoch": 0.16484942886812046, "grad_norm": 5.560269355773926, "learning_rate": 4.96793756551852e-06, "loss": 0.4170961380004883, "step": 635 }, { "epoch": 0.16510903426791276, "grad_norm": 7.019543647766113, "learning_rate": 4.967778234814035e-06, "loss": 0.41675546765327454, "step": 636 }, { "epoch": 0.1653686396677051, "grad_norm": 6.273468971252441, "learning_rate": 4.96761851205714e-06, "loss": 0.5248928070068359, "step": 637 }, { "epoch": 0.1656282450674974, "grad_norm": 5.7214508056640625, "learning_rate": 4.9674583972760676e-06, "loss": 0.4961697459220886, "step": 638 }, { "epoch": 0.1658878504672897, "grad_norm": 4.296957015991211, "learning_rate": 4.967297890499124e-06, "loss": 0.533170223236084, "step": 639 }, { "epoch": 0.16614745586708204, "grad_norm": 3.217339277267456, "learning_rate": 4.967136991754683e-06, "loss": 0.36066362261772156, "step": 640 }, { "epoch": 0.16640706126687435, "grad_norm": 7.417873382568359, "learning_rate": 4.966975701071188e-06, "loss": 0.39757949113845825, "step": 641 }, { "epoch": 0.16666666666666666, "grad_norm": 6.581031322479248, "learning_rate": 4.96681401847715e-06, "loss": 0.4816833734512329, "step": 642 }, { "epoch": 0.166926272066459, "grad_norm": 7.470818042755127, "learning_rate": 4.966651944001153e-06, "loss": 0.5409841537475586, "step": 643 }, { "epoch": 0.1671858774662513, "grad_norm": 6.0322346687316895, "learning_rate": 4.966489477671846e-06, "loss": 0.4125547707080841, "step": 644 }, { "epoch": 0.1674454828660436, "grad_norm": 9.019966125488281, "learning_rate": 4.966326619517951e-06, "loss": 0.5073610544204712, "step": 645 }, { "epoch": 0.16770508826583594, "grad_norm": 6.588280200958252, "learning_rate": 4.966163369568256e-06, "loss": 0.3928745985031128, "step": 646 }, { "epoch": 0.16796469366562825, "grad_norm": 7.8965840339660645, "learning_rate": 4.965999727851621e-06, "loss": 0.5252716541290283, "step": 647 }, { "epoch": 0.16822429906542055, "grad_norm": 3.785126209259033, "learning_rate": 4.965835694396973e-06, "loss": 0.4192432761192322, "step": 648 }, { "epoch": 0.16848390446521289, "grad_norm": 4.822234630584717, "learning_rate": 4.965671269233312e-06, "loss": 0.4858238697052002, "step": 649 }, { "epoch": 0.1687435098650052, "grad_norm": 9.95834732055664, "learning_rate": 4.9655064523897015e-06, "loss": 0.4734245836734772, "step": 650 }, { "epoch": 0.1690031152647975, "grad_norm": 10.77355670928955, "learning_rate": 4.965341243895279e-06, "loss": 0.5897024869918823, "step": 651 }, { "epoch": 0.16926272066458983, "grad_norm": 7.250357151031494, "learning_rate": 4.9651756437792485e-06, "loss": 0.542411208152771, "step": 652 }, { "epoch": 0.16952232606438214, "grad_norm": 6.609310626983643, "learning_rate": 4.965009652070885e-06, "loss": 0.5424877405166626, "step": 653 }, { "epoch": 0.16978193146417445, "grad_norm": 6.647575378417969, "learning_rate": 4.964843268799533e-06, "loss": 0.4247736930847168, "step": 654 }, { "epoch": 0.17004153686396678, "grad_norm": 6.627710819244385, "learning_rate": 4.964676493994604e-06, "loss": 0.45983704924583435, "step": 655 }, { "epoch": 0.1703011422637591, "grad_norm": 2.350557327270508, "learning_rate": 4.964509327685579e-06, "loss": 0.37700745463371277, "step": 656 }, { "epoch": 0.1705607476635514, "grad_norm": 5.505250453948975, "learning_rate": 4.964341769902012e-06, "loss": 0.5306976437568665, "step": 657 }, { "epoch": 0.17082035306334373, "grad_norm": 9.844902038574219, "learning_rate": 4.964173820673521e-06, "loss": 0.42204558849334717, "step": 658 }, { "epoch": 0.17107995846313603, "grad_norm": 7.031623363494873, "learning_rate": 4.964005480029797e-06, "loss": 0.40300095081329346, "step": 659 }, { "epoch": 0.17133956386292834, "grad_norm": 4.38377046585083, "learning_rate": 4.963836748000597e-06, "loss": 0.44131404161453247, "step": 660 }, { "epoch": 0.17159916926272067, "grad_norm": 4.912672996520996, "learning_rate": 4.963667624615751e-06, "loss": 0.4675649404525757, "step": 661 }, { "epoch": 0.17185877466251298, "grad_norm": 6.6803975105285645, "learning_rate": 4.9634981099051545e-06, "loss": 0.4476730227470398, "step": 662 }, { "epoch": 0.1721183800623053, "grad_norm": 6.349928379058838, "learning_rate": 4.963328203898775e-06, "loss": 0.4654144048690796, "step": 663 }, { "epoch": 0.17237798546209762, "grad_norm": 7.949074745178223, "learning_rate": 4.963157906626648e-06, "loss": 0.4684339761734009, "step": 664 }, { "epoch": 0.17263759086188993, "grad_norm": 4.70531702041626, "learning_rate": 4.9629872181188774e-06, "loss": 0.45842015743255615, "step": 665 }, { "epoch": 0.17289719626168223, "grad_norm": 5.162790775299072, "learning_rate": 4.962816138405637e-06, "loss": 0.4387383759021759, "step": 666 }, { "epoch": 0.17315680166147457, "grad_norm": 4.429661750793457, "learning_rate": 4.9626446675171704e-06, "loss": 0.39815354347229004, "step": 667 }, { "epoch": 0.17341640706126688, "grad_norm": 7.086657524108887, "learning_rate": 4.962472805483789e-06, "loss": 0.4228631258010864, "step": 668 }, { "epoch": 0.17367601246105918, "grad_norm": 7.893679618835449, "learning_rate": 4.962300552335875e-06, "loss": 0.47719600796699524, "step": 669 }, { "epoch": 0.17393561786085152, "grad_norm": 4.120937347412109, "learning_rate": 4.962127908103878e-06, "loss": 0.4893237054347992, "step": 670 }, { "epoch": 0.17419522326064382, "grad_norm": 3.4944143295288086, "learning_rate": 4.961954872818318e-06, "loss": 0.4570407569408417, "step": 671 }, { "epoch": 0.17445482866043613, "grad_norm": 6.570262432098389, "learning_rate": 4.961781446509784e-06, "loss": 0.5480052828788757, "step": 672 }, { "epoch": 0.17471443406022846, "grad_norm": 7.849591255187988, "learning_rate": 4.961607629208933e-06, "loss": 0.39215806126594543, "step": 673 }, { "epoch": 0.17497403946002077, "grad_norm": 7.637180328369141, "learning_rate": 4.961433420946492e-06, "loss": 0.5775356292724609, "step": 674 }, { "epoch": 0.17523364485981308, "grad_norm": 1.4592374563217163, "learning_rate": 4.961258821753257e-06, "loss": 0.4128004312515259, "step": 675 }, { "epoch": 0.1754932502596054, "grad_norm": 2.6439270973205566, "learning_rate": 4.961083831660095e-06, "loss": 0.4466286599636078, "step": 676 }, { "epoch": 0.17575285565939772, "grad_norm": 5.89976692199707, "learning_rate": 4.960908450697937e-06, "loss": 0.5264344215393066, "step": 677 }, { "epoch": 0.17601246105919002, "grad_norm": 9.049721717834473, "learning_rate": 4.960732678897788e-06, "loss": 0.4932531714439392, "step": 678 }, { "epoch": 0.17627206645898236, "grad_norm": 15.387346267700195, "learning_rate": 4.960556516290721e-06, "loss": 0.5494062900543213, "step": 679 }, { "epoch": 0.17653167185877466, "grad_norm": 3.581822395324707, "learning_rate": 4.960379962907878e-06, "loss": 0.4430345296859741, "step": 680 }, { "epoch": 0.17679127725856697, "grad_norm": 4.768352031707764, "learning_rate": 4.960203018780467e-06, "loss": 0.40963131189346313, "step": 681 }, { "epoch": 0.1770508826583593, "grad_norm": 9.787641525268555, "learning_rate": 4.9600256839397695e-06, "loss": 0.45412102341651917, "step": 682 }, { "epoch": 0.1773104880581516, "grad_norm": 8.932350158691406, "learning_rate": 4.959847958417134e-06, "loss": 0.46488335728645325, "step": 683 }, { "epoch": 0.17757009345794392, "grad_norm": 10.689441680908203, "learning_rate": 4.959669842243979e-06, "loss": 0.4957699775695801, "step": 684 }, { "epoch": 0.17782969885773625, "grad_norm": 9.847832679748535, "learning_rate": 4.95949133545179e-06, "loss": 0.5886994004249573, "step": 685 }, { "epoch": 0.17808930425752856, "grad_norm": 6.757986545562744, "learning_rate": 4.959312438072123e-06, "loss": 0.4935387969017029, "step": 686 }, { "epoch": 0.17834890965732086, "grad_norm": 7.664475917816162, "learning_rate": 4.959133150136605e-06, "loss": 0.5678622126579285, "step": 687 }, { "epoch": 0.1786085150571132, "grad_norm": 12.654040336608887, "learning_rate": 4.958953471676927e-06, "loss": 0.4713536500930786, "step": 688 }, { "epoch": 0.1788681204569055, "grad_norm": 4.0747599601745605, "learning_rate": 4.958773402724854e-06, "loss": 0.45275402069091797, "step": 689 }, { "epoch": 0.1791277258566978, "grad_norm": 2.514535665512085, "learning_rate": 4.958592943312218e-06, "loss": 0.4329811632633209, "step": 690 }, { "epoch": 0.17938733125649015, "grad_norm": 8.986869812011719, "learning_rate": 4.958412093470919e-06, "loss": 0.5845493078231812, "step": 691 }, { "epoch": 0.17964693665628245, "grad_norm": 7.440794467926025, "learning_rate": 4.958230853232928e-06, "loss": 0.5007561445236206, "step": 692 }, { "epoch": 0.17990654205607476, "grad_norm": 7.466744899749756, "learning_rate": 4.958049222630285e-06, "loss": 0.519059419631958, "step": 693 }, { "epoch": 0.1801661474558671, "grad_norm": 6.005471706390381, "learning_rate": 4.957867201695096e-06, "loss": 0.45612967014312744, "step": 694 }, { "epoch": 0.1804257528556594, "grad_norm": 4.722077369689941, "learning_rate": 4.957684790459539e-06, "loss": 0.43822139501571655, "step": 695 }, { "epoch": 0.1806853582554517, "grad_norm": 7.321015357971191, "learning_rate": 4.957501988955861e-06, "loss": 0.5382785201072693, "step": 696 }, { "epoch": 0.18094496365524404, "grad_norm": 5.630250453948975, "learning_rate": 4.9573187972163765e-06, "loss": 0.4141409397125244, "step": 697 }, { "epoch": 0.18120456905503635, "grad_norm": 3.4700753688812256, "learning_rate": 4.9571352152734696e-06, "loss": 0.4537573754787445, "step": 698 }, { "epoch": 0.18146417445482865, "grad_norm": 3.0617613792419434, "learning_rate": 4.956951243159593e-06, "loss": 0.4358789622783661, "step": 699 }, { "epoch": 0.181723779854621, "grad_norm": 3.720277786254883, "learning_rate": 4.956766880907269e-06, "loss": 0.41854754090309143, "step": 700 }, { "epoch": 0.1819833852544133, "grad_norm": 3.718637704849243, "learning_rate": 4.956582128549089e-06, "loss": 0.394420325756073, "step": 701 }, { "epoch": 0.1822429906542056, "grad_norm": 4.631192684173584, "learning_rate": 4.9563969861177126e-06, "loss": 0.4898313283920288, "step": 702 }, { "epoch": 0.18250259605399793, "grad_norm": 6.091010093688965, "learning_rate": 4.9562114536458686e-06, "loss": 0.5377552509307861, "step": 703 }, { "epoch": 0.18276220145379024, "grad_norm": 4.086174011230469, "learning_rate": 4.956025531166356e-06, "loss": 0.4484245777130127, "step": 704 }, { "epoch": 0.18302180685358255, "grad_norm": 4.847433090209961, "learning_rate": 4.955839218712039e-06, "loss": 0.45670264959335327, "step": 705 }, { "epoch": 0.18328141225337488, "grad_norm": 4.983518123626709, "learning_rate": 4.955652516315856e-06, "loss": 0.5078898668289185, "step": 706 }, { "epoch": 0.1835410176531672, "grad_norm": 2.494081497192383, "learning_rate": 4.955465424010812e-06, "loss": 0.4143308997154236, "step": 707 }, { "epoch": 0.1838006230529595, "grad_norm": 8.277965545654297, "learning_rate": 4.955277941829978e-06, "loss": 0.41533422470092773, "step": 708 }, { "epoch": 0.18406022845275183, "grad_norm": 14.353231430053711, "learning_rate": 4.955090069806499e-06, "loss": 0.4630325734615326, "step": 709 }, { "epoch": 0.18431983385254413, "grad_norm": 4.102137088775635, "learning_rate": 4.954901807973586e-06, "loss": 0.35169053077697754, "step": 710 }, { "epoch": 0.18457943925233644, "grad_norm": 6.903706073760986, "learning_rate": 4.954713156364517e-06, "loss": 0.4171766936779022, "step": 711 }, { "epoch": 0.18483904465212878, "grad_norm": 4.859437942504883, "learning_rate": 4.954524115012645e-06, "loss": 0.4171614646911621, "step": 712 }, { "epoch": 0.18509865005192108, "grad_norm": 3.822474479675293, "learning_rate": 4.9543346839513856e-06, "loss": 0.40428781509399414, "step": 713 }, { "epoch": 0.1853582554517134, "grad_norm": 2.282806396484375, "learning_rate": 4.954144863214226e-06, "loss": 0.42758095264434814, "step": 714 }, { "epoch": 0.18561786085150572, "grad_norm": 4.708287715911865, "learning_rate": 4.953954652834724e-06, "loss": 0.43213653564453125, "step": 715 }, { "epoch": 0.18587746625129803, "grad_norm": 5.212218761444092, "learning_rate": 4.953764052846502e-06, "loss": 0.44884181022644043, "step": 716 }, { "epoch": 0.18613707165109034, "grad_norm": 5.424969673156738, "learning_rate": 4.953573063283257e-06, "loss": 0.4313010275363922, "step": 717 }, { "epoch": 0.18639667705088267, "grad_norm": 2.5065414905548096, "learning_rate": 4.953381684178748e-06, "loss": 0.3752084970474243, "step": 718 }, { "epoch": 0.18665628245067498, "grad_norm": 4.948586463928223, "learning_rate": 4.9531899155668076e-06, "loss": 0.3938220739364624, "step": 719 }, { "epoch": 0.18691588785046728, "grad_norm": 4.943246841430664, "learning_rate": 4.952997757481338e-06, "loss": 0.48629891872406006, "step": 720 }, { "epoch": 0.18717549325025962, "grad_norm": 8.662168502807617, "learning_rate": 4.952805209956306e-06, "loss": 0.5353413820266724, "step": 721 }, { "epoch": 0.18743509865005192, "grad_norm": 3.9847991466522217, "learning_rate": 4.95261227302575e-06, "loss": 0.5671135187149048, "step": 722 }, { "epoch": 0.18769470404984423, "grad_norm": 4.072120666503906, "learning_rate": 4.952418946723778e-06, "loss": 0.4624062180519104, "step": 723 }, { "epoch": 0.18795430944963656, "grad_norm": 4.851650714874268, "learning_rate": 4.952225231084565e-06, "loss": 0.44251060485839844, "step": 724 }, { "epoch": 0.18821391484942887, "grad_norm": 3.440446138381958, "learning_rate": 4.9520311261423556e-06, "loss": 0.47629818320274353, "step": 725 }, { "epoch": 0.18847352024922118, "grad_norm": 3.04734468460083, "learning_rate": 4.951836631931461e-06, "loss": 0.4339742958545685, "step": 726 }, { "epoch": 0.1887331256490135, "grad_norm": 2.436107635498047, "learning_rate": 4.951641748486268e-06, "loss": 0.38685232400894165, "step": 727 }, { "epoch": 0.18899273104880582, "grad_norm": 3.623565196990967, "learning_rate": 4.951446475841223e-06, "loss": 0.48340511322021484, "step": 728 }, { "epoch": 0.18925233644859812, "grad_norm": 9.408638954162598, "learning_rate": 4.951250814030847e-06, "loss": 0.5653465390205383, "step": 729 }, { "epoch": 0.18951194184839046, "grad_norm": 3.260601282119751, "learning_rate": 4.951054763089731e-06, "loss": 0.4241333305835724, "step": 730 }, { "epoch": 0.18977154724818276, "grad_norm": 5.303624629974365, "learning_rate": 4.95085832305253e-06, "loss": 0.5546416640281677, "step": 731 }, { "epoch": 0.19003115264797507, "grad_norm": 5.745920181274414, "learning_rate": 4.950661493953969e-06, "loss": 0.5239241123199463, "step": 732 }, { "epoch": 0.1902907580477674, "grad_norm": 3.1498584747314453, "learning_rate": 4.950464275828845e-06, "loss": 0.392193078994751, "step": 733 }, { "epoch": 0.1905503634475597, "grad_norm": 3.379657030105591, "learning_rate": 4.9502666687120215e-06, "loss": 0.41689714789390564, "step": 734 }, { "epoch": 0.19080996884735202, "grad_norm": 4.451575756072998, "learning_rate": 4.95006867263843e-06, "loss": 0.39206308126449585, "step": 735 }, { "epoch": 0.19106957424714435, "grad_norm": 3.1807408332824707, "learning_rate": 4.949870287643072e-06, "loss": 0.44536107778549194, "step": 736 }, { "epoch": 0.19132917964693666, "grad_norm": 2.9686641693115234, "learning_rate": 4.949671513761018e-06, "loss": 0.4409957826137543, "step": 737 }, { "epoch": 0.19158878504672897, "grad_norm": 2.195521116256714, "learning_rate": 4.949472351027405e-06, "loss": 0.46418726444244385, "step": 738 }, { "epoch": 0.1918483904465213, "grad_norm": 3.9589805603027344, "learning_rate": 4.949272799477442e-06, "loss": 0.4353652596473694, "step": 739 }, { "epoch": 0.1921079958463136, "grad_norm": 5.9824628829956055, "learning_rate": 4.949072859146406e-06, "loss": 0.3692234456539154, "step": 740 }, { "epoch": 0.1923676012461059, "grad_norm": 4.307103633880615, "learning_rate": 4.948872530069639e-06, "loss": 0.4228411912918091, "step": 741 }, { "epoch": 0.19262720664589825, "grad_norm": 3.6221277713775635, "learning_rate": 4.948671812282557e-06, "loss": 0.4571298062801361, "step": 742 }, { "epoch": 0.19288681204569055, "grad_norm": 3.2487049102783203, "learning_rate": 4.948470705820642e-06, "loss": 0.4149661660194397, "step": 743 }, { "epoch": 0.19314641744548286, "grad_norm": 3.7862911224365234, "learning_rate": 4.948269210719443e-06, "loss": 0.4306761622428894, "step": 744 }, { "epoch": 0.1934060228452752, "grad_norm": 2.722661018371582, "learning_rate": 4.948067327014583e-06, "loss": 0.3987133502960205, "step": 745 }, { "epoch": 0.1936656282450675, "grad_norm": 9.653118133544922, "learning_rate": 4.947865054741748e-06, "loss": 0.41870367527008057, "step": 746 }, { "epoch": 0.1939252336448598, "grad_norm": 4.232216835021973, "learning_rate": 4.947662393936695e-06, "loss": 0.5656744241714478, "step": 747 }, { "epoch": 0.19418483904465214, "grad_norm": 8.075809478759766, "learning_rate": 4.947459344635251e-06, "loss": 0.47709327936172485, "step": 748 }, { "epoch": 0.19444444444444445, "grad_norm": 3.9063029289245605, "learning_rate": 4.9472559068733104e-06, "loss": 0.4723561406135559, "step": 749 }, { "epoch": 0.19470404984423675, "grad_norm": 4.572449684143066, "learning_rate": 4.9470520806868356e-06, "loss": 0.43773746490478516, "step": 750 }, { "epoch": 0.1949636552440291, "grad_norm": 3.2634236812591553, "learning_rate": 4.946847866111859e-06, "loss": 0.42635011672973633, "step": 751 }, { "epoch": 0.1952232606438214, "grad_norm": 2.9362030029296875, "learning_rate": 4.9466432631844805e-06, "loss": 0.40188103914260864, "step": 752 }, { "epoch": 0.1954828660436137, "grad_norm": 4.463234901428223, "learning_rate": 4.946438271940869e-06, "loss": 0.4349896311759949, "step": 753 }, { "epoch": 0.19574247144340604, "grad_norm": 8.071248054504395, "learning_rate": 4.946232892417264e-06, "loss": 0.42015981674194336, "step": 754 }, { "epoch": 0.19600207684319834, "grad_norm": 8.274728775024414, "learning_rate": 4.94602712464997e-06, "loss": 0.5796993970870972, "step": 755 }, { "epoch": 0.19626168224299065, "grad_norm": 3.6425352096557617, "learning_rate": 4.945820968675363e-06, "loss": 0.4986696243286133, "step": 756 }, { "epoch": 0.19652128764278298, "grad_norm": 4.483649730682373, "learning_rate": 4.945614424529886e-06, "loss": 0.4141484797000885, "step": 757 }, { "epoch": 0.1967808930425753, "grad_norm": 7.252917289733887, "learning_rate": 4.945407492250052e-06, "loss": 0.5435575842857361, "step": 758 }, { "epoch": 0.1970404984423676, "grad_norm": 3.479353189468384, "learning_rate": 4.945200171872442e-06, "loss": 0.35892951488494873, "step": 759 }, { "epoch": 0.19730010384215993, "grad_norm": 5.601675033569336, "learning_rate": 4.944992463433704e-06, "loss": 0.42571768164634705, "step": 760 }, { "epoch": 0.19755970924195224, "grad_norm": 2.5916531085968018, "learning_rate": 4.944784366970558e-06, "loss": 0.4359284043312073, "step": 761 }, { "epoch": 0.19781931464174454, "grad_norm": 3.2682082653045654, "learning_rate": 4.944575882519789e-06, "loss": 0.4046768546104431, "step": 762 }, { "epoch": 0.19807892004153688, "grad_norm": 5.8206257820129395, "learning_rate": 4.944367010118254e-06, "loss": 0.5090787410736084, "step": 763 }, { "epoch": 0.19833852544132918, "grad_norm": 3.438040018081665, "learning_rate": 4.944157749802876e-06, "loss": 0.47757524251937866, "step": 764 }, { "epoch": 0.1985981308411215, "grad_norm": 7.137020111083984, "learning_rate": 4.9439481016106465e-06, "loss": 0.4863269329071045, "step": 765 }, { "epoch": 0.19885773624091382, "grad_norm": 5.35149621963501, "learning_rate": 4.943738065578628e-06, "loss": 0.5843947529792786, "step": 766 }, { "epoch": 0.19911734164070613, "grad_norm": 6.225343227386475, "learning_rate": 4.943527641743949e-06, "loss": 0.4844297766685486, "step": 767 }, { "epoch": 0.19937694704049844, "grad_norm": 5.820602893829346, "learning_rate": 4.9433168301438084e-06, "loss": 0.4584214687347412, "step": 768 }, { "epoch": 0.19963655244029077, "grad_norm": 5.501189708709717, "learning_rate": 4.943105630815472e-06, "loss": 0.5056040287017822, "step": 769 }, { "epoch": 0.19989615784008308, "grad_norm": 5.139389991760254, "learning_rate": 4.942894043796276e-06, "loss": 0.4392760992050171, "step": 770 }, { "epoch": 0.20015576323987538, "grad_norm": 2.8660733699798584, "learning_rate": 4.942682069123623e-06, "loss": 0.3769621253013611, "step": 771 }, { "epoch": 0.20041536863966772, "grad_norm": 2.612196922302246, "learning_rate": 4.942469706834987e-06, "loss": 0.38168060779571533, "step": 772 }, { "epoch": 0.20067497403946002, "grad_norm": 4.897942066192627, "learning_rate": 4.942256956967907e-06, "loss": 0.4976491630077362, "step": 773 }, { "epoch": 0.20093457943925233, "grad_norm": 7.918035507202148, "learning_rate": 4.942043819559993e-06, "loss": 0.4980745017528534, "step": 774 }, { "epoch": 0.20119418483904467, "grad_norm": 3.046721935272217, "learning_rate": 4.941830294648924e-06, "loss": 0.4200249910354614, "step": 775 }, { "epoch": 0.20145379023883697, "grad_norm": 4.152204513549805, "learning_rate": 4.941616382272444e-06, "loss": 0.3654070794582367, "step": 776 }, { "epoch": 0.20171339563862928, "grad_norm": 5.850683689117432, "learning_rate": 4.94140208246837e-06, "loss": 0.4689580500125885, "step": 777 }, { "epoch": 0.2019730010384216, "grad_norm": 4.998443126678467, "learning_rate": 4.941187395274584e-06, "loss": 0.43881452083587646, "step": 778 }, { "epoch": 0.20223260643821392, "grad_norm": 3.5291495323181152, "learning_rate": 4.940972320729036e-06, "loss": 0.41285979747772217, "step": 779 }, { "epoch": 0.20249221183800623, "grad_norm": 4.421243667602539, "learning_rate": 4.940756858869751e-06, "loss": 0.40372228622436523, "step": 780 }, { "epoch": 0.20275181723779856, "grad_norm": 3.4035041332244873, "learning_rate": 4.940541009734814e-06, "loss": 0.5559270977973938, "step": 781 }, { "epoch": 0.20301142263759087, "grad_norm": 3.798179864883423, "learning_rate": 4.940324773362383e-06, "loss": 0.4595130681991577, "step": 782 }, { "epoch": 0.20327102803738317, "grad_norm": 4.288979530334473, "learning_rate": 4.940108149790684e-06, "loss": 0.5074107050895691, "step": 783 }, { "epoch": 0.2035306334371755, "grad_norm": 2.4176862239837646, "learning_rate": 4.939891139058011e-06, "loss": 0.3928662836551666, "step": 784 }, { "epoch": 0.2037902388369678, "grad_norm": 4.9653472900390625, "learning_rate": 4.939673741202726e-06, "loss": 0.49184370040893555, "step": 785 }, { "epoch": 0.20404984423676012, "grad_norm": 2.431661605834961, "learning_rate": 4.939455956263262e-06, "loss": 0.3755214810371399, "step": 786 }, { "epoch": 0.20430944963655245, "grad_norm": 3.6089184284210205, "learning_rate": 4.9392377842781156e-06, "loss": 0.4597274661064148, "step": 787 }, { "epoch": 0.20456905503634476, "grad_norm": 2.945220947265625, "learning_rate": 4.939019225285856e-06, "loss": 0.47284865379333496, "step": 788 }, { "epoch": 0.20482866043613707, "grad_norm": 3.668858051300049, "learning_rate": 4.938800279325119e-06, "loss": 0.42972517013549805, "step": 789 }, { "epoch": 0.2050882658359294, "grad_norm": 2.7108631134033203, "learning_rate": 4.93858094643461e-06, "loss": 0.4064463973045349, "step": 790 }, { "epoch": 0.2053478712357217, "grad_norm": 3.1718590259552, "learning_rate": 4.938361226653101e-06, "loss": 0.43218499422073364, "step": 791 }, { "epoch": 0.205607476635514, "grad_norm": 2.51731276512146, "learning_rate": 4.938141120019435e-06, "loss": 0.4428822994232178, "step": 792 }, { "epoch": 0.20586708203530635, "grad_norm": 2.7391276359558105, "learning_rate": 4.9379206265725196e-06, "loss": 0.38972559571266174, "step": 793 }, { "epoch": 0.20612668743509865, "grad_norm": 6.193827152252197, "learning_rate": 4.937699746351334e-06, "loss": 0.39360469579696655, "step": 794 }, { "epoch": 0.20638629283489096, "grad_norm": 3.9732935428619385, "learning_rate": 4.937478479394925e-06, "loss": 0.42568349838256836, "step": 795 }, { "epoch": 0.2066458982346833, "grad_norm": 5.1906256675720215, "learning_rate": 4.937256825742409e-06, "loss": 0.3980858325958252, "step": 796 }, { "epoch": 0.2069055036344756, "grad_norm": 4.817687511444092, "learning_rate": 4.937034785432967e-06, "loss": 0.45974040031433105, "step": 797 }, { "epoch": 0.2071651090342679, "grad_norm": 4.1978631019592285, "learning_rate": 4.936812358505851e-06, "loss": 0.42724740505218506, "step": 798 }, { "epoch": 0.20742471443406024, "grad_norm": 2.8924930095672607, "learning_rate": 4.936589545000381e-06, "loss": 0.40742823481559753, "step": 799 }, { "epoch": 0.20768431983385255, "grad_norm": 5.71169376373291, "learning_rate": 4.936366344955947e-06, "loss": 0.49115294218063354, "step": 800 }, { "epoch": 0.20794392523364486, "grad_norm": 3.1583755016326904, "learning_rate": 4.936142758412004e-06, "loss": 0.38663166761398315, "step": 801 }, { "epoch": 0.2082035306334372, "grad_norm": 2.73445200920105, "learning_rate": 4.935918785408076e-06, "loss": 0.4597519338130951, "step": 802 }, { "epoch": 0.2084631360332295, "grad_norm": 4.884742736816406, "learning_rate": 4.935694425983759e-06, "loss": 0.5111476182937622, "step": 803 }, { "epoch": 0.2087227414330218, "grad_norm": 8.236618995666504, "learning_rate": 4.935469680178713e-06, "loss": 0.567768931388855, "step": 804 }, { "epoch": 0.2089823468328141, "grad_norm": 9.963324546813965, "learning_rate": 4.9352445480326675e-06, "loss": 0.4719159007072449, "step": 805 }, { "epoch": 0.20924195223260644, "grad_norm": 4.372432231903076, "learning_rate": 4.935019029585421e-06, "loss": 0.49558573961257935, "step": 806 }, { "epoch": 0.20950155763239875, "grad_norm": 7.002654075622559, "learning_rate": 4.934793124876842e-06, "loss": 0.525686502456665, "step": 807 }, { "epoch": 0.20976116303219106, "grad_norm": 3.7902660369873047, "learning_rate": 4.934566833946863e-06, "loss": 0.42086851596832275, "step": 808 }, { "epoch": 0.2100207684319834, "grad_norm": 2.400790214538574, "learning_rate": 4.934340156835488e-06, "loss": 0.4263274371623993, "step": 809 }, { "epoch": 0.2102803738317757, "grad_norm": 4.4365644454956055, "learning_rate": 4.934113093582787e-06, "loss": 0.44491663575172424, "step": 810 }, { "epoch": 0.210539979231568, "grad_norm": 2.267230987548828, "learning_rate": 4.933885644228902e-06, "loss": 0.3405749499797821, "step": 811 }, { "epoch": 0.21079958463136034, "grad_norm": 5.710740089416504, "learning_rate": 4.933657808814038e-06, "loss": 0.4985428750514984, "step": 812 }, { "epoch": 0.21105919003115264, "grad_norm": 3.453378438949585, "learning_rate": 4.933429587378473e-06, "loss": 0.40341630578041077, "step": 813 }, { "epoch": 0.21131879543094495, "grad_norm": 5.2551140785217285, "learning_rate": 4.933200979962551e-06, "loss": 0.4128681719303131, "step": 814 }, { "epoch": 0.21157840083073728, "grad_norm": 3.657749891281128, "learning_rate": 4.932971986606685e-06, "loss": 0.3825056552886963, "step": 815 }, { "epoch": 0.2118380062305296, "grad_norm": 3.1560587882995605, "learning_rate": 4.9327426073513555e-06, "loss": 0.38066351413726807, "step": 816 }, { "epoch": 0.2120976116303219, "grad_norm": 3.5747413635253906, "learning_rate": 4.9325128422371095e-06, "loss": 0.3586266040802002, "step": 817 }, { "epoch": 0.21235721703011423, "grad_norm": 2.1260018348693848, "learning_rate": 4.932282691304567e-06, "loss": 0.35115256905555725, "step": 818 }, { "epoch": 0.21261682242990654, "grad_norm": 4.605777740478516, "learning_rate": 4.932052154594413e-06, "loss": 0.5246914625167847, "step": 819 }, { "epoch": 0.21287642782969884, "grad_norm": 5.205435276031494, "learning_rate": 4.931821232147399e-06, "loss": 0.49820268154144287, "step": 820 }, { "epoch": 0.21313603322949118, "grad_norm": 4.413577556610107, "learning_rate": 4.931589924004349e-06, "loss": 0.4939556121826172, "step": 821 }, { "epoch": 0.21339563862928349, "grad_norm": 2.521761894226074, "learning_rate": 4.931358230206152e-06, "loss": 0.36058491468429565, "step": 822 }, { "epoch": 0.2136552440290758, "grad_norm": 3.7947564125061035, "learning_rate": 4.931126150793767e-06, "loss": 0.47431933879852295, "step": 823 }, { "epoch": 0.21391484942886813, "grad_norm": 1.987440824508667, "learning_rate": 4.930893685808219e-06, "loss": 0.39318642020225525, "step": 824 }, { "epoch": 0.21417445482866043, "grad_norm": 4.394032955169678, "learning_rate": 4.930660835290603e-06, "loss": 0.42975282669067383, "step": 825 }, { "epoch": 0.21443406022845274, "grad_norm": 4.452022075653076, "learning_rate": 4.930427599282082e-06, "loss": 0.528367280960083, "step": 826 }, { "epoch": 0.21469366562824507, "grad_norm": 1.7890292406082153, "learning_rate": 4.930193977823887e-06, "loss": 0.4084460139274597, "step": 827 }, { "epoch": 0.21495327102803738, "grad_norm": 3.263679265975952, "learning_rate": 4.929959970957316e-06, "loss": 0.46950507164001465, "step": 828 }, { "epoch": 0.21521287642782969, "grad_norm": 2.4093945026397705, "learning_rate": 4.929725578723738e-06, "loss": 0.45306649804115295, "step": 829 }, { "epoch": 0.21547248182762202, "grad_norm": 4.347055435180664, "learning_rate": 4.929490801164585e-06, "loss": 0.45444175601005554, "step": 830 }, { "epoch": 0.21573208722741433, "grad_norm": 4.143245697021484, "learning_rate": 4.929255638321363e-06, "loss": 0.39457085728645325, "step": 831 }, { "epoch": 0.21599169262720663, "grad_norm": 2.1667275428771973, "learning_rate": 4.9290200902356424e-06, "loss": 0.3809296488761902, "step": 832 }, { "epoch": 0.21625129802699897, "grad_norm": 3.00693678855896, "learning_rate": 4.928784156949062e-06, "loss": 0.41104209423065186, "step": 833 }, { "epoch": 0.21651090342679127, "grad_norm": 3.1683833599090576, "learning_rate": 4.928547838503331e-06, "loss": 0.4862413704395294, "step": 834 }, { "epoch": 0.21677050882658358, "grad_norm": 2.8980560302734375, "learning_rate": 4.928311134940224e-06, "loss": 0.3938526511192322, "step": 835 }, { "epoch": 0.21703011422637591, "grad_norm": 4.8786187171936035, "learning_rate": 4.928074046301586e-06, "loss": 0.5133539438247681, "step": 836 }, { "epoch": 0.21728971962616822, "grad_norm": 4.7666778564453125, "learning_rate": 4.9278365726293274e-06, "loss": 0.4884096086025238, "step": 837 }, { "epoch": 0.21754932502596053, "grad_norm": 3.4704251289367676, "learning_rate": 4.927598713965428e-06, "loss": 0.37992823123931885, "step": 838 }, { "epoch": 0.21780893042575286, "grad_norm": 4.295401096343994, "learning_rate": 4.927360470351937e-06, "loss": 0.4818390905857086, "step": 839 }, { "epoch": 0.21806853582554517, "grad_norm": 3.834932804107666, "learning_rate": 4.927121841830969e-06, "loss": 0.38558369874954224, "step": 840 }, { "epoch": 0.21832814122533747, "grad_norm": 3.6374752521514893, "learning_rate": 4.926882828444709e-06, "loss": 0.3667765259742737, "step": 841 }, { "epoch": 0.2185877466251298, "grad_norm": 2.747602939605713, "learning_rate": 4.92664343023541e-06, "loss": 0.4063146412372589, "step": 842 }, { "epoch": 0.21884735202492211, "grad_norm": 4.240715980529785, "learning_rate": 4.926403647245391e-06, "loss": 0.4157320261001587, "step": 843 }, { "epoch": 0.21910695742471442, "grad_norm": 3.5728089809417725, "learning_rate": 4.926163479517039e-06, "loss": 0.40445229411125183, "step": 844 }, { "epoch": 0.21936656282450676, "grad_norm": 4.388854503631592, "learning_rate": 4.9259229270928115e-06, "loss": 0.38119328022003174, "step": 845 }, { "epoch": 0.21962616822429906, "grad_norm": 3.661146402359009, "learning_rate": 4.925681990015233e-06, "loss": 0.44095441699028015, "step": 846 }, { "epoch": 0.21988577362409137, "grad_norm": 5.359996795654297, "learning_rate": 4.9254406683268955e-06, "loss": 0.5231080055236816, "step": 847 }, { "epoch": 0.2201453790238837, "grad_norm": 4.511241436004639, "learning_rate": 4.925198962070459e-06, "loss": 0.4984607994556427, "step": 848 }, { "epoch": 0.220404984423676, "grad_norm": 7.313656806945801, "learning_rate": 4.92495687128865e-06, "loss": 0.499011367559433, "step": 849 }, { "epoch": 0.22066458982346832, "grad_norm": 5.083765506744385, "learning_rate": 4.924714396024267e-06, "loss": 0.4964337944984436, "step": 850 }, { "epoch": 0.22092419522326065, "grad_norm": 3.6432085037231445, "learning_rate": 4.9244715363201735e-06, "loss": 0.4808107614517212, "step": 851 }, { "epoch": 0.22118380062305296, "grad_norm": 2.9978952407836914, "learning_rate": 4.924228292219301e-06, "loss": 0.40246230363845825, "step": 852 }, { "epoch": 0.22144340602284526, "grad_norm": 2.579927682876587, "learning_rate": 4.923984663764649e-06, "loss": 0.3739129304885864, "step": 853 }, { "epoch": 0.2217030114226376, "grad_norm": 2.617384910583496, "learning_rate": 4.923740650999287e-06, "loss": 0.4158531427383423, "step": 854 }, { "epoch": 0.2219626168224299, "grad_norm": 2.855520725250244, "learning_rate": 4.92349625396635e-06, "loss": 0.3943828344345093, "step": 855 }, { "epoch": 0.2222222222222222, "grad_norm": 4.944854736328125, "learning_rate": 4.923251472709041e-06, "loss": 0.41683509945869446, "step": 856 }, { "epoch": 0.22248182762201454, "grad_norm": 4.3547821044921875, "learning_rate": 4.923006307270632e-06, "loss": 0.503020167350769, "step": 857 }, { "epoch": 0.22274143302180685, "grad_norm": 3.0001275539398193, "learning_rate": 4.922760757694464e-06, "loss": 0.40549954771995544, "step": 858 }, { "epoch": 0.22300103842159916, "grad_norm": 3.6726696491241455, "learning_rate": 4.922514824023944e-06, "loss": 0.3856039047241211, "step": 859 }, { "epoch": 0.2232606438213915, "grad_norm": 2.9763846397399902, "learning_rate": 4.922268506302547e-06, "loss": 0.4039670526981354, "step": 860 }, { "epoch": 0.2235202492211838, "grad_norm": 5.097870826721191, "learning_rate": 4.922021804573815e-06, "loss": 0.5253324508666992, "step": 861 }, { "epoch": 0.2237798546209761, "grad_norm": 2.4952287673950195, "learning_rate": 4.921774718881362e-06, "loss": 0.39579635858535767, "step": 862 }, { "epoch": 0.22403946002076844, "grad_norm": 9.224420547485352, "learning_rate": 4.921527249268866e-06, "loss": 0.5277907848358154, "step": 863 }, { "epoch": 0.22429906542056074, "grad_norm": 7.630325794219971, "learning_rate": 4.921279395780073e-06, "loss": 0.46887117624282837, "step": 864 }, { "epoch": 0.22455867082035305, "grad_norm": 2.4590208530426025, "learning_rate": 4.921031158458799e-06, "loss": 0.38920873403549194, "step": 865 }, { "epoch": 0.22481827622014539, "grad_norm": 4.910033226013184, "learning_rate": 4.920782537348926e-06, "loss": 0.45698779821395874, "step": 866 }, { "epoch": 0.2250778816199377, "grad_norm": 3.8671963214874268, "learning_rate": 4.9205335324944045e-06, "loss": 0.40374940633773804, "step": 867 }, { "epoch": 0.22533748701973, "grad_norm": 2.866438627243042, "learning_rate": 4.9202841439392536e-06, "loss": 0.4171903729438782, "step": 868 }, { "epoch": 0.22559709241952233, "grad_norm": 3.4686906337738037, "learning_rate": 4.920034371727559e-06, "loss": 0.41588154435157776, "step": 869 }, { "epoch": 0.22585669781931464, "grad_norm": 3.2656991481781006, "learning_rate": 4.919784215903474e-06, "loss": 0.4397324025630951, "step": 870 }, { "epoch": 0.22611630321910695, "grad_norm": 7.901153087615967, "learning_rate": 4.9195336765112215e-06, "loss": 0.5009063482284546, "step": 871 }, { "epoch": 0.22637590861889928, "grad_norm": 4.335110187530518, "learning_rate": 4.919282753595091e-06, "loss": 0.37024927139282227, "step": 872 }, { "epoch": 0.2266355140186916, "grad_norm": 4.28739070892334, "learning_rate": 4.919031447199439e-06, "loss": 0.49200549721717834, "step": 873 }, { "epoch": 0.2268951194184839, "grad_norm": 1.6720455884933472, "learning_rate": 4.918779757368692e-06, "loss": 0.4188620150089264, "step": 874 }, { "epoch": 0.22715472481827623, "grad_norm": 2.035219430923462, "learning_rate": 4.918527684147342e-06, "loss": 0.36379432678222656, "step": 875 }, { "epoch": 0.22741433021806853, "grad_norm": 2.668374538421631, "learning_rate": 4.918275227579951e-06, "loss": 0.3888930678367615, "step": 876 }, { "epoch": 0.22767393561786084, "grad_norm": 4.274421691894531, "learning_rate": 4.918022387711145e-06, "loss": 0.5136396884918213, "step": 877 }, { "epoch": 0.22793354101765317, "grad_norm": 4.091736793518066, "learning_rate": 4.917769164585623e-06, "loss": 0.36270779371261597, "step": 878 }, { "epoch": 0.22819314641744548, "grad_norm": 3.3666858673095703, "learning_rate": 4.917515558248148e-06, "loss": 0.42499053478240967, "step": 879 }, { "epoch": 0.2284527518172378, "grad_norm": 2.9613447189331055, "learning_rate": 4.9172615687435525e-06, "loss": 0.4051811397075653, "step": 880 }, { "epoch": 0.22871235721703012, "grad_norm": 2.6646387577056885, "learning_rate": 4.917007196116734e-06, "loss": 0.3955056965351105, "step": 881 }, { "epoch": 0.22897196261682243, "grad_norm": 4.860342025756836, "learning_rate": 4.916752440412661e-06, "loss": 0.5034935474395752, "step": 882 }, { "epoch": 0.22923156801661473, "grad_norm": 3.3192532062530518, "learning_rate": 4.91649730167637e-06, "loss": 0.4018516540527344, "step": 883 }, { "epoch": 0.22949117341640707, "grad_norm": 2.6419146060943604, "learning_rate": 4.916241779952961e-06, "loss": 0.5084601640701294, "step": 884 }, { "epoch": 0.22975077881619937, "grad_norm": 3.2962422370910645, "learning_rate": 4.915985875287607e-06, "loss": 0.37265825271606445, "step": 885 }, { "epoch": 0.23001038421599168, "grad_norm": 5.196918487548828, "learning_rate": 4.915729587725544e-06, "loss": 0.41911599040031433, "step": 886 }, { "epoch": 0.23026998961578402, "grad_norm": 2.4703240394592285, "learning_rate": 4.915472917312079e-06, "loss": 0.439456969499588, "step": 887 }, { "epoch": 0.23052959501557632, "grad_norm": 2.9547290802001953, "learning_rate": 4.915215864092584e-06, "loss": 0.37993890047073364, "step": 888 }, { "epoch": 0.23078920041536863, "grad_norm": 6.208432197570801, "learning_rate": 4.914958428112502e-06, "loss": 0.5050886869430542, "step": 889 }, { "epoch": 0.23104880581516096, "grad_norm": 3.4184410572052, "learning_rate": 4.91470060941734e-06, "loss": 0.414436399936676, "step": 890 }, { "epoch": 0.23130841121495327, "grad_norm": 3.579608678817749, "learning_rate": 4.914442408052676e-06, "loss": 0.38211244344711304, "step": 891 }, { "epoch": 0.23156801661474558, "grad_norm": 4.418009281158447, "learning_rate": 4.9141838240641535e-06, "loss": 0.5165382027626038, "step": 892 }, { "epoch": 0.2318276220145379, "grad_norm": 3.212695598602295, "learning_rate": 4.913924857497483e-06, "loss": 0.3762771785259247, "step": 893 }, { "epoch": 0.23208722741433022, "grad_norm": 3.912693500518799, "learning_rate": 4.913665508398447e-06, "loss": 0.4105697572231293, "step": 894 }, { "epoch": 0.23234683281412252, "grad_norm": 3.731504440307617, "learning_rate": 4.913405776812888e-06, "loss": 0.3999348282814026, "step": 895 }, { "epoch": 0.23260643821391486, "grad_norm": 2.390886068344116, "learning_rate": 4.913145662786725e-06, "loss": 0.36600226163864136, "step": 896 }, { "epoch": 0.23286604361370716, "grad_norm": 8.7077054977417, "learning_rate": 4.912885166365938e-06, "loss": 0.4228421151638031, "step": 897 }, { "epoch": 0.23312564901349947, "grad_norm": 3.847168445587158, "learning_rate": 4.912624287596577e-06, "loss": 0.4850623607635498, "step": 898 }, { "epoch": 0.2333852544132918, "grad_norm": 1.9591885805130005, "learning_rate": 4.91236302652476e-06, "loss": 0.40490031242370605, "step": 899 }, { "epoch": 0.2336448598130841, "grad_norm": 4.038721561431885, "learning_rate": 4.9121013831966704e-06, "loss": 0.5009117126464844, "step": 900 }, { "epoch": 0.23390446521287642, "grad_norm": 5.167749404907227, "learning_rate": 4.911839357658562e-06, "loss": 0.38688400387763977, "step": 901 }, { "epoch": 0.23416407061266875, "grad_norm": 7.293368339538574, "learning_rate": 4.911576949956755e-06, "loss": 0.42463451623916626, "step": 902 }, { "epoch": 0.23442367601246106, "grad_norm": 5.479471683502197, "learning_rate": 4.9113141601376365e-06, "loss": 0.49033400416374207, "step": 903 }, { "epoch": 0.23468328141225336, "grad_norm": 3.0708558559417725, "learning_rate": 4.911050988247663e-06, "loss": 0.4116549491882324, "step": 904 }, { "epoch": 0.2349428868120457, "grad_norm": 5.805029392242432, "learning_rate": 4.910787434333355e-06, "loss": 0.405192494392395, "step": 905 }, { "epoch": 0.235202492211838, "grad_norm": 4.7316765785217285, "learning_rate": 4.910523498441304e-06, "loss": 0.3859322667121887, "step": 906 }, { "epoch": 0.2354620976116303, "grad_norm": 3.3208980560302734, "learning_rate": 4.91025918061817e-06, "loss": 0.37584879994392395, "step": 907 }, { "epoch": 0.23572170301142265, "grad_norm": 9.14486026763916, "learning_rate": 4.909994480910674e-06, "loss": 0.4466344714164734, "step": 908 }, { "epoch": 0.23598130841121495, "grad_norm": 6.853972911834717, "learning_rate": 4.909729399365613e-06, "loss": 0.35904985666275024, "step": 909 }, { "epoch": 0.23624091381100726, "grad_norm": 5.46750545501709, "learning_rate": 4.909463936029843e-06, "loss": 0.38803228735923767, "step": 910 }, { "epoch": 0.2365005192107996, "grad_norm": 6.656450271606445, "learning_rate": 4.909198090950296e-06, "loss": 0.5166047215461731, "step": 911 }, { "epoch": 0.2367601246105919, "grad_norm": 3.830596685409546, "learning_rate": 4.908931864173965e-06, "loss": 0.38955193758010864, "step": 912 }, { "epoch": 0.2370197300103842, "grad_norm": 7.545762538909912, "learning_rate": 4.908665255747914e-06, "loss": 0.43641743063926697, "step": 913 }, { "epoch": 0.23727933541017654, "grad_norm": 4.624361515045166, "learning_rate": 4.908398265719273e-06, "loss": 0.3818376958370209, "step": 914 }, { "epoch": 0.23753894080996885, "grad_norm": 3.5605509281158447, "learning_rate": 4.908130894135238e-06, "loss": 0.42627036571502686, "step": 915 }, { "epoch": 0.23779854620976115, "grad_norm": 2.3802266120910645, "learning_rate": 4.907863141043076e-06, "loss": 0.377732515335083, "step": 916 }, { "epoch": 0.2380581516095535, "grad_norm": 2.3925600051879883, "learning_rate": 4.90759500649012e-06, "loss": 0.4408583641052246, "step": 917 }, { "epoch": 0.2383177570093458, "grad_norm": 4.5084428787231445, "learning_rate": 4.9073264905237685e-06, "loss": 0.5077947378158569, "step": 918 }, { "epoch": 0.2385773624091381, "grad_norm": 2.6929771900177, "learning_rate": 4.907057593191489e-06, "loss": 0.42790651321411133, "step": 919 }, { "epoch": 0.23883696780893043, "grad_norm": 2.6714224815368652, "learning_rate": 4.906788314540819e-06, "loss": 0.3954455256462097, "step": 920 }, { "epoch": 0.23909657320872274, "grad_norm": 2.6902217864990234, "learning_rate": 4.906518654619358e-06, "loss": 0.38332486152648926, "step": 921 }, { "epoch": 0.23935617860851505, "grad_norm": 3.136535406112671, "learning_rate": 4.906248613474776e-06, "loss": 0.5278078317642212, "step": 922 }, { "epoch": 0.23961578400830738, "grad_norm": 3.426710367202759, "learning_rate": 4.905978191154811e-06, "loss": 0.5105568170547485, "step": 923 }, { "epoch": 0.2398753894080997, "grad_norm": 4.878451347351074, "learning_rate": 4.905707387707267e-06, "loss": 0.44373974204063416, "step": 924 }, { "epoch": 0.240134994807892, "grad_norm": 4.358166694641113, "learning_rate": 4.905436203180016e-06, "loss": 0.44366544485092163, "step": 925 }, { "epoch": 0.24039460020768433, "grad_norm": 3.73917818069458, "learning_rate": 4.9051646376209976e-06, "loss": 0.38313472270965576, "step": 926 }, { "epoch": 0.24065420560747663, "grad_norm": 3.721634864807129, "learning_rate": 4.904892691078218e-06, "loss": 0.4221554398536682, "step": 927 }, { "epoch": 0.24091381100726894, "grad_norm": 3.8043880462646484, "learning_rate": 4.904620363599752e-06, "loss": 0.4063631594181061, "step": 928 }, { "epoch": 0.24117341640706128, "grad_norm": 4.2229156494140625, "learning_rate": 4.904347655233738e-06, "loss": 0.4412512183189392, "step": 929 }, { "epoch": 0.24143302180685358, "grad_norm": 4.7606892585754395, "learning_rate": 4.904074566028388e-06, "loss": 0.39022552967071533, "step": 930 }, { "epoch": 0.2416926272066459, "grad_norm": 8.869595527648926, "learning_rate": 4.903801096031976e-06, "loss": 0.5813888311386108, "step": 931 }, { "epoch": 0.24195223260643822, "grad_norm": 2.7582638263702393, "learning_rate": 4.903527245292847e-06, "loss": 0.41307923197746277, "step": 932 }, { "epoch": 0.24221183800623053, "grad_norm": 3.226087808609009, "learning_rate": 4.903253013859408e-06, "loss": 0.41453316807746887, "step": 933 }, { "epoch": 0.24247144340602284, "grad_norm": 4.927990913391113, "learning_rate": 4.9029784017801404e-06, "loss": 0.3888663351535797, "step": 934 }, { "epoch": 0.24273104880581517, "grad_norm": 4.030057430267334, "learning_rate": 4.902703409103588e-06, "loss": 0.3844885528087616, "step": 935 }, { "epoch": 0.24299065420560748, "grad_norm": 4.548539161682129, "learning_rate": 4.902428035878363e-06, "loss": 0.41527873277664185, "step": 936 }, { "epoch": 0.24325025960539978, "grad_norm": 7.8926568031311035, "learning_rate": 4.902152282153145e-06, "loss": 0.4717792868614197, "step": 937 }, { "epoch": 0.24350986500519212, "grad_norm": 4.652360916137695, "learning_rate": 4.901876147976682e-06, "loss": 0.5074950456619263, "step": 938 }, { "epoch": 0.24376947040498442, "grad_norm": 8.07552719116211, "learning_rate": 4.901599633397787e-06, "loss": 0.3799345791339874, "step": 939 }, { "epoch": 0.24402907580477673, "grad_norm": 5.645258903503418, "learning_rate": 4.901322738465341e-06, "loss": 0.5279576778411865, "step": 940 }, { "epoch": 0.24428868120456906, "grad_norm": 6.164303302764893, "learning_rate": 4.901045463228295e-06, "loss": 0.5069224834442139, "step": 941 }, { "epoch": 0.24454828660436137, "grad_norm": 3.5396311283111572, "learning_rate": 4.900767807735664e-06, "loss": 0.4541066884994507, "step": 942 }, { "epoch": 0.24480789200415368, "grad_norm": 6.6439385414123535, "learning_rate": 4.90048977203653e-06, "loss": 0.44967034459114075, "step": 943 }, { "epoch": 0.245067497403946, "grad_norm": 2.614448070526123, "learning_rate": 4.900211356180044e-06, "loss": 0.3747042417526245, "step": 944 }, { "epoch": 0.24532710280373832, "grad_norm": 5.970014572143555, "learning_rate": 4.899932560215423e-06, "loss": 0.4570661783218384, "step": 945 }, { "epoch": 0.24558670820353062, "grad_norm": 2.7541697025299072, "learning_rate": 4.899653384191952e-06, "loss": 0.3896752595901489, "step": 946 }, { "epoch": 0.24584631360332296, "grad_norm": 7.007810115814209, "learning_rate": 4.899373828158984e-06, "loss": 0.49569427967071533, "step": 947 }, { "epoch": 0.24610591900311526, "grad_norm": 3.8915228843688965, "learning_rate": 4.899093892165938e-06, "loss": 0.42125868797302246, "step": 948 }, { "epoch": 0.24636552440290757, "grad_norm": 3.9090654850006104, "learning_rate": 4.898813576262299e-06, "loss": 0.38135847449302673, "step": 949 }, { "epoch": 0.2466251298026999, "grad_norm": 7.834505081176758, "learning_rate": 4.8985328804976205e-06, "loss": 0.43062111735343933, "step": 950 }, { "epoch": 0.2468847352024922, "grad_norm": 2.842273473739624, "learning_rate": 4.898251804921523e-06, "loss": 0.35506436228752136, "step": 951 }, { "epoch": 0.24714434060228452, "grad_norm": 2.9120545387268066, "learning_rate": 4.897970349583697e-06, "loss": 0.39637666940689087, "step": 952 }, { "epoch": 0.24740394600207685, "grad_norm": 3.7920749187469482, "learning_rate": 4.8976885145338935e-06, "loss": 0.43374404311180115, "step": 953 }, { "epoch": 0.24766355140186916, "grad_norm": 4.228703022003174, "learning_rate": 4.897406299821936e-06, "loss": 0.5051562190055847, "step": 954 }, { "epoch": 0.24792315680166147, "grad_norm": 4.733020782470703, "learning_rate": 4.897123705497714e-06, "loss": 0.5348320007324219, "step": 955 }, { "epoch": 0.2481827622014538, "grad_norm": 4.66749906539917, "learning_rate": 4.896840731611185e-06, "loss": 0.4519251585006714, "step": 956 }, { "epoch": 0.2484423676012461, "grad_norm": 3.4987897872924805, "learning_rate": 4.896557378212369e-06, "loss": 0.40191423892974854, "step": 957 }, { "epoch": 0.2487019730010384, "grad_norm": 4.331125259399414, "learning_rate": 4.8962736453513595e-06, "loss": 0.4676969051361084, "step": 958 }, { "epoch": 0.24896157840083075, "grad_norm": 5.649655342102051, "learning_rate": 4.895989533078311e-06, "loss": 0.42679688334465027, "step": 959 }, { "epoch": 0.24922118380062305, "grad_norm": 2.154148578643799, "learning_rate": 4.895705041443452e-06, "loss": 0.4000723958015442, "step": 960 }, { "epoch": 0.24948078920041536, "grad_norm": 4.4495720863342285, "learning_rate": 4.89542017049707e-06, "loss": 0.42055004835128784, "step": 961 }, { "epoch": 0.2497403946002077, "grad_norm": 2.63195538520813, "learning_rate": 4.895134920289526e-06, "loss": 0.3712970018386841, "step": 962 }, { "epoch": 0.25, "grad_norm": 2.5729031562805176, "learning_rate": 4.894849290871245e-06, "loss": 0.42095863819122314, "step": 963 }, { "epoch": 0.2502596053997923, "grad_norm": 4.644844055175781, "learning_rate": 4.89456328229272e-06, "loss": 0.4075821042060852, "step": 964 }, { "epoch": 0.2505192107995846, "grad_norm": 2.3317439556121826, "learning_rate": 4.894276894604511e-06, "loss": 0.3699308931827545, "step": 965 }, { "epoch": 0.2507788161993769, "grad_norm": 9.077070236206055, "learning_rate": 4.893990127857244e-06, "loss": 0.4473446011543274, "step": 966 }, { "epoch": 0.2510384215991693, "grad_norm": 3.871135950088501, "learning_rate": 4.893702982101614e-06, "loss": 0.41600343585014343, "step": 967 }, { "epoch": 0.2512980269989616, "grad_norm": 2.6849887371063232, "learning_rate": 4.89341545738838e-06, "loss": 0.41536909341812134, "step": 968 }, { "epoch": 0.2515576323987539, "grad_norm": 7.2975969314575195, "learning_rate": 4.893127553768372e-06, "loss": 0.4689652621746063, "step": 969 }, { "epoch": 0.2518172377985462, "grad_norm": 3.4760570526123047, "learning_rate": 4.892839271292483e-06, "loss": 0.49512583017349243, "step": 970 }, { "epoch": 0.2520768431983385, "grad_norm": 4.16463041305542, "learning_rate": 4.892550610011675e-06, "loss": 0.35381507873535156, "step": 971 }, { "epoch": 0.2523364485981308, "grad_norm": 3.79732084274292, "learning_rate": 4.8922615699769775e-06, "loss": 0.4117632210254669, "step": 972 }, { "epoch": 0.2525960539979232, "grad_norm": 4.45475435256958, "learning_rate": 4.891972151239486e-06, "loss": 0.39642223715782166, "step": 973 }, { "epoch": 0.2528556593977155, "grad_norm": 2.460293769836426, "learning_rate": 4.891682353850362e-06, "loss": 0.3796429932117462, "step": 974 }, { "epoch": 0.2531152647975078, "grad_norm": 3.652521848678589, "learning_rate": 4.8913921778608355e-06, "loss": 0.3737701177597046, "step": 975 }, { "epoch": 0.2533748701973001, "grad_norm": 2.6571288108825684, "learning_rate": 4.891101623322205e-06, "loss": 0.4378017783164978, "step": 976 }, { "epoch": 0.2536344755970924, "grad_norm": 3.9913489818573, "learning_rate": 4.890810690285831e-06, "loss": 0.37533196806907654, "step": 977 }, { "epoch": 0.2538940809968847, "grad_norm": 5.564123630523682, "learning_rate": 4.8905193788031454e-06, "loss": 0.437336802482605, "step": 978 }, { "epoch": 0.25415368639667707, "grad_norm": 2.9397270679473877, "learning_rate": 4.890227688925645e-06, "loss": 0.4299911856651306, "step": 979 }, { "epoch": 0.2544132917964694, "grad_norm": 3.4426348209381104, "learning_rate": 4.8899356207048945e-06, "loss": 0.49257346987724304, "step": 980 }, { "epoch": 0.2546728971962617, "grad_norm": 2.735266923904419, "learning_rate": 4.889643174192523e-06, "loss": 0.38436585664749146, "step": 981 }, { "epoch": 0.254932502596054, "grad_norm": 5.509957313537598, "learning_rate": 4.8893503494402305e-06, "loss": 0.48014193773269653, "step": 982 }, { "epoch": 0.2551921079958463, "grad_norm": 2.462900400161743, "learning_rate": 4.889057146499781e-06, "loss": 0.5279625654220581, "step": 983 }, { "epoch": 0.2554517133956386, "grad_norm": 3.423114061355591, "learning_rate": 4.888763565423004e-06, "loss": 0.4593163728713989, "step": 984 }, { "epoch": 0.25571131879543096, "grad_norm": 5.171939373016357, "learning_rate": 4.888469606261803e-06, "loss": 0.3622766137123108, "step": 985 }, { "epoch": 0.25597092419522327, "grad_norm": 7.093839645385742, "learning_rate": 4.888175269068138e-06, "loss": 0.4202837347984314, "step": 986 }, { "epoch": 0.2562305295950156, "grad_norm": 3.6241037845611572, "learning_rate": 4.887880553894044e-06, "loss": 0.35261574387550354, "step": 987 }, { "epoch": 0.2564901349948079, "grad_norm": 4.9315080642700195, "learning_rate": 4.887585460791618e-06, "loss": 0.4605000913143158, "step": 988 }, { "epoch": 0.2567497403946002, "grad_norm": 2.6908674240112305, "learning_rate": 4.887289989813029e-06, "loss": 0.3430125415325165, "step": 989 }, { "epoch": 0.2570093457943925, "grad_norm": 4.7533769607543945, "learning_rate": 4.886994141010505e-06, "loss": 0.4755780100822449, "step": 990 }, { "epoch": 0.25726895119418486, "grad_norm": 5.959181308746338, "learning_rate": 4.886697914436348e-06, "loss": 0.476616233587265, "step": 991 }, { "epoch": 0.25752855659397716, "grad_norm": 2.397153854370117, "learning_rate": 4.8864013101429235e-06, "loss": 0.39397212862968445, "step": 992 }, { "epoch": 0.25778816199376947, "grad_norm": 3.0268707275390625, "learning_rate": 4.886104328182665e-06, "loss": 0.38814419507980347, "step": 993 }, { "epoch": 0.2580477673935618, "grad_norm": 3.4373619556427, "learning_rate": 4.885806968608072e-06, "loss": 0.44300392270088196, "step": 994 }, { "epoch": 0.2583073727933541, "grad_norm": 5.065760135650635, "learning_rate": 4.8855092314717095e-06, "loss": 0.41090184450149536, "step": 995 }, { "epoch": 0.2585669781931464, "grad_norm": 3.2039010524749756, "learning_rate": 4.885211116826212e-06, "loss": 0.3824582099914551, "step": 996 }, { "epoch": 0.25882658359293875, "grad_norm": 2.9946165084838867, "learning_rate": 4.884912624724279e-06, "loss": 0.43034231662750244, "step": 997 }, { "epoch": 0.25908618899273106, "grad_norm": 4.015328884124756, "learning_rate": 4.884613755218677e-06, "loss": 0.46445947885513306, "step": 998 }, { "epoch": 0.25934579439252337, "grad_norm": 3.723625421524048, "learning_rate": 4.884314508362239e-06, "loss": 0.3776552677154541, "step": 999 }, { "epoch": 0.25960539979231567, "grad_norm": 2.083570718765259, "learning_rate": 4.884014884207865e-06, "loss": 0.43173089623451233, "step": 1000 }, { "epoch": 0.259865005192108, "grad_norm": 3.665853500366211, "learning_rate": 4.8837148828085225e-06, "loss": 0.4978445768356323, "step": 1001 }, { "epoch": 0.2601246105919003, "grad_norm": 2.020503282546997, "learning_rate": 4.883414504217244e-06, "loss": 0.3639425039291382, "step": 1002 }, { "epoch": 0.26038421599169265, "grad_norm": 6.452237129211426, "learning_rate": 4.88311374848713e-06, "loss": 0.47473955154418945, "step": 1003 }, { "epoch": 0.26064382139148495, "grad_norm": 2.2978227138519287, "learning_rate": 4.882812615671347e-06, "loss": 0.4124607443809509, "step": 1004 }, { "epoch": 0.26090342679127726, "grad_norm": 4.105474948883057, "learning_rate": 4.882511105823128e-06, "loss": 0.42833787202835083, "step": 1005 }, { "epoch": 0.26116303219106957, "grad_norm": 7.393970012664795, "learning_rate": 4.882209218995775e-06, "loss": 0.3318769335746765, "step": 1006 }, { "epoch": 0.2614226375908619, "grad_norm": 2.7677829265594482, "learning_rate": 4.881906955242652e-06, "loss": 0.4024452567100525, "step": 1007 }, { "epoch": 0.2616822429906542, "grad_norm": 2.8658335208892822, "learning_rate": 4.881604314617194e-06, "loss": 0.3830868601799011, "step": 1008 }, { "epoch": 0.26194184839044654, "grad_norm": 4.917551517486572, "learning_rate": 4.8813012971729e-06, "loss": 0.4426054358482361, "step": 1009 }, { "epoch": 0.26220145379023885, "grad_norm": 4.850965976715088, "learning_rate": 4.880997902963337e-06, "loss": 0.4463675022125244, "step": 1010 }, { "epoch": 0.26246105919003115, "grad_norm": 2.9432616233825684, "learning_rate": 4.880694132042138e-06, "loss": 0.44384998083114624, "step": 1011 }, { "epoch": 0.26272066458982346, "grad_norm": 2.7179932594299316, "learning_rate": 4.8803899844630034e-06, "loss": 0.388680636882782, "step": 1012 }, { "epoch": 0.26298026998961577, "grad_norm": 1.5909464359283447, "learning_rate": 4.880085460279699e-06, "loss": 0.38521650433540344, "step": 1013 }, { "epoch": 0.2632398753894081, "grad_norm": 6.314777374267578, "learning_rate": 4.879780559546058e-06, "loss": 0.3500092625617981, "step": 1014 }, { "epoch": 0.26349948078920044, "grad_norm": 2.7588655948638916, "learning_rate": 4.879475282315978e-06, "loss": 0.3568416237831116, "step": 1015 }, { "epoch": 0.26375908618899274, "grad_norm": 1.760800838470459, "learning_rate": 4.879169628643428e-06, "loss": 0.4068537950515747, "step": 1016 }, { "epoch": 0.26401869158878505, "grad_norm": 5.084408760070801, "learning_rate": 4.878863598582439e-06, "loss": 0.438890278339386, "step": 1017 }, { "epoch": 0.26427829698857735, "grad_norm": 2.0299723148345947, "learning_rate": 4.87855719218711e-06, "loss": 0.3712101876735687, "step": 1018 }, { "epoch": 0.26453790238836966, "grad_norm": 2.5799825191497803, "learning_rate": 4.878250409511608e-06, "loss": 0.38834089040756226, "step": 1019 }, { "epoch": 0.26479750778816197, "grad_norm": 4.253144264221191, "learning_rate": 4.877943250610163e-06, "loss": 0.3904227614402771, "step": 1020 }, { "epoch": 0.26505711318795433, "grad_norm": 6.137848854064941, "learning_rate": 4.8776357155370745e-06, "loss": 0.5150287747383118, "step": 1021 }, { "epoch": 0.26531671858774664, "grad_norm": 4.212509632110596, "learning_rate": 4.877327804346709e-06, "loss": 0.4415993392467499, "step": 1022 }, { "epoch": 0.26557632398753894, "grad_norm": 7.090457439422607, "learning_rate": 4.877019517093497e-06, "loss": 0.36504319310188293, "step": 1023 }, { "epoch": 0.26583592938733125, "grad_norm": 3.185356378555298, "learning_rate": 4.876710853831935e-06, "loss": 0.3588036298751831, "step": 1024 }, { "epoch": 0.26609553478712356, "grad_norm": 2.1951732635498047, "learning_rate": 4.8764018146165905e-06, "loss": 0.35922685265541077, "step": 1025 }, { "epoch": 0.26635514018691586, "grad_norm": 2.7709782123565674, "learning_rate": 4.876092399502093e-06, "loss": 0.371099591255188, "step": 1026 }, { "epoch": 0.2666147455867082, "grad_norm": 2.1199047565460205, "learning_rate": 4.87578260854314e-06, "loss": 0.3593944311141968, "step": 1027 }, { "epoch": 0.26687435098650053, "grad_norm": 5.541018009185791, "learning_rate": 4.875472441794496e-06, "loss": 0.4610616862773895, "step": 1028 }, { "epoch": 0.26713395638629284, "grad_norm": 1.868592381477356, "learning_rate": 4.875161899310992e-06, "loss": 0.41045451164245605, "step": 1029 }, { "epoch": 0.26739356178608514, "grad_norm": 2.9982004165649414, "learning_rate": 4.874850981147523e-06, "loss": 0.4267057776451111, "step": 1030 }, { "epoch": 0.26765316718587745, "grad_norm": 5.1770501136779785, "learning_rate": 4.874539687359054e-06, "loss": 0.495263934135437, "step": 1031 }, { "epoch": 0.26791277258566976, "grad_norm": 4.975142478942871, "learning_rate": 4.874228018000613e-06, "loss": 0.4815172553062439, "step": 1032 }, { "epoch": 0.2681723779854621, "grad_norm": 1.3793938159942627, "learning_rate": 4.8739159731272975e-06, "loss": 0.37925994396209717, "step": 1033 }, { "epoch": 0.2684319833852544, "grad_norm": 2.739722490310669, "learning_rate": 4.873603552794268e-06, "loss": 0.4387574791908264, "step": 1034 }, { "epoch": 0.26869158878504673, "grad_norm": 1.6568567752838135, "learning_rate": 4.873290757056756e-06, "loss": 0.389684796333313, "step": 1035 }, { "epoch": 0.26895119418483904, "grad_norm": 3.1504335403442383, "learning_rate": 4.872977585970054e-06, "loss": 0.3834666609764099, "step": 1036 }, { "epoch": 0.26921079958463134, "grad_norm": 4.912981986999512, "learning_rate": 4.872664039589525e-06, "loss": 0.4985499382019043, "step": 1037 }, { "epoch": 0.26947040498442365, "grad_norm": 4.1924519538879395, "learning_rate": 4.872350117970596e-06, "loss": 0.4599314332008362, "step": 1038 }, { "epoch": 0.269730010384216, "grad_norm": 3.4948480129241943, "learning_rate": 4.8720358211687615e-06, "loss": 0.43704354763031006, "step": 1039 }, { "epoch": 0.2699896157840083, "grad_norm": 4.92131233215332, "learning_rate": 4.871721149239583e-06, "loss": 0.4911726117134094, "step": 1040 }, { "epoch": 0.2702492211838006, "grad_norm": 4.321204662322998, "learning_rate": 4.8714061022386845e-06, "loss": 0.4266268312931061, "step": 1041 }, { "epoch": 0.27050882658359293, "grad_norm": 4.602115631103516, "learning_rate": 4.8710906802217624e-06, "loss": 0.5351502895355225, "step": 1042 }, { "epoch": 0.27076843198338524, "grad_norm": 4.302332401275635, "learning_rate": 4.8707748832445745e-06, "loss": 0.4699697494506836, "step": 1043 }, { "epoch": 0.27102803738317754, "grad_norm": 3.135683536529541, "learning_rate": 4.870458711362946e-06, "loss": 0.41926324367523193, "step": 1044 }, { "epoch": 0.2712876427829699, "grad_norm": 2.6152429580688477, "learning_rate": 4.8701421646327694e-06, "loss": 0.42104724049568176, "step": 1045 }, { "epoch": 0.2715472481827622, "grad_norm": 3.6951141357421875, "learning_rate": 4.869825243110003e-06, "loss": 0.5116592049598694, "step": 1046 }, { "epoch": 0.2718068535825545, "grad_norm": 6.659826755523682, "learning_rate": 4.869507946850671e-06, "loss": 0.4678705334663391, "step": 1047 }, { "epoch": 0.2720664589823468, "grad_norm": 4.398642063140869, "learning_rate": 4.869190275910865e-06, "loss": 0.4824276268482208, "step": 1048 }, { "epoch": 0.27232606438213913, "grad_norm": 3.530334949493408, "learning_rate": 4.868872230346741e-06, "loss": 0.42399391531944275, "step": 1049 }, { "epoch": 0.27258566978193144, "grad_norm": 2.888996124267578, "learning_rate": 4.8685538102145215e-06, "loss": 0.4251899719238281, "step": 1050 }, { "epoch": 0.2728452751817238, "grad_norm": 3.3836991786956787, "learning_rate": 4.868235015570497e-06, "loss": 0.3708822727203369, "step": 1051 }, { "epoch": 0.2731048805815161, "grad_norm": 2.1597394943237305, "learning_rate": 4.867915846471024e-06, "loss": 0.3503548502922058, "step": 1052 }, { "epoch": 0.2733644859813084, "grad_norm": 6.774730682373047, "learning_rate": 4.867596302972523e-06, "loss": 0.3970799744129181, "step": 1053 }, { "epoch": 0.2736240913811007, "grad_norm": 4.2279438972473145, "learning_rate": 4.867276385131482e-06, "loss": 0.4186093807220459, "step": 1054 }, { "epoch": 0.273883696780893, "grad_norm": 3.4172234535217285, "learning_rate": 4.866956093004454e-06, "loss": 0.3722821772098541, "step": 1055 }, { "epoch": 0.27414330218068533, "grad_norm": 8.000335693359375, "learning_rate": 4.866635426648062e-06, "loss": 0.5407140254974365, "step": 1056 }, { "epoch": 0.2744029075804777, "grad_norm": 4.31519079208374, "learning_rate": 4.866314386118991e-06, "loss": 0.4446451663970947, "step": 1057 }, { "epoch": 0.27466251298027, "grad_norm": 3.6468260288238525, "learning_rate": 4.865992971473993e-06, "loss": 0.4818403720855713, "step": 1058 }, { "epoch": 0.2749221183800623, "grad_norm": 4.7143659591674805, "learning_rate": 4.865671182769888e-06, "loss": 0.42338305711746216, "step": 1059 }, { "epoch": 0.2751817237798546, "grad_norm": 5.337070465087891, "learning_rate": 4.865349020063561e-06, "loss": 0.47796088457107544, "step": 1060 }, { "epoch": 0.2754413291796469, "grad_norm": 4.745376110076904, "learning_rate": 4.865026483411961e-06, "loss": 0.4502163231372833, "step": 1061 }, { "epoch": 0.2757009345794392, "grad_norm": 5.682111740112305, "learning_rate": 4.864703572872107e-06, "loss": 0.4919745624065399, "step": 1062 }, { "epoch": 0.2759605399792316, "grad_norm": 2.768430709838867, "learning_rate": 4.864380288501082e-06, "loss": 0.4107127785682678, "step": 1063 }, { "epoch": 0.2762201453790239, "grad_norm": 3.2033562660217285, "learning_rate": 4.864056630356034e-06, "loss": 0.3711153566837311, "step": 1064 }, { "epoch": 0.2764797507788162, "grad_norm": 7.980413436889648, "learning_rate": 4.86373259849418e-06, "loss": 0.4349328875541687, "step": 1065 }, { "epoch": 0.2767393561786085, "grad_norm": 6.340795993804932, "learning_rate": 4.8634081929728e-06, "loss": 0.36514705419540405, "step": 1066 }, { "epoch": 0.2769989615784008, "grad_norm": 3.6440274715423584, "learning_rate": 4.863083413849243e-06, "loss": 0.3823854923248291, "step": 1067 }, { "epoch": 0.2772585669781931, "grad_norm": 7.441885471343994, "learning_rate": 4.862758261180921e-06, "loss": 0.5018795728683472, "step": 1068 }, { "epoch": 0.2775181723779855, "grad_norm": 4.107855796813965, "learning_rate": 4.8624327350253145e-06, "loss": 0.45749709010124207, "step": 1069 }, { "epoch": 0.2777777777777778, "grad_norm": 3.394002914428711, "learning_rate": 4.862106835439968e-06, "loss": 0.43154585361480713, "step": 1070 }, { "epoch": 0.2780373831775701, "grad_norm": 2.3803486824035645, "learning_rate": 4.861780562482495e-06, "loss": 0.3905729353427887, "step": 1071 }, { "epoch": 0.2782969885773624, "grad_norm": 6.541999340057373, "learning_rate": 4.861453916210571e-06, "loss": 0.5540496110916138, "step": 1072 }, { "epoch": 0.2785565939771547, "grad_norm": 3.8104300498962402, "learning_rate": 4.861126896681941e-06, "loss": 0.44095924496650696, "step": 1073 }, { "epoch": 0.278816199376947, "grad_norm": 1.8464593887329102, "learning_rate": 4.8607995039544135e-06, "loss": 0.3586999177932739, "step": 1074 }, { "epoch": 0.2790758047767394, "grad_norm": 1.7420165538787842, "learning_rate": 4.8604717380858655e-06, "loss": 0.35866305232048035, "step": 1075 }, { "epoch": 0.2793354101765317, "grad_norm": 2.8840088844299316, "learning_rate": 4.8601435991342375e-06, "loss": 0.4183834195137024, "step": 1076 }, { "epoch": 0.279595015576324, "grad_norm": 3.2764267921447754, "learning_rate": 4.859815087157536e-06, "loss": 0.47390228509902954, "step": 1077 }, { "epoch": 0.2798546209761163, "grad_norm": 5.809844017028809, "learning_rate": 4.859486202213836e-06, "loss": 0.5109002590179443, "step": 1078 }, { "epoch": 0.2801142263759086, "grad_norm": 7.814181804656982, "learning_rate": 4.859156944361276e-06, "loss": 0.482069730758667, "step": 1079 }, { "epoch": 0.2803738317757009, "grad_norm": 4.528997898101807, "learning_rate": 4.858827313658062e-06, "loss": 0.3859631419181824, "step": 1080 }, { "epoch": 0.28063343717549327, "grad_norm": 8.556408882141113, "learning_rate": 4.858497310162465e-06, "loss": 0.410190224647522, "step": 1081 }, { "epoch": 0.2808930425752856, "grad_norm": 4.966352939605713, "learning_rate": 4.858166933932821e-06, "loss": 0.39035844802856445, "step": 1082 }, { "epoch": 0.2811526479750779, "grad_norm": 2.288466215133667, "learning_rate": 4.857836185027534e-06, "loss": 0.4142606854438782, "step": 1083 }, { "epoch": 0.2814122533748702, "grad_norm": 2.7727982997894287, "learning_rate": 4.857505063505073e-06, "loss": 0.49155446887016296, "step": 1084 }, { "epoch": 0.2816718587746625, "grad_norm": 2.9982640743255615, "learning_rate": 4.857173569423971e-06, "loss": 0.48311862349510193, "step": 1085 }, { "epoch": 0.2819314641744548, "grad_norm": 4.979255676269531, "learning_rate": 4.856841702842831e-06, "loss": 0.45008939504623413, "step": 1086 }, { "epoch": 0.28219106957424717, "grad_norm": 5.755886077880859, "learning_rate": 4.856509463820318e-06, "loss": 0.5165913105010986, "step": 1087 }, { "epoch": 0.2824506749740395, "grad_norm": 5.050075054168701, "learning_rate": 4.856176852415164e-06, "loss": 0.34398189187049866, "step": 1088 }, { "epoch": 0.2827102803738318, "grad_norm": 5.835024833679199, "learning_rate": 4.855843868686168e-06, "loss": 0.43841636180877686, "step": 1089 }, { "epoch": 0.2829698857736241, "grad_norm": 4.141831874847412, "learning_rate": 4.855510512692194e-06, "loss": 0.434606671333313, "step": 1090 }, { "epoch": 0.2832294911734164, "grad_norm": 6.2325592041015625, "learning_rate": 4.8551767844921695e-06, "loss": 0.44280707836151123, "step": 1091 }, { "epoch": 0.2834890965732087, "grad_norm": 4.180543899536133, "learning_rate": 4.854842684145093e-06, "loss": 0.3369010090827942, "step": 1092 }, { "epoch": 0.28374870197300106, "grad_norm": 3.0986087322235107, "learning_rate": 4.854508211710025e-06, "loss": 0.3939056396484375, "step": 1093 }, { "epoch": 0.28400830737279337, "grad_norm": 3.2149972915649414, "learning_rate": 4.85417336724609e-06, "loss": 0.3680295944213867, "step": 1094 }, { "epoch": 0.2842679127725857, "grad_norm": 2.2460107803344727, "learning_rate": 4.853838150812485e-06, "loss": 0.37066686153411865, "step": 1095 }, { "epoch": 0.284527518172378, "grad_norm": 3.3826560974121094, "learning_rate": 4.853502562468464e-06, "loss": 0.408250093460083, "step": 1096 }, { "epoch": 0.2847871235721703, "grad_norm": 4.1299896240234375, "learning_rate": 4.853166602273356e-06, "loss": 0.4619618058204651, "step": 1097 }, { "epoch": 0.2850467289719626, "grad_norm": 5.976362228393555, "learning_rate": 4.852830270286548e-06, "loss": 0.4693785011768341, "step": 1098 }, { "epoch": 0.28530633437175495, "grad_norm": 5.387068748474121, "learning_rate": 4.852493566567496e-06, "loss": 0.4410749077796936, "step": 1099 }, { "epoch": 0.28556593977154726, "grad_norm": 4.817735195159912, "learning_rate": 4.852156491175724e-06, "loss": 0.3997863531112671, "step": 1100 }, { "epoch": 0.28582554517133957, "grad_norm": 3.0496103763580322, "learning_rate": 4.851819044170816e-06, "loss": 0.42382341623306274, "step": 1101 }, { "epoch": 0.2860851505711319, "grad_norm": 7.211275577545166, "learning_rate": 4.851481225612426e-06, "loss": 0.46932506561279297, "step": 1102 }, { "epoch": 0.2863447559709242, "grad_norm": 2.605039596557617, "learning_rate": 4.851143035560274e-06, "loss": 0.3916563391685486, "step": 1103 }, { "epoch": 0.2866043613707165, "grad_norm": 4.64489221572876, "learning_rate": 4.850804474074143e-06, "loss": 0.4039141535758972, "step": 1104 }, { "epoch": 0.28686396677050885, "grad_norm": 3.297976016998291, "learning_rate": 4.8504655412138816e-06, "loss": 0.4040074944496155, "step": 1105 }, { "epoch": 0.28712357217030116, "grad_norm": 5.181375503540039, "learning_rate": 4.850126237039408e-06, "loss": 0.42965102195739746, "step": 1106 }, { "epoch": 0.28738317757009346, "grad_norm": 2.6954104900360107, "learning_rate": 4.849786561610702e-06, "loss": 0.39497509598731995, "step": 1107 }, { "epoch": 0.28764278296988577, "grad_norm": 3.9573605060577393, "learning_rate": 4.84944651498781e-06, "loss": 0.3836199641227722, "step": 1108 }, { "epoch": 0.2879023883696781, "grad_norm": 3.5130116939544678, "learning_rate": 4.849106097230845e-06, "loss": 0.4068657457828522, "step": 1109 }, { "epoch": 0.2881619937694704, "grad_norm": 2.4198429584503174, "learning_rate": 4.848765308399987e-06, "loss": 0.43481171131134033, "step": 1110 }, { "epoch": 0.28842159916926274, "grad_norm": 3.6122498512268066, "learning_rate": 4.848424148555476e-06, "loss": 0.4166199862957001, "step": 1111 }, { "epoch": 0.28868120456905505, "grad_norm": 2.267737627029419, "learning_rate": 4.848082617757624e-06, "loss": 0.3844204545021057, "step": 1112 }, { "epoch": 0.28894080996884736, "grad_norm": 9.36392593383789, "learning_rate": 4.847740716066804e-06, "loss": 0.44072073698043823, "step": 1113 }, { "epoch": 0.28920041536863966, "grad_norm": 1.8543201684951782, "learning_rate": 4.847398443543459e-06, "loss": 0.39726579189300537, "step": 1114 }, { "epoch": 0.28946002076843197, "grad_norm": 4.9396281242370605, "learning_rate": 4.847055800248092e-06, "loss": 0.48099058866500854, "step": 1115 }, { "epoch": 0.2897196261682243, "grad_norm": 1.8896769285202026, "learning_rate": 4.846712786241275e-06, "loss": 0.36480867862701416, "step": 1116 }, { "epoch": 0.28997923156801664, "grad_norm": 5.504062652587891, "learning_rate": 4.8463694015836465e-06, "loss": 0.4414648413658142, "step": 1117 }, { "epoch": 0.29023883696780894, "grad_norm": 4.598651885986328, "learning_rate": 4.846025646335909e-06, "loss": 0.4052152931690216, "step": 1118 }, { "epoch": 0.29049844236760125, "grad_norm": 1.8958767652511597, "learning_rate": 4.845681520558829e-06, "loss": 0.36145639419555664, "step": 1119 }, { "epoch": 0.29075804776739356, "grad_norm": 2.6292669773101807, "learning_rate": 4.845337024313242e-06, "loss": 0.41130197048187256, "step": 1120 }, { "epoch": 0.29101765316718586, "grad_norm": 2.7702908515930176, "learning_rate": 4.844992157660044e-06, "loss": 0.38693690299987793, "step": 1121 }, { "epoch": 0.29127725856697817, "grad_norm": 3.7246463298797607, "learning_rate": 4.844646920660203e-06, "loss": 0.44330209493637085, "step": 1122 }, { "epoch": 0.29153686396677053, "grad_norm": 3.43548321723938, "learning_rate": 4.844301313374747e-06, "loss": 0.40609878301620483, "step": 1123 }, { "epoch": 0.29179646936656284, "grad_norm": 4.837420463562012, "learning_rate": 4.843955335864772e-06, "loss": 0.3302496075630188, "step": 1124 }, { "epoch": 0.29205607476635514, "grad_norm": 3.3315279483795166, "learning_rate": 4.843608988191439e-06, "loss": 0.41408997774124146, "step": 1125 }, { "epoch": 0.29231568016614745, "grad_norm": 4.206920623779297, "learning_rate": 4.843262270415974e-06, "loss": 0.41402363777160645, "step": 1126 }, { "epoch": 0.29257528556593976, "grad_norm": 4.869394302368164, "learning_rate": 4.842915182599669e-06, "loss": 0.3562074899673462, "step": 1127 }, { "epoch": 0.29283489096573206, "grad_norm": 2.3994123935699463, "learning_rate": 4.842567724803881e-06, "loss": 0.37640196084976196, "step": 1128 }, { "epoch": 0.2930944963655244, "grad_norm": 5.9465742111206055, "learning_rate": 4.842219897090033e-06, "loss": 0.3489716351032257, "step": 1129 }, { "epoch": 0.29335410176531673, "grad_norm": 7.35048770904541, "learning_rate": 4.8418716995196125e-06, "loss": 0.45861971378326416, "step": 1130 }, { "epoch": 0.29361370716510904, "grad_norm": 4.283884048461914, "learning_rate": 4.841523132154173e-06, "loss": 0.45817166566848755, "step": 1131 }, { "epoch": 0.29387331256490135, "grad_norm": 1.8537095785140991, "learning_rate": 4.841174195055333e-06, "loss": 0.3442278802394867, "step": 1132 }, { "epoch": 0.29413291796469365, "grad_norm": 6.532536506652832, "learning_rate": 4.8408248882847775e-06, "loss": 0.46860814094543457, "step": 1133 }, { "epoch": 0.29439252336448596, "grad_norm": 5.493465900421143, "learning_rate": 4.8404752119042556e-06, "loss": 0.3909040093421936, "step": 1134 }, { "epoch": 0.2946521287642783, "grad_norm": 4.565916538238525, "learning_rate": 4.8401251659755805e-06, "loss": 0.5020502805709839, "step": 1135 }, { "epoch": 0.2949117341640706, "grad_norm": 4.099337100982666, "learning_rate": 4.839774750560635e-06, "loss": 0.4997395873069763, "step": 1136 }, { "epoch": 0.29517133956386293, "grad_norm": 5.446395397186279, "learning_rate": 4.839423965721362e-06, "loss": 0.4047432243824005, "step": 1137 }, { "epoch": 0.29543094496365524, "grad_norm": 4.246713638305664, "learning_rate": 4.839072811519773e-06, "loss": 0.45715591311454773, "step": 1138 }, { "epoch": 0.29569055036344755, "grad_norm": 4.337608337402344, "learning_rate": 4.838721288017945e-06, "loss": 0.3906337022781372, "step": 1139 }, { "epoch": 0.29595015576323985, "grad_norm": 3.5186026096343994, "learning_rate": 4.838369395278019e-06, "loss": 0.38358715176582336, "step": 1140 }, { "epoch": 0.2962097611630322, "grad_norm": 2.1162774562835693, "learning_rate": 4.838017133362201e-06, "loss": 0.33443307876586914, "step": 1141 }, { "epoch": 0.2964693665628245, "grad_norm": 1.6631131172180176, "learning_rate": 4.8376645023327625e-06, "loss": 0.3792613446712494, "step": 1142 }, { "epoch": 0.2967289719626168, "grad_norm": 4.915071964263916, "learning_rate": 4.837311502252042e-06, "loss": 0.37035876512527466, "step": 1143 }, { "epoch": 0.29698857736240913, "grad_norm": 7.746335029602051, "learning_rate": 4.836958133182441e-06, "loss": 0.5078532695770264, "step": 1144 }, { "epoch": 0.29724818276220144, "grad_norm": 2.565842390060425, "learning_rate": 4.836604395186426e-06, "loss": 0.495985746383667, "step": 1145 }, { "epoch": 0.29750778816199375, "grad_norm": 3.6804568767547607, "learning_rate": 4.836250288326532e-06, "loss": 0.4057311415672302, "step": 1146 }, { "epoch": 0.2977673935617861, "grad_norm": 4.9186906814575195, "learning_rate": 4.835895812665356e-06, "loss": 0.526478111743927, "step": 1147 }, { "epoch": 0.2980269989615784, "grad_norm": 3.4457695484161377, "learning_rate": 4.835540968265559e-06, "loss": 0.3529323935508728, "step": 1148 }, { "epoch": 0.2982866043613707, "grad_norm": 2.8450846672058105, "learning_rate": 4.8351857551898734e-06, "loss": 0.38279032707214355, "step": 1149 }, { "epoch": 0.29854620976116303, "grad_norm": 9.263200759887695, "learning_rate": 4.83483017350109e-06, "loss": 0.5495753884315491, "step": 1150 }, { "epoch": 0.29880581516095533, "grad_norm": 7.323639392852783, "learning_rate": 4.834474223262068e-06, "loss": 0.494807630777359, "step": 1151 }, { "epoch": 0.29906542056074764, "grad_norm": 5.736459255218506, "learning_rate": 4.834117904535732e-06, "loss": 0.4860363304615021, "step": 1152 }, { "epoch": 0.29932502596054, "grad_norm": 3.630302906036377, "learning_rate": 4.83376121738507e-06, "loss": 0.3689073920249939, "step": 1153 }, { "epoch": 0.2995846313603323, "grad_norm": 2.4883158206939697, "learning_rate": 4.833404161873137e-06, "loss": 0.3632802367210388, "step": 1154 }, { "epoch": 0.2998442367601246, "grad_norm": 4.484736919403076, "learning_rate": 4.8330467380630515e-06, "loss": 0.42774683237075806, "step": 1155 }, { "epoch": 0.3001038421599169, "grad_norm": 3.1134424209594727, "learning_rate": 4.8326889460179984e-06, "loss": 0.42403584718704224, "step": 1156 }, { "epoch": 0.30036344755970923, "grad_norm": 5.480249881744385, "learning_rate": 4.832330785801227e-06, "loss": 0.4473101496696472, "step": 1157 }, { "epoch": 0.30062305295950154, "grad_norm": 3.8774397373199463, "learning_rate": 4.8319722574760504e-06, "loss": 0.4472652077674866, "step": 1158 }, { "epoch": 0.3008826583592939, "grad_norm": 2.726208448410034, "learning_rate": 4.8316133611058504e-06, "loss": 0.36595216393470764, "step": 1159 }, { "epoch": 0.3011422637590862, "grad_norm": 4.307088375091553, "learning_rate": 4.831254096754072e-06, "loss": 0.45828312635421753, "step": 1160 }, { "epoch": 0.3014018691588785, "grad_norm": 3.843519449234009, "learning_rate": 4.8308944644842225e-06, "loss": 0.4330870509147644, "step": 1161 }, { "epoch": 0.3016614745586708, "grad_norm": 3.6944520473480225, "learning_rate": 4.8305344643598774e-06, "loss": 0.3851553201675415, "step": 1162 }, { "epoch": 0.3019210799584631, "grad_norm": 3.3289077281951904, "learning_rate": 4.830174096444678e-06, "loss": 0.43335196375846863, "step": 1163 }, { "epoch": 0.30218068535825543, "grad_norm": 3.8133468627929688, "learning_rate": 4.8298133608023275e-06, "loss": 0.48173385858535767, "step": 1164 }, { "epoch": 0.3024402907580478, "grad_norm": 3.9045534133911133, "learning_rate": 4.829452257496596e-06, "loss": 0.38011419773101807, "step": 1165 }, { "epoch": 0.3026998961578401, "grad_norm": 3.773083448410034, "learning_rate": 4.829090786591319e-06, "loss": 0.374274343252182, "step": 1166 }, { "epoch": 0.3029595015576324, "grad_norm": 3.2113044261932373, "learning_rate": 4.828728948150395e-06, "loss": 0.357515811920166, "step": 1167 }, { "epoch": 0.3032191069574247, "grad_norm": 3.460674285888672, "learning_rate": 4.82836674223779e-06, "loss": 0.3798949420452118, "step": 1168 }, { "epoch": 0.303478712357217, "grad_norm": 2.9313926696777344, "learning_rate": 4.828004168917534e-06, "loss": 0.3711200952529907, "step": 1169 }, { "epoch": 0.3037383177570093, "grad_norm": 4.562788486480713, "learning_rate": 4.8276412282537205e-06, "loss": 0.4639163911342621, "step": 1170 }, { "epoch": 0.3039979231568017, "grad_norm": 2.7213706970214844, "learning_rate": 4.8272779203105095e-06, "loss": 0.3390510082244873, "step": 1171 }, { "epoch": 0.304257528556594, "grad_norm": 3.638188362121582, "learning_rate": 4.826914245152126e-06, "loss": 0.3719087243080139, "step": 1172 }, { "epoch": 0.3045171339563863, "grad_norm": 2.6248135566711426, "learning_rate": 4.826550202842858e-06, "loss": 0.422203004360199, "step": 1173 }, { "epoch": 0.3047767393561786, "grad_norm": 4.576785087585449, "learning_rate": 4.826185793447061e-06, "loss": 0.45530205965042114, "step": 1174 }, { "epoch": 0.3050363447559709, "grad_norm": 3.359740734100342, "learning_rate": 4.825821017029154e-06, "loss": 0.44443315267562866, "step": 1175 }, { "epoch": 0.3052959501557632, "grad_norm": 5.016263961791992, "learning_rate": 4.8254558736536216e-06, "loss": 0.3937220275402069, "step": 1176 }, { "epoch": 0.3055555555555556, "grad_norm": 2.7468433380126953, "learning_rate": 4.8250903633850125e-06, "loss": 0.3982740640640259, "step": 1177 }, { "epoch": 0.3058151609553479, "grad_norm": 3.936551332473755, "learning_rate": 4.82472448628794e-06, "loss": 0.3530845642089844, "step": 1178 }, { "epoch": 0.3060747663551402, "grad_norm": 4.956549167633057, "learning_rate": 4.824358242427083e-06, "loss": 0.4296691119670868, "step": 1179 }, { "epoch": 0.3063343717549325, "grad_norm": 3.090346574783325, "learning_rate": 4.823991631867186e-06, "loss": 0.34931105375289917, "step": 1180 }, { "epoch": 0.3065939771547248, "grad_norm": 4.141292095184326, "learning_rate": 4.8236246546730555e-06, "loss": 0.45552611351013184, "step": 1181 }, { "epoch": 0.3068535825545171, "grad_norm": 3.7389376163482666, "learning_rate": 4.823257310909567e-06, "loss": 0.40644127130508423, "step": 1182 }, { "epoch": 0.3071131879543095, "grad_norm": 4.915603160858154, "learning_rate": 4.822889600641657e-06, "loss": 0.3784467279911041, "step": 1183 }, { "epoch": 0.3073727933541018, "grad_norm": 7.304821014404297, "learning_rate": 4.822521523934328e-06, "loss": 0.45905569195747375, "step": 1184 }, { "epoch": 0.3076323987538941, "grad_norm": 2.108062744140625, "learning_rate": 4.822153080852648e-06, "loss": 0.3307369649410248, "step": 1185 }, { "epoch": 0.3078920041536864, "grad_norm": 4.701223373413086, "learning_rate": 4.82178427146175e-06, "loss": 0.4743773341178894, "step": 1186 }, { "epoch": 0.3081516095534787, "grad_norm": 3.4297003746032715, "learning_rate": 4.82141509582683e-06, "loss": 0.37743237614631653, "step": 1187 }, { "epoch": 0.308411214953271, "grad_norm": 4.081344127655029, "learning_rate": 4.821045554013151e-06, "loss": 0.4274507761001587, "step": 1188 }, { "epoch": 0.30867082035306337, "grad_norm": 2.871819019317627, "learning_rate": 4.820675646086037e-06, "loss": 0.3662743866443634, "step": 1189 }, { "epoch": 0.3089304257528557, "grad_norm": 2.7364399433135986, "learning_rate": 4.8203053721108815e-06, "loss": 0.37481677532196045, "step": 1190 }, { "epoch": 0.309190031152648, "grad_norm": 2.956726551055908, "learning_rate": 4.819934732153141e-06, "loss": 0.32499727606773376, "step": 1191 }, { "epoch": 0.3094496365524403, "grad_norm": 2.6685407161712646, "learning_rate": 4.819563726278334e-06, "loss": 0.3582373261451721, "step": 1192 }, { "epoch": 0.3097092419522326, "grad_norm": 2.330946922302246, "learning_rate": 4.819192354552047e-06, "loss": 0.355988085269928, "step": 1193 }, { "epoch": 0.3099688473520249, "grad_norm": 5.547435760498047, "learning_rate": 4.81882061703993e-06, "loss": 0.47215887904167175, "step": 1194 }, { "epoch": 0.31022845275181726, "grad_norm": 4.725836277008057, "learning_rate": 4.818448513807698e-06, "loss": 0.46013158559799194, "step": 1195 }, { "epoch": 0.31048805815160957, "grad_norm": 2.0951976776123047, "learning_rate": 4.818076044921129e-06, "loss": 0.349254310131073, "step": 1196 }, { "epoch": 0.3107476635514019, "grad_norm": 5.084940433502197, "learning_rate": 4.817703210446069e-06, "loss": 0.4163658618927002, "step": 1197 }, { "epoch": 0.3110072689511942, "grad_norm": 2.2856478691101074, "learning_rate": 4.817330010448426e-06, "loss": 0.3179847300052643, "step": 1198 }, { "epoch": 0.3112668743509865, "grad_norm": 4.132550239562988, "learning_rate": 4.816956444994172e-06, "loss": 0.43845418095588684, "step": 1199 }, { "epoch": 0.3115264797507788, "grad_norm": 2.2343504428863525, "learning_rate": 4.816582514149344e-06, "loss": 0.35760757327079773, "step": 1200 }, { "epoch": 0.31178608515057116, "grad_norm": 2.142848491668701, "learning_rate": 4.816208217980049e-06, "loss": 0.351085901260376, "step": 1201 }, { "epoch": 0.31204569055036346, "grad_norm": 3.0252857208251953, "learning_rate": 4.815833556552448e-06, "loss": 0.3640075922012329, "step": 1202 }, { "epoch": 0.31230529595015577, "grad_norm": 1.9247801303863525, "learning_rate": 4.815458529932778e-06, "loss": 0.347430020570755, "step": 1203 }, { "epoch": 0.3125649013499481, "grad_norm": 5.609139442443848, "learning_rate": 4.815083138187331e-06, "loss": 0.2871602773666382, "step": 1204 }, { "epoch": 0.3128245067497404, "grad_norm": 2.5212314128875732, "learning_rate": 4.8147073813824695e-06, "loss": 0.38491377234458923, "step": 1205 }, { "epoch": 0.3130841121495327, "grad_norm": 3.737740993499756, "learning_rate": 4.814331259584619e-06, "loss": 0.4050312638282776, "step": 1206 }, { "epoch": 0.31334371754932505, "grad_norm": 4.605377197265625, "learning_rate": 4.8139547728602685e-06, "loss": 0.4816815257072449, "step": 1207 }, { "epoch": 0.31360332294911736, "grad_norm": 3.571763753890991, "learning_rate": 4.8135779212759725e-06, "loss": 0.41475430130958557, "step": 1208 }, { "epoch": 0.31386292834890966, "grad_norm": 2.1349692344665527, "learning_rate": 4.81320070489835e-06, "loss": 0.3337150812149048, "step": 1209 }, { "epoch": 0.31412253374870197, "grad_norm": 5.412755012512207, "learning_rate": 4.812823123794084e-06, "loss": 0.4591892957687378, "step": 1210 }, { "epoch": 0.3143821391484943, "grad_norm": 1.949483036994934, "learning_rate": 4.8124451780299215e-06, "loss": 0.3600660264492035, "step": 1211 }, { "epoch": 0.3146417445482866, "grad_norm": 3.93221378326416, "learning_rate": 4.812066867672676e-06, "loss": 0.42851075530052185, "step": 1212 }, { "epoch": 0.31490134994807895, "grad_norm": 5.012834548950195, "learning_rate": 4.8116881927892225e-06, "loss": 0.450959175825119, "step": 1213 }, { "epoch": 0.31516095534787125, "grad_norm": 2.9661457538604736, "learning_rate": 4.811309153446503e-06, "loss": 0.499566912651062, "step": 1214 }, { "epoch": 0.31542056074766356, "grad_norm": 3.7699437141418457, "learning_rate": 4.810929749711523e-06, "loss": 0.4288010001182556, "step": 1215 }, { "epoch": 0.31568016614745587, "grad_norm": 3.441713809967041, "learning_rate": 4.810549981651353e-06, "loss": 0.48453429341316223, "step": 1216 }, { "epoch": 0.31593977154724817, "grad_norm": 3.4347147941589355, "learning_rate": 4.810169849333126e-06, "loss": 0.42433953285217285, "step": 1217 }, { "epoch": 0.3161993769470405, "grad_norm": 2.049811840057373, "learning_rate": 4.8097893528240415e-06, "loss": 0.3733103275299072, "step": 1218 }, { "epoch": 0.31645898234683284, "grad_norm": 3.309715509414673, "learning_rate": 4.809408492191362e-06, "loss": 0.48959288001060486, "step": 1219 }, { "epoch": 0.31671858774662515, "grad_norm": 2.809088945388794, "learning_rate": 4.809027267502415e-06, "loss": 0.3700229525566101, "step": 1220 }, { "epoch": 0.31697819314641745, "grad_norm": 1.8223443031311035, "learning_rate": 4.808645678824593e-06, "loss": 0.3353102207183838, "step": 1221 }, { "epoch": 0.31723779854620976, "grad_norm": 7.4418044090271, "learning_rate": 4.8082637262253515e-06, "loss": 0.4879790246486664, "step": 1222 }, { "epoch": 0.31749740394600207, "grad_norm": 3.592991590499878, "learning_rate": 4.807881409772211e-06, "loss": 0.3415326774120331, "step": 1223 }, { "epoch": 0.3177570093457944, "grad_norm": 4.75507116317749, "learning_rate": 4.807498729532758e-06, "loss": 0.4735530614852905, "step": 1224 }, { "epoch": 0.31801661474558673, "grad_norm": 5.032412528991699, "learning_rate": 4.807115685574638e-06, "loss": 0.4428050220012665, "step": 1225 }, { "epoch": 0.31827622014537904, "grad_norm": 2.9481632709503174, "learning_rate": 4.806732277965569e-06, "loss": 0.34553059935569763, "step": 1226 }, { "epoch": 0.31853582554517135, "grad_norm": 5.482689380645752, "learning_rate": 4.806348506773325e-06, "loss": 0.5036881566047668, "step": 1227 }, { "epoch": 0.31879543094496365, "grad_norm": 2.695323944091797, "learning_rate": 4.805964372065748e-06, "loss": 0.4159388244152069, "step": 1228 }, { "epoch": 0.31905503634475596, "grad_norm": 4.461690902709961, "learning_rate": 4.805579873910746e-06, "loss": 0.41489744186401367, "step": 1229 }, { "epoch": 0.31931464174454827, "grad_norm": 6.399365425109863, "learning_rate": 4.805195012376289e-06, "loss": 0.46261167526245117, "step": 1230 }, { "epoch": 0.31957424714434063, "grad_norm": 4.886571407318115, "learning_rate": 4.804809787530411e-06, "loss": 0.4633815884590149, "step": 1231 }, { "epoch": 0.31983385254413293, "grad_norm": 5.519341468811035, "learning_rate": 4.804424199441213e-06, "loss": 0.5253146886825562, "step": 1232 }, { "epoch": 0.32009345794392524, "grad_norm": 2.548219919204712, "learning_rate": 4.804038248176855e-06, "loss": 0.3530976474285126, "step": 1233 }, { "epoch": 0.32035306334371755, "grad_norm": 2.2334086894989014, "learning_rate": 4.803651933805567e-06, "loss": 0.3877641558647156, "step": 1234 }, { "epoch": 0.32061266874350985, "grad_norm": 4.954165935516357, "learning_rate": 4.803265256395639e-06, "loss": 0.38049986958503723, "step": 1235 }, { "epoch": 0.32087227414330216, "grad_norm": 2.279172658920288, "learning_rate": 4.802878216015428e-06, "loss": 0.37852558493614197, "step": 1236 }, { "epoch": 0.3211318795430945, "grad_norm": 4.792909145355225, "learning_rate": 4.802490812733352e-06, "loss": 0.40805289149284363, "step": 1237 }, { "epoch": 0.32139148494288683, "grad_norm": 4.149837970733643, "learning_rate": 4.8021030466178965e-06, "loss": 0.4203556776046753, "step": 1238 }, { "epoch": 0.32165109034267914, "grad_norm": 2.566074848175049, "learning_rate": 4.80171491773761e-06, "loss": 0.39477333426475525, "step": 1239 }, { "epoch": 0.32191069574247144, "grad_norm": 4.808086395263672, "learning_rate": 4.801326426161103e-06, "loss": 0.44544702768325806, "step": 1240 }, { "epoch": 0.32217030114226375, "grad_norm": 3.463855028152466, "learning_rate": 4.800937571957053e-06, "loss": 0.3637862205505371, "step": 1241 }, { "epoch": 0.32242990654205606, "grad_norm": 4.942208290100098, "learning_rate": 4.800548355194202e-06, "loss": 0.417628675699234, "step": 1242 }, { "epoch": 0.3226895119418484, "grad_norm": 3.6977522373199463, "learning_rate": 4.800158775941351e-06, "loss": 0.3768717050552368, "step": 1243 }, { "epoch": 0.3229491173416407, "grad_norm": 3.6194427013397217, "learning_rate": 4.799768834267372e-06, "loss": 0.386088103055954, "step": 1244 }, { "epoch": 0.32320872274143303, "grad_norm": 2.3448293209075928, "learning_rate": 4.799378530241197e-06, "loss": 0.372764527797699, "step": 1245 }, { "epoch": 0.32346832814122534, "grad_norm": 4.933867454528809, "learning_rate": 4.7989878639318225e-06, "loss": 0.4227370023727417, "step": 1246 }, { "epoch": 0.32372793354101764, "grad_norm": 3.775061845779419, "learning_rate": 4.798596835408309e-06, "loss": 0.4001414179801941, "step": 1247 }, { "epoch": 0.32398753894080995, "grad_norm": 3.3318612575531006, "learning_rate": 4.79820544473978e-06, "loss": 0.3561580777168274, "step": 1248 }, { "epoch": 0.3242471443406023, "grad_norm": 3.5992560386657715, "learning_rate": 4.797813691995428e-06, "loss": 0.3829188346862793, "step": 1249 }, { "epoch": 0.3245067497403946, "grad_norm": 4.235024929046631, "learning_rate": 4.7974215772445035e-06, "loss": 0.4907856285572052, "step": 1250 }, { "epoch": 0.3247663551401869, "grad_norm": 2.137521743774414, "learning_rate": 4.797029100556324e-06, "loss": 0.39378488063812256, "step": 1251 }, { "epoch": 0.32502596053997923, "grad_norm": 3.7815520763397217, "learning_rate": 4.796636262000269e-06, "loss": 0.3782323896884918, "step": 1252 }, { "epoch": 0.32528556593977154, "grad_norm": 2.7512917518615723, "learning_rate": 4.796243061645786e-06, "loss": 0.3820594251155853, "step": 1253 }, { "epoch": 0.32554517133956384, "grad_norm": 6.150915145874023, "learning_rate": 4.7958494995623824e-06, "loss": 0.48525139689445496, "step": 1254 }, { "epoch": 0.3258047767393562, "grad_norm": 2.0621776580810547, "learning_rate": 4.79545557581963e-06, "loss": 0.3786153793334961, "step": 1255 }, { "epoch": 0.3260643821391485, "grad_norm": 6.920357704162598, "learning_rate": 4.795061290487168e-06, "loss": 0.4271088242530823, "step": 1256 }, { "epoch": 0.3263239875389408, "grad_norm": 6.440591812133789, "learning_rate": 4.794666643634695e-06, "loss": 0.347311407327652, "step": 1257 }, { "epoch": 0.3265835929387331, "grad_norm": 3.648409128189087, "learning_rate": 4.794271635331975e-06, "loss": 0.35930901765823364, "step": 1258 }, { "epoch": 0.32684319833852543, "grad_norm": 2.2700612545013428, "learning_rate": 4.793876265648839e-06, "loss": 0.4017985463142395, "step": 1259 }, { "epoch": 0.32710280373831774, "grad_norm": 6.612871170043945, "learning_rate": 4.793480534655177e-06, "loss": 0.45921027660369873, "step": 1260 }, { "epoch": 0.3273624091381101, "grad_norm": 2.6300740242004395, "learning_rate": 4.793084442420946e-06, "loss": 0.366312712430954, "step": 1261 }, { "epoch": 0.3276220145379024, "grad_norm": 5.731856346130371, "learning_rate": 4.792687989016166e-06, "loss": 0.4510754942893982, "step": 1262 }, { "epoch": 0.3278816199376947, "grad_norm": 3.1784234046936035, "learning_rate": 4.792291174510921e-06, "loss": 0.38501375913619995, "step": 1263 }, { "epoch": 0.328141225337487, "grad_norm": 3.5762929916381836, "learning_rate": 4.791893998975359e-06, "loss": 0.3502483069896698, "step": 1264 }, { "epoch": 0.3284008307372793, "grad_norm": 3.592802047729492, "learning_rate": 4.791496462479691e-06, "loss": 0.407372385263443, "step": 1265 }, { "epoch": 0.32866043613707163, "grad_norm": 4.574284076690674, "learning_rate": 4.791098565094192e-06, "loss": 0.4970031976699829, "step": 1266 }, { "epoch": 0.328920041536864, "grad_norm": 5.0173821449279785, "learning_rate": 4.790700306889202e-06, "loss": 0.4585545063018799, "step": 1267 }, { "epoch": 0.3291796469366563, "grad_norm": 6.851771831512451, "learning_rate": 4.790301687935124e-06, "loss": 0.4388192892074585, "step": 1268 }, { "epoch": 0.3294392523364486, "grad_norm": 2.116011381149292, "learning_rate": 4.789902708302423e-06, "loss": 0.3696725368499756, "step": 1269 }, { "epoch": 0.3296988577362409, "grad_norm": 5.33963680267334, "learning_rate": 4.789503368061632e-06, "loss": 0.4773092269897461, "step": 1270 }, { "epoch": 0.3299584631360332, "grad_norm": 4.6679368019104, "learning_rate": 4.789103667283344e-06, "loss": 0.39494526386260986, "step": 1271 }, { "epoch": 0.3302180685358255, "grad_norm": 4.670599937438965, "learning_rate": 4.788703606038216e-06, "loss": 0.4419700503349304, "step": 1272 }, { "epoch": 0.3304776739356179, "grad_norm": 3.360764265060425, "learning_rate": 4.788303184396971e-06, "loss": 0.42000406980514526, "step": 1273 }, { "epoch": 0.3307372793354102, "grad_norm": 4.183567047119141, "learning_rate": 4.787902402430395e-06, "loss": 0.396578848361969, "step": 1274 }, { "epoch": 0.3309968847352025, "grad_norm": 4.090073585510254, "learning_rate": 4.787501260209334e-06, "loss": 0.39259833097457886, "step": 1275 }, { "epoch": 0.3312564901349948, "grad_norm": 3.2651872634887695, "learning_rate": 4.7870997578047035e-06, "loss": 0.36749398708343506, "step": 1276 }, { "epoch": 0.3315160955347871, "grad_norm": 6.664865493774414, "learning_rate": 4.7866978952874795e-06, "loss": 0.4343417286872864, "step": 1277 }, { "epoch": 0.3317757009345794, "grad_norm": 3.0697288513183594, "learning_rate": 4.786295672728702e-06, "loss": 0.37496575713157654, "step": 1278 }, { "epoch": 0.3320353063343718, "grad_norm": 4.277647495269775, "learning_rate": 4.785893090199475e-06, "loss": 0.41152942180633545, "step": 1279 }, { "epoch": 0.3322949117341641, "grad_norm": 2.8793020248413086, "learning_rate": 4.785490147770964e-06, "loss": 0.40221261978149414, "step": 1280 }, { "epoch": 0.3325545171339564, "grad_norm": 3.7745625972747803, "learning_rate": 4.785086845514403e-06, "loss": 0.4534064829349518, "step": 1281 }, { "epoch": 0.3328141225337487, "grad_norm": 4.539671421051025, "learning_rate": 4.784683183501084e-06, "loss": 0.48947399854660034, "step": 1282 }, { "epoch": 0.333073727933541, "grad_norm": 4.500210762023926, "learning_rate": 4.7842791618023666e-06, "loss": 0.4496017098426819, "step": 1283 }, { "epoch": 0.3333333333333333, "grad_norm": 4.107618808746338, "learning_rate": 4.783874780489673e-06, "loss": 0.3726791739463806, "step": 1284 }, { "epoch": 0.3335929387331256, "grad_norm": 3.4954636096954346, "learning_rate": 4.783470039634486e-06, "loss": 0.42195743322372437, "step": 1285 }, { "epoch": 0.333852544132918, "grad_norm": 5.789175033569336, "learning_rate": 4.783064939308357e-06, "loss": 0.5435001254081726, "step": 1286 }, { "epoch": 0.3341121495327103, "grad_norm": 2.7143216133117676, "learning_rate": 4.782659479582898e-06, "loss": 0.3672153353691101, "step": 1287 }, { "epoch": 0.3343717549325026, "grad_norm": 2.166100263595581, "learning_rate": 4.782253660529785e-06, "loss": 0.35158073902130127, "step": 1288 }, { "epoch": 0.3346313603322949, "grad_norm": 7.473636150360107, "learning_rate": 4.781847482220757e-06, "loss": 0.5192667245864868, "step": 1289 }, { "epoch": 0.3348909657320872, "grad_norm": 3.877372980117798, "learning_rate": 4.781440944727617e-06, "loss": 0.45532262325286865, "step": 1290 }, { "epoch": 0.3351505711318795, "grad_norm": 1.7808752059936523, "learning_rate": 4.781034048122232e-06, "loss": 0.35733550786972046, "step": 1291 }, { "epoch": 0.3354101765316719, "grad_norm": 3.1558542251586914, "learning_rate": 4.780626792476532e-06, "loss": 0.4936430752277374, "step": 1292 }, { "epoch": 0.3356697819314642, "grad_norm": 6.368197441101074, "learning_rate": 4.78021917786251e-06, "loss": 0.3673517405986786, "step": 1293 }, { "epoch": 0.3359293873312565, "grad_norm": 2.093775510787964, "learning_rate": 4.779811204352223e-06, "loss": 0.3884221911430359, "step": 1294 }, { "epoch": 0.3361889927310488, "grad_norm": 2.0596845149993896, "learning_rate": 4.779402872017792e-06, "loss": 0.3410511016845703, "step": 1295 }, { "epoch": 0.3364485981308411, "grad_norm": 3.1018383502960205, "learning_rate": 4.778994180931401e-06, "loss": 0.39300665259361267, "step": 1296 }, { "epoch": 0.3367082035306334, "grad_norm": 3.0695927143096924, "learning_rate": 4.778585131165295e-06, "loss": 0.43484896421432495, "step": 1297 }, { "epoch": 0.33696780893042577, "grad_norm": 5.4501633644104, "learning_rate": 4.778175722791788e-06, "loss": 0.24928104877471924, "step": 1298 }, { "epoch": 0.3372274143302181, "grad_norm": 3.86834716796875, "learning_rate": 4.777765955883251e-06, "loss": 0.40438738465309143, "step": 1299 }, { "epoch": 0.3374870197300104, "grad_norm": 5.120668411254883, "learning_rate": 4.777355830512122e-06, "loss": 0.5499252676963806, "step": 1300 }, { "epoch": 0.3377466251298027, "grad_norm": 5.014799118041992, "learning_rate": 4.776945346750905e-06, "loss": 0.38220593333244324, "step": 1301 }, { "epoch": 0.338006230529595, "grad_norm": 3.926717758178711, "learning_rate": 4.776534504672159e-06, "loss": 0.3787745535373688, "step": 1302 }, { "epoch": 0.3382658359293873, "grad_norm": 4.4767537117004395, "learning_rate": 4.7761233043485165e-06, "loss": 0.3462867736816406, "step": 1303 }, { "epoch": 0.33852544132917967, "grad_norm": 4.1718974113464355, "learning_rate": 4.7757117458526645e-06, "loss": 0.39544913172721863, "step": 1304 }, { "epoch": 0.338785046728972, "grad_norm": 7.00399112701416, "learning_rate": 4.775299829257358e-06, "loss": 0.4741795063018799, "step": 1305 }, { "epoch": 0.3390446521287643, "grad_norm": 5.55075740814209, "learning_rate": 4.7748875546354155e-06, "loss": 0.5019347667694092, "step": 1306 }, { "epoch": 0.3393042575285566, "grad_norm": 3.4250171184539795, "learning_rate": 4.774474922059718e-06, "loss": 0.36389490962028503, "step": 1307 }, { "epoch": 0.3395638629283489, "grad_norm": 2.531888723373413, "learning_rate": 4.774061931603207e-06, "loss": 0.3398536145687103, "step": 1308 }, { "epoch": 0.3398234683281412, "grad_norm": 2.7042744159698486, "learning_rate": 4.773648583338892e-06, "loss": 0.3739814758300781, "step": 1309 }, { "epoch": 0.34008307372793356, "grad_norm": 1.6696712970733643, "learning_rate": 4.773234877339843e-06, "loss": 0.3772973120212555, "step": 1310 }, { "epoch": 0.34034267912772587, "grad_norm": 3.1802079677581787, "learning_rate": 4.772820813679194e-06, "loss": 0.3917825222015381, "step": 1311 }, { "epoch": 0.3406022845275182, "grad_norm": 2.951615333557129, "learning_rate": 4.772406392430141e-06, "loss": 0.4478932321071625, "step": 1312 }, { "epoch": 0.3408618899273105, "grad_norm": 5.046337604522705, "learning_rate": 4.771991613665945e-06, "loss": 0.45151209831237793, "step": 1313 }, { "epoch": 0.3411214953271028, "grad_norm": 2.305988311767578, "learning_rate": 4.771576477459929e-06, "loss": 0.358615517616272, "step": 1314 }, { "epoch": 0.3413811007268951, "grad_norm": 2.5834968090057373, "learning_rate": 4.77116098388548e-06, "loss": 0.3942871689796448, "step": 1315 }, { "epoch": 0.34164070612668745, "grad_norm": 4.072824954986572, "learning_rate": 4.770745133016048e-06, "loss": 0.4128488302230835, "step": 1316 }, { "epoch": 0.34190031152647976, "grad_norm": 3.7411742210388184, "learning_rate": 4.770328924925145e-06, "loss": 0.32720744609832764, "step": 1317 }, { "epoch": 0.34215991692627207, "grad_norm": 4.674540996551514, "learning_rate": 4.769912359686346e-06, "loss": 0.40299734473228455, "step": 1318 }, { "epoch": 0.3424195223260644, "grad_norm": 2.6053109169006348, "learning_rate": 4.7694954373732935e-06, "loss": 0.3643034100532532, "step": 1319 }, { "epoch": 0.3426791277258567, "grad_norm": 2.840618848800659, "learning_rate": 4.769078158059687e-06, "loss": 0.3940591514110565, "step": 1320 }, { "epoch": 0.342938733125649, "grad_norm": 4.728226184844971, "learning_rate": 4.7686605218192935e-06, "loss": 0.45100703835487366, "step": 1321 }, { "epoch": 0.34319833852544135, "grad_norm": 4.197799205780029, "learning_rate": 4.768242528725941e-06, "loss": 0.45980119705200195, "step": 1322 }, { "epoch": 0.34345794392523366, "grad_norm": 2.667649507522583, "learning_rate": 4.767824178853521e-06, "loss": 0.38368386030197144, "step": 1323 }, { "epoch": 0.34371754932502596, "grad_norm": 3.17999005317688, "learning_rate": 4.767405472275988e-06, "loss": 0.3980559706687927, "step": 1324 }, { "epoch": 0.34397715472481827, "grad_norm": 2.509798049926758, "learning_rate": 4.76698640906736e-06, "loss": 0.3502470850944519, "step": 1325 }, { "epoch": 0.3442367601246106, "grad_norm": 3.6936252117156982, "learning_rate": 4.766566989301718e-06, "loss": 0.47864270210266113, "step": 1326 }, { "epoch": 0.3444963655244029, "grad_norm": 4.085460662841797, "learning_rate": 4.7661472130532056e-06, "loss": 0.44073349237442017, "step": 1327 }, { "epoch": 0.34475597092419524, "grad_norm": 2.8645787239074707, "learning_rate": 4.7657270803960285e-06, "loss": 0.39227429032325745, "step": 1328 }, { "epoch": 0.34501557632398755, "grad_norm": 4.508745193481445, "learning_rate": 4.765306591404459e-06, "loss": 0.44876450300216675, "step": 1329 }, { "epoch": 0.34527518172377986, "grad_norm": 3.064448356628418, "learning_rate": 4.764885746152828e-06, "loss": 0.35050514340400696, "step": 1330 }, { "epoch": 0.34553478712357216, "grad_norm": 2.4232048988342285, "learning_rate": 4.764464544715532e-06, "loss": 0.39649340510368347, "step": 1331 }, { "epoch": 0.34579439252336447, "grad_norm": 3.0931692123413086, "learning_rate": 4.764042987167029e-06, "loss": 0.42184197902679443, "step": 1332 }, { "epoch": 0.3460539979231568, "grad_norm": 3.545088529586792, "learning_rate": 4.763621073581842e-06, "loss": 0.39672237634658813, "step": 1333 }, { "epoch": 0.34631360332294914, "grad_norm": 3.0418081283569336, "learning_rate": 4.7631988040345554e-06, "loss": 0.3898998200893402, "step": 1334 }, { "epoch": 0.34657320872274144, "grad_norm": 3.238117218017578, "learning_rate": 4.762776178599815e-06, "loss": 0.3548673391342163, "step": 1335 }, { "epoch": 0.34683281412253375, "grad_norm": 4.803839206695557, "learning_rate": 4.762353197352333e-06, "loss": 0.47526830434799194, "step": 1336 }, { "epoch": 0.34709241952232606, "grad_norm": 3.4168059825897217, "learning_rate": 4.761929860366883e-06, "loss": 0.3908125162124634, "step": 1337 }, { "epoch": 0.34735202492211836, "grad_norm": 2.1756558418273926, "learning_rate": 4.761506167718302e-06, "loss": 0.326316773891449, "step": 1338 }, { "epoch": 0.34761163032191067, "grad_norm": 1.9358934164047241, "learning_rate": 4.761082119481486e-06, "loss": 0.37907564640045166, "step": 1339 }, { "epoch": 0.34787123572170303, "grad_norm": 5.158588409423828, "learning_rate": 4.7606577157314e-06, "loss": 0.409429669380188, "step": 1340 }, { "epoch": 0.34813084112149534, "grad_norm": 3.080065965652466, "learning_rate": 4.760232956543067e-06, "loss": 0.36958765983581543, "step": 1341 }, { "epoch": 0.34839044652128764, "grad_norm": 3.9281678199768066, "learning_rate": 4.759807841991576e-06, "loss": 0.41377246379852295, "step": 1342 }, { "epoch": 0.34865005192107995, "grad_norm": 2.9227750301361084, "learning_rate": 4.759382372152077e-06, "loss": 0.4388214945793152, "step": 1343 }, { "epoch": 0.34890965732087226, "grad_norm": 2.1689045429229736, "learning_rate": 4.7589565470997836e-06, "loss": 0.3885508179664612, "step": 1344 }, { "epoch": 0.34916926272066456, "grad_norm": 4.295146942138672, "learning_rate": 4.758530366909971e-06, "loss": 0.35204750299453735, "step": 1345 }, { "epoch": 0.3494288681204569, "grad_norm": 5.107452869415283, "learning_rate": 4.758103831657979e-06, "loss": 0.39914530515670776, "step": 1346 }, { "epoch": 0.34968847352024923, "grad_norm": 3.9889461994171143, "learning_rate": 4.75767694141921e-06, "loss": 0.46436500549316406, "step": 1347 }, { "epoch": 0.34994807892004154, "grad_norm": 4.516400337219238, "learning_rate": 4.757249696269126e-06, "loss": 0.4565621614456177, "step": 1348 }, { "epoch": 0.35020768431983385, "grad_norm": 9.792519569396973, "learning_rate": 4.756822096283257e-06, "loss": 0.5077624320983887, "step": 1349 }, { "epoch": 0.35046728971962615, "grad_norm": 7.33480978012085, "learning_rate": 4.7563941415371905e-06, "loss": 0.37906572222709656, "step": 1350 }, { "epoch": 0.35072689511941846, "grad_norm": 4.666172027587891, "learning_rate": 4.755965832106581e-06, "loss": 0.4862571358680725, "step": 1351 }, { "epoch": 0.3509865005192108, "grad_norm": 3.6261379718780518, "learning_rate": 4.755537168067142e-06, "loss": 0.48033952713012695, "step": 1352 }, { "epoch": 0.3512461059190031, "grad_norm": 4.968277454376221, "learning_rate": 4.755108149494653e-06, "loss": 0.3854409456253052, "step": 1353 }, { "epoch": 0.35150571131879543, "grad_norm": 5.0298943519592285, "learning_rate": 4.754678776464954e-06, "loss": 0.39739301800727844, "step": 1354 }, { "epoch": 0.35176531671858774, "grad_norm": 9.441045761108398, "learning_rate": 4.754249049053948e-06, "loss": 0.46873053908348083, "step": 1355 }, { "epoch": 0.35202492211838005, "grad_norm": 4.577944755554199, "learning_rate": 4.753818967337602e-06, "loss": 0.4129863679409027, "step": 1356 }, { "epoch": 0.35228452751817235, "grad_norm": 3.533799648284912, "learning_rate": 4.753388531391943e-06, "loss": 0.47487521171569824, "step": 1357 }, { "epoch": 0.3525441329179647, "grad_norm": 4.057412624359131, "learning_rate": 4.752957741293064e-06, "loss": 0.4165450930595398, "step": 1358 }, { "epoch": 0.352803738317757, "grad_norm": 4.76093864440918, "learning_rate": 4.752526597117117e-06, "loss": 0.4074958264827728, "step": 1359 }, { "epoch": 0.3530633437175493, "grad_norm": 6.585534572601318, "learning_rate": 4.7520950989403205e-06, "loss": 0.43549397587776184, "step": 1360 }, { "epoch": 0.35332294911734163, "grad_norm": 4.403043746948242, "learning_rate": 4.751663246838953e-06, "loss": 0.4217449426651001, "step": 1361 }, { "epoch": 0.35358255451713394, "grad_norm": 4.309803009033203, "learning_rate": 4.751231040889354e-06, "loss": 0.37678050994873047, "step": 1362 }, { "epoch": 0.35384215991692625, "grad_norm": 7.877964019775391, "learning_rate": 4.7507984811679296e-06, "loss": 0.489493191242218, "step": 1363 }, { "epoch": 0.3541017653167186, "grad_norm": 5.854603290557861, "learning_rate": 4.750365567751146e-06, "loss": 0.492220938205719, "step": 1364 }, { "epoch": 0.3543613707165109, "grad_norm": 4.326776027679443, "learning_rate": 4.749932300715532e-06, "loss": 0.3504951596260071, "step": 1365 }, { "epoch": 0.3546209761163032, "grad_norm": 5.481512069702148, "learning_rate": 4.74949868013768e-06, "loss": 0.3915300965309143, "step": 1366 }, { "epoch": 0.35488058151609553, "grad_norm": 2.8140978813171387, "learning_rate": 4.749064706094244e-06, "loss": 0.4214552044868469, "step": 1367 }, { "epoch": 0.35514018691588783, "grad_norm": 2.7579851150512695, "learning_rate": 4.74863037866194e-06, "loss": 0.34155023097991943, "step": 1368 }, { "epoch": 0.35539979231568014, "grad_norm": 7.828887939453125, "learning_rate": 4.748195697917547e-06, "loss": 0.46326133608818054, "step": 1369 }, { "epoch": 0.3556593977154725, "grad_norm": 7.159687519073486, "learning_rate": 4.747760663937908e-06, "loss": 0.45903509855270386, "step": 1370 }, { "epoch": 0.3559190031152648, "grad_norm": 2.2212002277374268, "learning_rate": 4.747325276799927e-06, "loss": 0.3622296452522278, "step": 1371 }, { "epoch": 0.3561786085150571, "grad_norm": 4.719243049621582, "learning_rate": 4.746889536580569e-06, "loss": 0.4654160141944885, "step": 1372 }, { "epoch": 0.3564382139148494, "grad_norm": 4.5042619705200195, "learning_rate": 4.7464534433568634e-06, "loss": 0.408547580242157, "step": 1373 }, { "epoch": 0.35669781931464173, "grad_norm": 2.9454619884490967, "learning_rate": 4.7460169972059015e-06, "loss": 0.3514745235443115, "step": 1374 }, { "epoch": 0.35695742471443404, "grad_norm": 6.595964431762695, "learning_rate": 4.7455801982048374e-06, "loss": 0.3965314030647278, "step": 1375 }, { "epoch": 0.3572170301142264, "grad_norm": 2.0119776725769043, "learning_rate": 4.7451430464308875e-06, "loss": 0.34845346212387085, "step": 1376 }, { "epoch": 0.3574766355140187, "grad_norm": 3.2215073108673096, "learning_rate": 4.74470554196133e-06, "loss": 0.4368758499622345, "step": 1377 }, { "epoch": 0.357736240913811, "grad_norm": 4.1094770431518555, "learning_rate": 4.744267684873505e-06, "loss": 0.39291590452194214, "step": 1378 }, { "epoch": 0.3579958463136033, "grad_norm": 3.050083875656128, "learning_rate": 4.743829475244816e-06, "loss": 0.33589375019073486, "step": 1379 }, { "epoch": 0.3582554517133956, "grad_norm": 3.656811237335205, "learning_rate": 4.743390913152728e-06, "loss": 0.36553794145584106, "step": 1380 }, { "epoch": 0.35851505711318793, "grad_norm": 3.639315366744995, "learning_rate": 4.74295199867477e-06, "loss": 0.414722740650177, "step": 1381 }, { "epoch": 0.3587746625129803, "grad_norm": 5.214455604553223, "learning_rate": 4.74251273188853e-06, "loss": 0.39730751514434814, "step": 1382 }, { "epoch": 0.3590342679127726, "grad_norm": 3.82958722114563, "learning_rate": 4.742073112871663e-06, "loss": 0.38175302743911743, "step": 1383 }, { "epoch": 0.3592938733125649, "grad_norm": 3.922302484512329, "learning_rate": 4.741633141701881e-06, "loss": 0.4731721878051758, "step": 1384 }, { "epoch": 0.3595534787123572, "grad_norm": 2.9188332557678223, "learning_rate": 4.741192818456961e-06, "loss": 0.3597003221511841, "step": 1385 }, { "epoch": 0.3598130841121495, "grad_norm": 4.205831050872803, "learning_rate": 4.740752143214744e-06, "loss": 0.419761598110199, "step": 1386 }, { "epoch": 0.3600726895119418, "grad_norm": 3.3623111248016357, "learning_rate": 4.74031111605313e-06, "loss": 0.4544760584831238, "step": 1387 }, { "epoch": 0.3603322949117342, "grad_norm": 2.7100067138671875, "learning_rate": 4.739869737050084e-06, "loss": 0.3812633156776428, "step": 1388 }, { "epoch": 0.3605919003115265, "grad_norm": 2.751950263977051, "learning_rate": 4.73942800628363e-06, "loss": 0.40243297815322876, "step": 1389 }, { "epoch": 0.3608515057113188, "grad_norm": 2.5617032051086426, "learning_rate": 4.7389859238318555e-06, "loss": 0.3871177136898041, "step": 1390 }, { "epoch": 0.3611111111111111, "grad_norm": 2.79906964302063, "learning_rate": 4.738543489772912e-06, "loss": 0.48279857635498047, "step": 1391 }, { "epoch": 0.3613707165109034, "grad_norm": 5.670616149902344, "learning_rate": 4.738100704185011e-06, "loss": 0.43282800912857056, "step": 1392 }, { "epoch": 0.3616303219106957, "grad_norm": 3.4023525714874268, "learning_rate": 4.737657567146427e-06, "loss": 0.3913515508174896, "step": 1393 }, { "epoch": 0.3618899273104881, "grad_norm": 3.5758347511291504, "learning_rate": 4.737214078735496e-06, "loss": 0.4097498655319214, "step": 1394 }, { "epoch": 0.3621495327102804, "grad_norm": 5.9566569328308105, "learning_rate": 4.736770239030618e-06, "loss": 0.39321985840797424, "step": 1395 }, { "epoch": 0.3624091381100727, "grad_norm": 3.5401134490966797, "learning_rate": 4.736326048110252e-06, "loss": 0.4418656826019287, "step": 1396 }, { "epoch": 0.362668743509865, "grad_norm": 3.7511112689971924, "learning_rate": 4.735881506052922e-06, "loss": 0.46275556087493896, "step": 1397 }, { "epoch": 0.3629283489096573, "grad_norm": 1.9438867568969727, "learning_rate": 4.735436612937211e-06, "loss": 0.346250057220459, "step": 1398 }, { "epoch": 0.3631879543094496, "grad_norm": 6.034595489501953, "learning_rate": 4.734991368841769e-06, "loss": 0.3755149245262146, "step": 1399 }, { "epoch": 0.363447559709242, "grad_norm": 3.6971473693847656, "learning_rate": 4.7345457738453025e-06, "loss": 0.3617875874042511, "step": 1400 }, { "epoch": 0.3637071651090343, "grad_norm": 2.7620911598205566, "learning_rate": 4.734099828026584e-06, "loss": 0.3956015110015869, "step": 1401 }, { "epoch": 0.3639667705088266, "grad_norm": 2.8236584663391113, "learning_rate": 4.733653531464445e-06, "loss": 0.3867536783218384, "step": 1402 }, { "epoch": 0.3642263759086189, "grad_norm": 3.2309799194335938, "learning_rate": 4.7332068842377815e-06, "loss": 0.3904813826084137, "step": 1403 }, { "epoch": 0.3644859813084112, "grad_norm": 2.9861958026885986, "learning_rate": 4.73275988642555e-06, "loss": 0.4213937819004059, "step": 1404 }, { "epoch": 0.3647455867082035, "grad_norm": 4.863443374633789, "learning_rate": 4.73231253810677e-06, "loss": 0.34663835167884827, "step": 1405 }, { "epoch": 0.36500519210799587, "grad_norm": 2.8646669387817383, "learning_rate": 4.731864839360523e-06, "loss": 0.4086180627346039, "step": 1406 }, { "epoch": 0.3652647975077882, "grad_norm": 2.255396604537964, "learning_rate": 4.73141679026595e-06, "loss": 0.3578150272369385, "step": 1407 }, { "epoch": 0.3655244029075805, "grad_norm": 4.3684282302856445, "learning_rate": 4.730968390902257e-06, "loss": 0.4635840356349945, "step": 1408 }, { "epoch": 0.3657840083073728, "grad_norm": 4.089345455169678, "learning_rate": 4.730519641348711e-06, "loss": 0.48242199420928955, "step": 1409 }, { "epoch": 0.3660436137071651, "grad_norm": 4.459425449371338, "learning_rate": 4.73007054168464e-06, "loss": 0.38099533319473267, "step": 1410 }, { "epoch": 0.3663032191069574, "grad_norm": 3.7729761600494385, "learning_rate": 4.729621091989434e-06, "loss": 0.3539939820766449, "step": 1411 }, { "epoch": 0.36656282450674976, "grad_norm": 4.146793365478516, "learning_rate": 4.729171292342549e-06, "loss": 0.369343101978302, "step": 1412 }, { "epoch": 0.36682242990654207, "grad_norm": 2.022719621658325, "learning_rate": 4.728721142823495e-06, "loss": 0.3559311628341675, "step": 1413 }, { "epoch": 0.3670820353063344, "grad_norm": 4.779301643371582, "learning_rate": 4.728270643511849e-06, "loss": 0.40504246950149536, "step": 1414 }, { "epoch": 0.3673416407061267, "grad_norm": 2.635424852371216, "learning_rate": 4.72781979448725e-06, "loss": 0.3570086359977722, "step": 1415 }, { "epoch": 0.367601246105919, "grad_norm": 3.2897603511810303, "learning_rate": 4.727368595829397e-06, "loss": 0.3584572970867157, "step": 1416 }, { "epoch": 0.3678608515057113, "grad_norm": 3.9713330268859863, "learning_rate": 4.726917047618053e-06, "loss": 0.3888546824455261, "step": 1417 }, { "epoch": 0.36812045690550366, "grad_norm": 4.216097831726074, "learning_rate": 4.72646514993304e-06, "loss": 0.3373606204986572, "step": 1418 }, { "epoch": 0.36838006230529596, "grad_norm": 3.4988327026367188, "learning_rate": 4.726012902854243e-06, "loss": 0.40360572934150696, "step": 1419 }, { "epoch": 0.36863966770508827, "grad_norm": 6.139561176300049, "learning_rate": 4.72556030646161e-06, "loss": 0.4001759886741638, "step": 1420 }, { "epoch": 0.3688992731048806, "grad_norm": 3.4460949897766113, "learning_rate": 4.7251073608351485e-06, "loss": 0.3859387934207916, "step": 1421 }, { "epoch": 0.3691588785046729, "grad_norm": 2.9304146766662598, "learning_rate": 4.724654066054931e-06, "loss": 0.3452138304710388, "step": 1422 }, { "epoch": 0.3694184839044652, "grad_norm": 4.695140361785889, "learning_rate": 4.724200422201087e-06, "loss": 0.4471472501754761, "step": 1423 }, { "epoch": 0.36967808930425755, "grad_norm": 3.4234089851379395, "learning_rate": 4.7237464293538115e-06, "loss": 0.37960344552993774, "step": 1424 }, { "epoch": 0.36993769470404986, "grad_norm": 4.2272748947143555, "learning_rate": 4.72329208759336e-06, "loss": 0.4563027024269104, "step": 1425 }, { "epoch": 0.37019730010384216, "grad_norm": 3.300928831100464, "learning_rate": 4.722837397000052e-06, "loss": 0.3304935693740845, "step": 1426 }, { "epoch": 0.37045690550363447, "grad_norm": 3.21929931640625, "learning_rate": 4.722382357654262e-06, "loss": 0.3508793115615845, "step": 1427 }, { "epoch": 0.3707165109034268, "grad_norm": 6.180950164794922, "learning_rate": 4.721926969636433e-06, "loss": 0.4479409456253052, "step": 1428 }, { "epoch": 0.3709761163032191, "grad_norm": 6.332870960235596, "learning_rate": 4.721471233027067e-06, "loss": 0.4483088254928589, "step": 1429 }, { "epoch": 0.37123572170301145, "grad_norm": 5.083216667175293, "learning_rate": 4.721015147906727e-06, "loss": 0.38838106393814087, "step": 1430 }, { "epoch": 0.37149532710280375, "grad_norm": 3.734659194946289, "learning_rate": 4.720558714356041e-06, "loss": 0.4155699908733368, "step": 1431 }, { "epoch": 0.37175493250259606, "grad_norm": 3.6558377742767334, "learning_rate": 4.720101932455693e-06, "loss": 0.3721305727958679, "step": 1432 }, { "epoch": 0.37201453790238836, "grad_norm": 4.731104373931885, "learning_rate": 4.719644802286433e-06, "loss": 0.4763936400413513, "step": 1433 }, { "epoch": 0.37227414330218067, "grad_norm": 6.241245269775391, "learning_rate": 4.71918732392907e-06, "loss": 0.4089983403682709, "step": 1434 }, { "epoch": 0.372533748701973, "grad_norm": 3.448152542114258, "learning_rate": 4.718729497464477e-06, "loss": 0.3618403673171997, "step": 1435 }, { "epoch": 0.37279335410176534, "grad_norm": 4.7687788009643555, "learning_rate": 4.7182713229735874e-06, "loss": 0.3791795074939728, "step": 1436 }, { "epoch": 0.37305295950155765, "grad_norm": 5.530126094818115, "learning_rate": 4.717812800537394e-06, "loss": 0.4563780426979065, "step": 1437 }, { "epoch": 0.37331256490134995, "grad_norm": 2.3599305152893066, "learning_rate": 4.717353930236956e-06, "loss": 0.37386295199394226, "step": 1438 }, { "epoch": 0.37357217030114226, "grad_norm": 4.468238830566406, "learning_rate": 4.716894712153388e-06, "loss": 0.5494559407234192, "step": 1439 }, { "epoch": 0.37383177570093457, "grad_norm": 4.64698600769043, "learning_rate": 4.716435146367872e-06, "loss": 0.39609602093696594, "step": 1440 }, { "epoch": 0.37409138110072687, "grad_norm": 5.557136535644531, "learning_rate": 4.715975232961647e-06, "loss": 0.4040434658527374, "step": 1441 }, { "epoch": 0.37435098650051923, "grad_norm": 2.169447422027588, "learning_rate": 4.715514972016016e-06, "loss": 0.3947751522064209, "step": 1442 }, { "epoch": 0.37461059190031154, "grad_norm": 5.739151477813721, "learning_rate": 4.715054363612343e-06, "loss": 0.42137300968170166, "step": 1443 }, { "epoch": 0.37487019730010385, "grad_norm": 5.174201011657715, "learning_rate": 4.714593407832051e-06, "loss": 0.38310685753822327, "step": 1444 }, { "epoch": 0.37512980269989615, "grad_norm": 7.207179546356201, "learning_rate": 4.714132104756628e-06, "loss": 0.4118761420249939, "step": 1445 }, { "epoch": 0.37538940809968846, "grad_norm": 6.302114009857178, "learning_rate": 4.7136704544676215e-06, "loss": 0.4542405903339386, "step": 1446 }, { "epoch": 0.37564901349948077, "grad_norm": 4.1500983238220215, "learning_rate": 4.713208457046641e-06, "loss": 0.36027321219444275, "step": 1447 }, { "epoch": 0.37590861889927313, "grad_norm": 3.843628168106079, "learning_rate": 4.7127461125753575e-06, "loss": 0.4817083477973938, "step": 1448 }, { "epoch": 0.37616822429906543, "grad_norm": 3.419886350631714, "learning_rate": 4.7122834211355e-06, "loss": 0.3399337828159332, "step": 1449 }, { "epoch": 0.37642782969885774, "grad_norm": 4.390472412109375, "learning_rate": 4.711820382808866e-06, "loss": 0.4459332823753357, "step": 1450 }, { "epoch": 0.37668743509865005, "grad_norm": 6.223132133483887, "learning_rate": 4.711356997677308e-06, "loss": 0.3928259313106537, "step": 1451 }, { "epoch": 0.37694704049844235, "grad_norm": 4.51955509185791, "learning_rate": 4.710893265822741e-06, "loss": 0.3025397062301636, "step": 1452 }, { "epoch": 0.37720664589823466, "grad_norm": 2.895057439804077, "learning_rate": 4.710429187327144e-06, "loss": 0.39998695254325867, "step": 1453 }, { "epoch": 0.377466251298027, "grad_norm": 2.9372034072875977, "learning_rate": 4.709964762272554e-06, "loss": 0.36147668957710266, "step": 1454 }, { "epoch": 0.37772585669781933, "grad_norm": 1.5468995571136475, "learning_rate": 4.709499990741071e-06, "loss": 0.36905330419540405, "step": 1455 }, { "epoch": 0.37798546209761164, "grad_norm": 2.8391306400299072, "learning_rate": 4.709034872814856e-06, "loss": 0.3338516652584076, "step": 1456 }, { "epoch": 0.37824506749740394, "grad_norm": 5.785586357116699, "learning_rate": 4.708569408576133e-06, "loss": 0.46586889028549194, "step": 1457 }, { "epoch": 0.37850467289719625, "grad_norm": 1.9883127212524414, "learning_rate": 4.708103598107182e-06, "loss": 0.3352522850036621, "step": 1458 }, { "epoch": 0.37876427829698855, "grad_norm": 3.5564258098602295, "learning_rate": 4.707637441490351e-06, "loss": 0.3629472255706787, "step": 1459 }, { "epoch": 0.3790238836967809, "grad_norm": 7.176527500152588, "learning_rate": 4.707170938808044e-06, "loss": 0.48105353116989136, "step": 1460 }, { "epoch": 0.3792834890965732, "grad_norm": 2.8159172534942627, "learning_rate": 4.706704090142728e-06, "loss": 0.3273930549621582, "step": 1461 }, { "epoch": 0.37954309449636553, "grad_norm": 4.8997955322265625, "learning_rate": 4.706236895576931e-06, "loss": 0.37347930669784546, "step": 1462 }, { "epoch": 0.37980269989615784, "grad_norm": 3.508281946182251, "learning_rate": 4.705769355193244e-06, "loss": 0.34244465827941895, "step": 1463 }, { "epoch": 0.38006230529595014, "grad_norm": 3.707587480545044, "learning_rate": 4.705301469074314e-06, "loss": 0.4152682423591614, "step": 1464 }, { "epoch": 0.38032191069574245, "grad_norm": 3.1752936840057373, "learning_rate": 4.704833237302857e-06, "loss": 0.3560377061367035, "step": 1465 }, { "epoch": 0.3805815160955348, "grad_norm": 4.4633708000183105, "learning_rate": 4.7043646599616425e-06, "loss": 0.36994343996047974, "step": 1466 }, { "epoch": 0.3808411214953271, "grad_norm": 4.56000280380249, "learning_rate": 4.703895737133505e-06, "loss": 0.4552842974662781, "step": 1467 }, { "epoch": 0.3811007268951194, "grad_norm": 6.910962104797363, "learning_rate": 4.703426468901339e-06, "loss": 0.46859145164489746, "step": 1468 }, { "epoch": 0.38136033229491173, "grad_norm": 2.8279130458831787, "learning_rate": 4.702956855348102e-06, "loss": 0.3933699131011963, "step": 1469 }, { "epoch": 0.38161993769470404, "grad_norm": 3.1087563037872314, "learning_rate": 4.702486896556809e-06, "loss": 0.4092293083667755, "step": 1470 }, { "epoch": 0.38187954309449634, "grad_norm": 11.880378723144531, "learning_rate": 4.702016592610539e-06, "loss": 0.46732521057128906, "step": 1471 }, { "epoch": 0.3821391484942887, "grad_norm": 5.036388874053955, "learning_rate": 4.70154594359243e-06, "loss": 0.44532880187034607, "step": 1472 }, { "epoch": 0.382398753894081, "grad_norm": 3.967312812805176, "learning_rate": 4.701074949585684e-06, "loss": 0.4400010108947754, "step": 1473 }, { "epoch": 0.3826583592938733, "grad_norm": 4.963210582733154, "learning_rate": 4.7006036106735594e-06, "loss": 0.3752323091030121, "step": 1474 }, { "epoch": 0.3829179646936656, "grad_norm": 4.532613277435303, "learning_rate": 4.700131926939379e-06, "loss": 0.39263197779655457, "step": 1475 }, { "epoch": 0.38317757009345793, "grad_norm": 7.079682350158691, "learning_rate": 4.699659898466527e-06, "loss": 0.46808576583862305, "step": 1476 }, { "epoch": 0.38343717549325024, "grad_norm": 5.0410332679748535, "learning_rate": 4.699187525338447e-06, "loss": 0.4291010797023773, "step": 1477 }, { "epoch": 0.3836967808930426, "grad_norm": 4.954433441162109, "learning_rate": 4.698714807638641e-06, "loss": 0.457876980304718, "step": 1478 }, { "epoch": 0.3839563862928349, "grad_norm": 4.834138870239258, "learning_rate": 4.698241745450678e-06, "loss": 0.42877835035324097, "step": 1479 }, { "epoch": 0.3842159916926272, "grad_norm": 5.16781759262085, "learning_rate": 4.697768338858183e-06, "loss": 0.3627418279647827, "step": 1480 }, { "epoch": 0.3844755970924195, "grad_norm": 5.654480934143066, "learning_rate": 4.697294587944844e-06, "loss": 0.458498477935791, "step": 1481 }, { "epoch": 0.3847352024922118, "grad_norm": 8.355738639831543, "learning_rate": 4.696820492794408e-06, "loss": 0.390785813331604, "step": 1482 }, { "epoch": 0.38499480789200413, "grad_norm": 5.7961530685424805, "learning_rate": 4.6963460534906865e-06, "loss": 0.40179866552352905, "step": 1483 }, { "epoch": 0.3852544132917965, "grad_norm": 2.8339955806732178, "learning_rate": 4.6958712701175465e-06, "loss": 0.3452455401420593, "step": 1484 }, { "epoch": 0.3855140186915888, "grad_norm": 2.2498645782470703, "learning_rate": 4.695396142758922e-06, "loss": 0.37054234743118286, "step": 1485 }, { "epoch": 0.3857736240913811, "grad_norm": 5.312519073486328, "learning_rate": 4.694920671498802e-06, "loss": 0.4013946056365967, "step": 1486 }, { "epoch": 0.3860332294911734, "grad_norm": 5.212416648864746, "learning_rate": 4.694444856421242e-06, "loss": 0.39991411566734314, "step": 1487 }, { "epoch": 0.3862928348909657, "grad_norm": 6.714379787445068, "learning_rate": 4.693968697610351e-06, "loss": 0.4783760905265808, "step": 1488 }, { "epoch": 0.386552440290758, "grad_norm": 5.247308731079102, "learning_rate": 4.693492195150306e-06, "loss": 0.4535803198814392, "step": 1489 }, { "epoch": 0.3868120456905504, "grad_norm": 4.658491611480713, "learning_rate": 4.693015349125341e-06, "loss": 0.39063048362731934, "step": 1490 }, { "epoch": 0.3870716510903427, "grad_norm": 3.9801928997039795, "learning_rate": 4.692538159619751e-06, "loss": 0.45056870579719543, "step": 1491 }, { "epoch": 0.387331256490135, "grad_norm": 3.3554179668426514, "learning_rate": 4.692060626717894e-06, "loss": 0.3521830439567566, "step": 1492 }, { "epoch": 0.3875908618899273, "grad_norm": 6.202844142913818, "learning_rate": 4.691582750504184e-06, "loss": 0.38055089116096497, "step": 1493 }, { "epoch": 0.3878504672897196, "grad_norm": 4.494955539703369, "learning_rate": 4.691104531063101e-06, "loss": 0.45287519693374634, "step": 1494 }, { "epoch": 0.3881100726895119, "grad_norm": 3.623600721359253, "learning_rate": 4.6906259684791816e-06, "loss": 0.3611608147621155, "step": 1495 }, { "epoch": 0.3883696780893043, "grad_norm": 1.6473522186279297, "learning_rate": 4.690147062837026e-06, "loss": 0.37186872959136963, "step": 1496 }, { "epoch": 0.3886292834890966, "grad_norm": 3.439016580581665, "learning_rate": 4.689667814221293e-06, "loss": 0.3677493929862976, "step": 1497 }, { "epoch": 0.3888888888888889, "grad_norm": 2.7475383281707764, "learning_rate": 4.689188222716703e-06, "loss": 0.38966190814971924, "step": 1498 }, { "epoch": 0.3891484942886812, "grad_norm": 4.717802047729492, "learning_rate": 4.688708288408036e-06, "loss": 0.4502902626991272, "step": 1499 }, { "epoch": 0.3894080996884735, "grad_norm": 3.2162280082702637, "learning_rate": 4.688228011380135e-06, "loss": 0.4022447466850281, "step": 1500 }, { "epoch": 0.3896677050882658, "grad_norm": 3.9223620891571045, "learning_rate": 4.687747391717901e-06, "loss": 0.40299731492996216, "step": 1501 }, { "epoch": 0.3899273104880582, "grad_norm": 2.3417580127716064, "learning_rate": 4.687266429506296e-06, "loss": 0.3836326599121094, "step": 1502 }, { "epoch": 0.3901869158878505, "grad_norm": 4.886773109436035, "learning_rate": 4.686785124830345e-06, "loss": 0.3642473816871643, "step": 1503 }, { "epoch": 0.3904465212876428, "grad_norm": 4.769381523132324, "learning_rate": 4.686303477775129e-06, "loss": 0.41507798433303833, "step": 1504 }, { "epoch": 0.3907061266874351, "grad_norm": 4.104416847229004, "learning_rate": 4.685821488425795e-06, "loss": 0.371759831905365, "step": 1505 }, { "epoch": 0.3909657320872274, "grad_norm": 2.700202703475952, "learning_rate": 4.6853391568675456e-06, "loss": 0.3346399664878845, "step": 1506 }, { "epoch": 0.3912253374870197, "grad_norm": 1.7630672454833984, "learning_rate": 4.684856483185647e-06, "loss": 0.35402727127075195, "step": 1507 }, { "epoch": 0.39148494288681207, "grad_norm": 7.2361345291137695, "learning_rate": 4.684373467465424e-06, "loss": 0.4084126651287079, "step": 1508 }, { "epoch": 0.3917445482866044, "grad_norm": 6.205450534820557, "learning_rate": 4.683890109792264e-06, "loss": 0.4959922730922699, "step": 1509 }, { "epoch": 0.3920041536863967, "grad_norm": 4.614753723144531, "learning_rate": 4.683406410251612e-06, "loss": 0.4340168535709381, "step": 1510 }, { "epoch": 0.392263759086189, "grad_norm": 2.496480941772461, "learning_rate": 4.682922368928977e-06, "loss": 0.33118292689323425, "step": 1511 }, { "epoch": 0.3925233644859813, "grad_norm": 3.316011428833008, "learning_rate": 4.682437985909924e-06, "loss": 0.38853856921195984, "step": 1512 }, { "epoch": 0.3927829698857736, "grad_norm": 4.040672779083252, "learning_rate": 4.6819532612800824e-06, "loss": 0.4122788608074188, "step": 1513 }, { "epoch": 0.39304257528556596, "grad_norm": 7.52345085144043, "learning_rate": 4.68146819512514e-06, "loss": 0.48266321420669556, "step": 1514 }, { "epoch": 0.39330218068535827, "grad_norm": 4.921835422515869, "learning_rate": 4.680982787530845e-06, "loss": 0.44935959577560425, "step": 1515 }, { "epoch": 0.3935617860851506, "grad_norm": 3.684065580368042, "learning_rate": 4.680497038583008e-06, "loss": 0.43052947521209717, "step": 1516 }, { "epoch": 0.3938213914849429, "grad_norm": 3.9652366638183594, "learning_rate": 4.680010948367496e-06, "loss": 0.3577646017074585, "step": 1517 }, { "epoch": 0.3940809968847352, "grad_norm": 2.0754833221435547, "learning_rate": 4.67952451697024e-06, "loss": 0.37320321798324585, "step": 1518 }, { "epoch": 0.3943406022845275, "grad_norm": 3.9769949913024902, "learning_rate": 4.67903774447723e-06, "loss": 0.4208689332008362, "step": 1519 }, { "epoch": 0.39460020768431986, "grad_norm": 4.600765228271484, "learning_rate": 4.678550630974515e-06, "loss": 0.5261613726615906, "step": 1520 }, { "epoch": 0.39485981308411217, "grad_norm": 3.132821559906006, "learning_rate": 4.678063176548209e-06, "loss": 0.3664577305316925, "step": 1521 }, { "epoch": 0.39511941848390447, "grad_norm": 3.1047234535217285, "learning_rate": 4.677575381284478e-06, "loss": 0.36480483412742615, "step": 1522 }, { "epoch": 0.3953790238836968, "grad_norm": 5.63509464263916, "learning_rate": 4.6770872452695546e-06, "loss": 0.37542909383773804, "step": 1523 }, { "epoch": 0.3956386292834891, "grad_norm": 3.8917813301086426, "learning_rate": 4.6765987685897315e-06, "loss": 0.427950382232666, "step": 1524 }, { "epoch": 0.3958982346832814, "grad_norm": 5.80477237701416, "learning_rate": 4.6761099513313595e-06, "loss": 0.44590941071510315, "step": 1525 }, { "epoch": 0.39615784008307375, "grad_norm": 4.536252975463867, "learning_rate": 4.67562079358085e-06, "loss": 0.44463878870010376, "step": 1526 }, { "epoch": 0.39641744548286606, "grad_norm": 3.892179012298584, "learning_rate": 4.675131295424675e-06, "loss": 0.3761870563030243, "step": 1527 }, { "epoch": 0.39667705088265837, "grad_norm": 4.867231845855713, "learning_rate": 4.674641456949368e-06, "loss": 0.37757718563079834, "step": 1528 }, { "epoch": 0.3969366562824507, "grad_norm": 4.016723155975342, "learning_rate": 4.674151278241518e-06, "loss": 0.4014413058757782, "step": 1529 }, { "epoch": 0.397196261682243, "grad_norm": 3.882009506225586, "learning_rate": 4.673660759387779e-06, "loss": 0.3861332833766937, "step": 1530 }, { "epoch": 0.3974558670820353, "grad_norm": 5.015659332275391, "learning_rate": 4.673169900474865e-06, "loss": 0.3794547915458679, "step": 1531 }, { "epoch": 0.39771547248182765, "grad_norm": 2.8577284812927246, "learning_rate": 4.672678701589547e-06, "loss": 0.37834984064102173, "step": 1532 }, { "epoch": 0.39797507788161995, "grad_norm": 4.848259925842285, "learning_rate": 4.672187162818658e-06, "loss": 0.33744609355926514, "step": 1533 }, { "epoch": 0.39823468328141226, "grad_norm": 5.146939277648926, "learning_rate": 4.671695284249091e-06, "loss": 0.32163769006729126, "step": 1534 }, { "epoch": 0.39849428868120457, "grad_norm": 3.2366538047790527, "learning_rate": 4.671203065967799e-06, "loss": 0.32680028676986694, "step": 1535 }, { "epoch": 0.3987538940809969, "grad_norm": 5.0766777992248535, "learning_rate": 4.670710508061794e-06, "loss": 0.4276353120803833, "step": 1536 }, { "epoch": 0.3990134994807892, "grad_norm": 4.588027000427246, "learning_rate": 4.67021761061815e-06, "loss": 0.3858858048915863, "step": 1537 }, { "epoch": 0.39927310488058154, "grad_norm": 4.345805644989014, "learning_rate": 4.669724373724e-06, "loss": 0.45840802788734436, "step": 1538 }, { "epoch": 0.39953271028037385, "grad_norm": 4.58542537689209, "learning_rate": 4.6692307974665355e-06, "loss": 0.43831154704093933, "step": 1539 }, { "epoch": 0.39979231568016615, "grad_norm": 2.5178000926971436, "learning_rate": 4.668736881933012e-06, "loss": 0.3596705198287964, "step": 1540 }, { "epoch": 0.40005192107995846, "grad_norm": 4.961409091949463, "learning_rate": 4.66824262721074e-06, "loss": 0.38335180282592773, "step": 1541 }, { "epoch": 0.40031152647975077, "grad_norm": 4.530200481414795, "learning_rate": 4.6677480333870935e-06, "loss": 0.3479784429073334, "step": 1542 }, { "epoch": 0.4005711318795431, "grad_norm": 3.525968551635742, "learning_rate": 4.667253100549506e-06, "loss": 0.3980603516101837, "step": 1543 }, { "epoch": 0.40083073727933544, "grad_norm": 2.588526964187622, "learning_rate": 4.666757828785469e-06, "loss": 0.3869856297969818, "step": 1544 }, { "epoch": 0.40109034267912774, "grad_norm": 1.9054961204528809, "learning_rate": 4.666262218182535e-06, "loss": 0.38786616921424866, "step": 1545 }, { "epoch": 0.40134994807892005, "grad_norm": 2.0394368171691895, "learning_rate": 4.665766268828319e-06, "loss": 0.35867762565612793, "step": 1546 }, { "epoch": 0.40160955347871236, "grad_norm": 3.4058399200439453, "learning_rate": 4.66526998081049e-06, "loss": 0.379557341337204, "step": 1547 }, { "epoch": 0.40186915887850466, "grad_norm": 1.741400957107544, "learning_rate": 4.664773354216785e-06, "loss": 0.36526745557785034, "step": 1548 }, { "epoch": 0.40212876427829697, "grad_norm": 3.7764720916748047, "learning_rate": 4.664276389134991e-06, "loss": 0.3580799698829651, "step": 1549 }, { "epoch": 0.40238836967808933, "grad_norm": 3.6446547508239746, "learning_rate": 4.663779085652964e-06, "loss": 0.4088647663593292, "step": 1550 }, { "epoch": 0.40264797507788164, "grad_norm": 5.162906169891357, "learning_rate": 4.663281443858614e-06, "loss": 0.4124714732170105, "step": 1551 }, { "epoch": 0.40290758047767394, "grad_norm": 4.031432628631592, "learning_rate": 4.662783463839913e-06, "loss": 0.3625961244106293, "step": 1552 }, { "epoch": 0.40316718587746625, "grad_norm": 3.918586492538452, "learning_rate": 4.662285145684892e-06, "loss": 0.38661283254623413, "step": 1553 }, { "epoch": 0.40342679127725856, "grad_norm": 5.805911540985107, "learning_rate": 4.661786489481644e-06, "loss": 0.4871971309185028, "step": 1554 }, { "epoch": 0.40368639667705086, "grad_norm": 7.855861663818359, "learning_rate": 4.661287495318317e-06, "loss": 0.4230889678001404, "step": 1555 }, { "epoch": 0.4039460020768432, "grad_norm": 6.239718437194824, "learning_rate": 4.660788163283125e-06, "loss": 0.5232515335083008, "step": 1556 }, { "epoch": 0.40420560747663553, "grad_norm": 5.833248615264893, "learning_rate": 4.6602884934643364e-06, "loss": 0.47846466302871704, "step": 1557 }, { "epoch": 0.40446521287642784, "grad_norm": 3.4631009101867676, "learning_rate": 4.659788485950282e-06, "loss": 0.4274548292160034, "step": 1558 }, { "epoch": 0.40472481827622014, "grad_norm": 3.7878243923187256, "learning_rate": 4.659288140829351e-06, "loss": 0.3592222332954407, "step": 1559 }, { "epoch": 0.40498442367601245, "grad_norm": 3.503089189529419, "learning_rate": 4.658787458189995e-06, "loss": 0.4178747534751892, "step": 1560 }, { "epoch": 0.40524402907580476, "grad_norm": 3.9146106243133545, "learning_rate": 4.658286438120721e-06, "loss": 0.4145658016204834, "step": 1561 }, { "epoch": 0.4055036344755971, "grad_norm": 4.309313774108887, "learning_rate": 4.657785080710099e-06, "loss": 0.4357701241970062, "step": 1562 }, { "epoch": 0.4057632398753894, "grad_norm": 2.261482000350952, "learning_rate": 4.657283386046757e-06, "loss": 0.3422403335571289, "step": 1563 }, { "epoch": 0.40602284527518173, "grad_norm": 3.3500356674194336, "learning_rate": 4.656781354219383e-06, "loss": 0.4518405795097351, "step": 1564 }, { "epoch": 0.40628245067497404, "grad_norm": 6.868721008300781, "learning_rate": 4.656278985316725e-06, "loss": 0.3548021912574768, "step": 1565 }, { "epoch": 0.40654205607476634, "grad_norm": 4.506768226623535, "learning_rate": 4.655776279427591e-06, "loss": 0.38561657071113586, "step": 1566 }, { "epoch": 0.40680166147455865, "grad_norm": 2.036473274230957, "learning_rate": 4.655273236640847e-06, "loss": 0.3749697506427765, "step": 1567 }, { "epoch": 0.407061266874351, "grad_norm": 3.8495230674743652, "learning_rate": 4.6547698570454206e-06, "loss": 0.41681092977523804, "step": 1568 }, { "epoch": 0.4073208722741433, "grad_norm": 6.513577461242676, "learning_rate": 4.654266140730297e-06, "loss": 0.4711287021636963, "step": 1569 }, { "epoch": 0.4075804776739356, "grad_norm": 2.571235179901123, "learning_rate": 4.653762087784521e-06, "loss": 0.3524416983127594, "step": 1570 }, { "epoch": 0.40784008307372793, "grad_norm": 3.736748456954956, "learning_rate": 4.653257698297198e-06, "loss": 0.3554302155971527, "step": 1571 }, { "epoch": 0.40809968847352024, "grad_norm": 4.872110366821289, "learning_rate": 4.652752972357492e-06, "loss": 0.46137410402297974, "step": 1572 }, { "epoch": 0.40835929387331255, "grad_norm": 4.716984748840332, "learning_rate": 4.652247910054629e-06, "loss": 0.39902251958847046, "step": 1573 }, { "epoch": 0.4086188992731049, "grad_norm": 5.244745254516602, "learning_rate": 4.6517425114778905e-06, "loss": 0.414243221282959, "step": 1574 }, { "epoch": 0.4088785046728972, "grad_norm": 4.440649509429932, "learning_rate": 4.65123677671662e-06, "loss": 0.35623496770858765, "step": 1575 }, { "epoch": 0.4091381100726895, "grad_norm": 6.764517307281494, "learning_rate": 4.6507307058602205e-06, "loss": 0.3992854654788971, "step": 1576 }, { "epoch": 0.4093977154724818, "grad_norm": 5.712675094604492, "learning_rate": 4.650224298998154e-06, "loss": 0.3861038088798523, "step": 1577 }, { "epoch": 0.40965732087227413, "grad_norm": 4.290748119354248, "learning_rate": 4.649717556219939e-06, "loss": 0.41736137866973877, "step": 1578 }, { "epoch": 0.40991692627206644, "grad_norm": 3.8587799072265625, "learning_rate": 4.649210477615159e-06, "loss": 0.376677006483078, "step": 1579 }, { "epoch": 0.4101765316718588, "grad_norm": 4.417436599731445, "learning_rate": 4.648703063273452e-06, "loss": 0.3728463053703308, "step": 1580 }, { "epoch": 0.4104361370716511, "grad_norm": 4.0281476974487305, "learning_rate": 4.6481953132845184e-06, "loss": 0.434215784072876, "step": 1581 }, { "epoch": 0.4106957424714434, "grad_norm": 5.075652599334717, "learning_rate": 4.647687227738116e-06, "loss": 0.46659427881240845, "step": 1582 }, { "epoch": 0.4109553478712357, "grad_norm": 7.363152503967285, "learning_rate": 4.647178806724064e-06, "loss": 0.3753526210784912, "step": 1583 }, { "epoch": 0.411214953271028, "grad_norm": 5.141430854797363, "learning_rate": 4.646670050332238e-06, "loss": 0.3727869391441345, "step": 1584 }, { "epoch": 0.41147455867082033, "grad_norm": 8.20910358428955, "learning_rate": 4.646160958652575e-06, "loss": 0.4337628483772278, "step": 1585 }, { "epoch": 0.4117341640706127, "grad_norm": 2.603416919708252, "learning_rate": 4.645651531775071e-06, "loss": 0.3440665304660797, "step": 1586 }, { "epoch": 0.411993769470405, "grad_norm": 3.2354631423950195, "learning_rate": 4.64514176978978e-06, "loss": 0.423834890127182, "step": 1587 }, { "epoch": 0.4122533748701973, "grad_norm": 5.8533244132995605, "learning_rate": 4.6446316727868175e-06, "loss": 0.5059441924095154, "step": 1588 }, { "epoch": 0.4125129802699896, "grad_norm": 5.79716682434082, "learning_rate": 4.644121240856357e-06, "loss": 0.3913712501525879, "step": 1589 }, { "epoch": 0.4127725856697819, "grad_norm": 7.222247123718262, "learning_rate": 4.6436104740886305e-06, "loss": 0.31017810106277466, "step": 1590 }, { "epoch": 0.41303219106957423, "grad_norm": 4.196223258972168, "learning_rate": 4.64309937257393e-06, "loss": 0.46007809042930603, "step": 1591 }, { "epoch": 0.4132917964693666, "grad_norm": 6.126249313354492, "learning_rate": 4.642587936402607e-06, "loss": 0.41942667961120605, "step": 1592 }, { "epoch": 0.4135514018691589, "grad_norm": 4.5316948890686035, "learning_rate": 4.642076165665071e-06, "loss": 0.40487682819366455, "step": 1593 }, { "epoch": 0.4138110072689512, "grad_norm": 3.216381311416626, "learning_rate": 4.641564060451792e-06, "loss": 0.42187878489494324, "step": 1594 }, { "epoch": 0.4140706126687435, "grad_norm": 2.307612657546997, "learning_rate": 4.641051620853298e-06, "loss": 0.3883415758609772, "step": 1595 }, { "epoch": 0.4143302180685358, "grad_norm": 5.901413440704346, "learning_rate": 4.640538846960177e-06, "loss": 0.354388952255249, "step": 1596 }, { "epoch": 0.4145898234683281, "grad_norm": 7.392515182495117, "learning_rate": 4.640025738863076e-06, "loss": 0.4318666160106659, "step": 1597 }, { "epoch": 0.4148494288681205, "grad_norm": 5.946094036102295, "learning_rate": 4.639512296652699e-06, "loss": 0.5172109603881836, "step": 1598 }, { "epoch": 0.4151090342679128, "grad_norm": 2.6118640899658203, "learning_rate": 4.638998520419812e-06, "loss": 0.31910231709480286, "step": 1599 }, { "epoch": 0.4153686396677051, "grad_norm": 4.436158180236816, "learning_rate": 4.63848441025524e-06, "loss": 0.34986209869384766, "step": 1600 }, { "epoch": 0.4156282450674974, "grad_norm": 4.584709167480469, "learning_rate": 4.6379699662498646e-06, "loss": 0.44832372665405273, "step": 1601 }, { "epoch": 0.4158878504672897, "grad_norm": 4.655623912811279, "learning_rate": 4.637455188494627e-06, "loss": 0.48840558528900146, "step": 1602 }, { "epoch": 0.416147455867082, "grad_norm": 2.678450345993042, "learning_rate": 4.636940077080531e-06, "loss": 0.37317782640457153, "step": 1603 }, { "epoch": 0.4164070612668744, "grad_norm": 2.568145751953125, "learning_rate": 4.6364246320986325e-06, "loss": 0.3885074257850647, "step": 1604 }, { "epoch": 0.4166666666666667, "grad_norm": 1.5991637706756592, "learning_rate": 4.6359088536400534e-06, "loss": 0.36980873346328735, "step": 1605 }, { "epoch": 0.416926272066459, "grad_norm": 2.1943533420562744, "learning_rate": 4.635392741795971e-06, "loss": 0.40457242727279663, "step": 1606 }, { "epoch": 0.4171858774662513, "grad_norm": 4.205132007598877, "learning_rate": 4.63487629665762e-06, "loss": 0.4042184054851532, "step": 1607 }, { "epoch": 0.4174454828660436, "grad_norm": 6.361348628997803, "learning_rate": 4.634359518316299e-06, "loss": 0.49331313371658325, "step": 1608 }, { "epoch": 0.4177050882658359, "grad_norm": 5.023858070373535, "learning_rate": 4.6338424068633615e-06, "loss": 0.3117924928665161, "step": 1609 }, { "epoch": 0.4179646936656282, "grad_norm": 4.707794189453125, "learning_rate": 4.6333249623902195e-06, "loss": 0.3660535216331482, "step": 1610 }, { "epoch": 0.4182242990654206, "grad_norm": 7.775334358215332, "learning_rate": 4.632807184988348e-06, "loss": 0.3472670912742615, "step": 1611 }, { "epoch": 0.4184839044652129, "grad_norm": 8.60116958618164, "learning_rate": 4.6322890747492765e-06, "loss": 0.42986810207366943, "step": 1612 }, { "epoch": 0.4187435098650052, "grad_norm": 3.0990002155303955, "learning_rate": 4.631770631764595e-06, "loss": 0.3754419684410095, "step": 1613 }, { "epoch": 0.4190031152647975, "grad_norm": 4.556484222412109, "learning_rate": 4.631251856125952e-06, "loss": 0.4884305000305176, "step": 1614 }, { "epoch": 0.4192627206645898, "grad_norm": 3.4534833431243896, "learning_rate": 4.630732747925057e-06, "loss": 0.43084508180618286, "step": 1615 }, { "epoch": 0.4195223260643821, "grad_norm": 2.0990755558013916, "learning_rate": 4.630213307253674e-06, "loss": 0.3855700194835663, "step": 1616 }, { "epoch": 0.4197819314641745, "grad_norm": 3.9257428646087646, "learning_rate": 4.6296935342036305e-06, "loss": 0.4570782780647278, "step": 1617 }, { "epoch": 0.4200415368639668, "grad_norm": 5.581472873687744, "learning_rate": 4.629173428866808e-06, "loss": 0.33447134494781494, "step": 1618 }, { "epoch": 0.4203011422637591, "grad_norm": 4.84060525894165, "learning_rate": 4.628652991335153e-06, "loss": 0.44785088300704956, "step": 1619 }, { "epoch": 0.4205607476635514, "grad_norm": 2.092803955078125, "learning_rate": 4.628132221700663e-06, "loss": 0.368630051612854, "step": 1620 }, { "epoch": 0.4208203530633437, "grad_norm": 2.5814473628997803, "learning_rate": 4.627611120055399e-06, "loss": 0.3396196961402893, "step": 1621 }, { "epoch": 0.421079958463136, "grad_norm": 3.0825650691986084, "learning_rate": 4.627089686491482e-06, "loss": 0.3462132215499878, "step": 1622 }, { "epoch": 0.42133956386292837, "grad_norm": 2.853040933609009, "learning_rate": 4.626567921101087e-06, "loss": 0.4224758446216583, "step": 1623 }, { "epoch": 0.4215991692627207, "grad_norm": 2.5930514335632324, "learning_rate": 4.626045823976453e-06, "loss": 0.3569386601448059, "step": 1624 }, { "epoch": 0.421858774662513, "grad_norm": 2.7312369346618652, "learning_rate": 4.625523395209871e-06, "loss": 0.33880430459976196, "step": 1625 }, { "epoch": 0.4221183800623053, "grad_norm": 4.5047831535339355, "learning_rate": 4.625000634893698e-06, "loss": 0.371901273727417, "step": 1626 }, { "epoch": 0.4223779854620976, "grad_norm": 6.08768367767334, "learning_rate": 4.624477543120344e-06, "loss": 0.4350731670856476, "step": 1627 }, { "epoch": 0.4226375908618899, "grad_norm": 3.1298635005950928, "learning_rate": 4.62395411998228e-06, "loss": 0.36034345626831055, "step": 1628 }, { "epoch": 0.42289719626168226, "grad_norm": 3.5703537464141846, "learning_rate": 4.623430365572036e-06, "loss": 0.3104487359523773, "step": 1629 }, { "epoch": 0.42315680166147457, "grad_norm": 4.8731279373168945, "learning_rate": 4.622906279982199e-06, "loss": 0.5136111974716187, "step": 1630 }, { "epoch": 0.4234164070612669, "grad_norm": 4.466079235076904, "learning_rate": 4.6223818633054155e-06, "loss": 0.3943455219268799, "step": 1631 }, { "epoch": 0.4236760124610592, "grad_norm": 2.4715375900268555, "learning_rate": 4.62185711563439e-06, "loss": 0.38271450996398926, "step": 1632 }, { "epoch": 0.4239356178608515, "grad_norm": 2.396941661834717, "learning_rate": 4.621332037061887e-06, "loss": 0.35880181193351746, "step": 1633 }, { "epoch": 0.4241952232606438, "grad_norm": 4.463871955871582, "learning_rate": 4.620806627680728e-06, "loss": 0.40555673837661743, "step": 1634 }, { "epoch": 0.42445482866043616, "grad_norm": 4.767510890960693, "learning_rate": 4.6202808875837915e-06, "loss": 0.4725264310836792, "step": 1635 }, { "epoch": 0.42471443406022846, "grad_norm": 5.109041690826416, "learning_rate": 4.619754816864019e-06, "loss": 0.45863354206085205, "step": 1636 }, { "epoch": 0.42497403946002077, "grad_norm": 3.6781115531921387, "learning_rate": 4.619228415614406e-06, "loss": 0.4153437614440918, "step": 1637 }, { "epoch": 0.4252336448598131, "grad_norm": 3.4629504680633545, "learning_rate": 4.61870168392801e-06, "loss": 0.37730473279953003, "step": 1638 }, { "epoch": 0.4254932502596054, "grad_norm": 2.914731025695801, "learning_rate": 4.6181746218979424e-06, "loss": 0.34273698925971985, "step": 1639 }, { "epoch": 0.4257528556593977, "grad_norm": 5.548107147216797, "learning_rate": 4.6176472296173775e-06, "loss": 0.3614075183868408, "step": 1640 }, { "epoch": 0.42601246105919005, "grad_norm": 4.267474174499512, "learning_rate": 4.617119507179546e-06, "loss": 0.33695122599601746, "step": 1641 }, { "epoch": 0.42627206645898236, "grad_norm": 3.026127576828003, "learning_rate": 4.616591454677737e-06, "loss": 0.356842577457428, "step": 1642 }, { "epoch": 0.42653167185877466, "grad_norm": 2.6761696338653564, "learning_rate": 4.616063072205298e-06, "loss": 0.3667711019515991, "step": 1643 }, { "epoch": 0.42679127725856697, "grad_norm": 5.602174758911133, "learning_rate": 4.615534359855636e-06, "loss": 0.44606152176856995, "step": 1644 }, { "epoch": 0.4270508826583593, "grad_norm": 3.9709596633911133, "learning_rate": 4.615005317722213e-06, "loss": 0.38032740354537964, "step": 1645 }, { "epoch": 0.4273104880581516, "grad_norm": 4.712994575500488, "learning_rate": 4.614475945898554e-06, "loss": 0.3206869661808014, "step": 1646 }, { "epoch": 0.42757009345794394, "grad_norm": 3.89030122756958, "learning_rate": 4.613946244478238e-06, "loss": 0.35534536838531494, "step": 1647 }, { "epoch": 0.42782969885773625, "grad_norm": 3.3408336639404297, "learning_rate": 4.613416213554904e-06, "loss": 0.3096921443939209, "step": 1648 }, { "epoch": 0.42808930425752856, "grad_norm": 2.7064995765686035, "learning_rate": 4.61288585322225e-06, "loss": 0.31999239325523376, "step": 1649 }, { "epoch": 0.42834890965732086, "grad_norm": 3.4798600673675537, "learning_rate": 4.6123551635740336e-06, "loss": 0.3477141857147217, "step": 1650 }, { "epoch": 0.42860851505711317, "grad_norm": 3.8143417835235596, "learning_rate": 4.611824144704064e-06, "loss": 0.3825860619544983, "step": 1651 }, { "epoch": 0.4288681204569055, "grad_norm": 5.265408515930176, "learning_rate": 4.611292796706218e-06, "loss": 0.34906190633773804, "step": 1652 }, { "epoch": 0.42912772585669784, "grad_norm": 2.2761151790618896, "learning_rate": 4.610761119674422e-06, "loss": 0.3477930426597595, "step": 1653 }, { "epoch": 0.42938733125649015, "grad_norm": 2.7082269191741943, "learning_rate": 4.610229113702666e-06, "loss": 0.37922632694244385, "step": 1654 }, { "epoch": 0.42964693665628245, "grad_norm": 3.9772632122039795, "learning_rate": 4.609696778884997e-06, "loss": 0.35693758726119995, "step": 1655 }, { "epoch": 0.42990654205607476, "grad_norm": 6.901135444641113, "learning_rate": 4.6091641153155175e-06, "loss": 0.3607182800769806, "step": 1656 }, { "epoch": 0.43016614745586707, "grad_norm": 7.098071575164795, "learning_rate": 4.608631123088393e-06, "loss": 0.3552490472793579, "step": 1657 }, { "epoch": 0.43042575285565937, "grad_norm": 3.3352723121643066, "learning_rate": 4.6080978022978425e-06, "loss": 0.3523080348968506, "step": 1658 }, { "epoch": 0.43068535825545173, "grad_norm": 2.536179780960083, "learning_rate": 4.607564153038146e-06, "loss": 0.3999714255332947, "step": 1659 }, { "epoch": 0.43094496365524404, "grad_norm": 4.231399059295654, "learning_rate": 4.607030175403638e-06, "loss": 0.40056443214416504, "step": 1660 }, { "epoch": 0.43120456905503635, "grad_norm": 5.910015106201172, "learning_rate": 4.606495869488716e-06, "loss": 0.42756354808807373, "step": 1661 }, { "epoch": 0.43146417445482865, "grad_norm": 4.104414939880371, "learning_rate": 4.605961235387834e-06, "loss": 0.4172632694244385, "step": 1662 }, { "epoch": 0.43172377985462096, "grad_norm": 8.160662651062012, "learning_rate": 4.605426273195499e-06, "loss": 0.3836804926395416, "step": 1663 }, { "epoch": 0.43198338525441327, "grad_norm": 4.174800872802734, "learning_rate": 4.604890983006285e-06, "loss": 0.3676336109638214, "step": 1664 }, { "epoch": 0.4322429906542056, "grad_norm": 6.1606855392456055, "learning_rate": 4.604355364914816e-06, "loss": 0.4396513104438782, "step": 1665 }, { "epoch": 0.43250259605399793, "grad_norm": 5.6459479331970215, "learning_rate": 4.603819419015776e-06, "loss": 0.44451653957366943, "step": 1666 }, { "epoch": 0.43276220145379024, "grad_norm": 5.690495014190674, "learning_rate": 4.603283145403911e-06, "loss": 0.367783784866333, "step": 1667 }, { "epoch": 0.43302180685358255, "grad_norm": 4.814173221588135, "learning_rate": 4.602746544174021e-06, "loss": 0.36391347646713257, "step": 1668 }, { "epoch": 0.43328141225337485, "grad_norm": 4.473586559295654, "learning_rate": 4.602209615420963e-06, "loss": 0.3973459303379059, "step": 1669 }, { "epoch": 0.43354101765316716, "grad_norm": 3.450763463973999, "learning_rate": 4.601672359239654e-06, "loss": 0.3429182767868042, "step": 1670 }, { "epoch": 0.4338006230529595, "grad_norm": 2.511845350265503, "learning_rate": 4.6011347757250716e-06, "loss": 0.4254160523414612, "step": 1671 }, { "epoch": 0.43406022845275183, "grad_norm": 7.579526424407959, "learning_rate": 4.600596864972246e-06, "loss": 0.4394533634185791, "step": 1672 }, { "epoch": 0.43431983385254413, "grad_norm": 3.691852331161499, "learning_rate": 4.600058627076266e-06, "loss": 0.3431342542171478, "step": 1673 }, { "epoch": 0.43457943925233644, "grad_norm": 3.6592557430267334, "learning_rate": 4.599520062132283e-06, "loss": 0.39080560207366943, "step": 1674 }, { "epoch": 0.43483904465212875, "grad_norm": 5.352041721343994, "learning_rate": 4.598981170235501e-06, "loss": 0.4083825945854187, "step": 1675 }, { "epoch": 0.43509865005192105, "grad_norm": 2.8021976947784424, "learning_rate": 4.598441951481184e-06, "loss": 0.3504238724708557, "step": 1676 }, { "epoch": 0.4353582554517134, "grad_norm": 3.1547188758850098, "learning_rate": 4.597902405964654e-06, "loss": 0.3415984511375427, "step": 1677 }, { "epoch": 0.4356178608515057, "grad_norm": 5.63324499130249, "learning_rate": 4.59736253378129e-06, "loss": 0.34780359268188477, "step": 1678 }, { "epoch": 0.43587746625129803, "grad_norm": 3.6169400215148926, "learning_rate": 4.596822335026529e-06, "loss": 0.3590664565563202, "step": 1679 }, { "epoch": 0.43613707165109034, "grad_norm": 5.777566432952881, "learning_rate": 4.596281809795866e-06, "loss": 0.40318864583969116, "step": 1680 }, { "epoch": 0.43639667705088264, "grad_norm": 5.314262390136719, "learning_rate": 4.5957409581848535e-06, "loss": 0.38411086797714233, "step": 1681 }, { "epoch": 0.43665628245067495, "grad_norm": 6.3712568283081055, "learning_rate": 4.595199780289101e-06, "loss": 0.504605233669281, "step": 1682 }, { "epoch": 0.4369158878504673, "grad_norm": 2.915933609008789, "learning_rate": 4.5946582762042765e-06, "loss": 0.42209163308143616, "step": 1683 }, { "epoch": 0.4371754932502596, "grad_norm": 4.660593509674072, "learning_rate": 4.594116446026106e-06, "loss": 0.3879043459892273, "step": 1684 }, { "epoch": 0.4374350986500519, "grad_norm": 2.117903470993042, "learning_rate": 4.5935742898503725e-06, "loss": 0.36057591438293457, "step": 1685 }, { "epoch": 0.43769470404984423, "grad_norm": 2.4487457275390625, "learning_rate": 4.5930318077729165e-06, "loss": 0.3590145707130432, "step": 1686 }, { "epoch": 0.43795430944963654, "grad_norm": 2.147085189819336, "learning_rate": 4.592488999889638e-06, "loss": 0.3627552390098572, "step": 1687 }, { "epoch": 0.43821391484942884, "grad_norm": 3.571781635284424, "learning_rate": 4.5919458662964905e-06, "loss": 0.3269352614879608, "step": 1688 }, { "epoch": 0.4384735202492212, "grad_norm": 4.111054420471191, "learning_rate": 4.591402407089489e-06, "loss": 0.34870392084121704, "step": 1689 }, { "epoch": 0.4387331256490135, "grad_norm": 3.8589353561401367, "learning_rate": 4.590858622364705e-06, "loss": 0.3624837398529053, "step": 1690 }, { "epoch": 0.4389927310488058, "grad_norm": 3.9202373027801514, "learning_rate": 4.590314512218266e-06, "loss": 0.4175286293029785, "step": 1691 }, { "epoch": 0.4392523364485981, "grad_norm": 2.255610704421997, "learning_rate": 4.58977007674636e-06, "loss": 0.37417033314704895, "step": 1692 }, { "epoch": 0.43951194184839043, "grad_norm": 2.3449254035949707, "learning_rate": 4.589225316045228e-06, "loss": 0.35842403769493103, "step": 1693 }, { "epoch": 0.43977154724818274, "grad_norm": 3.5626657009124756, "learning_rate": 4.588680230211174e-06, "loss": 0.3715386986732483, "step": 1694 }, { "epoch": 0.4400311526479751, "grad_norm": 2.529059410095215, "learning_rate": 4.588134819340554e-06, "loss": 0.3422824442386627, "step": 1695 }, { "epoch": 0.4402907580477674, "grad_norm": 4.079051971435547, "learning_rate": 4.587589083529788e-06, "loss": 0.47300639748573303, "step": 1696 }, { "epoch": 0.4405503634475597, "grad_norm": 4.581569194793701, "learning_rate": 4.587043022875345e-06, "loss": 0.3753414750099182, "step": 1697 }, { "epoch": 0.440809968847352, "grad_norm": 3.196943759918213, "learning_rate": 4.586496637473759e-06, "loss": 0.3631375730037689, "step": 1698 }, { "epoch": 0.4410695742471443, "grad_norm": 5.1715288162231445, "learning_rate": 4.585949927421618e-06, "loss": 0.3905678689479828, "step": 1699 }, { "epoch": 0.44132917964693663, "grad_norm": 3.4472720623016357, "learning_rate": 4.5854028928155674e-06, "loss": 0.32523655891418457, "step": 1700 }, { "epoch": 0.441588785046729, "grad_norm": 2.342561721801758, "learning_rate": 4.584855533752311e-06, "loss": 0.3594233989715576, "step": 1701 }, { "epoch": 0.4418483904465213, "grad_norm": 2.495537519454956, "learning_rate": 4.584307850328608e-06, "loss": 0.3518226444721222, "step": 1702 }, { "epoch": 0.4421079958463136, "grad_norm": 3.3291609287261963, "learning_rate": 4.5837598426412775e-06, "loss": 0.31965458393096924, "step": 1703 }, { "epoch": 0.4423676012461059, "grad_norm": 1.9121322631835938, "learning_rate": 4.583211510787194e-06, "loss": 0.34949997067451477, "step": 1704 }, { "epoch": 0.4426272066458982, "grad_norm": 3.6071174144744873, "learning_rate": 4.582662854863291e-06, "loss": 0.33826130628585815, "step": 1705 }, { "epoch": 0.4428868120456905, "grad_norm": 4.903621673583984, "learning_rate": 4.582113874966558e-06, "loss": 0.518252432346344, "step": 1706 }, { "epoch": 0.4431464174454829, "grad_norm": 4.9368414878845215, "learning_rate": 4.581564571194041e-06, "loss": 0.3901490867137909, "step": 1707 }, { "epoch": 0.4434060228452752, "grad_norm": 9.454474449157715, "learning_rate": 4.581014943642845e-06, "loss": 0.4410479962825775, "step": 1708 }, { "epoch": 0.4436656282450675, "grad_norm": 4.183172702789307, "learning_rate": 4.580464992410132e-06, "loss": 0.3993755280971527, "step": 1709 }, { "epoch": 0.4439252336448598, "grad_norm": 7.440271854400635, "learning_rate": 4.57991471759312e-06, "loss": 0.4506521224975586, "step": 1710 }, { "epoch": 0.4441848390446521, "grad_norm": 5.541108131408691, "learning_rate": 4.579364119289086e-06, "loss": 0.45531147718429565, "step": 1711 }, { "epoch": 0.4444444444444444, "grad_norm": 4.986243724822998, "learning_rate": 4.578813197595363e-06, "loss": 0.46498945355415344, "step": 1712 }, { "epoch": 0.4447040498442368, "grad_norm": 2.9146487712860107, "learning_rate": 4.578261952609339e-06, "loss": 0.3833392560482025, "step": 1713 }, { "epoch": 0.4449636552440291, "grad_norm": 2.8397748470306396, "learning_rate": 4.577710384428466e-06, "loss": 0.3737495541572571, "step": 1714 }, { "epoch": 0.4452232606438214, "grad_norm": 8.00634765625, "learning_rate": 4.577158493150244e-06, "loss": 0.4429088234901428, "step": 1715 }, { "epoch": 0.4454828660436137, "grad_norm": 11.150620460510254, "learning_rate": 4.576606278872238e-06, "loss": 0.42469921708106995, "step": 1716 }, { "epoch": 0.445742471443406, "grad_norm": 4.87630033493042, "learning_rate": 4.576053741692065e-06, "loss": 0.4095156192779541, "step": 1717 }, { "epoch": 0.4460020768431983, "grad_norm": 4.121866226196289, "learning_rate": 4.575500881707402e-06, "loss": 0.44539111852645874, "step": 1718 }, { "epoch": 0.4462616822429907, "grad_norm": 5.350185871124268, "learning_rate": 4.574947699015981e-06, "loss": 0.4242284595966339, "step": 1719 }, { "epoch": 0.446521287642783, "grad_norm": 7.062849521636963, "learning_rate": 4.574394193715593e-06, "loss": 0.4672541618347168, "step": 1720 }, { "epoch": 0.4467808930425753, "grad_norm": 5.223994255065918, "learning_rate": 4.573840365904084e-06, "loss": 0.3795183300971985, "step": 1721 }, { "epoch": 0.4470404984423676, "grad_norm": 6.031862735748291, "learning_rate": 4.57328621567936e-06, "loss": 0.43865862488746643, "step": 1722 }, { "epoch": 0.4473001038421599, "grad_norm": 5.837775230407715, "learning_rate": 4.57273174313938e-06, "loss": 0.3650306463241577, "step": 1723 }, { "epoch": 0.4475597092419522, "grad_norm": 6.062453746795654, "learning_rate": 4.5721769483821625e-06, "loss": 0.5227347612380981, "step": 1724 }, { "epoch": 0.44781931464174457, "grad_norm": 6.247106075286865, "learning_rate": 4.571621831505783e-06, "loss": 0.38125595450401306, "step": 1725 }, { "epoch": 0.4480789200415369, "grad_norm": 9.670899391174316, "learning_rate": 4.571066392608374e-06, "loss": 0.44630318880081177, "step": 1726 }, { "epoch": 0.4483385254413292, "grad_norm": 5.309098243713379, "learning_rate": 4.5705106317881225e-06, "loss": 0.4579392373561859, "step": 1727 }, { "epoch": 0.4485981308411215, "grad_norm": 7.812030792236328, "learning_rate": 4.569954549143276e-06, "loss": 0.47125089168548584, "step": 1728 }, { "epoch": 0.4488577362409138, "grad_norm": 3.501797676086426, "learning_rate": 4.569398144772137e-06, "loss": 0.3507091999053955, "step": 1729 }, { "epoch": 0.4491173416407061, "grad_norm": 3.8316550254821777, "learning_rate": 4.568841418773064e-06, "loss": 0.34737643599510193, "step": 1730 }, { "epoch": 0.44937694704049846, "grad_norm": 3.1635115146636963, "learning_rate": 4.568284371244475e-06, "loss": 0.391374796628952, "step": 1731 }, { "epoch": 0.44963655244029077, "grad_norm": 6.211935043334961, "learning_rate": 4.567727002284842e-06, "loss": 0.4383975863456726, "step": 1732 }, { "epoch": 0.4498961578400831, "grad_norm": 3.6005892753601074, "learning_rate": 4.567169311992696e-06, "loss": 0.39122092723846436, "step": 1733 }, { "epoch": 0.4501557632398754, "grad_norm": 7.722121238708496, "learning_rate": 4.566611300466622e-06, "loss": 0.42411357164382935, "step": 1734 }, { "epoch": 0.4504153686396677, "grad_norm": 1.7925854921340942, "learning_rate": 4.566052967805266e-06, "loss": 0.34722793102264404, "step": 1735 }, { "epoch": 0.45067497403946, "grad_norm": 3.5909383296966553, "learning_rate": 4.565494314107327e-06, "loss": 0.3234894871711731, "step": 1736 }, { "epoch": 0.45093457943925236, "grad_norm": 3.9643948078155518, "learning_rate": 4.564935339471563e-06, "loss": 0.3368566334247589, "step": 1737 }, { "epoch": 0.45119418483904467, "grad_norm": 3.526350259780884, "learning_rate": 4.564376043996787e-06, "loss": 0.38838472962379456, "step": 1738 }, { "epoch": 0.45145379023883697, "grad_norm": 4.518139839172363, "learning_rate": 4.5638164277818705e-06, "loss": 0.38017213344573975, "step": 1739 }, { "epoch": 0.4517133956386293, "grad_norm": 3.3490371704101562, "learning_rate": 4.56325649092574e-06, "loss": 0.39989665150642395, "step": 1740 }, { "epoch": 0.4519730010384216, "grad_norm": 4.928135395050049, "learning_rate": 4.56269623352738e-06, "loss": 0.3924477696418762, "step": 1741 }, { "epoch": 0.4522326064382139, "grad_norm": 4.648492813110352, "learning_rate": 4.562135655685831e-06, "loss": 0.37492048740386963, "step": 1742 }, { "epoch": 0.45249221183800625, "grad_norm": 2.6392340660095215, "learning_rate": 4.561574757500192e-06, "loss": 0.38857030868530273, "step": 1743 }, { "epoch": 0.45275181723779856, "grad_norm": 3.8006703853607178, "learning_rate": 4.5610135390696135e-06, "loss": 0.3768388628959656, "step": 1744 }, { "epoch": 0.45301142263759087, "grad_norm": 4.6807146072387695, "learning_rate": 4.560452000493309e-06, "loss": 0.3235628604888916, "step": 1745 }, { "epoch": 0.4532710280373832, "grad_norm": 3.95963454246521, "learning_rate": 4.559890141870545e-06, "loss": 0.42946165800094604, "step": 1746 }, { "epoch": 0.4535306334371755, "grad_norm": 2.2430837154388428, "learning_rate": 4.559327963300643e-06, "loss": 0.34977373480796814, "step": 1747 }, { "epoch": 0.4537902388369678, "grad_norm": 4.444501876831055, "learning_rate": 4.558765464882987e-06, "loss": 0.5369732975959778, "step": 1748 }, { "epoch": 0.45404984423676015, "grad_norm": 4.9862823486328125, "learning_rate": 4.558202646717011e-06, "loss": 0.3570418059825897, "step": 1749 }, { "epoch": 0.45430944963655245, "grad_norm": 4.345773696899414, "learning_rate": 4.557639508902211e-06, "loss": 0.3708871006965637, "step": 1750 }, { "epoch": 0.45456905503634476, "grad_norm": 4.458191394805908, "learning_rate": 4.557076051538134e-06, "loss": 0.3492734730243683, "step": 1751 }, { "epoch": 0.45482866043613707, "grad_norm": 5.263578414916992, "learning_rate": 4.556512274724387e-06, "loss": 0.4273880124092102, "step": 1752 }, { "epoch": 0.4550882658359294, "grad_norm": 5.712528228759766, "learning_rate": 4.555948178560635e-06, "loss": 0.29794150590896606, "step": 1753 }, { "epoch": 0.4553478712357217, "grad_norm": 2.4268431663513184, "learning_rate": 4.555383763146596e-06, "loss": 0.38288283348083496, "step": 1754 }, { "epoch": 0.45560747663551404, "grad_norm": 4.380865097045898, "learning_rate": 4.554819028582044e-06, "loss": 0.32618480920791626, "step": 1755 }, { "epoch": 0.45586708203530635, "grad_norm": 5.464202404022217, "learning_rate": 4.5542539749668134e-06, "loss": 0.3703242540359497, "step": 1756 }, { "epoch": 0.45612668743509865, "grad_norm": 4.340280055999756, "learning_rate": 4.553688602400792e-06, "loss": 0.3957999646663666, "step": 1757 }, { "epoch": 0.45638629283489096, "grad_norm": 5.64797306060791, "learning_rate": 4.5531229109839244e-06, "loss": 0.4187386631965637, "step": 1758 }, { "epoch": 0.45664589823468327, "grad_norm": 2.714930295944214, "learning_rate": 4.552556900816212e-06, "loss": 0.3592471778392792, "step": 1759 }, { "epoch": 0.4569055036344756, "grad_norm": 3.259232997894287, "learning_rate": 4.551990571997713e-06, "loss": 0.3520239591598511, "step": 1760 }, { "epoch": 0.45716510903426794, "grad_norm": 3.2872884273529053, "learning_rate": 4.551423924628541e-06, "loss": 0.3400155305862427, "step": 1761 }, { "epoch": 0.45742471443406024, "grad_norm": 3.288694381713867, "learning_rate": 4.550856958808867e-06, "loss": 0.4049977660179138, "step": 1762 }, { "epoch": 0.45768431983385255, "grad_norm": 4.37725305557251, "learning_rate": 4.550289674638915e-06, "loss": 0.4437434673309326, "step": 1763 }, { "epoch": 0.45794392523364486, "grad_norm": 3.9137284755706787, "learning_rate": 4.549722072218971e-06, "loss": 0.398410439491272, "step": 1764 }, { "epoch": 0.45820353063343716, "grad_norm": 7.957957744598389, "learning_rate": 4.5491541516493725e-06, "loss": 0.3785589933395386, "step": 1765 }, { "epoch": 0.45846313603322947, "grad_norm": 4.128979206085205, "learning_rate": 4.548585913030515e-06, "loss": 0.3762856721878052, "step": 1766 }, { "epoch": 0.45872274143302183, "grad_norm": 4.223452568054199, "learning_rate": 4.548017356462851e-06, "loss": 0.37784671783447266, "step": 1767 }, { "epoch": 0.45898234683281414, "grad_norm": 5.298379898071289, "learning_rate": 4.547448482046887e-06, "loss": 0.5086718797683716, "step": 1768 }, { "epoch": 0.45924195223260644, "grad_norm": 4.571142196655273, "learning_rate": 4.546879289883187e-06, "loss": 0.4291154742240906, "step": 1769 }, { "epoch": 0.45950155763239875, "grad_norm": 6.090576171875, "learning_rate": 4.5463097800723725e-06, "loss": 0.44498008489608765, "step": 1770 }, { "epoch": 0.45976116303219106, "grad_norm": 3.8714284896850586, "learning_rate": 4.545739952715118e-06, "loss": 0.33412685990333557, "step": 1771 }, { "epoch": 0.46002076843198336, "grad_norm": 2.742611885070801, "learning_rate": 4.5451698079121575e-06, "loss": 0.4027654230594635, "step": 1772 }, { "epoch": 0.4602803738317757, "grad_norm": 8.266721725463867, "learning_rate": 4.544599345764279e-06, "loss": 0.4090747833251953, "step": 1773 }, { "epoch": 0.46053997923156803, "grad_norm": 4.875608921051025, "learning_rate": 4.544028566372326e-06, "loss": 0.39785218238830566, "step": 1774 }, { "epoch": 0.46079958463136034, "grad_norm": 3.9207499027252197, "learning_rate": 4.543457469837202e-06, "loss": 0.3713378310203552, "step": 1775 }, { "epoch": 0.46105919003115264, "grad_norm": 5.667232036590576, "learning_rate": 4.542886056259861e-06, "loss": 0.34357085824012756, "step": 1776 }, { "epoch": 0.46131879543094495, "grad_norm": 3.460522413253784, "learning_rate": 4.542314325741316e-06, "loss": 0.3682856857776642, "step": 1777 }, { "epoch": 0.46157840083073726, "grad_norm": 3.4325006008148193, "learning_rate": 4.541742278382638e-06, "loss": 0.3944237232208252, "step": 1778 }, { "epoch": 0.4618380062305296, "grad_norm": 2.8642842769622803, "learning_rate": 4.541169914284951e-06, "loss": 0.38474389910697937, "step": 1779 }, { "epoch": 0.4620976116303219, "grad_norm": 4.874148845672607, "learning_rate": 4.5405972335494345e-06, "loss": 0.3769119381904602, "step": 1780 }, { "epoch": 0.46235721703011423, "grad_norm": 6.152498245239258, "learning_rate": 4.540024236277327e-06, "loss": 0.4160597324371338, "step": 1781 }, { "epoch": 0.46261682242990654, "grad_norm": 4.386363506317139, "learning_rate": 4.539450922569921e-06, "loss": 0.4557957947254181, "step": 1782 }, { "epoch": 0.46287642782969884, "grad_norm": 4.118651390075684, "learning_rate": 4.538877292528564e-06, "loss": 0.3934877812862396, "step": 1783 }, { "epoch": 0.46313603322949115, "grad_norm": 2.5055999755859375, "learning_rate": 4.538303346254662e-06, "loss": 0.3354106843471527, "step": 1784 }, { "epoch": 0.4633956386292835, "grad_norm": 3.864515781402588, "learning_rate": 4.537729083849675e-06, "loss": 0.40995556116104126, "step": 1785 }, { "epoch": 0.4636552440290758, "grad_norm": 2.3552229404449463, "learning_rate": 4.53715450541512e-06, "loss": 0.39171719551086426, "step": 1786 }, { "epoch": 0.4639148494288681, "grad_norm": 3.7902114391326904, "learning_rate": 4.5365796110525674e-06, "loss": 0.3889704942703247, "step": 1787 }, { "epoch": 0.46417445482866043, "grad_norm": 6.608195781707764, "learning_rate": 4.5360044008636485e-06, "loss": 0.4211600422859192, "step": 1788 }, { "epoch": 0.46443406022845274, "grad_norm": 3.774488687515259, "learning_rate": 4.535428874950045e-06, "loss": 0.4322618842124939, "step": 1789 }, { "epoch": 0.46469366562824505, "grad_norm": 3.078605890274048, "learning_rate": 4.5348530334134975e-06, "loss": 0.3764423429965973, "step": 1790 }, { "epoch": 0.4649532710280374, "grad_norm": 5.844646453857422, "learning_rate": 4.534276876355801e-06, "loss": 0.35500138998031616, "step": 1791 }, { "epoch": 0.4652128764278297, "grad_norm": 5.535872936248779, "learning_rate": 4.533700403878806e-06, "loss": 0.46205684542655945, "step": 1792 }, { "epoch": 0.465472481827622, "grad_norm": 3.7025349140167236, "learning_rate": 4.533123616084423e-06, "loss": 0.3513544499874115, "step": 1793 }, { "epoch": 0.4657320872274143, "grad_norm": 5.381964683532715, "learning_rate": 4.5325465130746125e-06, "loss": 0.41437798738479614, "step": 1794 }, { "epoch": 0.46599169262720663, "grad_norm": 4.54433012008667, "learning_rate": 4.531969094951393e-06, "loss": 0.43021419644355774, "step": 1795 }, { "epoch": 0.46625129802699894, "grad_norm": 4.2511186599731445, "learning_rate": 4.5313913618168394e-06, "loss": 0.3619190454483032, "step": 1796 }, { "epoch": 0.4665109034267913, "grad_norm": 4.617771625518799, "learning_rate": 4.530813313773081e-06, "loss": 0.36804917454719543, "step": 1797 }, { "epoch": 0.4667705088265836, "grad_norm": 4.682255268096924, "learning_rate": 4.530234950922304e-06, "loss": 0.34833401441574097, "step": 1798 }, { "epoch": 0.4670301142263759, "grad_norm": 7.359766483306885, "learning_rate": 4.52965627336675e-06, "loss": 0.40498483180999756, "step": 1799 }, { "epoch": 0.4672897196261682, "grad_norm": 3.3489511013031006, "learning_rate": 4.529077281208716e-06, "loss": 0.35074126720428467, "step": 1800 }, { "epoch": 0.4675493250259605, "grad_norm": 3.015000820159912, "learning_rate": 4.528497974550553e-06, "loss": 0.35143595933914185, "step": 1801 }, { "epoch": 0.46780893042575283, "grad_norm": 2.8391642570495605, "learning_rate": 4.527918353494672e-06, "loss": 0.35098910331726074, "step": 1802 }, { "epoch": 0.4680685358255452, "grad_norm": 4.155757904052734, "learning_rate": 4.527338418143533e-06, "loss": 0.42244893312454224, "step": 1803 }, { "epoch": 0.4683281412253375, "grad_norm": 6.019104957580566, "learning_rate": 4.526758168599658e-06, "loss": 0.35509544610977173, "step": 1804 }, { "epoch": 0.4685877466251298, "grad_norm": 6.128937721252441, "learning_rate": 4.526177604965622e-06, "loss": 0.39257872104644775, "step": 1805 }, { "epoch": 0.4688473520249221, "grad_norm": 2.8968191146850586, "learning_rate": 4.525596727344054e-06, "loss": 0.3644883632659912, "step": 1806 }, { "epoch": 0.4691069574247144, "grad_norm": 2.3636958599090576, "learning_rate": 4.52501553583764e-06, "loss": 0.38294750452041626, "step": 1807 }, { "epoch": 0.46936656282450673, "grad_norm": 2.2761149406433105, "learning_rate": 4.524434030549122e-06, "loss": 0.35879167914390564, "step": 1808 }, { "epoch": 0.4696261682242991, "grad_norm": 7.369694232940674, "learning_rate": 4.523852211581297e-06, "loss": 0.43243029713630676, "step": 1809 }, { "epoch": 0.4698857736240914, "grad_norm": 3.0807032585144043, "learning_rate": 4.523270079037016e-06, "loss": 0.32419532537460327, "step": 1810 }, { "epoch": 0.4701453790238837, "grad_norm": 2.478717565536499, "learning_rate": 4.522687633019189e-06, "loss": 0.33465689420700073, "step": 1811 }, { "epoch": 0.470404984423676, "grad_norm": 1.930153727531433, "learning_rate": 4.522104873630776e-06, "loss": 0.3807913064956665, "step": 1812 }, { "epoch": 0.4706645898234683, "grad_norm": 5.694454193115234, "learning_rate": 4.521521800974798e-06, "loss": 0.45948269963264465, "step": 1813 }, { "epoch": 0.4709241952232606, "grad_norm": 4.600359916687012, "learning_rate": 4.520938415154328e-06, "loss": 0.4332333207130432, "step": 1814 }, { "epoch": 0.471183800623053, "grad_norm": 1.918096661567688, "learning_rate": 4.520354716272495e-06, "loss": 0.3501400649547577, "step": 1815 }, { "epoch": 0.4714434060228453, "grad_norm": 3.9057323932647705, "learning_rate": 4.519770704432484e-06, "loss": 0.3994508981704712, "step": 1816 }, { "epoch": 0.4717030114226376, "grad_norm": 7.197213649749756, "learning_rate": 4.519186379737535e-06, "loss": 0.4306333065032959, "step": 1817 }, { "epoch": 0.4719626168224299, "grad_norm": 3.3738324642181396, "learning_rate": 4.518601742290943e-06, "loss": 0.40879690647125244, "step": 1818 }, { "epoch": 0.4722222222222222, "grad_norm": 4.4356794357299805, "learning_rate": 4.518016792196059e-06, "loss": 0.4320928454399109, "step": 1819 }, { "epoch": 0.4724818276220145, "grad_norm": 5.043928146362305, "learning_rate": 4.5174315295562885e-06, "loss": 0.4662013649940491, "step": 1820 }, { "epoch": 0.4727414330218069, "grad_norm": 3.0871458053588867, "learning_rate": 4.516845954475091e-06, "loss": 0.37266018986701965, "step": 1821 }, { "epoch": 0.4730010384215992, "grad_norm": 4.041164398193359, "learning_rate": 4.516260067055985e-06, "loss": 0.3279162347316742, "step": 1822 }, { "epoch": 0.4732606438213915, "grad_norm": 3.7441179752349854, "learning_rate": 4.515673867402541e-06, "loss": 0.36140573024749756, "step": 1823 }, { "epoch": 0.4735202492211838, "grad_norm": 7.093626976013184, "learning_rate": 4.515087355618387e-06, "loss": 0.4544649124145508, "step": 1824 }, { "epoch": 0.4737798546209761, "grad_norm": 3.514885902404785, "learning_rate": 4.514500531807201e-06, "loss": 0.34277471899986267, "step": 1825 }, { "epoch": 0.4740394600207684, "grad_norm": 5.223942279815674, "learning_rate": 4.513913396072725e-06, "loss": 0.39922136068344116, "step": 1826 }, { "epoch": 0.4742990654205608, "grad_norm": 4.49864387512207, "learning_rate": 4.513325948518748e-06, "loss": 0.354830265045166, "step": 1827 }, { "epoch": 0.4745586708203531, "grad_norm": 7.555840015411377, "learning_rate": 4.512738189249119e-06, "loss": 0.36810797452926636, "step": 1828 }, { "epoch": 0.4748182762201454, "grad_norm": 6.11877965927124, "learning_rate": 4.512150118367739e-06, "loss": 0.4195060729980469, "step": 1829 }, { "epoch": 0.4750778816199377, "grad_norm": 5.208657264709473, "learning_rate": 4.511561735978564e-06, "loss": 0.40206649899482727, "step": 1830 }, { "epoch": 0.47533748701973, "grad_norm": 2.84731388092041, "learning_rate": 4.510973042185611e-06, "loss": 0.350206583738327, "step": 1831 }, { "epoch": 0.4755970924195223, "grad_norm": 4.089078903198242, "learning_rate": 4.5103840370929446e-06, "loss": 0.3871828317642212, "step": 1832 }, { "epoch": 0.47585669781931467, "grad_norm": 5.104269981384277, "learning_rate": 4.509794720804688e-06, "loss": 0.35808414220809937, "step": 1833 }, { "epoch": 0.476116303219107, "grad_norm": 5.504467964172363, "learning_rate": 4.509205093425018e-06, "loss": 0.33586516976356506, "step": 1834 }, { "epoch": 0.4763759086188993, "grad_norm": 3.08829927444458, "learning_rate": 4.508615155058168e-06, "loss": 0.3864139914512634, "step": 1835 }, { "epoch": 0.4766355140186916, "grad_norm": 3.890481948852539, "learning_rate": 4.508024905808426e-06, "loss": 0.36956310272216797, "step": 1836 }, { "epoch": 0.4768951194184839, "grad_norm": 2.7871150970458984, "learning_rate": 4.507434345780133e-06, "loss": 0.3861805498600006, "step": 1837 }, { "epoch": 0.4771547248182762, "grad_norm": 5.049299716949463, "learning_rate": 4.506843475077689e-06, "loss": 0.41917717456817627, "step": 1838 }, { "epoch": 0.47741433021806856, "grad_norm": 5.681003570556641, "learning_rate": 4.5062522938055444e-06, "loss": 0.46202385425567627, "step": 1839 }, { "epoch": 0.47767393561786087, "grad_norm": 5.536965370178223, "learning_rate": 4.505660802068207e-06, "loss": 0.37573495507240295, "step": 1840 }, { "epoch": 0.4779335410176532, "grad_norm": 4.511649131774902, "learning_rate": 4.50506899997024e-06, "loss": 0.32505881786346436, "step": 1841 }, { "epoch": 0.4781931464174455, "grad_norm": 4.431359767913818, "learning_rate": 4.504476887616258e-06, "loss": 0.41538211703300476, "step": 1842 }, { "epoch": 0.4784527518172378, "grad_norm": 5.108992576599121, "learning_rate": 4.503884465110935e-06, "loss": 0.4660467505455017, "step": 1843 }, { "epoch": 0.4787123572170301, "grad_norm": 5.312428951263428, "learning_rate": 4.503291732558998e-06, "loss": 0.4030066728591919, "step": 1844 }, { "epoch": 0.47897196261682246, "grad_norm": 8.690288543701172, "learning_rate": 4.502698690065227e-06, "loss": 0.38403186202049255, "step": 1845 }, { "epoch": 0.47923156801661476, "grad_norm": 2.5967795848846436, "learning_rate": 4.5021053377344596e-06, "loss": 0.38517242670059204, "step": 1846 }, { "epoch": 0.47949117341640707, "grad_norm": 3.188491106033325, "learning_rate": 4.501511675671586e-06, "loss": 0.3602001368999481, "step": 1847 }, { "epoch": 0.4797507788161994, "grad_norm": 5.17393684387207, "learning_rate": 4.500917703981553e-06, "loss": 0.47572818398475647, "step": 1848 }, { "epoch": 0.4800103842159917, "grad_norm": 3.984272003173828, "learning_rate": 4.5003234227693596e-06, "loss": 0.3747629225254059, "step": 1849 }, { "epoch": 0.480269989615784, "grad_norm": 3.9462127685546875, "learning_rate": 4.499728832140063e-06, "loss": 0.4285392761230469, "step": 1850 }, { "epoch": 0.48052959501557635, "grad_norm": 3.6159896850585938, "learning_rate": 4.499133932198772e-06, "loss": 0.41877174377441406, "step": 1851 }, { "epoch": 0.48078920041536866, "grad_norm": 4.249211311340332, "learning_rate": 4.498538723050651e-06, "loss": 0.4296954274177551, "step": 1852 }, { "epoch": 0.48104880581516096, "grad_norm": 6.499308109283447, "learning_rate": 4.4979432048009215e-06, "loss": 0.3129948675632477, "step": 1853 }, { "epoch": 0.48130841121495327, "grad_norm": 4.691756725311279, "learning_rate": 4.497347377554855e-06, "loss": 0.3627750277519226, "step": 1854 }, { "epoch": 0.4815680166147456, "grad_norm": 5.16414213180542, "learning_rate": 4.4967512414177816e-06, "loss": 0.32643571496009827, "step": 1855 }, { "epoch": 0.4818276220145379, "grad_norm": 3.2301218509674072, "learning_rate": 4.496154796495083e-06, "loss": 0.36241620779037476, "step": 1856 }, { "epoch": 0.48208722741433024, "grad_norm": 3.7195990085601807, "learning_rate": 4.495558042892199e-06, "loss": 0.3976619243621826, "step": 1857 }, { "epoch": 0.48234683281412255, "grad_norm": 3.6220059394836426, "learning_rate": 4.49496098071462e-06, "loss": 0.3694382905960083, "step": 1858 }, { "epoch": 0.48260643821391486, "grad_norm": 4.054015636444092, "learning_rate": 4.494363610067895e-06, "loss": 0.41894203424453735, "step": 1859 }, { "epoch": 0.48286604361370716, "grad_norm": 6.2425971031188965, "learning_rate": 4.493765931057624e-06, "loss": 0.3055838346481323, "step": 1860 }, { "epoch": 0.48312564901349947, "grad_norm": 8.9160795211792, "learning_rate": 4.493167943789463e-06, "loss": 0.4082030653953552, "step": 1861 }, { "epoch": 0.4833852544132918, "grad_norm": 4.042598247528076, "learning_rate": 4.492569648369124e-06, "loss": 0.3513409495353699, "step": 1862 }, { "epoch": 0.48364485981308414, "grad_norm": 3.348313808441162, "learning_rate": 4.4919710449023695e-06, "loss": 0.359609991312027, "step": 1863 }, { "epoch": 0.48390446521287644, "grad_norm": 6.819497108459473, "learning_rate": 4.491372133495021e-06, "loss": 0.4565924406051636, "step": 1864 }, { "epoch": 0.48416407061266875, "grad_norm": 6.540281772613525, "learning_rate": 4.49077291425295e-06, "loss": 0.43990373611450195, "step": 1865 }, { "epoch": 0.48442367601246106, "grad_norm": 5.49338960647583, "learning_rate": 4.490173387282087e-06, "loss": 0.3795768618583679, "step": 1866 }, { "epoch": 0.48468328141225336, "grad_norm": 4.191503524780273, "learning_rate": 4.489573552688414e-06, "loss": 0.31092339754104614, "step": 1867 }, { "epoch": 0.48494288681204567, "grad_norm": 2.5088510513305664, "learning_rate": 4.488973410577968e-06, "loss": 0.3768196105957031, "step": 1868 }, { "epoch": 0.48520249221183803, "grad_norm": 3.5757317543029785, "learning_rate": 4.48837296105684e-06, "loss": 0.3387879729270935, "step": 1869 }, { "epoch": 0.48546209761163034, "grad_norm": 5.255555629730225, "learning_rate": 4.4877722042311765e-06, "loss": 0.39753323793411255, "step": 1870 }, { "epoch": 0.48572170301142265, "grad_norm": 4.226877689361572, "learning_rate": 4.487171140207176e-06, "loss": 0.38580185174942017, "step": 1871 }, { "epoch": 0.48598130841121495, "grad_norm": 4.465850353240967, "learning_rate": 4.4865697690910945e-06, "loss": 0.4025876522064209, "step": 1872 }, { "epoch": 0.48624091381100726, "grad_norm": 4.493003845214844, "learning_rate": 4.48596809098924e-06, "loss": 0.39691323041915894, "step": 1873 }, { "epoch": 0.48650051921079956, "grad_norm": 3.2832260131835938, "learning_rate": 4.485366106007975e-06, "loss": 0.3736487329006195, "step": 1874 }, { "epoch": 0.4867601246105919, "grad_norm": 4.466094017028809, "learning_rate": 4.484763814253717e-06, "loss": 0.4226858615875244, "step": 1875 }, { "epoch": 0.48701973001038423, "grad_norm": 2.6897034645080566, "learning_rate": 4.484161215832938e-06, "loss": 0.35778337717056274, "step": 1876 }, { "epoch": 0.48727933541017654, "grad_norm": 7.39514684677124, "learning_rate": 4.483558310852163e-06, "loss": 0.4671779274940491, "step": 1877 }, { "epoch": 0.48753894080996885, "grad_norm": 6.5165629386901855, "learning_rate": 4.482955099417971e-06, "loss": 0.2842996120452881, "step": 1878 }, { "epoch": 0.48779854620976115, "grad_norm": 4.942131519317627, "learning_rate": 4.482351581636998e-06, "loss": 0.24778956174850464, "step": 1879 }, { "epoch": 0.48805815160955346, "grad_norm": 4.804888725280762, "learning_rate": 4.48174775761593e-06, "loss": 0.353432834148407, "step": 1880 }, { "epoch": 0.4883177570093458, "grad_norm": 4.530853748321533, "learning_rate": 4.48114362746151e-06, "loss": 0.4008972942829132, "step": 1881 }, { "epoch": 0.4885773624091381, "grad_norm": 5.037768363952637, "learning_rate": 4.4805391912805366e-06, "loss": 0.3683888912200928, "step": 1882 }, { "epoch": 0.48883696780893043, "grad_norm": 2.86234712600708, "learning_rate": 4.4799344491798564e-06, "loss": 0.3699234127998352, "step": 1883 }, { "epoch": 0.48909657320872274, "grad_norm": 6.913188457489014, "learning_rate": 4.4793294012663765e-06, "loss": 0.48262834548950195, "step": 1884 }, { "epoch": 0.48935617860851505, "grad_norm": 5.078420162200928, "learning_rate": 4.478724047647054e-06, "loss": 0.4065423011779785, "step": 1885 }, { "epoch": 0.48961578400830735, "grad_norm": 6.5027546882629395, "learning_rate": 4.478118388428904e-06, "loss": 0.39275556802749634, "step": 1886 }, { "epoch": 0.4898753894080997, "grad_norm": 2.8440821170806885, "learning_rate": 4.47751242371899e-06, "loss": 0.37687405943870544, "step": 1887 }, { "epoch": 0.490134994807892, "grad_norm": 2.7193169593811035, "learning_rate": 4.476906153624435e-06, "loss": 0.3114715814590454, "step": 1888 }, { "epoch": 0.49039460020768433, "grad_norm": 5.500936508178711, "learning_rate": 4.476299578252414e-06, "loss": 0.3957255482673645, "step": 1889 }, { "epoch": 0.49065420560747663, "grad_norm": 6.837021827697754, "learning_rate": 4.475692697710153e-06, "loss": 0.40968969464302063, "step": 1890 }, { "epoch": 0.49091381100726894, "grad_norm": 7.1599345207214355, "learning_rate": 4.475085512104937e-06, "loss": 0.3806394338607788, "step": 1891 }, { "epoch": 0.49117341640706125, "grad_norm": 6.1397318840026855, "learning_rate": 4.474478021544102e-06, "loss": 0.39058661460876465, "step": 1892 }, { "epoch": 0.4914330218068536, "grad_norm": 2.7586863040924072, "learning_rate": 4.473870226135036e-06, "loss": 0.40628939867019653, "step": 1893 }, { "epoch": 0.4916926272066459, "grad_norm": 3.911691665649414, "learning_rate": 4.473262125985188e-06, "loss": 0.39030373096466064, "step": 1894 }, { "epoch": 0.4919522326064382, "grad_norm": 4.408880710601807, "learning_rate": 4.472653721202052e-06, "loss": 0.3788686990737915, "step": 1895 }, { "epoch": 0.49221183800623053, "grad_norm": 13.054080963134766, "learning_rate": 4.472045011893182e-06, "loss": 0.49171411991119385, "step": 1896 }, { "epoch": 0.49247144340602284, "grad_norm": 2.8227615356445312, "learning_rate": 4.471435998166185e-06, "loss": 0.369594544172287, "step": 1897 }, { "epoch": 0.49273104880581514, "grad_norm": 2.422945261001587, "learning_rate": 4.470826680128717e-06, "loss": 0.384022980928421, "step": 1898 }, { "epoch": 0.4929906542056075, "grad_norm": 4.535058975219727, "learning_rate": 4.470217057888495e-06, "loss": 0.3979049324989319, "step": 1899 }, { "epoch": 0.4932502596053998, "grad_norm": 3.8983500003814697, "learning_rate": 4.469607131553284e-06, "loss": 0.3813532590866089, "step": 1900 }, { "epoch": 0.4935098650051921, "grad_norm": 4.569293022155762, "learning_rate": 4.468996901230907e-06, "loss": 0.3201420307159424, "step": 1901 }, { "epoch": 0.4937694704049844, "grad_norm": 4.990977764129639, "learning_rate": 4.468386367029236e-06, "loss": 0.47857314348220825, "step": 1902 }, { "epoch": 0.49402907580477673, "grad_norm": 5.399364471435547, "learning_rate": 4.467775529056203e-06, "loss": 0.3432418704032898, "step": 1903 }, { "epoch": 0.49428868120456904, "grad_norm": 6.003928184509277, "learning_rate": 4.467164387419787e-06, "loss": 0.2695464491844177, "step": 1904 }, { "epoch": 0.4945482866043614, "grad_norm": 2.5625717639923096, "learning_rate": 4.466552942228026e-06, "loss": 0.34912335872650146, "step": 1905 }, { "epoch": 0.4948078920041537, "grad_norm": 4.393949508666992, "learning_rate": 4.465941193589008e-06, "loss": 0.3241601884365082, "step": 1906 }, { "epoch": 0.495067497403946, "grad_norm": 7.893722057342529, "learning_rate": 4.465329141610877e-06, "loss": 0.3704107999801636, "step": 1907 }, { "epoch": 0.4953271028037383, "grad_norm": 7.4095563888549805, "learning_rate": 4.46471678640183e-06, "loss": 0.3702346682548523, "step": 1908 }, { "epoch": 0.4955867082035306, "grad_norm": 7.266937255859375, "learning_rate": 4.4641041280701164e-06, "loss": 0.33717235922813416, "step": 1909 }, { "epoch": 0.49584631360332293, "grad_norm": 3.7489774227142334, "learning_rate": 4.463491166724041e-06, "loss": 0.35632550716400146, "step": 1910 }, { "epoch": 0.4961059190031153, "grad_norm": 4.028563022613525, "learning_rate": 4.462877902471961e-06, "loss": 0.3453257083892822, "step": 1911 }, { "epoch": 0.4963655244029076, "grad_norm": 4.8731160163879395, "learning_rate": 4.462264335422288e-06, "loss": 0.3362821042537689, "step": 1912 }, { "epoch": 0.4966251298026999, "grad_norm": 6.118870735168457, "learning_rate": 4.4616504656834855e-06, "loss": 0.34033215045928955, "step": 1913 }, { "epoch": 0.4968847352024922, "grad_norm": 5.436732292175293, "learning_rate": 4.461036293364073e-06, "loss": 0.3658844828605652, "step": 1914 }, { "epoch": 0.4971443406022845, "grad_norm": 7.0946149826049805, "learning_rate": 4.46042181857262e-06, "loss": 0.3240516185760498, "step": 1915 }, { "epoch": 0.4974039460020768, "grad_norm": 4.031335830688477, "learning_rate": 4.459807041417755e-06, "loss": 0.3711243271827698, "step": 1916 }, { "epoch": 0.4976635514018692, "grad_norm": 4.508841514587402, "learning_rate": 4.4591919620081526e-06, "loss": 0.3742380440235138, "step": 1917 }, { "epoch": 0.4979231568016615, "grad_norm": 4.824053764343262, "learning_rate": 4.458576580452547e-06, "loss": 0.3536514639854431, "step": 1918 }, { "epoch": 0.4981827622014538, "grad_norm": 2.873645067214966, "learning_rate": 4.457960896859724e-06, "loss": 0.34789350628852844, "step": 1919 }, { "epoch": 0.4984423676012461, "grad_norm": 9.833234786987305, "learning_rate": 4.4573449113385214e-06, "loss": 0.42809516191482544, "step": 1920 }, { "epoch": 0.4987019730010384, "grad_norm": 5.143031597137451, "learning_rate": 4.456728623997831e-06, "loss": 0.3913032114505768, "step": 1921 }, { "epoch": 0.4989615784008307, "grad_norm": 3.3430118560791016, "learning_rate": 4.456112034946599e-06, "loss": 0.371737539768219, "step": 1922 }, { "epoch": 0.4992211838006231, "grad_norm": 4.007157325744629, "learning_rate": 4.455495144293824e-06, "loss": 0.36947304010391235, "step": 1923 }, { "epoch": 0.4994807892004154, "grad_norm": 5.261094093322754, "learning_rate": 4.454877952148558e-06, "loss": 0.42824283242225647, "step": 1924 }, { "epoch": 0.4997403946002077, "grad_norm": 4.275559902191162, "learning_rate": 4.454260458619907e-06, "loss": 0.40371039509773254, "step": 1925 }, { "epoch": 0.5, "grad_norm": 2.3502824306488037, "learning_rate": 4.45364266381703e-06, "loss": 0.33165186643600464, "step": 1926 }, { "epoch": 0.5002596053997923, "grad_norm": 4.460386276245117, "learning_rate": 4.453024567849136e-06, "loss": 0.34777534008026123, "step": 1927 }, { "epoch": 0.5005192107995846, "grad_norm": 6.470502853393555, "learning_rate": 4.452406170825494e-06, "loss": 0.3999742567539215, "step": 1928 }, { "epoch": 0.5007788161993769, "grad_norm": 3.6890408992767334, "learning_rate": 4.451787472855421e-06, "loss": 0.35296183824539185, "step": 1929 }, { "epoch": 0.5010384215991692, "grad_norm": 4.500651836395264, "learning_rate": 4.451168474048288e-06, "loss": 0.42950117588043213, "step": 1930 }, { "epoch": 0.5012980269989615, "grad_norm": 6.4493727684021, "learning_rate": 4.450549174513521e-06, "loss": 0.45143893361091614, "step": 1931 }, { "epoch": 0.5015576323987538, "grad_norm": 5.872805595397949, "learning_rate": 4.449929574360597e-06, "loss": 0.5230668783187866, "step": 1932 }, { "epoch": 0.5018172377985463, "grad_norm": 5.62290096282959, "learning_rate": 4.4493096736990476e-06, "loss": 0.28999438881874084, "step": 1933 }, { "epoch": 0.5020768431983386, "grad_norm": 2.2293007373809814, "learning_rate": 4.448689472638457e-06, "loss": 0.34450840950012207, "step": 1934 }, { "epoch": 0.5023364485981309, "grad_norm": 4.671031475067139, "learning_rate": 4.448068971288462e-06, "loss": 0.3703320324420929, "step": 1935 }, { "epoch": 0.5025960539979232, "grad_norm": 4.077779769897461, "learning_rate": 4.447448169758754e-06, "loss": 0.3086358904838562, "step": 1936 }, { "epoch": 0.5028556593977155, "grad_norm": 3.457805633544922, "learning_rate": 4.446827068159076e-06, "loss": 0.3310493230819702, "step": 1937 }, { "epoch": 0.5031152647975078, "grad_norm": 6.57681941986084, "learning_rate": 4.446205666599224e-06, "loss": 0.4236891269683838, "step": 1938 }, { "epoch": 0.5033748701973001, "grad_norm": 6.192856788635254, "learning_rate": 4.445583965189049e-06, "loss": 0.4107367694377899, "step": 1939 }, { "epoch": 0.5036344755970924, "grad_norm": 3.5447046756744385, "learning_rate": 4.444961964038452e-06, "loss": 0.3549615442752838, "step": 1940 }, { "epoch": 0.5038940809968847, "grad_norm": 6.469011306762695, "learning_rate": 4.444339663257389e-06, "loss": 0.36178159713745117, "step": 1941 }, { "epoch": 0.504153686396677, "grad_norm": 4.743015766143799, "learning_rate": 4.443717062955869e-06, "loss": 0.41529351472854614, "step": 1942 }, { "epoch": 0.5044132917964693, "grad_norm": 3.191650152206421, "learning_rate": 4.443094163243954e-06, "loss": 0.33003801107406616, "step": 1943 }, { "epoch": 0.5046728971962616, "grad_norm": 9.188947677612305, "learning_rate": 4.442470964231758e-06, "loss": 0.3849238157272339, "step": 1944 }, { "epoch": 0.504932502596054, "grad_norm": 4.932680130004883, "learning_rate": 4.441847466029447e-06, "loss": 0.348910927772522, "step": 1945 }, { "epoch": 0.5051921079958464, "grad_norm": 5.83506965637207, "learning_rate": 4.441223668747241e-06, "loss": 0.3268173038959503, "step": 1946 }, { "epoch": 0.5054517133956387, "grad_norm": 2.43631911277771, "learning_rate": 4.440599572495416e-06, "loss": 0.35481804609298706, "step": 1947 }, { "epoch": 0.505711318795431, "grad_norm": 3.162735939025879, "learning_rate": 4.439975177384296e-06, "loss": 0.34726083278656006, "step": 1948 }, { "epoch": 0.5059709241952233, "grad_norm": 3.557500123977661, "learning_rate": 4.439350483524259e-06, "loss": 0.3431321680545807, "step": 1949 }, { "epoch": 0.5062305295950156, "grad_norm": 3.9297244548797607, "learning_rate": 4.4387254910257386e-06, "loss": 0.32698941230773926, "step": 1950 }, { "epoch": 0.5064901349948079, "grad_norm": 5.166150093078613, "learning_rate": 4.438100199999217e-06, "loss": 0.31102296710014343, "step": 1951 }, { "epoch": 0.5067497403946002, "grad_norm": 5.2780561447143555, "learning_rate": 4.437474610555234e-06, "loss": 0.3698318600654602, "step": 1952 }, { "epoch": 0.5070093457943925, "grad_norm": 3.7498137950897217, "learning_rate": 4.436848722804376e-06, "loss": 0.3521405756473541, "step": 1953 }, { "epoch": 0.5072689511941848, "grad_norm": 5.819508075714111, "learning_rate": 4.436222536857289e-06, "loss": 0.37051254510879517, "step": 1954 }, { "epoch": 0.5075285565939771, "grad_norm": 4.8307623863220215, "learning_rate": 4.435596052824666e-06, "loss": 0.3147444725036621, "step": 1955 }, { "epoch": 0.5077881619937694, "grad_norm": 6.17814826965332, "learning_rate": 4.434969270817257e-06, "loss": 0.3531414866447449, "step": 1956 }, { "epoch": 0.5080477673935618, "grad_norm": 6.251739025115967, "learning_rate": 4.4343421909458605e-06, "loss": 0.4109035134315491, "step": 1957 }, { "epoch": 0.5083073727933541, "grad_norm": 8.213174819946289, "learning_rate": 4.433714813321331e-06, "loss": 0.44548964500427246, "step": 1958 }, { "epoch": 0.5085669781931464, "grad_norm": 3.305529832839966, "learning_rate": 4.433087138054575e-06, "loss": 0.3159274458885193, "step": 1959 }, { "epoch": 0.5088265835929388, "grad_norm": 5.742868900299072, "learning_rate": 4.4324591652565505e-06, "loss": 0.39475011825561523, "step": 1960 }, { "epoch": 0.5090861889927311, "grad_norm": 6.834959983825684, "learning_rate": 4.4318308950382685e-06, "loss": 0.39637964963912964, "step": 1961 }, { "epoch": 0.5093457943925234, "grad_norm": 2.4286997318267822, "learning_rate": 4.431202327510793e-06, "loss": 0.3599260151386261, "step": 1962 }, { "epoch": 0.5096053997923157, "grad_norm": 5.121759414672852, "learning_rate": 4.43057346278524e-06, "loss": 0.3568517565727234, "step": 1963 }, { "epoch": 0.509865005192108, "grad_norm": 5.273621082305908, "learning_rate": 4.42994430097278e-06, "loss": 0.38211897015571594, "step": 1964 }, { "epoch": 0.5101246105919003, "grad_norm": 6.744298934936523, "learning_rate": 4.429314842184632e-06, "loss": 0.2621268033981323, "step": 1965 }, { "epoch": 0.5103842159916926, "grad_norm": 5.181143283843994, "learning_rate": 4.428685086532072e-06, "loss": 0.4157333970069885, "step": 1966 }, { "epoch": 0.5106438213914849, "grad_norm": 5.600048542022705, "learning_rate": 4.428055034126426e-06, "loss": 0.36543476581573486, "step": 1967 }, { "epoch": 0.5109034267912772, "grad_norm": 7.020823955535889, "learning_rate": 4.427424685079071e-06, "loss": 0.39240461587905884, "step": 1968 }, { "epoch": 0.5111630321910696, "grad_norm": 6.248912334442139, "learning_rate": 4.42679403950144e-06, "loss": 0.3036401867866516, "step": 1969 }, { "epoch": 0.5114226375908619, "grad_norm": 5.2753777503967285, "learning_rate": 4.426163097505017e-06, "loss": 0.3695783019065857, "step": 1970 }, { "epoch": 0.5116822429906542, "grad_norm": 2.6173784732818604, "learning_rate": 4.425531859201337e-06, "loss": 0.36492154002189636, "step": 1971 }, { "epoch": 0.5119418483904465, "grad_norm": 2.863253593444824, "learning_rate": 4.424900324701989e-06, "loss": 0.32936763763427734, "step": 1972 }, { "epoch": 0.5122014537902388, "grad_norm": 3.16676926612854, "learning_rate": 4.424268494118613e-06, "loss": 0.3546141982078552, "step": 1973 }, { "epoch": 0.5124610591900312, "grad_norm": 4.51838493347168, "learning_rate": 4.423636367562903e-06, "loss": 0.3599461615085602, "step": 1974 }, { "epoch": 0.5127206645898235, "grad_norm": 3.457026958465576, "learning_rate": 4.423003945146605e-06, "loss": 0.32117098569869995, "step": 1975 }, { "epoch": 0.5129802699896158, "grad_norm": 7.368382453918457, "learning_rate": 4.422371226981517e-06, "loss": 0.34175968170166016, "step": 1976 }, { "epoch": 0.5132398753894081, "grad_norm": 5.7598443031311035, "learning_rate": 4.421738213179487e-06, "loss": 0.3602323532104492, "step": 1977 }, { "epoch": 0.5134994807892004, "grad_norm": 4.766915798187256, "learning_rate": 4.421104903852419e-06, "loss": 0.3880806565284729, "step": 1978 }, { "epoch": 0.5137590861889927, "grad_norm": 5.118077754974365, "learning_rate": 4.420471299112267e-06, "loss": 0.3735669255256653, "step": 1979 }, { "epoch": 0.514018691588785, "grad_norm": 3.9935269355773926, "learning_rate": 4.419837399071038e-06, "loss": 0.32347986102104187, "step": 1980 }, { "epoch": 0.5142782969885774, "grad_norm": 3.7519776821136475, "learning_rate": 4.419203203840792e-06, "loss": 0.3170253038406372, "step": 1981 }, { "epoch": 0.5145379023883697, "grad_norm": 3.6411683559417725, "learning_rate": 4.418568713533638e-06, "loss": 0.3361263871192932, "step": 1982 }, { "epoch": 0.514797507788162, "grad_norm": 5.249903202056885, "learning_rate": 4.4179339282617416e-06, "loss": 0.4078413248062134, "step": 1983 }, { "epoch": 0.5150571131879543, "grad_norm": 4.36924934387207, "learning_rate": 4.417298848137317e-06, "loss": 0.27185118198394775, "step": 1984 }, { "epoch": 0.5153167185877466, "grad_norm": 4.565593719482422, "learning_rate": 4.416663473272632e-06, "loss": 0.4032168984413147, "step": 1985 }, { "epoch": 0.5155763239875389, "grad_norm": 8.50494384765625, "learning_rate": 4.416027803780006e-06, "loss": 0.4163379669189453, "step": 1986 }, { "epoch": 0.5158359293873312, "grad_norm": 3.8828203678131104, "learning_rate": 4.415391839771812e-06, "loss": 0.37214016914367676, "step": 1987 }, { "epoch": 0.5160955347871236, "grad_norm": 2.780263662338257, "learning_rate": 4.414755581360473e-06, "loss": 0.35949838161468506, "step": 1988 }, { "epoch": 0.5163551401869159, "grad_norm": 4.602520942687988, "learning_rate": 4.414119028658465e-06, "loss": 0.3685632646083832, "step": 1989 }, { "epoch": 0.5166147455867082, "grad_norm": 5.144067764282227, "learning_rate": 4.4134821817783155e-06, "loss": 0.3397172689437866, "step": 1990 }, { "epoch": 0.5168743509865005, "grad_norm": 4.699976921081543, "learning_rate": 4.4128450408326065e-06, "loss": 0.4016708731651306, "step": 1991 }, { "epoch": 0.5171339563862928, "grad_norm": 5.428966999053955, "learning_rate": 4.412207605933967e-06, "loss": 0.34171366691589355, "step": 1992 }, { "epoch": 0.5173935617860852, "grad_norm": 4.94646692276001, "learning_rate": 4.411569877195082e-06, "loss": 0.34986764192581177, "step": 1993 }, { "epoch": 0.5176531671858775, "grad_norm": 2.7532222270965576, "learning_rate": 4.410931854728689e-06, "loss": 0.35676971077919006, "step": 1994 }, { "epoch": 0.5179127725856698, "grad_norm": 5.541217803955078, "learning_rate": 4.410293538647573e-06, "loss": 0.380888968706131, "step": 1995 }, { "epoch": 0.5181723779854621, "grad_norm": 5.096859455108643, "learning_rate": 4.409654929064575e-06, "loss": 0.3361680507659912, "step": 1996 }, { "epoch": 0.5184319833852544, "grad_norm": 2.7317371368408203, "learning_rate": 4.4090160260925874e-06, "loss": 0.3304269313812256, "step": 1997 }, { "epoch": 0.5186915887850467, "grad_norm": 3.528367280960083, "learning_rate": 4.408376829844553e-06, "loss": 0.3606870472431183, "step": 1998 }, { "epoch": 0.518951194184839, "grad_norm": 9.099910736083984, "learning_rate": 4.407737340433466e-06, "loss": 0.4599234461784363, "step": 1999 }, { "epoch": 0.5192107995846313, "grad_norm": 6.6725077629089355, "learning_rate": 4.407097557972375e-06, "loss": 0.37515655159950256, "step": 2000 }, { "epoch": 0.5194704049844237, "grad_norm": 4.590224742889404, "learning_rate": 4.406457482574379e-06, "loss": 0.378417044878006, "step": 2001 }, { "epoch": 0.519730010384216, "grad_norm": 9.930837631225586, "learning_rate": 4.405817114352627e-06, "loss": 0.45417606830596924, "step": 2002 }, { "epoch": 0.5199896157840083, "grad_norm": 7.147353172302246, "learning_rate": 4.405176453420322e-06, "loss": 0.370900958776474, "step": 2003 }, { "epoch": 0.5202492211838006, "grad_norm": 4.201982021331787, "learning_rate": 4.4045354998907196e-06, "loss": 0.3911549150943756, "step": 2004 }, { "epoch": 0.520508826583593, "grad_norm": 3.8525938987731934, "learning_rate": 4.4038942538771235e-06, "loss": 0.29850414395332336, "step": 2005 }, { "epoch": 0.5207684319833853, "grad_norm": 4.059137344360352, "learning_rate": 4.403252715492893e-06, "loss": 0.35231804847717285, "step": 2006 }, { "epoch": 0.5210280373831776, "grad_norm": 3.169070243835449, "learning_rate": 4.402610884851437e-06, "loss": 0.3160070478916168, "step": 2007 }, { "epoch": 0.5212876427829699, "grad_norm": 4.038784980773926, "learning_rate": 4.401968762066216e-06, "loss": 0.32974880933761597, "step": 2008 }, { "epoch": 0.5215472481827622, "grad_norm": 6.06164026260376, "learning_rate": 4.4013263472507434e-06, "loss": 0.3251032531261444, "step": 2009 }, { "epoch": 0.5218068535825545, "grad_norm": 3.3744077682495117, "learning_rate": 4.400683640518583e-06, "loss": 0.3530527949333191, "step": 2010 }, { "epoch": 0.5220664589823468, "grad_norm": 2.7755119800567627, "learning_rate": 4.40004064198335e-06, "loss": 0.3297640085220337, "step": 2011 }, { "epoch": 0.5223260643821391, "grad_norm": 4.352728366851807, "learning_rate": 4.399397351758714e-06, "loss": 0.41863054037094116, "step": 2012 }, { "epoch": 0.5225856697819314, "grad_norm": 6.906839370727539, "learning_rate": 4.39875376995839e-06, "loss": 0.38729244470596313, "step": 2013 }, { "epoch": 0.5228452751817237, "grad_norm": 3.075197458267212, "learning_rate": 4.3981098966961524e-06, "loss": 0.3561784625053406, "step": 2014 }, { "epoch": 0.523104880581516, "grad_norm": 6.037327289581299, "learning_rate": 4.397465732085822e-06, "loss": 0.420632004737854, "step": 2015 }, { "epoch": 0.5233644859813084, "grad_norm": 8.178013801574707, "learning_rate": 4.396821276241272e-06, "loss": 0.3742044270038605, "step": 2016 }, { "epoch": 0.5236240913811008, "grad_norm": 5.10501766204834, "learning_rate": 4.396176529276426e-06, "loss": 0.3872550129890442, "step": 2017 }, { "epoch": 0.5238836967808931, "grad_norm": 7.027287006378174, "learning_rate": 4.3955314913052636e-06, "loss": 0.3461635410785675, "step": 2018 }, { "epoch": 0.5241433021806854, "grad_norm": 7.374515533447266, "learning_rate": 4.394886162441811e-06, "loss": 0.28601720929145813, "step": 2019 }, { "epoch": 0.5244029075804777, "grad_norm": 5.747159004211426, "learning_rate": 4.394240542800148e-06, "loss": 0.36338409781455994, "step": 2020 }, { "epoch": 0.52466251298027, "grad_norm": 2.944599151611328, "learning_rate": 4.393594632494404e-06, "loss": 0.3400633931159973, "step": 2021 }, { "epoch": 0.5249221183800623, "grad_norm": 3.3417112827301025, "learning_rate": 4.3929484316387636e-06, "loss": 0.36828434467315674, "step": 2022 }, { "epoch": 0.5251817237798546, "grad_norm": 7.028200626373291, "learning_rate": 4.392301940347458e-06, "loss": 0.3166755735874176, "step": 2023 }, { "epoch": 0.5254413291796469, "grad_norm": 5.1927008628845215, "learning_rate": 4.391655158734774e-06, "loss": 0.4131122827529907, "step": 2024 }, { "epoch": 0.5257009345794392, "grad_norm": 8.909172058105469, "learning_rate": 4.391008086915046e-06, "loss": 0.4459782838821411, "step": 2025 }, { "epoch": 0.5259605399792315, "grad_norm": 2.6896986961364746, "learning_rate": 4.390360725002663e-06, "loss": 0.34734365344047546, "step": 2026 }, { "epoch": 0.5262201453790238, "grad_norm": 3.807565927505493, "learning_rate": 4.389713073112063e-06, "loss": 0.3551183044910431, "step": 2027 }, { "epoch": 0.5264797507788161, "grad_norm": 5.799769401550293, "learning_rate": 4.389065131357736e-06, "loss": 0.39571505784988403, "step": 2028 }, { "epoch": 0.5267393561786086, "grad_norm": 2.997257947921753, "learning_rate": 4.388416899854224e-06, "loss": 0.3782396912574768, "step": 2029 }, { "epoch": 0.5269989615784009, "grad_norm": 3.9218573570251465, "learning_rate": 4.387768378716117e-06, "loss": 0.38151097297668457, "step": 2030 }, { "epoch": 0.5272585669781932, "grad_norm": 2.132268190383911, "learning_rate": 4.387119568058063e-06, "loss": 0.36554357409477234, "step": 2031 }, { "epoch": 0.5275181723779855, "grad_norm": 6.342168807983398, "learning_rate": 4.386470467994753e-06, "loss": 0.28481948375701904, "step": 2032 }, { "epoch": 0.5277777777777778, "grad_norm": 5.667883396148682, "learning_rate": 4.385821078640935e-06, "loss": 0.4115374982357025, "step": 2033 }, { "epoch": 0.5280373831775701, "grad_norm": 3.3798069953918457, "learning_rate": 4.385171400111405e-06, "loss": 0.32788723707199097, "step": 2034 }, { "epoch": 0.5282969885773624, "grad_norm": 3.9429078102111816, "learning_rate": 4.3845214325210124e-06, "loss": 0.3541773557662964, "step": 2035 }, { "epoch": 0.5285565939771547, "grad_norm": 2.1682956218719482, "learning_rate": 4.383871175984656e-06, "loss": 0.33877089619636536, "step": 2036 }, { "epoch": 0.528816199376947, "grad_norm": 7.128172397613525, "learning_rate": 4.383220630617287e-06, "loss": 0.36090248823165894, "step": 2037 }, { "epoch": 0.5290758047767393, "grad_norm": 3.91050386428833, "learning_rate": 4.3825697965339055e-06, "loss": 0.3680996894836426, "step": 2038 }, { "epoch": 0.5293354101765316, "grad_norm": 4.486211776733398, "learning_rate": 4.3819186738495645e-06, "loss": 0.38513410091400146, "step": 2039 }, { "epoch": 0.5295950155763239, "grad_norm": 2.699392557144165, "learning_rate": 4.381267262679369e-06, "loss": 0.3684455454349518, "step": 2040 }, { "epoch": 0.5298546209761164, "grad_norm": 3.4473533630371094, "learning_rate": 4.380615563138472e-06, "loss": 0.37787026166915894, "step": 2041 }, { "epoch": 0.5301142263759087, "grad_norm": 5.856087684631348, "learning_rate": 4.3799635753420794e-06, "loss": 0.2966080904006958, "step": 2042 }, { "epoch": 0.530373831775701, "grad_norm": 3.8841750621795654, "learning_rate": 4.379311299405449e-06, "loss": 0.3316246271133423, "step": 2043 }, { "epoch": 0.5306334371754933, "grad_norm": 4.430863380432129, "learning_rate": 4.378658735443886e-06, "loss": 0.3515787422657013, "step": 2044 }, { "epoch": 0.5308930425752856, "grad_norm": 8.011249542236328, "learning_rate": 4.37800588357275e-06, "loss": 0.3651692867279053, "step": 2045 }, { "epoch": 0.5311526479750779, "grad_norm": 3.6477677822113037, "learning_rate": 4.37735274390745e-06, "loss": 0.39327889680862427, "step": 2046 }, { "epoch": 0.5314122533748702, "grad_norm": 6.112733840942383, "learning_rate": 4.376699316563447e-06, "loss": 0.32600730657577515, "step": 2047 }, { "epoch": 0.5316718587746625, "grad_norm": 5.558367729187012, "learning_rate": 4.3760456016562505e-06, "loss": 0.3167305588722229, "step": 2048 }, { "epoch": 0.5319314641744548, "grad_norm": 3.335597515106201, "learning_rate": 4.375391599301424e-06, "loss": 0.2922672927379608, "step": 2049 }, { "epoch": 0.5321910695742471, "grad_norm": 3.7596964836120605, "learning_rate": 4.374737309614579e-06, "loss": 0.3667748272418976, "step": 2050 }, { "epoch": 0.5324506749740394, "grad_norm": 4.6090922355651855, "learning_rate": 4.374082732711379e-06, "loss": 0.34863680601119995, "step": 2051 }, { "epoch": 0.5327102803738317, "grad_norm": 3.0304412841796875, "learning_rate": 4.373427868707539e-06, "loss": 0.30020174384117126, "step": 2052 }, { "epoch": 0.5329698857736241, "grad_norm": 6.693353176116943, "learning_rate": 4.3727727177188226e-06, "loss": 0.2944449186325073, "step": 2053 }, { "epoch": 0.5332294911734164, "grad_norm": 6.581692218780518, "learning_rate": 4.372117279861047e-06, "loss": 0.2578529715538025, "step": 2054 }, { "epoch": 0.5334890965732088, "grad_norm": 6.672374725341797, "learning_rate": 4.371461555250077e-06, "loss": 0.3327677845954895, "step": 2055 }, { "epoch": 0.5337487019730011, "grad_norm": 7.310926914215088, "learning_rate": 4.370805544001831e-06, "loss": 0.3411298394203186, "step": 2056 }, { "epoch": 0.5340083073727934, "grad_norm": 3.897193431854248, "learning_rate": 4.370149246232277e-06, "loss": 0.3432196378707886, "step": 2057 }, { "epoch": 0.5342679127725857, "grad_norm": 3.736485719680786, "learning_rate": 4.3694926620574315e-06, "loss": 0.3712823987007141, "step": 2058 }, { "epoch": 0.534527518172378, "grad_norm": 7.295075416564941, "learning_rate": 4.3688357915933656e-06, "loss": 0.3695761561393738, "step": 2059 }, { "epoch": 0.5347871235721703, "grad_norm": 6.126203536987305, "learning_rate": 4.368178634956199e-06, "loss": 0.4108314514160156, "step": 2060 }, { "epoch": 0.5350467289719626, "grad_norm": 7.035964488983154, "learning_rate": 4.3675211922621e-06, "loss": 0.34433192014694214, "step": 2061 }, { "epoch": 0.5353063343717549, "grad_norm": 6.5642290115356445, "learning_rate": 4.36686346362729e-06, "loss": 0.3029049038887024, "step": 2062 }, { "epoch": 0.5355659397715472, "grad_norm": 3.9095237255096436, "learning_rate": 4.366205449168042e-06, "loss": 0.3248435854911804, "step": 2063 }, { "epoch": 0.5358255451713395, "grad_norm": 2.8021740913391113, "learning_rate": 4.3655471490006766e-06, "loss": 0.31823885440826416, "step": 2064 }, { "epoch": 0.5360851505711319, "grad_norm": 2.1168787479400635, "learning_rate": 4.364888563241566e-06, "loss": 0.3472137749195099, "step": 2065 }, { "epoch": 0.5363447559709242, "grad_norm": 2.6240909099578857, "learning_rate": 4.364229692007134e-06, "loss": 0.3888222575187683, "step": 2066 }, { "epoch": 0.5366043613707165, "grad_norm": 4.6624836921691895, "learning_rate": 4.363570535413852e-06, "loss": 0.3240125775337219, "step": 2067 }, { "epoch": 0.5368639667705088, "grad_norm": 5.850358486175537, "learning_rate": 4.362911093578246e-06, "loss": 0.3489924669265747, "step": 2068 }, { "epoch": 0.5371235721703012, "grad_norm": 6.215240955352783, "learning_rate": 4.362251366616891e-06, "loss": 0.4511135220527649, "step": 2069 }, { "epoch": 0.5373831775700935, "grad_norm": 6.292510032653809, "learning_rate": 4.361591354646409e-06, "loss": 0.386809766292572, "step": 2070 }, { "epoch": 0.5376427829698858, "grad_norm": 6.688182830810547, "learning_rate": 4.360931057783475e-06, "loss": 0.3849412202835083, "step": 2071 }, { "epoch": 0.5379023883696781, "grad_norm": 6.443875312805176, "learning_rate": 4.360270476144817e-06, "loss": 0.3530896008014679, "step": 2072 }, { "epoch": 0.5381619937694704, "grad_norm": 5.381707668304443, "learning_rate": 4.359609609847208e-06, "loss": 0.35839951038360596, "step": 2073 }, { "epoch": 0.5384215991692627, "grad_norm": 4.999324321746826, "learning_rate": 4.358948459007475e-06, "loss": 0.34525585174560547, "step": 2074 }, { "epoch": 0.538681204569055, "grad_norm": 7.52186918258667, "learning_rate": 4.358287023742495e-06, "loss": 0.32008981704711914, "step": 2075 }, { "epoch": 0.5389408099688473, "grad_norm": 2.218958854675293, "learning_rate": 4.357625304169194e-06, "loss": 0.3833862543106079, "step": 2076 }, { "epoch": 0.5392004153686397, "grad_norm": 3.1158854961395264, "learning_rate": 4.356963300404549e-06, "loss": 0.31471291184425354, "step": 2077 }, { "epoch": 0.539460020768432, "grad_norm": 2.5870535373687744, "learning_rate": 4.356301012565588e-06, "loss": 0.3742595911026001, "step": 2078 }, { "epoch": 0.5397196261682243, "grad_norm": 7.14106559753418, "learning_rate": 4.355638440769385e-06, "loss": 0.3969798982143402, "step": 2079 }, { "epoch": 0.5399792315680166, "grad_norm": 4.864229202270508, "learning_rate": 4.354975585133072e-06, "loss": 0.3554210066795349, "step": 2080 }, { "epoch": 0.5402388369678089, "grad_norm": 4.9783244132995605, "learning_rate": 4.354312445773825e-06, "loss": 0.4170185327529907, "step": 2081 }, { "epoch": 0.5404984423676013, "grad_norm": 7.074699401855469, "learning_rate": 4.353649022808869e-06, "loss": 0.4046960473060608, "step": 2082 }, { "epoch": 0.5407580477673936, "grad_norm": 5.236598014831543, "learning_rate": 4.352985316355487e-06, "loss": 0.4107678532600403, "step": 2083 }, { "epoch": 0.5410176531671859, "grad_norm": 4.028833866119385, "learning_rate": 4.3523213265310036e-06, "loss": 0.32316339015960693, "step": 2084 }, { "epoch": 0.5412772585669782, "grad_norm": 2.7254605293273926, "learning_rate": 4.351657053452798e-06, "loss": 0.39177215099334717, "step": 2085 }, { "epoch": 0.5415368639667705, "grad_norm": 7.739705562591553, "learning_rate": 4.350992497238298e-06, "loss": 0.35709792375564575, "step": 2086 }, { "epoch": 0.5417964693665628, "grad_norm": 4.755579948425293, "learning_rate": 4.350327658004983e-06, "loss": 0.3495714068412781, "step": 2087 }, { "epoch": 0.5420560747663551, "grad_norm": 2.1141910552978516, "learning_rate": 4.349662535870381e-06, "loss": 0.34969449043273926, "step": 2088 }, { "epoch": 0.5423156801661475, "grad_norm": 8.66731071472168, "learning_rate": 4.348997130952069e-06, "loss": 0.3930588960647583, "step": 2089 }, { "epoch": 0.5425752855659398, "grad_norm": 6.74434757232666, "learning_rate": 4.348331443367677e-06, "loss": 0.42745742201805115, "step": 2090 }, { "epoch": 0.5428348909657321, "grad_norm": 2.7467429637908936, "learning_rate": 4.3476654732348826e-06, "loss": 0.3145074248313904, "step": 2091 }, { "epoch": 0.5430944963655244, "grad_norm": 5.95159387588501, "learning_rate": 4.346999220671414e-06, "loss": 0.41479289531707764, "step": 2092 }, { "epoch": 0.5433541017653167, "grad_norm": 3.2043538093566895, "learning_rate": 4.34633268579505e-06, "loss": 0.3235129117965698, "step": 2093 }, { "epoch": 0.543613707165109, "grad_norm": 4.199824333190918, "learning_rate": 4.345665868723618e-06, "loss": 0.36098259687423706, "step": 2094 }, { "epoch": 0.5438733125649013, "grad_norm": 8.566095352172852, "learning_rate": 4.3449987695749964e-06, "loss": 0.31639325618743896, "step": 2095 }, { "epoch": 0.5441329179646937, "grad_norm": 6.739482402801514, "learning_rate": 4.344331388467113e-06, "loss": 0.38460272550582886, "step": 2096 }, { "epoch": 0.544392523364486, "grad_norm": 2.563218832015991, "learning_rate": 4.343663725517946e-06, "loss": 0.35457849502563477, "step": 2097 }, { "epoch": 0.5446521287642783, "grad_norm": 9.051881790161133, "learning_rate": 4.342995780845522e-06, "loss": 0.4669705629348755, "step": 2098 }, { "epoch": 0.5449117341640706, "grad_norm": 9.86410140991211, "learning_rate": 4.342327554567918e-06, "loss": 0.369933158159256, "step": 2099 }, { "epoch": 0.5451713395638629, "grad_norm": 5.537013530731201, "learning_rate": 4.341659046803263e-06, "loss": 0.3731176257133484, "step": 2100 }, { "epoch": 0.5454309449636553, "grad_norm": 3.0085084438323975, "learning_rate": 4.340990257669732e-06, "loss": 0.36932894587516785, "step": 2101 }, { "epoch": 0.5456905503634476, "grad_norm": 4.751584053039551, "learning_rate": 4.340321187285553e-06, "loss": 0.3859615921974182, "step": 2102 }, { "epoch": 0.5459501557632399, "grad_norm": 8.408539772033691, "learning_rate": 4.339651835769e-06, "loss": 0.39896124601364136, "step": 2103 }, { "epoch": 0.5462097611630322, "grad_norm": 5.038994312286377, "learning_rate": 4.338982203238403e-06, "loss": 0.36968517303466797, "step": 2104 }, { "epoch": 0.5464693665628245, "grad_norm": 6.153397560119629, "learning_rate": 4.338312289812134e-06, "loss": 0.40076735615730286, "step": 2105 }, { "epoch": 0.5467289719626168, "grad_norm": 4.924874305725098, "learning_rate": 4.33764209560862e-06, "loss": 0.4152206778526306, "step": 2106 }, { "epoch": 0.5469885773624091, "grad_norm": 2.5537118911743164, "learning_rate": 4.336971620746334e-06, "loss": 0.32431554794311523, "step": 2107 }, { "epoch": 0.5472481827622014, "grad_norm": 4.73814582824707, "learning_rate": 4.336300865343805e-06, "loss": 0.40524816513061523, "step": 2108 }, { "epoch": 0.5475077881619937, "grad_norm": 4.819533348083496, "learning_rate": 4.335629829519602e-06, "loss": 0.35588014125823975, "step": 2109 }, { "epoch": 0.547767393561786, "grad_norm": 4.100233554840088, "learning_rate": 4.334958513392353e-06, "loss": 0.3391392230987549, "step": 2110 }, { "epoch": 0.5480269989615784, "grad_norm": 4.677302360534668, "learning_rate": 4.33428691708073e-06, "loss": 0.3449963927268982, "step": 2111 }, { "epoch": 0.5482866043613707, "grad_norm": 5.411343574523926, "learning_rate": 4.333615040703454e-06, "loss": 0.29863643646240234, "step": 2112 }, { "epoch": 0.5485462097611631, "grad_norm": 3.448880195617676, "learning_rate": 4.332942884379299e-06, "loss": 0.34862178564071655, "step": 2113 }, { "epoch": 0.5488058151609554, "grad_norm": 2.7321646213531494, "learning_rate": 4.332270448227087e-06, "loss": 0.3229767084121704, "step": 2114 }, { "epoch": 0.5490654205607477, "grad_norm": 2.4955413341522217, "learning_rate": 4.331597732365689e-06, "loss": 0.34270304441452026, "step": 2115 }, { "epoch": 0.54932502596054, "grad_norm": 6.283299922943115, "learning_rate": 4.330924736914026e-06, "loss": 0.3706386387348175, "step": 2116 }, { "epoch": 0.5495846313603323, "grad_norm": 6.056734085083008, "learning_rate": 4.3302514619910665e-06, "loss": 0.3427633047103882, "step": 2117 }, { "epoch": 0.5498442367601246, "grad_norm": 5.005572319030762, "learning_rate": 4.329577907715833e-06, "loss": 0.39425623416900635, "step": 2118 }, { "epoch": 0.5501038421599169, "grad_norm": 6.246262073516846, "learning_rate": 4.328904074207392e-06, "loss": 0.35484829545021057, "step": 2119 }, { "epoch": 0.5503634475597092, "grad_norm": 12.289922714233398, "learning_rate": 4.328229961584864e-06, "loss": 0.41981425881385803, "step": 2120 }, { "epoch": 0.5506230529595015, "grad_norm": 5.270451068878174, "learning_rate": 4.327555569967414e-06, "loss": 0.3750650882720947, "step": 2121 }, { "epoch": 0.5508826583592938, "grad_norm": 3.6346490383148193, "learning_rate": 4.326880899474261e-06, "loss": 0.38808292150497437, "step": 2122 }, { "epoch": 0.5511422637590861, "grad_norm": 2.593775510787964, "learning_rate": 4.32620595022467e-06, "loss": 0.36414068937301636, "step": 2123 }, { "epoch": 0.5514018691588785, "grad_norm": 5.984305381774902, "learning_rate": 4.325530722337959e-06, "loss": 0.41630521416664124, "step": 2124 }, { "epoch": 0.5516614745586709, "grad_norm": 4.842377185821533, "learning_rate": 4.32485521593349e-06, "loss": 0.3441247344017029, "step": 2125 }, { "epoch": 0.5519210799584632, "grad_norm": 3.309098243713379, "learning_rate": 4.324179431130679e-06, "loss": 0.34345221519470215, "step": 2126 }, { "epoch": 0.5521806853582555, "grad_norm": 4.659794330596924, "learning_rate": 4.323503368048987e-06, "loss": 0.3328994810581207, "step": 2127 }, { "epoch": 0.5524402907580478, "grad_norm": 4.222017288208008, "learning_rate": 4.32282702680793e-06, "loss": 0.2547718286514282, "step": 2128 }, { "epoch": 0.5526998961578401, "grad_norm": 6.2819366455078125, "learning_rate": 4.322150407527067e-06, "loss": 0.31883490085601807, "step": 2129 }, { "epoch": 0.5529595015576324, "grad_norm": 4.969221591949463, "learning_rate": 4.321473510326009e-06, "loss": 0.35080599784851074, "step": 2130 }, { "epoch": 0.5532191069574247, "grad_norm": 7.275143623352051, "learning_rate": 4.320796335324416e-06, "loss": 0.39965301752090454, "step": 2131 }, { "epoch": 0.553478712357217, "grad_norm": 4.2101969718933105, "learning_rate": 4.3201188826419985e-06, "loss": 0.34576597809791565, "step": 2132 }, { "epoch": 0.5537383177570093, "grad_norm": 4.372494220733643, "learning_rate": 4.319441152398513e-06, "loss": 0.34278279542922974, "step": 2133 }, { "epoch": 0.5539979231568016, "grad_norm": 3.730402708053589, "learning_rate": 4.318763144713767e-06, "loss": 0.4012802541255951, "step": 2134 }, { "epoch": 0.5542575285565939, "grad_norm": 7.25547981262207, "learning_rate": 4.318084859707617e-06, "loss": 0.3420664668083191, "step": 2135 }, { "epoch": 0.5545171339563862, "grad_norm": 3.783637762069702, "learning_rate": 4.317406297499968e-06, "loss": 0.3353502154350281, "step": 2136 }, { "epoch": 0.5547767393561787, "grad_norm": 5.443531036376953, "learning_rate": 4.316727458210774e-06, "loss": 0.3027438521385193, "step": 2137 }, { "epoch": 0.555036344755971, "grad_norm": 4.025300025939941, "learning_rate": 4.31604834196004e-06, "loss": 0.3466494083404541, "step": 2138 }, { "epoch": 0.5552959501557633, "grad_norm": 8.091418266296387, "learning_rate": 4.315368948867816e-06, "loss": 0.32702213525772095, "step": 2139 }, { "epoch": 0.5555555555555556, "grad_norm": 9.114936828613281, "learning_rate": 4.3146892790542035e-06, "loss": 0.3515990674495697, "step": 2140 }, { "epoch": 0.5558151609553479, "grad_norm": 6.529482841491699, "learning_rate": 4.314009332639355e-06, "loss": 0.3710808753967285, "step": 2141 }, { "epoch": 0.5560747663551402, "grad_norm": 2.5695900917053223, "learning_rate": 4.313329109743466e-06, "loss": 0.35494422912597656, "step": 2142 }, { "epoch": 0.5563343717549325, "grad_norm": 3.2572972774505615, "learning_rate": 4.312648610486786e-06, "loss": 0.3523227572441101, "step": 2143 }, { "epoch": 0.5565939771547248, "grad_norm": 8.34841251373291, "learning_rate": 4.311967834989612e-06, "loss": 0.3703414797782898, "step": 2144 }, { "epoch": 0.5568535825545171, "grad_norm": 4.629737377166748, "learning_rate": 4.311286783372289e-06, "loss": 0.3726652264595032, "step": 2145 }, { "epoch": 0.5571131879543094, "grad_norm": 3.117027521133423, "learning_rate": 4.310605455755211e-06, "loss": 0.39132633805274963, "step": 2146 }, { "epoch": 0.5573727933541017, "grad_norm": 2.1397409439086914, "learning_rate": 4.3099238522588225e-06, "loss": 0.3525291979312897, "step": 2147 }, { "epoch": 0.557632398753894, "grad_norm": 3.037203311920166, "learning_rate": 4.309241973003614e-06, "loss": 0.3294105529785156, "step": 2148 }, { "epoch": 0.5578920041536864, "grad_norm": 6.270113945007324, "learning_rate": 4.3085598181101256e-06, "loss": 0.4029061198234558, "step": 2149 }, { "epoch": 0.5581516095534788, "grad_norm": 6.003632068634033, "learning_rate": 4.307877387698949e-06, "loss": 0.34250640869140625, "step": 2150 }, { "epoch": 0.5584112149532711, "grad_norm": 8.424132347106934, "learning_rate": 4.30719468189072e-06, "loss": 0.3092590570449829, "step": 2151 }, { "epoch": 0.5586708203530634, "grad_norm": 3.4613895416259766, "learning_rate": 4.306511700806127e-06, "loss": 0.3245619237422943, "step": 2152 }, { "epoch": 0.5589304257528557, "grad_norm": 6.831888675689697, "learning_rate": 4.305828444565904e-06, "loss": 0.3300519585609436, "step": 2153 }, { "epoch": 0.559190031152648, "grad_norm": 3.842355728149414, "learning_rate": 4.305144913290837e-06, "loss": 0.32086342573165894, "step": 2154 }, { "epoch": 0.5594496365524403, "grad_norm": 8.97780990600586, "learning_rate": 4.304461107101756e-06, "loss": 0.415046364068985, "step": 2155 }, { "epoch": 0.5597092419522326, "grad_norm": 4.485945701599121, "learning_rate": 4.303777026119545e-06, "loss": 0.3787631690502167, "step": 2156 }, { "epoch": 0.5599688473520249, "grad_norm": 6.512650012969971, "learning_rate": 4.3030926704651314e-06, "loss": 0.3949935734272003, "step": 2157 }, { "epoch": 0.5602284527518172, "grad_norm": 3.0357413291931152, "learning_rate": 4.302408040259495e-06, "loss": 0.36764228343963623, "step": 2158 }, { "epoch": 0.5604880581516095, "grad_norm": 7.003152370452881, "learning_rate": 4.301723135623662e-06, "loss": 0.428938090801239, "step": 2159 }, { "epoch": 0.5607476635514018, "grad_norm": 6.605358600616455, "learning_rate": 4.30103795667871e-06, "loss": 0.2300841212272644, "step": 2160 }, { "epoch": 0.5610072689511942, "grad_norm": 3.6016345024108887, "learning_rate": 4.300352503545761e-06, "loss": 0.33322733640670776, "step": 2161 }, { "epoch": 0.5612668743509865, "grad_norm": 8.658014297485352, "learning_rate": 4.299666776345987e-06, "loss": 0.39323127269744873, "step": 2162 }, { "epoch": 0.5615264797507789, "grad_norm": 3.647137403488159, "learning_rate": 4.298980775200609e-06, "loss": 0.30714207887649536, "step": 2163 }, { "epoch": 0.5617860851505712, "grad_norm": 2.7250452041625977, "learning_rate": 4.298294500230898e-06, "loss": 0.3373458981513977, "step": 2164 }, { "epoch": 0.5620456905503635, "grad_norm": 2.8494973182678223, "learning_rate": 4.29760795155817e-06, "loss": 0.3738449215888977, "step": 2165 }, { "epoch": 0.5623052959501558, "grad_norm": 4.768583297729492, "learning_rate": 4.296921129303792e-06, "loss": 0.3555263578891754, "step": 2166 }, { "epoch": 0.5625649013499481, "grad_norm": 3.239309787750244, "learning_rate": 4.296234033589178e-06, "loss": 0.34695565700531006, "step": 2167 }, { "epoch": 0.5628245067497404, "grad_norm": 6.730901718139648, "learning_rate": 4.295546664535791e-06, "loss": 0.3261781334877014, "step": 2168 }, { "epoch": 0.5630841121495327, "grad_norm": 3.6974971294403076, "learning_rate": 4.2948590222651424e-06, "loss": 0.3284180164337158, "step": 2169 }, { "epoch": 0.563343717549325, "grad_norm": 4.433708667755127, "learning_rate": 4.294171106898791e-06, "loss": 0.34935033321380615, "step": 2170 }, { "epoch": 0.5636033229491173, "grad_norm": 3.285536766052246, "learning_rate": 4.293482918558344e-06, "loss": 0.33352404832839966, "step": 2171 }, { "epoch": 0.5638629283489096, "grad_norm": 5.05916166305542, "learning_rate": 4.2927944573654595e-06, "loss": 0.37818896770477295, "step": 2172 }, { "epoch": 0.564122533748702, "grad_norm": 4.588708400726318, "learning_rate": 4.292105723441839e-06, "loss": 0.35186904668807983, "step": 2173 }, { "epoch": 0.5643821391484943, "grad_norm": 9.771332740783691, "learning_rate": 4.291416716909237e-06, "loss": 0.32389020919799805, "step": 2174 }, { "epoch": 0.5646417445482866, "grad_norm": 2.690288543701172, "learning_rate": 4.290727437889453e-06, "loss": 0.3428365886211395, "step": 2175 }, { "epoch": 0.564901349948079, "grad_norm": 3.016122817993164, "learning_rate": 4.290037886504335e-06, "loss": 0.3106638193130493, "step": 2176 }, { "epoch": 0.5651609553478713, "grad_norm": 6.368580341339111, "learning_rate": 4.289348062875782e-06, "loss": 0.35580164194107056, "step": 2177 }, { "epoch": 0.5654205607476636, "grad_norm": 4.949483871459961, "learning_rate": 4.288657967125738e-06, "loss": 0.42646145820617676, "step": 2178 }, { "epoch": 0.5656801661474559, "grad_norm": 7.860677242279053, "learning_rate": 4.2879675993761954e-06, "loss": 0.4372427463531494, "step": 2179 }, { "epoch": 0.5659397715472482, "grad_norm": 4.300817489624023, "learning_rate": 4.287276959749196e-06, "loss": 0.32624849677085876, "step": 2180 }, { "epoch": 0.5661993769470405, "grad_norm": 4.560674667358398, "learning_rate": 4.286586048366829e-06, "loss": 0.3006485104560852, "step": 2181 }, { "epoch": 0.5664589823468328, "grad_norm": 9.457296371459961, "learning_rate": 4.285894865351233e-06, "loss": 0.2871008813381195, "step": 2182 }, { "epoch": 0.5667185877466251, "grad_norm": 6.379358768463135, "learning_rate": 4.2852034108245895e-06, "loss": 0.3012307286262512, "step": 2183 }, { "epoch": 0.5669781931464174, "grad_norm": 2.8254008293151855, "learning_rate": 4.284511684909136e-06, "loss": 0.3182714283466339, "step": 2184 }, { "epoch": 0.5672377985462098, "grad_norm": 5.065138339996338, "learning_rate": 4.2838196877271536e-06, "loss": 0.34413981437683105, "step": 2185 }, { "epoch": 0.5674974039460021, "grad_norm": 4.3002424240112305, "learning_rate": 4.283127419400969e-06, "loss": 0.3512340784072876, "step": 2186 }, { "epoch": 0.5677570093457944, "grad_norm": 2.8864388465881348, "learning_rate": 4.28243488005296e-06, "loss": 0.3236296772956848, "step": 2187 }, { "epoch": 0.5680166147455867, "grad_norm": 10.125116348266602, "learning_rate": 4.281742069805553e-06, "loss": 0.23430192470550537, "step": 2188 }, { "epoch": 0.568276220145379, "grad_norm": 3.6660752296447754, "learning_rate": 4.281048988781221e-06, "loss": 0.38669976592063904, "step": 2189 }, { "epoch": 0.5685358255451713, "grad_norm": 6.646910667419434, "learning_rate": 4.280355637102483e-06, "loss": 0.16360945999622345, "step": 2190 }, { "epoch": 0.5687954309449637, "grad_norm": 4.5892229080200195, "learning_rate": 4.279662014891909e-06, "loss": 0.3484877943992615, "step": 2191 }, { "epoch": 0.569055036344756, "grad_norm": 7.175396919250488, "learning_rate": 4.2789681222721155e-06, "loss": 0.3932071924209595, "step": 2192 }, { "epoch": 0.5693146417445483, "grad_norm": 3.411170244216919, "learning_rate": 4.278273959365768e-06, "loss": 0.321115106344223, "step": 2193 }, { "epoch": 0.5695742471443406, "grad_norm": 7.982096195220947, "learning_rate": 4.277579526295575e-06, "loss": 0.3112480640411377, "step": 2194 }, { "epoch": 0.5698338525441329, "grad_norm": 5.898558616638184, "learning_rate": 4.2768848231843e-06, "loss": 0.3978562355041504, "step": 2195 }, { "epoch": 0.5700934579439252, "grad_norm": 3.1182973384857178, "learning_rate": 4.27618985015475e-06, "loss": 0.3952854871749878, "step": 2196 }, { "epoch": 0.5703530633437176, "grad_norm": 6.347334861755371, "learning_rate": 4.275494607329778e-06, "loss": 0.3511177897453308, "step": 2197 }, { "epoch": 0.5706126687435099, "grad_norm": 4.908451557159424, "learning_rate": 4.27479909483229e-06, "loss": 0.318437397480011, "step": 2198 }, { "epoch": 0.5708722741433022, "grad_norm": 9.295195579528809, "learning_rate": 4.274103312785235e-06, "loss": 0.38272833824157715, "step": 2199 }, { "epoch": 0.5711318795430945, "grad_norm": 6.3721232414245605, "learning_rate": 4.27340726131161e-06, "loss": 0.3503730893135071, "step": 2200 }, { "epoch": 0.5713914849428868, "grad_norm": 5.955994606018066, "learning_rate": 4.272710940534465e-06, "loss": 0.37525755167007446, "step": 2201 }, { "epoch": 0.5716510903426791, "grad_norm": 4.160092353820801, "learning_rate": 4.27201435057689e-06, "loss": 0.34542378783226013, "step": 2202 }, { "epoch": 0.5719106957424714, "grad_norm": 2.7724432945251465, "learning_rate": 4.271317491562028e-06, "loss": 0.3204669952392578, "step": 2203 }, { "epoch": 0.5721703011422637, "grad_norm": 2.6783297061920166, "learning_rate": 4.270620363613066e-06, "loss": 0.34504416584968567, "step": 2204 }, { "epoch": 0.572429906542056, "grad_norm": 6.462103843688965, "learning_rate": 4.269922966853242e-06, "loss": 0.23106631636619568, "step": 2205 }, { "epoch": 0.5726895119418484, "grad_norm": 3.3266892433166504, "learning_rate": 4.269225301405838e-06, "loss": 0.33810120820999146, "step": 2206 }, { "epoch": 0.5729491173416407, "grad_norm": 5.312996864318848, "learning_rate": 4.268527367394188e-06, "loss": 0.3967660963535309, "step": 2207 }, { "epoch": 0.573208722741433, "grad_norm": 5.966437339782715, "learning_rate": 4.267829164941669e-06, "loss": 0.32816195487976074, "step": 2208 }, { "epoch": 0.5734683281412254, "grad_norm": 4.787424564361572, "learning_rate": 4.267130694171706e-06, "loss": 0.3450429439544678, "step": 2209 }, { "epoch": 0.5737279335410177, "grad_norm": 6.85829496383667, "learning_rate": 4.266431955207774e-06, "loss": 0.3982638716697693, "step": 2210 }, { "epoch": 0.57398753894081, "grad_norm": 7.981616973876953, "learning_rate": 4.265732948173395e-06, "loss": 0.338273823261261, "step": 2211 }, { "epoch": 0.5742471443406023, "grad_norm": 4.388020992279053, "learning_rate": 4.265033673192136e-06, "loss": 0.3619858920574188, "step": 2212 }, { "epoch": 0.5745067497403946, "grad_norm": 7.987864971160889, "learning_rate": 4.264334130387614e-06, "loss": 0.36047419905662537, "step": 2213 }, { "epoch": 0.5747663551401869, "grad_norm": 6.579910755157471, "learning_rate": 4.26363431988349e-06, "loss": 0.405236154794693, "step": 2214 }, { "epoch": 0.5750259605399792, "grad_norm": 8.229434967041016, "learning_rate": 4.262934241803477e-06, "loss": 0.33389049768447876, "step": 2215 }, { "epoch": 0.5752855659397715, "grad_norm": 4.523291110992432, "learning_rate": 4.2622338962713315e-06, "loss": 0.3321370482444763, "step": 2216 }, { "epoch": 0.5755451713395638, "grad_norm": 10.042624473571777, "learning_rate": 4.261533283410858e-06, "loss": 0.37556523084640503, "step": 2217 }, { "epoch": 0.5758047767393562, "grad_norm": 4.231428146362305, "learning_rate": 4.26083240334591e-06, "loss": 0.34977179765701294, "step": 2218 }, { "epoch": 0.5760643821391485, "grad_norm": 2.5969321727752686, "learning_rate": 4.260131256200387e-06, "loss": 0.3687884211540222, "step": 2219 }, { "epoch": 0.5763239875389408, "grad_norm": 7.043548583984375, "learning_rate": 4.259429842098235e-06, "loss": 0.3226698637008667, "step": 2220 }, { "epoch": 0.5765835929387332, "grad_norm": 5.080862522125244, "learning_rate": 4.258728161163448e-06, "loss": 0.33676350116729736, "step": 2221 }, { "epoch": 0.5768431983385255, "grad_norm": 6.509128093719482, "learning_rate": 4.258026213520067e-06, "loss": 0.3729029595851898, "step": 2222 }, { "epoch": 0.5771028037383178, "grad_norm": 6.3983564376831055, "learning_rate": 4.257323999292182e-06, "loss": 0.4136315882205963, "step": 2223 }, { "epoch": 0.5773624091381101, "grad_norm": 3.4356725215911865, "learning_rate": 4.256621518603926e-06, "loss": 0.3129759430885315, "step": 2224 }, { "epoch": 0.5776220145379024, "grad_norm": 6.571971893310547, "learning_rate": 4.255918771579482e-06, "loss": 0.37077486515045166, "step": 2225 }, { "epoch": 0.5778816199376947, "grad_norm": 6.056186676025391, "learning_rate": 4.255215758343082e-06, "loss": 0.3364145755767822, "step": 2226 }, { "epoch": 0.578141225337487, "grad_norm": 6.040012359619141, "learning_rate": 4.2545124790189995e-06, "loss": 0.35203227400779724, "step": 2227 }, { "epoch": 0.5784008307372793, "grad_norm": 5.781042098999023, "learning_rate": 4.2538089337315594e-06, "loss": 0.3900821805000305, "step": 2228 }, { "epoch": 0.5786604361370716, "grad_norm": 5.472891807556152, "learning_rate": 4.253105122605134e-06, "loss": 0.3324563503265381, "step": 2229 }, { "epoch": 0.5789200415368639, "grad_norm": 5.481311321258545, "learning_rate": 4.252401045764138e-06, "loss": 0.34565770626068115, "step": 2230 }, { "epoch": 0.5791796469366562, "grad_norm": 5.464287757873535, "learning_rate": 4.251696703333037e-06, "loss": 0.3323848843574524, "step": 2231 }, { "epoch": 0.5794392523364486, "grad_norm": 3.1315815448760986, "learning_rate": 4.250992095436345e-06, "loss": 0.353705495595932, "step": 2232 }, { "epoch": 0.579698857736241, "grad_norm": 4.926029205322266, "learning_rate": 4.250287222198618e-06, "loss": 0.32017073035240173, "step": 2233 }, { "epoch": 0.5799584631360333, "grad_norm": 3.063260316848755, "learning_rate": 4.249582083744461e-06, "loss": 0.3455771803855896, "step": 2234 }, { "epoch": 0.5802180685358256, "grad_norm": 8.394463539123535, "learning_rate": 4.248876680198529e-06, "loss": 0.34881505370140076, "step": 2235 }, { "epoch": 0.5804776739356179, "grad_norm": 4.393715858459473, "learning_rate": 4.248171011685519e-06, "loss": 0.3576321005821228, "step": 2236 }, { "epoch": 0.5807372793354102, "grad_norm": 4.938849449157715, "learning_rate": 4.247465078330177e-06, "loss": 0.31526774168014526, "step": 2237 }, { "epoch": 0.5809968847352025, "grad_norm": 7.852706432342529, "learning_rate": 4.246758880257299e-06, "loss": 0.3498382568359375, "step": 2238 }, { "epoch": 0.5812564901349948, "grad_norm": 2.6935367584228516, "learning_rate": 4.24605241759172e-06, "loss": 0.35387927293777466, "step": 2239 }, { "epoch": 0.5815160955347871, "grad_norm": 4.203397274017334, "learning_rate": 4.245345690458329e-06, "loss": 0.303256094455719, "step": 2240 }, { "epoch": 0.5817757009345794, "grad_norm": 7.636551856994629, "learning_rate": 4.244638698982059e-06, "loss": 0.27720558643341064, "step": 2241 }, { "epoch": 0.5820353063343717, "grad_norm": 3.729282855987549, "learning_rate": 4.243931443287889e-06, "loss": 0.32945549488067627, "step": 2242 }, { "epoch": 0.582294911734164, "grad_norm": 4.300685882568359, "learning_rate": 4.243223923500846e-06, "loss": 0.3320115804672241, "step": 2243 }, { "epoch": 0.5825545171339563, "grad_norm": 2.7030231952667236, "learning_rate": 4.2425161397460055e-06, "loss": 0.33426353335380554, "step": 2244 }, { "epoch": 0.5828141225337488, "grad_norm": 5.548990726470947, "learning_rate": 4.241808092148485e-06, "loss": 0.3527759313583374, "step": 2245 }, { "epoch": 0.5830737279335411, "grad_norm": 5.218124866485596, "learning_rate": 4.241099780833451e-06, "loss": 0.26396262645721436, "step": 2246 }, { "epoch": 0.5833333333333334, "grad_norm": 2.483875036239624, "learning_rate": 4.240391205926118e-06, "loss": 0.3377290368080139, "step": 2247 }, { "epoch": 0.5835929387331257, "grad_norm": 3.230426788330078, "learning_rate": 4.239682367551745e-06, "loss": 0.36727964878082275, "step": 2248 }, { "epoch": 0.583852544132918, "grad_norm": 3.6234350204467773, "learning_rate": 4.238973265835639e-06, "loss": 0.32895156741142273, "step": 2249 }, { "epoch": 0.5841121495327103, "grad_norm": 4.297674655914307, "learning_rate": 4.238263900903152e-06, "loss": 0.35933536291122437, "step": 2250 }, { "epoch": 0.5843717549325026, "grad_norm": 2.562973976135254, "learning_rate": 4.2375542728796835e-06, "loss": 0.35990309715270996, "step": 2251 }, { "epoch": 0.5846313603322949, "grad_norm": 4.577208995819092, "learning_rate": 4.236844381890681e-06, "loss": 0.30480873584747314, "step": 2252 }, { "epoch": 0.5848909657320872, "grad_norm": 2.4523515701293945, "learning_rate": 4.236134228061636e-06, "loss": 0.3836563229560852, "step": 2253 }, { "epoch": 0.5851505711318795, "grad_norm": 3.7912347316741943, "learning_rate": 4.235423811518087e-06, "loss": 0.28660276532173157, "step": 2254 }, { "epoch": 0.5854101765316718, "grad_norm": 8.544589042663574, "learning_rate": 4.2347131323856195e-06, "loss": 0.3681766390800476, "step": 2255 }, { "epoch": 0.5856697819314641, "grad_norm": 7.479752540588379, "learning_rate": 4.234002190789867e-06, "loss": 0.3214144706726074, "step": 2256 }, { "epoch": 0.5859293873312564, "grad_norm": 3.5955748558044434, "learning_rate": 4.233290986856504e-06, "loss": 0.3193932771682739, "step": 2257 }, { "epoch": 0.5861889927310489, "grad_norm": 4.641018390655518, "learning_rate": 4.23257952071126e-06, "loss": 0.33719760179519653, "step": 2258 }, { "epoch": 0.5864485981308412, "grad_norm": 9.844422340393066, "learning_rate": 4.231867792479902e-06, "loss": 0.301805317401886, "step": 2259 }, { "epoch": 0.5867082035306335, "grad_norm": 1.9739149808883667, "learning_rate": 4.2311558022882485e-06, "loss": 0.3497903645038605, "step": 2260 }, { "epoch": 0.5869678089304258, "grad_norm": 4.083166122436523, "learning_rate": 4.2304435502621635e-06, "loss": 0.3206367492675781, "step": 2261 }, { "epoch": 0.5872274143302181, "grad_norm": 2.581089496612549, "learning_rate": 4.229731036527556e-06, "loss": 0.3413611054420471, "step": 2262 }, { "epoch": 0.5874870197300104, "grad_norm": 2.8956425189971924, "learning_rate": 4.229018261210383e-06, "loss": 0.35947465896606445, "step": 2263 }, { "epoch": 0.5877466251298027, "grad_norm": 6.6976423263549805, "learning_rate": 4.2283052244366465e-06, "loss": 0.35057780146598816, "step": 2264 }, { "epoch": 0.588006230529595, "grad_norm": 7.425684928894043, "learning_rate": 4.227591926332394e-06, "loss": 0.3619864583015442, "step": 2265 }, { "epoch": 0.5882658359293873, "grad_norm": 7.489083290100098, "learning_rate": 4.226878367023724e-06, "loss": 0.33006733655929565, "step": 2266 }, { "epoch": 0.5885254413291796, "grad_norm": 2.559170961380005, "learning_rate": 4.226164546636772e-06, "loss": 0.3680758774280548, "step": 2267 }, { "epoch": 0.5887850467289719, "grad_norm": 3.454261541366577, "learning_rate": 4.2254504652977285e-06, "loss": 0.3683934807777405, "step": 2268 }, { "epoch": 0.5890446521287642, "grad_norm": 7.148316860198975, "learning_rate": 4.224736123132826e-06, "loss": 0.23678641021251678, "step": 2269 }, { "epoch": 0.5893042575285566, "grad_norm": 9.061856269836426, "learning_rate": 4.224021520268345e-06, "loss": 0.34709569811820984, "step": 2270 }, { "epoch": 0.589563862928349, "grad_norm": 4.0831804275512695, "learning_rate": 4.2233066568306084e-06, "loss": 0.36434274911880493, "step": 2271 }, { "epoch": 0.5898234683281413, "grad_norm": 9.442937850952148, "learning_rate": 4.22259153294599e-06, "loss": 0.3634567856788635, "step": 2272 }, { "epoch": 0.5900830737279336, "grad_norm": 3.60640811920166, "learning_rate": 4.221876148740906e-06, "loss": 0.34751468896865845, "step": 2273 }, { "epoch": 0.5903426791277259, "grad_norm": 7.154349327087402, "learning_rate": 4.221160504341821e-06, "loss": 0.3469536304473877, "step": 2274 }, { "epoch": 0.5906022845275182, "grad_norm": 4.05644416809082, "learning_rate": 4.220444599875243e-06, "loss": 0.30809247493743896, "step": 2275 }, { "epoch": 0.5908618899273105, "grad_norm": 5.847764015197754, "learning_rate": 4.219728435467729e-06, "loss": 0.334394246339798, "step": 2276 }, { "epoch": 0.5911214953271028, "grad_norm": 5.728611469268799, "learning_rate": 4.21901201124588e-06, "loss": 0.36543378233909607, "step": 2277 }, { "epoch": 0.5913811007268951, "grad_norm": 9.493387222290039, "learning_rate": 4.2182953273363445e-06, "loss": 0.29710572957992554, "step": 2278 }, { "epoch": 0.5916407061266874, "grad_norm": 9.482949256896973, "learning_rate": 4.217578383865813e-06, "loss": 0.2440991997718811, "step": 2279 }, { "epoch": 0.5919003115264797, "grad_norm": 6.764925956726074, "learning_rate": 4.216861180961026e-06, "loss": 0.3570413291454315, "step": 2280 }, { "epoch": 0.592159916926272, "grad_norm": 6.020168304443359, "learning_rate": 4.21614371874877e-06, "loss": 0.32367485761642456, "step": 2281 }, { "epoch": 0.5924195223260644, "grad_norm": 6.3086724281311035, "learning_rate": 4.215425997355875e-06, "loss": 0.33510035276412964, "step": 2282 }, { "epoch": 0.5926791277258567, "grad_norm": 7.245692253112793, "learning_rate": 4.214708016909216e-06, "loss": 0.20161768794059753, "step": 2283 }, { "epoch": 0.592938733125649, "grad_norm": 10.43326473236084, "learning_rate": 4.213989777535719e-06, "loss": 0.27885571122169495, "step": 2284 }, { "epoch": 0.5931983385254413, "grad_norm": 3.140660285949707, "learning_rate": 4.2132712793623485e-06, "loss": 0.32850727438926697, "step": 2285 }, { "epoch": 0.5934579439252337, "grad_norm": 4.1044182777404785, "learning_rate": 4.2125525225161205e-06, "loss": 0.33981144428253174, "step": 2286 }, { "epoch": 0.593717549325026, "grad_norm": 9.673297882080078, "learning_rate": 4.211833507124095e-06, "loss": 0.28389665484428406, "step": 2287 }, { "epoch": 0.5939771547248183, "grad_norm": 9.825828552246094, "learning_rate": 4.211114233313377e-06, "loss": 0.3789229393005371, "step": 2288 }, { "epoch": 0.5942367601246106, "grad_norm": 3.918830156326294, "learning_rate": 4.2103947012111176e-06, "loss": 0.32997429370880127, "step": 2289 }, { "epoch": 0.5944963655244029, "grad_norm": 3.1225016117095947, "learning_rate": 4.209674910944513e-06, "loss": 0.34798312187194824, "step": 2290 }, { "epoch": 0.5947559709241952, "grad_norm": 4.636140823364258, "learning_rate": 4.208954862640807e-06, "loss": 0.30780988931655884, "step": 2291 }, { "epoch": 0.5950155763239875, "grad_norm": 3.68346905708313, "learning_rate": 4.208234556427288e-06, "loss": 0.3280426263809204, "step": 2292 }, { "epoch": 0.5952751817237798, "grad_norm": 7.2355122566223145, "learning_rate": 4.207513992431286e-06, "loss": 0.40822869539260864, "step": 2293 }, { "epoch": 0.5955347871235722, "grad_norm": 5.183229923248291, "learning_rate": 4.206793170780185e-06, "loss": 0.31157052516937256, "step": 2294 }, { "epoch": 0.5957943925233645, "grad_norm": 7.189670562744141, "learning_rate": 4.206072091601406e-06, "loss": 0.44345855712890625, "step": 2295 }, { "epoch": 0.5960539979231568, "grad_norm": 5.2006144523620605, "learning_rate": 4.2053507550224224e-06, "loss": 0.36559760570526123, "step": 2296 }, { "epoch": 0.5963136033229491, "grad_norm": 5.999999523162842, "learning_rate": 4.204629161170747e-06, "loss": 0.3190068006515503, "step": 2297 }, { "epoch": 0.5965732087227414, "grad_norm": 3.334054946899414, "learning_rate": 4.2039073101739434e-06, "loss": 0.29349634051322937, "step": 2298 }, { "epoch": 0.5968328141225338, "grad_norm": 4.338716983795166, "learning_rate": 4.203185202159617e-06, "loss": 0.32736289501190186, "step": 2299 }, { "epoch": 0.5970924195223261, "grad_norm": 6.627211570739746, "learning_rate": 4.202462837255421e-06, "loss": 0.35160714387893677, "step": 2300 }, { "epoch": 0.5973520249221184, "grad_norm": 3.0221450328826904, "learning_rate": 4.201740215589051e-06, "loss": 0.3152666687965393, "step": 2301 }, { "epoch": 0.5976116303219107, "grad_norm": 7.32452392578125, "learning_rate": 4.201017337288253e-06, "loss": 0.3293278217315674, "step": 2302 }, { "epoch": 0.597871235721703, "grad_norm": 5.1773505210876465, "learning_rate": 4.2002942024808125e-06, "loss": 0.35608336329460144, "step": 2303 }, { "epoch": 0.5981308411214953, "grad_norm": 2.808333396911621, "learning_rate": 4.199570811294564e-06, "loss": 0.28653156757354736, "step": 2304 }, { "epoch": 0.5983904465212876, "grad_norm": 1.6214686632156372, "learning_rate": 4.198847163857388e-06, "loss": 0.37644895911216736, "step": 2305 }, { "epoch": 0.59865005192108, "grad_norm": 5.2184553146362305, "learning_rate": 4.1981232602972075e-06, "loss": 0.29580140113830566, "step": 2306 }, { "epoch": 0.5989096573208723, "grad_norm": 3.603668689727783, "learning_rate": 4.197399100741991e-06, "loss": 0.34655430912971497, "step": 2307 }, { "epoch": 0.5991692627206646, "grad_norm": 6.015984058380127, "learning_rate": 4.196674685319755e-06, "loss": 0.38106417655944824, "step": 2308 }, { "epoch": 0.5994288681204569, "grad_norm": 3.6764001846313477, "learning_rate": 4.19595001415856e-06, "loss": 0.32101303339004517, "step": 2309 }, { "epoch": 0.5996884735202492, "grad_norm": 3.049039125442505, "learning_rate": 4.19522508738651e-06, "loss": 0.3689619302749634, "step": 2310 }, { "epoch": 0.5999480789200415, "grad_norm": 3.6592040061950684, "learning_rate": 4.194499905131755e-06, "loss": 0.3256945312023163, "step": 2311 }, { "epoch": 0.6002076843198338, "grad_norm": 3.647172451019287, "learning_rate": 4.1937744675224925e-06, "loss": 0.3224126100540161, "step": 2312 }, { "epoch": 0.6004672897196262, "grad_norm": 3.5297815799713135, "learning_rate": 4.193048774686961e-06, "loss": 0.31088414788246155, "step": 2313 }, { "epoch": 0.6007268951194185, "grad_norm": 6.890163898468018, "learning_rate": 4.192322826753449e-06, "loss": 0.2394341677427292, "step": 2314 }, { "epoch": 0.6009865005192108, "grad_norm": 3.3420586585998535, "learning_rate": 4.1915966238502855e-06, "loss": 0.3540811538696289, "step": 2315 }, { "epoch": 0.6012461059190031, "grad_norm": 6.351218223571777, "learning_rate": 4.1908701661058465e-06, "loss": 0.2714214324951172, "step": 2316 }, { "epoch": 0.6015057113187954, "grad_norm": 4.670633792877197, "learning_rate": 4.190143453648554e-06, "loss": 0.31294968724250793, "step": 2317 }, { "epoch": 0.6017653167185878, "grad_norm": 6.2785162925720215, "learning_rate": 4.1894164866068745e-06, "loss": 0.2670730650424957, "step": 2318 }, { "epoch": 0.6020249221183801, "grad_norm": 4.223156452178955, "learning_rate": 4.188689265109318e-06, "loss": 0.32184210419654846, "step": 2319 }, { "epoch": 0.6022845275181724, "grad_norm": 6.848569393157959, "learning_rate": 4.187961789284441e-06, "loss": 0.3812180161476135, "step": 2320 }, { "epoch": 0.6025441329179647, "grad_norm": 8.116573333740234, "learning_rate": 4.187234059260845e-06, "loss": 0.2778923213481903, "step": 2321 }, { "epoch": 0.602803738317757, "grad_norm": 7.746269226074219, "learning_rate": 4.186506075167174e-06, "loss": 0.4368421733379364, "step": 2322 }, { "epoch": 0.6030633437175493, "grad_norm": 4.171141147613525, "learning_rate": 4.1857778371321225e-06, "loss": 0.3619633913040161, "step": 2323 }, { "epoch": 0.6033229491173416, "grad_norm": 8.322500228881836, "learning_rate": 4.185049345284423e-06, "loss": 0.40743690729141235, "step": 2324 }, { "epoch": 0.6035825545171339, "grad_norm": 2.6423380374908447, "learning_rate": 4.184320599752858e-06, "loss": 0.3178674578666687, "step": 2325 }, { "epoch": 0.6038421599169262, "grad_norm": 4.0508809089660645, "learning_rate": 4.183591600666253e-06, "loss": 0.284612774848938, "step": 2326 }, { "epoch": 0.6041017653167186, "grad_norm": 6.471649646759033, "learning_rate": 4.182862348153478e-06, "loss": 0.2786465585231781, "step": 2327 }, { "epoch": 0.6043613707165109, "grad_norm": 8.560372352600098, "learning_rate": 4.182132842343448e-06, "loss": 0.4332643449306488, "step": 2328 }, { "epoch": 0.6046209761163032, "grad_norm": 8.082881927490234, "learning_rate": 4.181403083365122e-06, "loss": 0.23446522653102875, "step": 2329 }, { "epoch": 0.6048805815160956, "grad_norm": 4.857285499572754, "learning_rate": 4.180673071347506e-06, "loss": 0.34611713886260986, "step": 2330 }, { "epoch": 0.6051401869158879, "grad_norm": 9.545954704284668, "learning_rate": 4.17994280641965e-06, "loss": 0.38576334714889526, "step": 2331 }, { "epoch": 0.6053997923156802, "grad_norm": 4.202125549316406, "learning_rate": 4.179212288710646e-06, "loss": 0.35573139786720276, "step": 2332 }, { "epoch": 0.6056593977154725, "grad_norm": 4.975178241729736, "learning_rate": 4.178481518349634e-06, "loss": 0.36971884965896606, "step": 2333 }, { "epoch": 0.6059190031152648, "grad_norm": 2.7661631107330322, "learning_rate": 4.1777504954657975e-06, "loss": 0.3993336856365204, "step": 2334 }, { "epoch": 0.6061786085150571, "grad_norm": 7.720414638519287, "learning_rate": 4.1770192201883656e-06, "loss": 0.38248053193092346, "step": 2335 }, { "epoch": 0.6064382139148494, "grad_norm": 7.5883283615112305, "learning_rate": 4.17628769264661e-06, "loss": 0.413118839263916, "step": 2336 }, { "epoch": 0.6066978193146417, "grad_norm": 8.86955451965332, "learning_rate": 4.175555912969846e-06, "loss": 0.39345473051071167, "step": 2337 }, { "epoch": 0.606957424714434, "grad_norm": 3.3753459453582764, "learning_rate": 4.17482388128744e-06, "loss": 0.3074023723602295, "step": 2338 }, { "epoch": 0.6072170301142263, "grad_norm": 7.6445441246032715, "learning_rate": 4.174091597728793e-06, "loss": 0.3833739459514618, "step": 2339 }, { "epoch": 0.6074766355140186, "grad_norm": 6.381545066833496, "learning_rate": 4.173359062423361e-06, "loss": 0.3404807448387146, "step": 2340 }, { "epoch": 0.607736240913811, "grad_norm": 2.797419548034668, "learning_rate": 4.172626275500637e-06, "loss": 0.33216971158981323, "step": 2341 }, { "epoch": 0.6079958463136034, "grad_norm": 2.9701929092407227, "learning_rate": 4.171893237090161e-06, "loss": 0.34131258726119995, "step": 2342 }, { "epoch": 0.6082554517133957, "grad_norm": 8.102046966552734, "learning_rate": 4.171159947321519e-06, "loss": 0.3078620433807373, "step": 2343 }, { "epoch": 0.608515057113188, "grad_norm": 3.867018461227417, "learning_rate": 4.170426406324337e-06, "loss": 0.31741780042648315, "step": 2344 }, { "epoch": 0.6087746625129803, "grad_norm": 3.3387913703918457, "learning_rate": 4.16969261422829e-06, "loss": 0.296018123626709, "step": 2345 }, { "epoch": 0.6090342679127726, "grad_norm": 3.3646185398101807, "learning_rate": 4.168958571163097e-06, "loss": 0.35404491424560547, "step": 2346 }, { "epoch": 0.6092938733125649, "grad_norm": 6.7094597816467285, "learning_rate": 4.168224277258517e-06, "loss": 0.32670310139656067, "step": 2347 }, { "epoch": 0.6095534787123572, "grad_norm": 8.867667198181152, "learning_rate": 4.167489732644358e-06, "loss": 0.47776225209236145, "step": 2348 }, { "epoch": 0.6098130841121495, "grad_norm": 9.530304908752441, "learning_rate": 4.166754937450471e-06, "loss": 0.3065824508666992, "step": 2349 }, { "epoch": 0.6100726895119418, "grad_norm": 7.583315849304199, "learning_rate": 4.1660198918067504e-06, "loss": 0.27098721265792847, "step": 2350 }, { "epoch": 0.6103322949117341, "grad_norm": 5.405821800231934, "learning_rate": 4.165284595843135e-06, "loss": 0.30963021516799927, "step": 2351 }, { "epoch": 0.6105919003115264, "grad_norm": 5.835495471954346, "learning_rate": 4.1645490496896085e-06, "loss": 0.3040151596069336, "step": 2352 }, { "epoch": 0.6108515057113187, "grad_norm": 9.27981948852539, "learning_rate": 4.1638132534762e-06, "loss": 0.28977417945861816, "step": 2353 }, { "epoch": 0.6111111111111112, "grad_norm": 6.542445659637451, "learning_rate": 4.163077207332979e-06, "loss": 0.34753894805908203, "step": 2354 }, { "epoch": 0.6113707165109035, "grad_norm": 6.117591857910156, "learning_rate": 4.1623409113900636e-06, "loss": 0.3653704822063446, "step": 2355 }, { "epoch": 0.6116303219106958, "grad_norm": 3.0803864002227783, "learning_rate": 4.161604365777613e-06, "loss": 0.32915037870407104, "step": 2356 }, { "epoch": 0.6118899273104881, "grad_norm": 9.979731559753418, "learning_rate": 4.160867570625833e-06, "loss": 0.2982148230075836, "step": 2357 }, { "epoch": 0.6121495327102804, "grad_norm": 4.472545146942139, "learning_rate": 4.16013052606497e-06, "loss": 0.34612858295440674, "step": 2358 }, { "epoch": 0.6124091381100727, "grad_norm": 4.396087169647217, "learning_rate": 4.159393232225318e-06, "loss": 0.33899930119514465, "step": 2359 }, { "epoch": 0.612668743509865, "grad_norm": 5.958179473876953, "learning_rate": 4.1586556892372135e-06, "loss": 0.38232678174972534, "step": 2360 }, { "epoch": 0.6129283489096573, "grad_norm": 3.826098918914795, "learning_rate": 4.157917897231037e-06, "loss": 0.32531988620758057, "step": 2361 }, { "epoch": 0.6131879543094496, "grad_norm": 6.386044025421143, "learning_rate": 4.157179856337214e-06, "loss": 0.41567087173461914, "step": 2362 }, { "epoch": 0.6134475597092419, "grad_norm": 7.1516313552856445, "learning_rate": 4.156441566686212e-06, "loss": 0.342014342546463, "step": 2363 }, { "epoch": 0.6137071651090342, "grad_norm": 7.374477386474609, "learning_rate": 4.155703028408544e-06, "loss": 0.36505773663520813, "step": 2364 }, { "epoch": 0.6139667705088265, "grad_norm": 6.6403117179870605, "learning_rate": 4.1549642416347676e-06, "loss": 0.3680807948112488, "step": 2365 }, { "epoch": 0.614226375908619, "grad_norm": 5.6066718101501465, "learning_rate": 4.154225206495482e-06, "loss": 0.3269347846508026, "step": 2366 }, { "epoch": 0.6144859813084113, "grad_norm": 5.965860843658447, "learning_rate": 4.153485923121332e-06, "loss": 0.36014676094055176, "step": 2367 }, { "epoch": 0.6147455867082036, "grad_norm": 8.602084159851074, "learning_rate": 4.152746391643008e-06, "loss": 0.3345829248428345, "step": 2368 }, { "epoch": 0.6150051921079959, "grad_norm": 10.094486236572266, "learning_rate": 4.152006612191239e-06, "loss": 0.2645454704761505, "step": 2369 }, { "epoch": 0.6152647975077882, "grad_norm": 6.3028974533081055, "learning_rate": 4.151266584896803e-06, "loss": 0.3481214642524719, "step": 2370 }, { "epoch": 0.6155244029075805, "grad_norm": 2.5049803256988525, "learning_rate": 4.1505263098905196e-06, "loss": 0.3378007709980011, "step": 2371 }, { "epoch": 0.6157840083073728, "grad_norm": 2.9429779052734375, "learning_rate": 4.149785787303253e-06, "loss": 0.36135780811309814, "step": 2372 }, { "epoch": 0.6160436137071651, "grad_norm": 6.129002571105957, "learning_rate": 4.14904501726591e-06, "loss": 0.36601483821868896, "step": 2373 }, { "epoch": 0.6163032191069574, "grad_norm": 7.62504768371582, "learning_rate": 4.148303999909441e-06, "loss": 0.36281275749206543, "step": 2374 }, { "epoch": 0.6165628245067497, "grad_norm": 6.616208553314209, "learning_rate": 4.147562735364842e-06, "loss": 0.35305750370025635, "step": 2375 }, { "epoch": 0.616822429906542, "grad_norm": 4.064519882202148, "learning_rate": 4.146821223763151e-06, "loss": 0.34878286719322205, "step": 2376 }, { "epoch": 0.6170820353063343, "grad_norm": 4.162723064422607, "learning_rate": 4.146079465235452e-06, "loss": 0.27954432368278503, "step": 2377 }, { "epoch": 0.6173416407061267, "grad_norm": 3.0757555961608887, "learning_rate": 4.145337459912868e-06, "loss": 0.3564755916595459, "step": 2378 }, { "epoch": 0.617601246105919, "grad_norm": 2.974301338195801, "learning_rate": 4.144595207926571e-06, "loss": 0.3018914461135864, "step": 2379 }, { "epoch": 0.6178608515057114, "grad_norm": 3.952824115753174, "learning_rate": 4.143852709407773e-06, "loss": 0.25701451301574707, "step": 2380 }, { "epoch": 0.6181204569055037, "grad_norm": 3.9604616165161133, "learning_rate": 4.143109964487731e-06, "loss": 0.3268059492111206, "step": 2381 }, { "epoch": 0.618380062305296, "grad_norm": 4.055233955383301, "learning_rate": 4.1423669732977455e-06, "loss": 0.30552157759666443, "step": 2382 }, { "epoch": 0.6186396677050883, "grad_norm": 4.930546283721924, "learning_rate": 4.1416237359691595e-06, "loss": 0.3160625100135803, "step": 2383 }, { "epoch": 0.6188992731048806, "grad_norm": 7.459299087524414, "learning_rate": 4.140880252633362e-06, "loss": 0.34105563163757324, "step": 2384 }, { "epoch": 0.6191588785046729, "grad_norm": 8.456650733947754, "learning_rate": 4.140136523421782e-06, "loss": 0.352370023727417, "step": 2385 }, { "epoch": 0.6194184839044652, "grad_norm": 2.648425817489624, "learning_rate": 4.139392548465895e-06, "loss": 0.34753602743148804, "step": 2386 }, { "epoch": 0.6196780893042575, "grad_norm": 8.61762809753418, "learning_rate": 4.138648327897216e-06, "loss": 0.25695285201072693, "step": 2387 }, { "epoch": 0.6199376947040498, "grad_norm": 3.306076765060425, "learning_rate": 4.137903861847311e-06, "loss": 0.3205874562263489, "step": 2388 }, { "epoch": 0.6201973001038421, "grad_norm": 2.338226556777954, "learning_rate": 4.137159150447782e-06, "loss": 0.3482781946659088, "step": 2389 }, { "epoch": 0.6204569055036345, "grad_norm": 7.598644256591797, "learning_rate": 4.136414193830276e-06, "loss": 0.31712615489959717, "step": 2390 }, { "epoch": 0.6207165109034268, "grad_norm": 10.33790397644043, "learning_rate": 4.135668992126485e-06, "loss": 0.29865753650665283, "step": 2391 }, { "epoch": 0.6209761163032191, "grad_norm": 7.8847246170043945, "learning_rate": 4.134923545468144e-06, "loss": 0.36676037311553955, "step": 2392 }, { "epoch": 0.6212357217030114, "grad_norm": 2.7318344116210938, "learning_rate": 4.134177853987032e-06, "loss": 0.348527193069458, "step": 2393 }, { "epoch": 0.6214953271028038, "grad_norm": 5.293981075286865, "learning_rate": 4.133431917814967e-06, "loss": 0.3015458583831787, "step": 2394 }, { "epoch": 0.6217549325025961, "grad_norm": 5.474769592285156, "learning_rate": 4.132685737083817e-06, "loss": 0.319536417722702, "step": 2395 }, { "epoch": 0.6220145379023884, "grad_norm": 6.850740432739258, "learning_rate": 4.131939311925486e-06, "loss": 0.21608564257621765, "step": 2396 }, { "epoch": 0.6222741433021807, "grad_norm": 7.382437229156494, "learning_rate": 4.131192642471929e-06, "loss": 0.26148003339767456, "step": 2397 }, { "epoch": 0.622533748701973, "grad_norm": 2.9015796184539795, "learning_rate": 4.130445728855137e-06, "loss": 0.338599294424057, "step": 2398 }, { "epoch": 0.6227933541017653, "grad_norm": 2.817629098892212, "learning_rate": 4.129698571207148e-06, "loss": 0.3593374192714691, "step": 2399 }, { "epoch": 0.6230529595015576, "grad_norm": 7.67690896987915, "learning_rate": 4.128951169660043e-06, "loss": 0.27419227361679077, "step": 2400 }, { "epoch": 0.6233125649013499, "grad_norm": 7.8108367919921875, "learning_rate": 4.1282035243459446e-06, "loss": 0.2939184308052063, "step": 2401 }, { "epoch": 0.6235721703011423, "grad_norm": 7.3770880699157715, "learning_rate": 4.1274556353970196e-06, "loss": 0.3488439917564392, "step": 2402 }, { "epoch": 0.6238317757009346, "grad_norm": 5.792477130889893, "learning_rate": 4.126707502945478e-06, "loss": 0.3594919443130493, "step": 2403 }, { "epoch": 0.6240913811007269, "grad_norm": 8.018189430236816, "learning_rate": 4.125959127123572e-06, "loss": 0.3509752154350281, "step": 2404 }, { "epoch": 0.6243509865005192, "grad_norm": 3.4550082683563232, "learning_rate": 4.125210508063599e-06, "loss": 0.3263411521911621, "step": 2405 }, { "epoch": 0.6246105919003115, "grad_norm": 3.2065913677215576, "learning_rate": 4.1244616458978945e-06, "loss": 0.3031631112098694, "step": 2406 }, { "epoch": 0.6248701973001038, "grad_norm": 2.5989158153533936, "learning_rate": 4.1237125407588434e-06, "loss": 0.3071833550930023, "step": 2407 }, { "epoch": 0.6251298026998962, "grad_norm": 7.632009506225586, "learning_rate": 4.1229631927788684e-06, "loss": 0.3522469401359558, "step": 2408 }, { "epoch": 0.6253894080996885, "grad_norm": 9.129480361938477, "learning_rate": 4.122213602090438e-06, "loss": 0.34655287861824036, "step": 2409 }, { "epoch": 0.6256490134994808, "grad_norm": 2.582334280014038, "learning_rate": 4.121463768826061e-06, "loss": 0.32407861948013306, "step": 2410 }, { "epoch": 0.6259086188992731, "grad_norm": 9.865705490112305, "learning_rate": 4.120713693118293e-06, "loss": 0.4155358672142029, "step": 2411 }, { "epoch": 0.6261682242990654, "grad_norm": 7.663102626800537, "learning_rate": 4.119963375099729e-06, "loss": 0.39205679297447205, "step": 2412 }, { "epoch": 0.6264278296988577, "grad_norm": 6.676271915435791, "learning_rate": 4.119212814903009e-06, "loss": 0.35360246896743774, "step": 2413 }, { "epoch": 0.6266874350986501, "grad_norm": 3.091705083847046, "learning_rate": 4.118462012660813e-06, "loss": 0.3274223804473877, "step": 2414 }, { "epoch": 0.6269470404984424, "grad_norm": 6.47527551651001, "learning_rate": 4.117710968505867e-06, "loss": 0.3336954116821289, "step": 2415 }, { "epoch": 0.6272066458982347, "grad_norm": 4.627782344818115, "learning_rate": 4.116959682570938e-06, "loss": 0.3385609984397888, "step": 2416 }, { "epoch": 0.627466251298027, "grad_norm": 4.9991607666015625, "learning_rate": 4.1162081549888375e-06, "loss": 0.3510575592517853, "step": 2417 }, { "epoch": 0.6277258566978193, "grad_norm": 4.829471588134766, "learning_rate": 4.1154563858924164e-06, "loss": 0.28850650787353516, "step": 2418 }, { "epoch": 0.6279854620976116, "grad_norm": 10.389395713806152, "learning_rate": 4.114704375414572e-06, "loss": 0.3515781760215759, "step": 2419 }, { "epoch": 0.6282450674974039, "grad_norm": 4.968364715576172, "learning_rate": 4.1139521236882405e-06, "loss": 0.2783280611038208, "step": 2420 }, { "epoch": 0.6285046728971962, "grad_norm": 5.192104816436768, "learning_rate": 4.113199630846405e-06, "loss": 0.3463130593299866, "step": 2421 }, { "epoch": 0.6287642782969886, "grad_norm": 2.8886852264404297, "learning_rate": 4.112446897022086e-06, "loss": 0.3325861096382141, "step": 2422 }, { "epoch": 0.6290238836967809, "grad_norm": 8.474891662597656, "learning_rate": 4.111693922348353e-06, "loss": 0.27295440435409546, "step": 2423 }, { "epoch": 0.6292834890965732, "grad_norm": 7.015961647033691, "learning_rate": 4.110940706958313e-06, "loss": 0.2933773994445801, "step": 2424 }, { "epoch": 0.6295430944963655, "grad_norm": 3.240461826324463, "learning_rate": 4.110187250985117e-06, "loss": 0.32714521884918213, "step": 2425 }, { "epoch": 0.6298026998961579, "grad_norm": 5.6848344802856445, "learning_rate": 4.10943355456196e-06, "loss": 0.34628090262413025, "step": 2426 }, { "epoch": 0.6300623052959502, "grad_norm": 3.470036745071411, "learning_rate": 4.108679617822077e-06, "loss": 0.3452421724796295, "step": 2427 }, { "epoch": 0.6303219106957425, "grad_norm": 3.2938995361328125, "learning_rate": 4.107925440898747e-06, "loss": 0.348415732383728, "step": 2428 }, { "epoch": 0.6305815160955348, "grad_norm": 7.156288146972656, "learning_rate": 4.107171023925292e-06, "loss": 0.38203608989715576, "step": 2429 }, { "epoch": 0.6308411214953271, "grad_norm": 2.7610361576080322, "learning_rate": 4.106416367035075e-06, "loss": 0.35662388801574707, "step": 2430 }, { "epoch": 0.6311007268951194, "grad_norm": 10.744914054870605, "learning_rate": 4.1056614703615015e-06, "loss": 0.32914382219314575, "step": 2431 }, { "epoch": 0.6313603322949117, "grad_norm": 8.904333114624023, "learning_rate": 4.1049063340380205e-06, "loss": 0.22341105341911316, "step": 2432 }, { "epoch": 0.631619937694704, "grad_norm": 4.325235366821289, "learning_rate": 4.104150958198123e-06, "loss": 0.33111056685447693, "step": 2433 }, { "epoch": 0.6318795430944963, "grad_norm": 7.6804609298706055, "learning_rate": 4.103395342975343e-06, "loss": 0.32966944575309753, "step": 2434 }, { "epoch": 0.6321391484942886, "grad_norm": 3.854677677154541, "learning_rate": 4.102639488503254e-06, "loss": 0.3298600912094116, "step": 2435 }, { "epoch": 0.632398753894081, "grad_norm": 7.440173625946045, "learning_rate": 4.101883394915475e-06, "loss": 0.17730043828487396, "step": 2436 }, { "epoch": 0.6326583592938733, "grad_norm": 9.153301239013672, "learning_rate": 4.101127062345666e-06, "loss": 0.3271061182022095, "step": 2437 }, { "epoch": 0.6329179646936657, "grad_norm": 6.8643059730529785, "learning_rate": 4.100370490927529e-06, "loss": 0.3096931278705597, "step": 2438 }, { "epoch": 0.633177570093458, "grad_norm": 4.06552791595459, "learning_rate": 4.0996136807948085e-06, "loss": 0.3360443711280823, "step": 2439 }, { "epoch": 0.6334371754932503, "grad_norm": 5.431007385253906, "learning_rate": 4.0988566320812915e-06, "loss": 0.3068235218524933, "step": 2440 }, { "epoch": 0.6336967808930426, "grad_norm": 3.933539390563965, "learning_rate": 4.098099344920806e-06, "loss": 0.3010520935058594, "step": 2441 }, { "epoch": 0.6339563862928349, "grad_norm": 6.6259050369262695, "learning_rate": 4.097341819447224e-06, "loss": 0.37828826904296875, "step": 2442 }, { "epoch": 0.6342159916926272, "grad_norm": 6.4788689613342285, "learning_rate": 4.096584055794459e-06, "loss": 0.26487210392951965, "step": 2443 }, { "epoch": 0.6344755970924195, "grad_norm": 6.125831127166748, "learning_rate": 4.095826054096465e-06, "loss": 0.3192579746246338, "step": 2444 }, { "epoch": 0.6347352024922118, "grad_norm": 10.84037971496582, "learning_rate": 4.09506781448724e-06, "loss": 0.40140193700790405, "step": 2445 }, { "epoch": 0.6349948078920041, "grad_norm": 8.220819473266602, "learning_rate": 4.094309337100823e-06, "loss": 0.30340492725372314, "step": 2446 }, { "epoch": 0.6352544132917964, "grad_norm": 3.1432039737701416, "learning_rate": 4.093550622071296e-06, "loss": 0.31956690549850464, "step": 2447 }, { "epoch": 0.6355140186915887, "grad_norm": 9.322043418884277, "learning_rate": 4.092791669532784e-06, "loss": 0.32056283950805664, "step": 2448 }, { "epoch": 0.635773624091381, "grad_norm": 3.13401460647583, "learning_rate": 4.0920324796194485e-06, "loss": 0.3447343707084656, "step": 2449 }, { "epoch": 0.6360332294911735, "grad_norm": 8.332501411437988, "learning_rate": 4.091273052465501e-06, "loss": 0.3576911985874176, "step": 2450 }, { "epoch": 0.6362928348909658, "grad_norm": 4.165661811828613, "learning_rate": 4.090513388205187e-06, "loss": 0.3003813326358795, "step": 2451 }, { "epoch": 0.6365524402907581, "grad_norm": 11.282734870910645, "learning_rate": 4.0897534869728e-06, "loss": 0.31230831146240234, "step": 2452 }, { "epoch": 0.6368120456905504, "grad_norm": 7.416577339172363, "learning_rate": 4.088993348902673e-06, "loss": 0.2973179519176483, "step": 2453 }, { "epoch": 0.6370716510903427, "grad_norm": 10.089622497558594, "learning_rate": 4.0882329741291815e-06, "loss": 0.44441401958465576, "step": 2454 }, { "epoch": 0.637331256490135, "grad_norm": 4.373473644256592, "learning_rate": 4.087472362786741e-06, "loss": 0.3288571238517761, "step": 2455 }, { "epoch": 0.6375908618899273, "grad_norm": 4.43070650100708, "learning_rate": 4.086711515009811e-06, "loss": 0.3420923352241516, "step": 2456 }, { "epoch": 0.6378504672897196, "grad_norm": 5.055431365966797, "learning_rate": 4.085950430932892e-06, "loss": 0.36797046661376953, "step": 2457 }, { "epoch": 0.6381100726895119, "grad_norm": 3.8621816635131836, "learning_rate": 4.085189110690526e-06, "loss": 0.32770150899887085, "step": 2458 }, { "epoch": 0.6383696780893042, "grad_norm": 6.899590492248535, "learning_rate": 4.084427554417296e-06, "loss": 0.30502942204475403, "step": 2459 }, { "epoch": 0.6386292834890965, "grad_norm": 4.123472213745117, "learning_rate": 4.08366576224783e-06, "loss": 0.28924238681793213, "step": 2460 }, { "epoch": 0.6388888888888888, "grad_norm": 6.527901649475098, "learning_rate": 4.082903734316793e-06, "loss": 0.3939235806465149, "step": 2461 }, { "epoch": 0.6391484942886813, "grad_norm": 7.444573402404785, "learning_rate": 4.082141470758896e-06, "loss": 0.32063835859298706, "step": 2462 }, { "epoch": 0.6394080996884736, "grad_norm": 9.269742965698242, "learning_rate": 4.081378971708889e-06, "loss": 0.3223039209842682, "step": 2463 }, { "epoch": 0.6396677050882659, "grad_norm": 10.414433479309082, "learning_rate": 4.080616237301563e-06, "loss": 0.3621061444282532, "step": 2464 }, { "epoch": 0.6399273104880582, "grad_norm": 4.980473518371582, "learning_rate": 4.079853267671755e-06, "loss": 0.313160240650177, "step": 2465 }, { "epoch": 0.6401869158878505, "grad_norm": 8.565773963928223, "learning_rate": 4.079090062954339e-06, "loss": 0.21858403086662292, "step": 2466 }, { "epoch": 0.6404465212876428, "grad_norm": 4.110352993011475, "learning_rate": 4.078326623284231e-06, "loss": 0.35039353370666504, "step": 2467 }, { "epoch": 0.6407061266874351, "grad_norm": 9.300946235656738, "learning_rate": 4.077562948796391e-06, "loss": 0.307138592004776, "step": 2468 }, { "epoch": 0.6409657320872274, "grad_norm": 6.085049152374268, "learning_rate": 4.076799039625819e-06, "loss": 0.19978094100952148, "step": 2469 }, { "epoch": 0.6412253374870197, "grad_norm": 8.5566987991333, "learning_rate": 4.076034895907556e-06, "loss": 0.34931373596191406, "step": 2470 }, { "epoch": 0.641484942886812, "grad_norm": 4.499106407165527, "learning_rate": 4.075270517776686e-06, "loss": 0.3130737543106079, "step": 2471 }, { "epoch": 0.6417445482866043, "grad_norm": 6.410663604736328, "learning_rate": 4.0745059053683325e-06, "loss": 0.20250147581100464, "step": 2472 }, { "epoch": 0.6420041536863966, "grad_norm": 4.620729923248291, "learning_rate": 4.073741058817663e-06, "loss": 0.3103942275047302, "step": 2473 }, { "epoch": 0.642263759086189, "grad_norm": 5.022600173950195, "learning_rate": 4.072975978259883e-06, "loss": 0.32560038566589355, "step": 2474 }, { "epoch": 0.6425233644859814, "grad_norm": 9.990958213806152, "learning_rate": 4.072210663830243e-06, "loss": 0.26450031995773315, "step": 2475 }, { "epoch": 0.6427829698857737, "grad_norm": 6.4186015129089355, "learning_rate": 4.0714451156640314e-06, "loss": 0.3858366012573242, "step": 2476 }, { "epoch": 0.643042575285566, "grad_norm": 5.044713973999023, "learning_rate": 4.070679333896582e-06, "loss": 0.33817344903945923, "step": 2477 }, { "epoch": 0.6433021806853583, "grad_norm": 7.912944793701172, "learning_rate": 4.069913318663264e-06, "loss": 0.359377384185791, "step": 2478 }, { "epoch": 0.6435617860851506, "grad_norm": 4.970251083374023, "learning_rate": 4.069147070099495e-06, "loss": 0.34930574893951416, "step": 2479 }, { "epoch": 0.6438213914849429, "grad_norm": 2.7781291007995605, "learning_rate": 4.068380588340728e-06, "loss": 0.31761807203292847, "step": 2480 }, { "epoch": 0.6440809968847352, "grad_norm": 2.134077787399292, "learning_rate": 4.067613873522459e-06, "loss": 0.3443428874015808, "step": 2481 }, { "epoch": 0.6443406022845275, "grad_norm": 8.310761451721191, "learning_rate": 4.066846925780226e-06, "loss": 0.29753345251083374, "step": 2482 }, { "epoch": 0.6446002076843198, "grad_norm": 3.6051065921783447, "learning_rate": 4.06607974524961e-06, "loss": 0.331936776638031, "step": 2483 }, { "epoch": 0.6448598130841121, "grad_norm": 4.615748405456543, "learning_rate": 4.065312332066229e-06, "loss": 0.338500052690506, "step": 2484 }, { "epoch": 0.6451194184839044, "grad_norm": 3.84820294380188, "learning_rate": 4.064544686365744e-06, "loss": 0.3363666534423828, "step": 2485 }, { "epoch": 0.6453790238836968, "grad_norm": 8.40056037902832, "learning_rate": 4.063776808283857e-06, "loss": 0.28681671619415283, "step": 2486 }, { "epoch": 0.6456386292834891, "grad_norm": 3.2089078426361084, "learning_rate": 4.0630086979563125e-06, "loss": 0.2952520251274109, "step": 2487 }, { "epoch": 0.6458982346832814, "grad_norm": 4.257599830627441, "learning_rate": 4.062240355518895e-06, "loss": 0.3248385787010193, "step": 2488 }, { "epoch": 0.6461578400830738, "grad_norm": 2.7495570182800293, "learning_rate": 4.061471781107427e-06, "loss": 0.34331390261650085, "step": 2489 }, { "epoch": 0.6464174454828661, "grad_norm": 7.345691204071045, "learning_rate": 4.060702974857778e-06, "loss": 0.4144839644432068, "step": 2490 }, { "epoch": 0.6466770508826584, "grad_norm": 4.530089855194092, "learning_rate": 4.059933936905854e-06, "loss": 0.34641149640083313, "step": 2491 }, { "epoch": 0.6469366562824507, "grad_norm": 2.759171962738037, "learning_rate": 4.059164667387603e-06, "loss": 0.35216283798217773, "step": 2492 }, { "epoch": 0.647196261682243, "grad_norm": 5.5373735427856445, "learning_rate": 4.058395166439015e-06, "loss": 0.2852635681629181, "step": 2493 }, { "epoch": 0.6474558670820353, "grad_norm": 4.729726314544678, "learning_rate": 4.05762543419612e-06, "loss": 0.3887569308280945, "step": 2494 }, { "epoch": 0.6477154724818276, "grad_norm": 2.6139965057373047, "learning_rate": 4.056855470794988e-06, "loss": 0.35638153553009033, "step": 2495 }, { "epoch": 0.6479750778816199, "grad_norm": 2.501086950302124, "learning_rate": 4.0560852763717335e-06, "loss": 0.31490543484687805, "step": 2496 }, { "epoch": 0.6482346832814122, "grad_norm": 3.083724021911621, "learning_rate": 4.0553148510625065e-06, "loss": 0.30288806557655334, "step": 2497 }, { "epoch": 0.6484942886812046, "grad_norm": 3.9588844776153564, "learning_rate": 4.054544195003502e-06, "loss": 0.29866260290145874, "step": 2498 }, { "epoch": 0.6487538940809969, "grad_norm": 3.0614817142486572, "learning_rate": 4.053773308330953e-06, "loss": 0.37139368057250977, "step": 2499 }, { "epoch": 0.6490134994807892, "grad_norm": 3.399096727371216, "learning_rate": 4.053002191181137e-06, "loss": 0.33428123593330383, "step": 2500 }, { "epoch": 0.6492731048805815, "grad_norm": 8.651840209960938, "learning_rate": 4.052230843690367e-06, "loss": 0.2519874572753906, "step": 2501 }, { "epoch": 0.6495327102803738, "grad_norm": 7.071606636047363, "learning_rate": 4.051459265995001e-06, "loss": 0.3779914975166321, "step": 2502 }, { "epoch": 0.6497923156801662, "grad_norm": 7.29551887512207, "learning_rate": 4.050687458231437e-06, "loss": 0.22010979056358337, "step": 2503 }, { "epoch": 0.6500519210799585, "grad_norm": 3.7811481952667236, "learning_rate": 4.049915420536112e-06, "loss": 0.28957605361938477, "step": 2504 }, { "epoch": 0.6503115264797508, "grad_norm": 4.362481117248535, "learning_rate": 4.049143153045505e-06, "loss": 0.3292616009712219, "step": 2505 }, { "epoch": 0.6505711318795431, "grad_norm": 5.1608428955078125, "learning_rate": 4.048370655896135e-06, "loss": 0.3111330270767212, "step": 2506 }, { "epoch": 0.6508307372793354, "grad_norm": 3.227114200592041, "learning_rate": 4.047597929224561e-06, "loss": 0.3515481650829315, "step": 2507 }, { "epoch": 0.6510903426791277, "grad_norm": 7.13957405090332, "learning_rate": 4.0468249731673845e-06, "loss": 0.2916203737258911, "step": 2508 }, { "epoch": 0.65134994807892, "grad_norm": 9.278000831604004, "learning_rate": 4.046051787861247e-06, "loss": 0.3757617473602295, "step": 2509 }, { "epoch": 0.6516095534787124, "grad_norm": 3.6301002502441406, "learning_rate": 4.045278373442828e-06, "loss": 0.3389647603034973, "step": 2510 }, { "epoch": 0.6518691588785047, "grad_norm": 3.840616464614868, "learning_rate": 4.04450473004885e-06, "loss": 0.3158912658691406, "step": 2511 }, { "epoch": 0.652128764278297, "grad_norm": 7.906988143920898, "learning_rate": 4.043730857816077e-06, "loss": 0.37390345335006714, "step": 2512 }, { "epoch": 0.6523883696780893, "grad_norm": 2.6721839904785156, "learning_rate": 4.042956756881311e-06, "loss": 0.330922394990921, "step": 2513 }, { "epoch": 0.6526479750778816, "grad_norm": 7.3968634605407715, "learning_rate": 4.042182427381395e-06, "loss": 0.3304350972175598, "step": 2514 }, { "epoch": 0.6529075804776739, "grad_norm": 7.299001216888428, "learning_rate": 4.041407869453212e-06, "loss": 0.3200218081474304, "step": 2515 }, { "epoch": 0.6531671858774662, "grad_norm": 8.252583503723145, "learning_rate": 4.0406330832336885e-06, "loss": 0.34246522188186646, "step": 2516 }, { "epoch": 0.6534267912772586, "grad_norm": 5.36100435256958, "learning_rate": 4.039858068859787e-06, "loss": 0.36331093311309814, "step": 2517 }, { "epoch": 0.6536863966770509, "grad_norm": 2.56915020942688, "learning_rate": 4.039082826468511e-06, "loss": 0.3340567350387573, "step": 2518 }, { "epoch": 0.6539460020768432, "grad_norm": 2.7925806045532227, "learning_rate": 4.03830735619691e-06, "loss": 0.3362952768802643, "step": 2519 }, { "epoch": 0.6542056074766355, "grad_norm": 3.3447177410125732, "learning_rate": 4.037531658182065e-06, "loss": 0.34130406379699707, "step": 2520 }, { "epoch": 0.6544652128764278, "grad_norm": 4.5379438400268555, "learning_rate": 4.036755732561103e-06, "loss": 0.2879318594932556, "step": 2521 }, { "epoch": 0.6547248182762202, "grad_norm": 3.4215657711029053, "learning_rate": 4.035979579471192e-06, "loss": 0.35872188210487366, "step": 2522 }, { "epoch": 0.6549844236760125, "grad_norm": 3.136849880218506, "learning_rate": 4.035203199049536e-06, "loss": 0.30129244923591614, "step": 2523 }, { "epoch": 0.6552440290758048, "grad_norm": 4.137152671813965, "learning_rate": 4.0344265914333805e-06, "loss": 0.28087469935417175, "step": 2524 }, { "epoch": 0.6555036344755971, "grad_norm": 8.223304748535156, "learning_rate": 4.033649756760014e-06, "loss": 0.23933076858520508, "step": 2525 }, { "epoch": 0.6557632398753894, "grad_norm": 6.175085544586182, "learning_rate": 4.032872695166763e-06, "loss": 0.38493290543556213, "step": 2526 }, { "epoch": 0.6560228452751817, "grad_norm": 2.712491035461426, "learning_rate": 4.032095406790992e-06, "loss": 0.3168244957923889, "step": 2527 }, { "epoch": 0.656282450674974, "grad_norm": 8.659340858459473, "learning_rate": 4.031317891770109e-06, "loss": 0.37947261333465576, "step": 2528 }, { "epoch": 0.6565420560747663, "grad_norm": 7.90275764465332, "learning_rate": 4.030540150241563e-06, "loss": 0.3614569306373596, "step": 2529 }, { "epoch": 0.6568016614745587, "grad_norm": 2.285099744796753, "learning_rate": 4.029762182342836e-06, "loss": 0.3303183913230896, "step": 2530 }, { "epoch": 0.657061266874351, "grad_norm": 3.130901336669922, "learning_rate": 4.02898398821146e-06, "loss": 0.3483976423740387, "step": 2531 }, { "epoch": 0.6573208722741433, "grad_norm": 7.342230796813965, "learning_rate": 4.028205567984999e-06, "loss": 0.27168893814086914, "step": 2532 }, { "epoch": 0.6575804776739356, "grad_norm": 3.6542725563049316, "learning_rate": 4.0274269218010606e-06, "loss": 0.3374681770801544, "step": 2533 }, { "epoch": 0.657840083073728, "grad_norm": 3.7305760383605957, "learning_rate": 4.026648049797292e-06, "loss": 0.3244352638721466, "step": 2534 }, { "epoch": 0.6580996884735203, "grad_norm": 6.387324810028076, "learning_rate": 4.025868952111379e-06, "loss": 0.3579496145248413, "step": 2535 }, { "epoch": 0.6583592938733126, "grad_norm": 5.327479839324951, "learning_rate": 4.025089628881049e-06, "loss": 0.31146904826164246, "step": 2536 }, { "epoch": 0.6586188992731049, "grad_norm": 6.381228923797607, "learning_rate": 4.024310080244069e-06, "loss": 0.31734126806259155, "step": 2537 }, { "epoch": 0.6588785046728972, "grad_norm": 7.613063335418701, "learning_rate": 4.023530306338244e-06, "loss": 0.39189666509628296, "step": 2538 }, { "epoch": 0.6591381100726895, "grad_norm": 6.605711460113525, "learning_rate": 4.02275030730142e-06, "loss": 0.35107100009918213, "step": 2539 }, { "epoch": 0.6593977154724818, "grad_norm": 2.230379581451416, "learning_rate": 4.021970083271486e-06, "loss": 0.33423876762390137, "step": 2540 }, { "epoch": 0.6596573208722741, "grad_norm": 5.619781494140625, "learning_rate": 4.021189634386363e-06, "loss": 0.3117086887359619, "step": 2541 }, { "epoch": 0.6599169262720664, "grad_norm": 6.388324737548828, "learning_rate": 4.0204089607840204e-06, "loss": 0.3357692360877991, "step": 2542 }, { "epoch": 0.6601765316718587, "grad_norm": 2.480140447616577, "learning_rate": 4.019628062602462e-06, "loss": 0.35518813133239746, "step": 2543 }, { "epoch": 0.660436137071651, "grad_norm": 2.79907488822937, "learning_rate": 4.018846939979732e-06, "loss": 0.3201768696308136, "step": 2544 }, { "epoch": 0.6606957424714434, "grad_norm": 4.231306076049805, "learning_rate": 4.018065593053917e-06, "loss": 0.28522008657455444, "step": 2545 }, { "epoch": 0.6609553478712358, "grad_norm": 5.36696195602417, "learning_rate": 4.01728402196314e-06, "loss": 0.3287312984466553, "step": 2546 }, { "epoch": 0.6612149532710281, "grad_norm": 6.524415969848633, "learning_rate": 4.016502226845564e-06, "loss": 0.29299721121788025, "step": 2547 }, { "epoch": 0.6614745586708204, "grad_norm": 4.3133544921875, "learning_rate": 4.015720207839394e-06, "loss": 0.2965812087059021, "step": 2548 }, { "epoch": 0.6617341640706127, "grad_norm": 4.7893524169921875, "learning_rate": 4.014937965082871e-06, "loss": 0.3193790316581726, "step": 2549 }, { "epoch": 0.661993769470405, "grad_norm": 3.2172341346740723, "learning_rate": 4.014155498714281e-06, "loss": 0.30622348189353943, "step": 2550 }, { "epoch": 0.6622533748701973, "grad_norm": 6.805437088012695, "learning_rate": 4.0133728088719425e-06, "loss": 0.29801902174949646, "step": 2551 }, { "epoch": 0.6625129802699896, "grad_norm": 6.973002910614014, "learning_rate": 4.0125898956942195e-06, "loss": 0.2911819517612457, "step": 2552 }, { "epoch": 0.6627725856697819, "grad_norm": 4.075840950012207, "learning_rate": 4.011806759319513e-06, "loss": 0.34031474590301514, "step": 2553 }, { "epoch": 0.6630321910695742, "grad_norm": 8.42811393737793, "learning_rate": 4.011023399886262e-06, "loss": 0.2669587731361389, "step": 2554 }, { "epoch": 0.6632917964693665, "grad_norm": 9.092823028564453, "learning_rate": 4.010239817532947e-06, "loss": 0.34026116132736206, "step": 2555 }, { "epoch": 0.6635514018691588, "grad_norm": 8.601698875427246, "learning_rate": 4.009456012398089e-06, "loss": 0.3520546555519104, "step": 2556 }, { "epoch": 0.6638110072689511, "grad_norm": 7.6183319091796875, "learning_rate": 4.008671984620246e-06, "loss": 0.37643054127693176, "step": 2557 }, { "epoch": 0.6640706126687436, "grad_norm": 8.284773826599121, "learning_rate": 4.007887734338016e-06, "loss": 0.3827401399612427, "step": 2558 }, { "epoch": 0.6643302180685359, "grad_norm": 8.896693229675293, "learning_rate": 4.007103261690035e-06, "loss": 0.2113659679889679, "step": 2559 }, { "epoch": 0.6645898234683282, "grad_norm": 5.456121444702148, "learning_rate": 4.006318566814982e-06, "loss": 0.34621623158454895, "step": 2560 }, { "epoch": 0.6648494288681205, "grad_norm": 4.404480457305908, "learning_rate": 4.005533649851573e-06, "loss": 0.28355804085731506, "step": 2561 }, { "epoch": 0.6651090342679128, "grad_norm": 8.272794723510742, "learning_rate": 4.004748510938562e-06, "loss": 0.39221182465553284, "step": 2562 }, { "epoch": 0.6653686396677051, "grad_norm": 8.256567001342773, "learning_rate": 4.003963150214743e-06, "loss": 0.35062387585639954, "step": 2563 }, { "epoch": 0.6656282450674974, "grad_norm": 3.118058681488037, "learning_rate": 4.003177567818952e-06, "loss": 0.28379157185554504, "step": 2564 }, { "epoch": 0.6658878504672897, "grad_norm": 5.746425628662109, "learning_rate": 4.002391763890062e-06, "loss": 0.3352375030517578, "step": 2565 }, { "epoch": 0.666147455867082, "grad_norm": 9.36815071105957, "learning_rate": 4.001605738566983e-06, "loss": 0.2796403765678406, "step": 2566 }, { "epoch": 0.6664070612668743, "grad_norm": 8.210277557373047, "learning_rate": 4.000819491988667e-06, "loss": 0.2633998990058899, "step": 2567 }, { "epoch": 0.6666666666666666, "grad_norm": 2.698838233947754, "learning_rate": 4.000033024294105e-06, "loss": 0.3028698265552521, "step": 2568 }, { "epoch": 0.6669262720664589, "grad_norm": 3.9329073429107666, "learning_rate": 3.999246335622327e-06, "loss": 0.32651621103286743, "step": 2569 }, { "epoch": 0.6671858774662512, "grad_norm": 4.617372512817383, "learning_rate": 3.9984594261124e-06, "loss": 0.31241631507873535, "step": 2570 }, { "epoch": 0.6674454828660437, "grad_norm": 3.101355791091919, "learning_rate": 3.997672295903433e-06, "loss": 0.3543844521045685, "step": 2571 }, { "epoch": 0.667705088265836, "grad_norm": 6.823626518249512, "learning_rate": 3.996884945134572e-06, "loss": 0.2265743464231491, "step": 2572 }, { "epoch": 0.6679646936656283, "grad_norm": 8.493046760559082, "learning_rate": 3.996097373945003e-06, "loss": 0.39547502994537354, "step": 2573 }, { "epoch": 0.6682242990654206, "grad_norm": 8.97276496887207, "learning_rate": 3.995309582473949e-06, "loss": 0.26538634300231934, "step": 2574 }, { "epoch": 0.6684839044652129, "grad_norm": 8.688188552856445, "learning_rate": 3.994521570860676e-06, "loss": 0.34946927428245544, "step": 2575 }, { "epoch": 0.6687435098650052, "grad_norm": 3.868516683578491, "learning_rate": 3.993733339244484e-06, "loss": 0.3313429355621338, "step": 2576 }, { "epoch": 0.6690031152647975, "grad_norm": 5.850308895111084, "learning_rate": 3.992944887764715e-06, "loss": 0.32413536310195923, "step": 2577 }, { "epoch": 0.6692627206645898, "grad_norm": 3.503746747970581, "learning_rate": 3.9921562165607494e-06, "loss": 0.36005449295043945, "step": 2578 }, { "epoch": 0.6695223260643821, "grad_norm": 5.32078218460083, "learning_rate": 3.991367325772007e-06, "loss": 0.311268150806427, "step": 2579 }, { "epoch": 0.6697819314641744, "grad_norm": 7.512322425842285, "learning_rate": 3.990578215537945e-06, "loss": 0.27128860354423523, "step": 2580 }, { "epoch": 0.6700415368639667, "grad_norm": 8.641524314880371, "learning_rate": 3.98978888599806e-06, "loss": 0.3610469698905945, "step": 2581 }, { "epoch": 0.670301142263759, "grad_norm": 7.548431873321533, "learning_rate": 3.988999337291887e-06, "loss": 0.30355381965637207, "step": 2582 }, { "epoch": 0.6705607476635514, "grad_norm": 9.084489822387695, "learning_rate": 3.988209569559001e-06, "loss": 0.2108740657567978, "step": 2583 }, { "epoch": 0.6708203530633438, "grad_norm": 4.319596767425537, "learning_rate": 3.987419582939014e-06, "loss": 0.30407023429870605, "step": 2584 }, { "epoch": 0.6710799584631361, "grad_norm": 4.655062675476074, "learning_rate": 3.986629377571579e-06, "loss": 0.3783068060874939, "step": 2585 }, { "epoch": 0.6713395638629284, "grad_norm": 5.8237504959106445, "learning_rate": 3.985838953596383e-06, "loss": 0.29830026626586914, "step": 2586 }, { "epoch": 0.6715991692627207, "grad_norm": 5.669497489929199, "learning_rate": 3.985048311153158e-06, "loss": 0.3805500864982605, "step": 2587 }, { "epoch": 0.671858774662513, "grad_norm": 8.279289245605469, "learning_rate": 3.98425745038167e-06, "loss": 0.35706865787506104, "step": 2588 }, { "epoch": 0.6721183800623053, "grad_norm": 5.872347831726074, "learning_rate": 3.983466371421727e-06, "loss": 0.2605457305908203, "step": 2589 }, { "epoch": 0.6723779854620976, "grad_norm": 2.771860122680664, "learning_rate": 3.982675074413171e-06, "loss": 0.2976481020450592, "step": 2590 }, { "epoch": 0.6726375908618899, "grad_norm": 7.007797718048096, "learning_rate": 3.981883559495886e-06, "loss": 0.37832558155059814, "step": 2591 }, { "epoch": 0.6728971962616822, "grad_norm": 7.9158830642700195, "learning_rate": 3.9810918268097945e-06, "loss": 0.31955432891845703, "step": 2592 }, { "epoch": 0.6731568016614745, "grad_norm": 12.287946701049805, "learning_rate": 3.980299876494857e-06, "loss": 0.333919882774353, "step": 2593 }, { "epoch": 0.6734164070612668, "grad_norm": 3.063068151473999, "learning_rate": 3.979507708691071e-06, "loss": 0.33248084783554077, "step": 2594 }, { "epoch": 0.6736760124610592, "grad_norm": 5.197213172912598, "learning_rate": 3.978715323538474e-06, "loss": 0.29414892196655273, "step": 2595 }, { "epoch": 0.6739356178608515, "grad_norm": 12.602152824401855, "learning_rate": 3.977922721177141e-06, "loss": 0.2712162733078003, "step": 2596 }, { "epoch": 0.6741952232606438, "grad_norm": 8.058186531066895, "learning_rate": 3.977129901747187e-06, "loss": 0.3238281011581421, "step": 2597 }, { "epoch": 0.6744548286604362, "grad_norm": 3.7136642932891846, "learning_rate": 3.976336865388765e-06, "loss": 0.3610742390155792, "step": 2598 }, { "epoch": 0.6747144340602285, "grad_norm": 2.984464645385742, "learning_rate": 3.975543612242063e-06, "loss": 0.348063200712204, "step": 2599 }, { "epoch": 0.6749740394600208, "grad_norm": 3.6718475818634033, "learning_rate": 3.974750142447312e-06, "loss": 0.32277435064315796, "step": 2600 }, { "epoch": 0.6752336448598131, "grad_norm": 4.373973846435547, "learning_rate": 3.97395645614478e-06, "loss": 0.2891371548175812, "step": 2601 }, { "epoch": 0.6754932502596054, "grad_norm": 7.1238579750061035, "learning_rate": 3.97316255347477e-06, "loss": 0.320731520652771, "step": 2602 }, { "epoch": 0.6757528556593977, "grad_norm": 7.373082637786865, "learning_rate": 3.972368434577628e-06, "loss": 0.3367016911506653, "step": 2603 }, { "epoch": 0.67601246105919, "grad_norm": 3.410918712615967, "learning_rate": 3.971574099593735e-06, "loss": 0.2943477928638458, "step": 2604 }, { "epoch": 0.6762720664589823, "grad_norm": 2.956984281539917, "learning_rate": 3.970779548663512e-06, "loss": 0.31635981798171997, "step": 2605 }, { "epoch": 0.6765316718587746, "grad_norm": 10.42543888092041, "learning_rate": 3.969984781927417e-06, "loss": 0.31702345609664917, "step": 2606 }, { "epoch": 0.676791277258567, "grad_norm": 5.973167419433594, "learning_rate": 3.969189799525946e-06, "loss": 0.3295087218284607, "step": 2607 }, { "epoch": 0.6770508826583593, "grad_norm": 9.384100914001465, "learning_rate": 3.9683946015996335e-06, "loss": 0.3403032720088959, "step": 2608 }, { "epoch": 0.6773104880581516, "grad_norm": 5.290361404418945, "learning_rate": 3.967599188289054e-06, "loss": 0.2663963735103607, "step": 2609 }, { "epoch": 0.677570093457944, "grad_norm": 5.052774906158447, "learning_rate": 3.966803559734818e-06, "loss": 0.33594077825546265, "step": 2610 }, { "epoch": 0.6778296988577363, "grad_norm": 4.17582893371582, "learning_rate": 3.966007716077572e-06, "loss": 0.3699631690979004, "step": 2611 }, { "epoch": 0.6780893042575286, "grad_norm": 9.480850219726562, "learning_rate": 3.965211657458006e-06, "loss": 0.34117066860198975, "step": 2612 }, { "epoch": 0.6783489096573209, "grad_norm": 7.366368293762207, "learning_rate": 3.964415384016843e-06, "loss": 0.3297448754310608, "step": 2613 }, { "epoch": 0.6786085150571132, "grad_norm": 6.125423431396484, "learning_rate": 3.963618895894847e-06, "loss": 0.3148707151412964, "step": 2614 }, { "epoch": 0.6788681204569055, "grad_norm": 5.741026878356934, "learning_rate": 3.962822193232818e-06, "loss": 0.2640247941017151, "step": 2615 }, { "epoch": 0.6791277258566978, "grad_norm": 13.693994522094727, "learning_rate": 3.9620252761715955e-06, "loss": 0.31700581312179565, "step": 2616 }, { "epoch": 0.6793873312564901, "grad_norm": 5.960350036621094, "learning_rate": 3.961228144852056e-06, "loss": 0.3486345410346985, "step": 2617 }, { "epoch": 0.6796469366562824, "grad_norm": 4.764342784881592, "learning_rate": 3.960430799415114e-06, "loss": 0.3461197018623352, "step": 2618 }, { "epoch": 0.6799065420560748, "grad_norm": 9.054594039916992, "learning_rate": 3.959633240001721e-06, "loss": 0.23939862847328186, "step": 2619 }, { "epoch": 0.6801661474558671, "grad_norm": 5.265802383422852, "learning_rate": 3.958835466752868e-06, "loss": 0.2738643288612366, "step": 2620 }, { "epoch": 0.6804257528556594, "grad_norm": 11.098971366882324, "learning_rate": 3.958037479809583e-06, "loss": 0.33372223377227783, "step": 2621 }, { "epoch": 0.6806853582554517, "grad_norm": 11.855712890625, "learning_rate": 3.957239279312934e-06, "loss": 0.2840711176395416, "step": 2622 }, { "epoch": 0.680944963655244, "grad_norm": 4.575098514556885, "learning_rate": 3.9564408654040206e-06, "loss": 0.3261733651161194, "step": 2623 }, { "epoch": 0.6812045690550363, "grad_norm": 4.78666353225708, "learning_rate": 3.955642238223987e-06, "loss": 0.3369854986667633, "step": 2624 }, { "epoch": 0.6814641744548287, "grad_norm": 8.693231582641602, "learning_rate": 3.954843397914011e-06, "loss": 0.2121257781982422, "step": 2625 }, { "epoch": 0.681723779854621, "grad_norm": 9.989075660705566, "learning_rate": 3.954044344615309e-06, "loss": 0.23478052020072937, "step": 2626 }, { "epoch": 0.6819833852544133, "grad_norm": 6.839006423950195, "learning_rate": 3.953245078469137e-06, "loss": 0.3052237033843994, "step": 2627 }, { "epoch": 0.6822429906542056, "grad_norm": 4.647641181945801, "learning_rate": 3.952445599616784e-06, "loss": 0.30037087202072144, "step": 2628 }, { "epoch": 0.6825025960539979, "grad_norm": 3.3461029529571533, "learning_rate": 3.951645908199583e-06, "loss": 0.3148265480995178, "step": 2629 }, { "epoch": 0.6827622014537902, "grad_norm": 3.916424512863159, "learning_rate": 3.950846004358899e-06, "loss": 0.3388400673866272, "step": 2630 }, { "epoch": 0.6830218068535826, "grad_norm": 6.55959939956665, "learning_rate": 3.950045888236137e-06, "loss": 0.3353137671947479, "step": 2631 }, { "epoch": 0.6832814122533749, "grad_norm": 4.270446300506592, "learning_rate": 3.949245559972739e-06, "loss": 0.3638981878757477, "step": 2632 }, { "epoch": 0.6835410176531672, "grad_norm": 4.936000347137451, "learning_rate": 3.9484450197101856e-06, "loss": 0.312782347202301, "step": 2633 }, { "epoch": 0.6838006230529595, "grad_norm": 2.9970192909240723, "learning_rate": 3.947644267589993e-06, "loss": 0.3508727252483368, "step": 2634 }, { "epoch": 0.6840602284527518, "grad_norm": 3.0352563858032227, "learning_rate": 3.946843303753716e-06, "loss": 0.3286130428314209, "step": 2635 }, { "epoch": 0.6843198338525441, "grad_norm": 6.928016662597656, "learning_rate": 3.946042128342948e-06, "loss": 0.351778507232666, "step": 2636 }, { "epoch": 0.6845794392523364, "grad_norm": 4.556210041046143, "learning_rate": 3.945240741499317e-06, "loss": 0.3210931718349457, "step": 2637 }, { "epoch": 0.6848390446521287, "grad_norm": 7.04144287109375, "learning_rate": 3.94443914336449e-06, "loss": 0.2490537464618683, "step": 2638 }, { "epoch": 0.685098650051921, "grad_norm": 7.8947553634643555, "learning_rate": 3.9436373340801724e-06, "loss": 0.33542323112487793, "step": 2639 }, { "epoch": 0.6853582554517134, "grad_norm": 8.042719841003418, "learning_rate": 3.9428353137881034e-06, "loss": 0.3641524016857147, "step": 2640 }, { "epoch": 0.6856178608515057, "grad_norm": 2.9306704998016357, "learning_rate": 3.942033082630064e-06, "loss": 0.31096330285072327, "step": 2641 }, { "epoch": 0.685877466251298, "grad_norm": 4.059353351593018, "learning_rate": 3.94123064074787e-06, "loss": 0.32119250297546387, "step": 2642 }, { "epoch": 0.6861370716510904, "grad_norm": 9.718823432922363, "learning_rate": 3.940427988283374e-06, "loss": 0.32003945112228394, "step": 2643 }, { "epoch": 0.6863966770508827, "grad_norm": 6.708807468414307, "learning_rate": 3.939625125378467e-06, "loss": 0.2723679542541504, "step": 2644 }, { "epoch": 0.686656282450675, "grad_norm": 7.526975154876709, "learning_rate": 3.938822052175076e-06, "loss": 0.30893099308013916, "step": 2645 }, { "epoch": 0.6869158878504673, "grad_norm": 5.438453674316406, "learning_rate": 3.9380187688151664e-06, "loss": 0.2901490032672882, "step": 2646 }, { "epoch": 0.6871754932502596, "grad_norm": 7.672667503356934, "learning_rate": 3.9372152754407415e-06, "loss": 0.30421680212020874, "step": 2647 }, { "epoch": 0.6874350986500519, "grad_norm": 7.057112216949463, "learning_rate": 3.936411572193839e-06, "loss": 0.2922493815422058, "step": 2648 }, { "epoch": 0.6876947040498442, "grad_norm": 3.583958387374878, "learning_rate": 3.9356076592165355e-06, "loss": 0.3592865765094757, "step": 2649 }, { "epoch": 0.6879543094496365, "grad_norm": 3.076672077178955, "learning_rate": 3.934803536650945e-06, "loss": 0.31186002492904663, "step": 2650 }, { "epoch": 0.6882139148494288, "grad_norm": 9.597038269042969, "learning_rate": 3.933999204639218e-06, "loss": 0.3644079864025116, "step": 2651 }, { "epoch": 0.6884735202492211, "grad_norm": 6.5841803550720215, "learning_rate": 3.933194663323541e-06, "loss": 0.28236809372901917, "step": 2652 }, { "epoch": 0.6887331256490135, "grad_norm": 7.387386798858643, "learning_rate": 3.93238991284614e-06, "loss": 0.29856306314468384, "step": 2653 }, { "epoch": 0.6889927310488058, "grad_norm": 11.63085651397705, "learning_rate": 3.931584953349274e-06, "loss": 0.2838893532752991, "step": 2654 }, { "epoch": 0.6892523364485982, "grad_norm": 3.362978458404541, "learning_rate": 3.930779784975244e-06, "loss": 0.30033403635025024, "step": 2655 }, { "epoch": 0.6895119418483905, "grad_norm": 6.931088447570801, "learning_rate": 3.929974407866384e-06, "loss": 0.29770562052726746, "step": 2656 }, { "epoch": 0.6897715472481828, "grad_norm": 8.55103874206543, "learning_rate": 3.929168822165067e-06, "loss": 0.30613988637924194, "step": 2657 }, { "epoch": 0.6900311526479751, "grad_norm": 9.974847793579102, "learning_rate": 3.9283630280137e-06, "loss": 0.2981482148170471, "step": 2658 }, { "epoch": 0.6902907580477674, "grad_norm": 6.738798141479492, "learning_rate": 3.927557025554733e-06, "loss": 0.26678842306137085, "step": 2659 }, { "epoch": 0.6905503634475597, "grad_norm": 9.737244606018066, "learning_rate": 3.926750814930645e-06, "loss": 0.27406108379364014, "step": 2660 }, { "epoch": 0.690809968847352, "grad_norm": 3.9931228160858154, "learning_rate": 3.925944396283957e-06, "loss": 0.36763688921928406, "step": 2661 }, { "epoch": 0.6910695742471443, "grad_norm": 8.973091125488281, "learning_rate": 3.9251377697572254e-06, "loss": 0.3366454243659973, "step": 2662 }, { "epoch": 0.6913291796469366, "grad_norm": 3.3567497730255127, "learning_rate": 3.9243309354930426e-06, "loss": 0.3380943536758423, "step": 2663 }, { "epoch": 0.6915887850467289, "grad_norm": 5.34902286529541, "learning_rate": 3.9235238936340405e-06, "loss": 0.24885955452919006, "step": 2664 }, { "epoch": 0.6918483904465212, "grad_norm": 3.1990902423858643, "learning_rate": 3.922716644322883e-06, "loss": 0.3082743287086487, "step": 2665 }, { "epoch": 0.6921079958463136, "grad_norm": 7.589498043060303, "learning_rate": 3.921909187702275e-06, "loss": 0.266104519367218, "step": 2666 }, { "epoch": 0.692367601246106, "grad_norm": 8.09836483001709, "learning_rate": 3.921101523914956e-06, "loss": 0.2938930094242096, "step": 2667 }, { "epoch": 0.6926272066458983, "grad_norm": 4.791653156280518, "learning_rate": 3.920293653103701e-06, "loss": 0.32129940390586853, "step": 2668 }, { "epoch": 0.6928868120456906, "grad_norm": 4.273577690124512, "learning_rate": 3.9194855754113245e-06, "loss": 0.4196903705596924, "step": 2669 }, { "epoch": 0.6931464174454829, "grad_norm": 8.655780792236328, "learning_rate": 3.918677290980678e-06, "loss": 0.3565971255302429, "step": 2670 }, { "epoch": 0.6934060228452752, "grad_norm": 7.229770660400391, "learning_rate": 3.917868799954644e-06, "loss": 0.2265188992023468, "step": 2671 }, { "epoch": 0.6936656282450675, "grad_norm": 3.185812473297119, "learning_rate": 3.9170601024761465e-06, "loss": 0.3161048889160156, "step": 2672 }, { "epoch": 0.6939252336448598, "grad_norm": 6.276147365570068, "learning_rate": 3.916251198688145e-06, "loss": 0.2899622321128845, "step": 2673 }, { "epoch": 0.6941848390446521, "grad_norm": 6.174062728881836, "learning_rate": 3.915442088733636e-06, "loss": 0.2105107307434082, "step": 2674 }, { "epoch": 0.6944444444444444, "grad_norm": 8.996543884277344, "learning_rate": 3.9146327727556504e-06, "loss": 0.3322332799434662, "step": 2675 }, { "epoch": 0.6947040498442367, "grad_norm": 7.323724746704102, "learning_rate": 3.913823250897257e-06, "loss": 0.32480692863464355, "step": 2676 }, { "epoch": 0.694963655244029, "grad_norm": 8.117177963256836, "learning_rate": 3.913013523301561e-06, "loss": 0.3171759247779846, "step": 2677 }, { "epoch": 0.6952232606438213, "grad_norm": 8.238717079162598, "learning_rate": 3.912203590111703e-06, "loss": 0.3814895451068878, "step": 2678 }, { "epoch": 0.6954828660436138, "grad_norm": 3.7793924808502197, "learning_rate": 3.911393451470863e-06, "loss": 0.3059905767440796, "step": 2679 }, { "epoch": 0.6957424714434061, "grad_norm": 4.260164737701416, "learning_rate": 3.910583107522251e-06, "loss": 0.3367055058479309, "step": 2680 }, { "epoch": 0.6960020768431984, "grad_norm": 3.840280294418335, "learning_rate": 3.90977255840912e-06, "loss": 0.36673563718795776, "step": 2681 }, { "epoch": 0.6962616822429907, "grad_norm": 10.008910179138184, "learning_rate": 3.9089618042747564e-06, "loss": 0.3268711566925049, "step": 2682 }, { "epoch": 0.696521287642783, "grad_norm": 8.277371406555176, "learning_rate": 3.908150845262483e-06, "loss": 0.28733569383621216, "step": 2683 }, { "epoch": 0.6967808930425753, "grad_norm": 10.338465690612793, "learning_rate": 3.907339681515657e-06, "loss": 0.27474647760391235, "step": 2684 }, { "epoch": 0.6970404984423676, "grad_norm": 5.809814453125, "learning_rate": 3.906528313177676e-06, "loss": 0.33912065625190735, "step": 2685 }, { "epoch": 0.6973001038421599, "grad_norm": 9.558116912841797, "learning_rate": 3.90571674039197e-06, "loss": 0.22919771075248718, "step": 2686 }, { "epoch": 0.6975597092419522, "grad_norm": 5.0338239669799805, "learning_rate": 3.904904963302007e-06, "loss": 0.2932897210121155, "step": 2687 }, { "epoch": 0.6978193146417445, "grad_norm": 9.535999298095703, "learning_rate": 3.904092982051289e-06, "loss": 0.19543758034706116, "step": 2688 }, { "epoch": 0.6980789200415368, "grad_norm": 8.257675170898438, "learning_rate": 3.903280796783358e-06, "loss": 0.2590647339820862, "step": 2689 }, { "epoch": 0.6983385254413291, "grad_norm": 8.250618934631348, "learning_rate": 3.902468407641788e-06, "loss": 0.34178829193115234, "step": 2690 }, { "epoch": 0.6985981308411215, "grad_norm": 8.30501651763916, "learning_rate": 3.901655814770193e-06, "loss": 0.3431852459907532, "step": 2691 }, { "epoch": 0.6988577362409139, "grad_norm": 8.159916877746582, "learning_rate": 3.900843018312218e-06, "loss": 0.22562722861766815, "step": 2692 }, { "epoch": 0.6991173416407062, "grad_norm": 4.684873104095459, "learning_rate": 3.90003001841155e-06, "loss": 0.3515438735485077, "step": 2693 }, { "epoch": 0.6993769470404985, "grad_norm": 7.181957721710205, "learning_rate": 3.899216815211905e-06, "loss": 0.3416045606136322, "step": 2694 }, { "epoch": 0.6996365524402908, "grad_norm": 4.969326496124268, "learning_rate": 3.898403408857042e-06, "loss": 0.30741724371910095, "step": 2695 }, { "epoch": 0.6998961578400831, "grad_norm": 6.894644260406494, "learning_rate": 3.897589799490749e-06, "loss": 0.3359134793281555, "step": 2696 }, { "epoch": 0.7001557632398754, "grad_norm": 5.087929725646973, "learning_rate": 3.8967759872568584e-06, "loss": 0.2887576222419739, "step": 2697 }, { "epoch": 0.7004153686396677, "grad_norm": 8.24668025970459, "learning_rate": 3.89596197229923e-06, "loss": 0.28690582513809204, "step": 2698 }, { "epoch": 0.70067497403946, "grad_norm": 4.4931640625, "learning_rate": 3.895147754761763e-06, "loss": 0.2943609952926636, "step": 2699 }, { "epoch": 0.7009345794392523, "grad_norm": 2.8703389167785645, "learning_rate": 3.894333334788395e-06, "loss": 0.3619137108325958, "step": 2700 }, { "epoch": 0.7011941848390446, "grad_norm": 8.906783103942871, "learning_rate": 3.893518712523094e-06, "loss": 0.2785770893096924, "step": 2701 }, { "epoch": 0.7014537902388369, "grad_norm": 8.91602897644043, "learning_rate": 3.8927038881098675e-06, "loss": 0.2640310227870941, "step": 2702 }, { "epoch": 0.7017133956386293, "grad_norm": 8.450770378112793, "learning_rate": 3.891888861692759e-06, "loss": 0.2592787742614746, "step": 2703 }, { "epoch": 0.7019730010384216, "grad_norm": 3.1866812705993652, "learning_rate": 3.891073633415845e-06, "loss": 0.2921825647354126, "step": 2704 }, { "epoch": 0.702232606438214, "grad_norm": 8.216004371643066, "learning_rate": 3.89025820342324e-06, "loss": 0.4071740508079529, "step": 2705 }, { "epoch": 0.7024922118380063, "grad_norm": 7.689459323883057, "learning_rate": 3.889442571859093e-06, "loss": 0.27891474962234497, "step": 2706 }, { "epoch": 0.7027518172377986, "grad_norm": 5.587665557861328, "learning_rate": 3.8886267388675885e-06, "loss": 0.31787437200546265, "step": 2707 }, { "epoch": 0.7030114226375909, "grad_norm": 4.279594421386719, "learning_rate": 3.887810704592949e-06, "loss": 0.3547498881816864, "step": 2708 }, { "epoch": 0.7032710280373832, "grad_norm": 3.6020641326904297, "learning_rate": 3.886994469179429e-06, "loss": 0.33156973123550415, "step": 2709 }, { "epoch": 0.7035306334371755, "grad_norm": 6.955546855926514, "learning_rate": 3.886178032771319e-06, "loss": 0.22540056705474854, "step": 2710 }, { "epoch": 0.7037902388369678, "grad_norm": 3.6359689235687256, "learning_rate": 3.8853613955129495e-06, "loss": 0.28765201568603516, "step": 2711 }, { "epoch": 0.7040498442367601, "grad_norm": 4.249972343444824, "learning_rate": 3.88454455754868e-06, "loss": 0.28525933623313904, "step": 2712 }, { "epoch": 0.7043094496365524, "grad_norm": 4.73268461227417, "learning_rate": 3.883727519022912e-06, "loss": 0.3206278383731842, "step": 2713 }, { "epoch": 0.7045690550363447, "grad_norm": 8.490235328674316, "learning_rate": 3.882910280080077e-06, "loss": 0.3039211630821228, "step": 2714 }, { "epoch": 0.7048286604361371, "grad_norm": 5.078009128570557, "learning_rate": 3.882092840864645e-06, "loss": 0.27599701285362244, "step": 2715 }, { "epoch": 0.7050882658359294, "grad_norm": 3.766091823577881, "learning_rate": 3.88127520152112e-06, "loss": 0.35946929454803467, "step": 2716 }, { "epoch": 0.7053478712357217, "grad_norm": 12.23863410949707, "learning_rate": 3.880457362194041e-06, "loss": 0.3113272786140442, "step": 2717 }, { "epoch": 0.705607476635514, "grad_norm": 4.3841352462768555, "learning_rate": 3.879639323027986e-06, "loss": 0.26667463779449463, "step": 2718 }, { "epoch": 0.7058670820353063, "grad_norm": 6.895863056182861, "learning_rate": 3.878821084167563e-06, "loss": 0.2526852488517761, "step": 2719 }, { "epoch": 0.7061266874350987, "grad_norm": 6.309176921844482, "learning_rate": 3.8780026457574195e-06, "loss": 0.2707745134830475, "step": 2720 }, { "epoch": 0.706386292834891, "grad_norm": 4.574375152587891, "learning_rate": 3.877184007942236e-06, "loss": 0.30595672130584717, "step": 2721 }, { "epoch": 0.7066458982346833, "grad_norm": 4.9104204177856445, "learning_rate": 3.8763651708667285e-06, "loss": 0.3086663484573364, "step": 2722 }, { "epoch": 0.7069055036344756, "grad_norm": 3.9033002853393555, "learning_rate": 3.8755461346756505e-06, "loss": 0.3333122432231903, "step": 2723 }, { "epoch": 0.7071651090342679, "grad_norm": 6.969695091247559, "learning_rate": 3.874726899513786e-06, "loss": 0.19441252946853638, "step": 2724 }, { "epoch": 0.7074247144340602, "grad_norm": 5.504904270172119, "learning_rate": 3.873907465525959e-06, "loss": 0.3123531639575958, "step": 2725 }, { "epoch": 0.7076843198338525, "grad_norm": 3.7606499195098877, "learning_rate": 3.873087832857026e-06, "loss": 0.31453847885131836, "step": 2726 }, { "epoch": 0.7079439252336449, "grad_norm": 8.29478931427002, "learning_rate": 3.8722680016518796e-06, "loss": 0.2868101894855499, "step": 2727 }, { "epoch": 0.7082035306334372, "grad_norm": 5.113729000091553, "learning_rate": 3.8714479720554475e-06, "loss": 0.2607365846633911, "step": 2728 }, { "epoch": 0.7084631360332295, "grad_norm": 6.426567077636719, "learning_rate": 3.870627744212691e-06, "loss": 0.22680775821208954, "step": 2729 }, { "epoch": 0.7087227414330218, "grad_norm": 3.745753049850464, "learning_rate": 3.869807318268609e-06, "loss": 0.3327738046646118, "step": 2730 }, { "epoch": 0.7089823468328141, "grad_norm": 3.9127533435821533, "learning_rate": 3.868986694368232e-06, "loss": 0.2893221974372864, "step": 2731 }, { "epoch": 0.7092419522326064, "grad_norm": 9.748130798339844, "learning_rate": 3.8681658726566305e-06, "loss": 0.28328025341033936, "step": 2732 }, { "epoch": 0.7095015576323987, "grad_norm": 6.394356727600098, "learning_rate": 3.8673448532789044e-06, "loss": 0.27085524797439575, "step": 2733 }, { "epoch": 0.7097611630321911, "grad_norm": 5.255858421325684, "learning_rate": 3.8665236363801915e-06, "loss": 0.27735644578933716, "step": 2734 }, { "epoch": 0.7100207684319834, "grad_norm": 11.885483741760254, "learning_rate": 3.865702222105666e-06, "loss": 0.19333143532276154, "step": 2735 }, { "epoch": 0.7102803738317757, "grad_norm": 9.919534683227539, "learning_rate": 3.8648806106005335e-06, "loss": 0.3487294614315033, "step": 2736 }, { "epoch": 0.710539979231568, "grad_norm": 7.5633392333984375, "learning_rate": 3.864058802010036e-06, "loss": 0.2904289960861206, "step": 2737 }, { "epoch": 0.7107995846313603, "grad_norm": 11.233528137207031, "learning_rate": 3.86323679647945e-06, "loss": 0.24014973640441895, "step": 2738 }, { "epoch": 0.7110591900311527, "grad_norm": 4.525427341461182, "learning_rate": 3.8624145941540896e-06, "loss": 0.30040156841278076, "step": 2739 }, { "epoch": 0.711318795430945, "grad_norm": 7.454717636108398, "learning_rate": 3.861592195179299e-06, "loss": 0.3080747723579407, "step": 2740 }, { "epoch": 0.7115784008307373, "grad_norm": 3.874720811843872, "learning_rate": 3.860769599700461e-06, "loss": 0.3066476583480835, "step": 2741 }, { "epoch": 0.7118380062305296, "grad_norm": 9.437897682189941, "learning_rate": 3.859946807862991e-06, "loss": 0.3238568902015686, "step": 2742 }, { "epoch": 0.7120976116303219, "grad_norm": 9.176191329956055, "learning_rate": 3.8591238198123395e-06, "loss": 0.2434917688369751, "step": 2743 }, { "epoch": 0.7123572170301142, "grad_norm": 9.619548797607422, "learning_rate": 3.8583006356939926e-06, "loss": 0.3039019703865051, "step": 2744 }, { "epoch": 0.7126168224299065, "grad_norm": 8.89979362487793, "learning_rate": 3.85747725565347e-06, "loss": 0.3098166286945343, "step": 2745 }, { "epoch": 0.7128764278296988, "grad_norm": 3.9698870182037354, "learning_rate": 3.856653679836326e-06, "loss": 0.3531225025653839, "step": 2746 }, { "epoch": 0.7131360332294912, "grad_norm": 3.8890931606292725, "learning_rate": 3.85582990838815e-06, "loss": 0.3605901002883911, "step": 2747 }, { "epoch": 0.7133956386292835, "grad_norm": 10.532821655273438, "learning_rate": 3.855005941454567e-06, "loss": 0.3965827226638794, "step": 2748 }, { "epoch": 0.7136552440290758, "grad_norm": 3.8469302654266357, "learning_rate": 3.854181779181235e-06, "loss": 0.29986655712127686, "step": 2749 }, { "epoch": 0.7139148494288681, "grad_norm": 7.301671981811523, "learning_rate": 3.853357421713847e-06, "loss": 0.1859714388847351, "step": 2750 }, { "epoch": 0.7141744548286605, "grad_norm": 3.7810635566711426, "learning_rate": 3.852532869198129e-06, "loss": 0.34031111001968384, "step": 2751 }, { "epoch": 0.7144340602284528, "grad_norm": 3.725578784942627, "learning_rate": 3.851708121779846e-06, "loss": 0.3127458095550537, "step": 2752 }, { "epoch": 0.7146936656282451, "grad_norm": 3.132255792617798, "learning_rate": 3.8508831796047925e-06, "loss": 0.34379303455352783, "step": 2753 }, { "epoch": 0.7149532710280374, "grad_norm": 4.666211128234863, "learning_rate": 3.850058042818799e-06, "loss": 0.3348623514175415, "step": 2754 }, { "epoch": 0.7152128764278297, "grad_norm": 2.3896892070770264, "learning_rate": 3.849232711567732e-06, "loss": 0.3231153190135956, "step": 2755 }, { "epoch": 0.715472481827622, "grad_norm": 8.466791152954102, "learning_rate": 3.848407185997491e-06, "loss": 0.35943523049354553, "step": 2756 }, { "epoch": 0.7157320872274143, "grad_norm": 4.278163433074951, "learning_rate": 3.847581466254009e-06, "loss": 0.32314932346343994, "step": 2757 }, { "epoch": 0.7159916926272066, "grad_norm": 7.948033809661865, "learning_rate": 3.846755552483256e-06, "loss": 0.24154609441757202, "step": 2758 }, { "epoch": 0.7162512980269989, "grad_norm": 3.2893424034118652, "learning_rate": 3.845929444831234e-06, "loss": 0.3087875247001648, "step": 2759 }, { "epoch": 0.7165109034267912, "grad_norm": 8.457123756408691, "learning_rate": 3.845103143443978e-06, "loss": 0.2788037061691284, "step": 2760 }, { "epoch": 0.7167705088265836, "grad_norm": 10.300225257873535, "learning_rate": 3.844276648467561e-06, "loss": 0.23829463124275208, "step": 2761 }, { "epoch": 0.7170301142263759, "grad_norm": 5.141012668609619, "learning_rate": 3.843449960048089e-06, "loss": 0.35911059379577637, "step": 2762 }, { "epoch": 0.7172897196261683, "grad_norm": 4.563177585601807, "learning_rate": 3.8426230783317e-06, "loss": 0.31662651896476746, "step": 2763 }, { "epoch": 0.7175493250259606, "grad_norm": 6.221364974975586, "learning_rate": 3.841796003464569e-06, "loss": 0.3552378714084625, "step": 2764 }, { "epoch": 0.7178089304257529, "grad_norm": 10.177115440368652, "learning_rate": 3.8409687355929035e-06, "loss": 0.2182801365852356, "step": 2765 }, { "epoch": 0.7180685358255452, "grad_norm": 9.90854263305664, "learning_rate": 3.840141274862945e-06, "loss": 0.3606598377227783, "step": 2766 }, { "epoch": 0.7183281412253375, "grad_norm": 5.050907135009766, "learning_rate": 3.83931362142097e-06, "loss": 0.30773240327835083, "step": 2767 }, { "epoch": 0.7185877466251298, "grad_norm": 8.133278846740723, "learning_rate": 3.83848577541329e-06, "loss": 0.24466970562934875, "step": 2768 }, { "epoch": 0.7188473520249221, "grad_norm": 7.145341873168945, "learning_rate": 3.837657736986246e-06, "loss": 0.2698323726654053, "step": 2769 }, { "epoch": 0.7191069574247144, "grad_norm": 4.106204986572266, "learning_rate": 3.8368295062862196e-06, "loss": 0.2982563078403473, "step": 2770 }, { "epoch": 0.7193665628245067, "grad_norm": 8.924750328063965, "learning_rate": 3.836001083459621e-06, "loss": 0.32984253764152527, "step": 2771 }, { "epoch": 0.719626168224299, "grad_norm": 10.454530715942383, "learning_rate": 3.835172468652897e-06, "loss": 0.26203495264053345, "step": 2772 }, { "epoch": 0.7198857736240913, "grad_norm": 3.5942318439483643, "learning_rate": 3.834343662012528e-06, "loss": 0.3298960328102112, "step": 2773 }, { "epoch": 0.7201453790238836, "grad_norm": 4.385974884033203, "learning_rate": 3.833514663685027e-06, "loss": 0.33799758553504944, "step": 2774 }, { "epoch": 0.7204049844236761, "grad_norm": 10.85119342803955, "learning_rate": 3.832685473816944e-06, "loss": 0.2756970524787903, "step": 2775 }, { "epoch": 0.7206645898234684, "grad_norm": 5.117369174957275, "learning_rate": 3.831856092554858e-06, "loss": 0.3844870924949646, "step": 2776 }, { "epoch": 0.7209241952232607, "grad_norm": 4.823635101318359, "learning_rate": 3.8310265200453865e-06, "loss": 0.26775041222572327, "step": 2777 }, { "epoch": 0.721183800623053, "grad_norm": 3.6997427940368652, "learning_rate": 3.830196756435179e-06, "loss": 0.32572680711746216, "step": 2778 }, { "epoch": 0.7214434060228453, "grad_norm": 7.543986797332764, "learning_rate": 3.829366801870917e-06, "loss": 0.24624603986740112, "step": 2779 }, { "epoch": 0.7217030114226376, "grad_norm": 3.2135531902313232, "learning_rate": 3.828536656499321e-06, "loss": 0.26697325706481934, "step": 2780 }, { "epoch": 0.7219626168224299, "grad_norm": 3.3375864028930664, "learning_rate": 3.827706320467137e-06, "loss": 0.310050904750824, "step": 2781 }, { "epoch": 0.7222222222222222, "grad_norm": 3.3981127738952637, "learning_rate": 3.826875793921152e-06, "loss": 0.303930401802063, "step": 2782 }, { "epoch": 0.7224818276220145, "grad_norm": 4.642174243927002, "learning_rate": 3.826045077008185e-06, "loss": 0.31197842955589294, "step": 2783 }, { "epoch": 0.7227414330218068, "grad_norm": 14.007144927978516, "learning_rate": 3.825214169875085e-06, "loss": 0.2421206682920456, "step": 2784 }, { "epoch": 0.7230010384215991, "grad_norm": 10.25511646270752, "learning_rate": 3.82438307266874e-06, "loss": 0.26743435859680176, "step": 2785 }, { "epoch": 0.7232606438213914, "grad_norm": 4.425293922424316, "learning_rate": 3.8235517855360685e-06, "loss": 0.3275769054889679, "step": 2786 }, { "epoch": 0.7235202492211839, "grad_norm": 4.016909122467041, "learning_rate": 3.822720308624021e-06, "loss": 0.3119441866874695, "step": 2787 }, { "epoch": 0.7237798546209762, "grad_norm": 7.250908374786377, "learning_rate": 3.821888642079586e-06, "loss": 0.21720822155475616, "step": 2788 }, { "epoch": 0.7240394600207685, "grad_norm": 5.678585052490234, "learning_rate": 3.821056786049781e-06, "loss": 0.3072463274002075, "step": 2789 }, { "epoch": 0.7242990654205608, "grad_norm": 10.052546501159668, "learning_rate": 3.8202247406816614e-06, "loss": 0.2719196081161499, "step": 2790 }, { "epoch": 0.7245586708203531, "grad_norm": 8.62768840789795, "learning_rate": 3.819392506122312e-06, "loss": 0.1875724345445633, "step": 2791 }, { "epoch": 0.7248182762201454, "grad_norm": 8.195952415466309, "learning_rate": 3.8185600825188526e-06, "loss": 0.43389031291007996, "step": 2792 }, { "epoch": 0.7250778816199377, "grad_norm": 5.927317142486572, "learning_rate": 3.817727470018439e-06, "loss": 0.3421080410480499, "step": 2793 }, { "epoch": 0.72533748701973, "grad_norm": 3.5928025245666504, "learning_rate": 3.816894668768255e-06, "loss": 0.2802497148513794, "step": 2794 }, { "epoch": 0.7255970924195223, "grad_norm": 4.528817653656006, "learning_rate": 3.816061678915523e-06, "loss": 0.3241894245147705, "step": 2795 }, { "epoch": 0.7258566978193146, "grad_norm": 8.351576805114746, "learning_rate": 3.815228500607495e-06, "loss": 0.23446065187454224, "step": 2796 }, { "epoch": 0.7261163032191069, "grad_norm": 9.363031387329102, "learning_rate": 3.8143951339914596e-06, "loss": 0.3098154366016388, "step": 2797 }, { "epoch": 0.7263759086188992, "grad_norm": 6.569129943847656, "learning_rate": 3.813561579214736e-06, "loss": 0.2938039302825928, "step": 2798 }, { "epoch": 0.7266355140186916, "grad_norm": 8.163849830627441, "learning_rate": 3.8127278364246766e-06, "loss": 0.21680831909179688, "step": 2799 }, { "epoch": 0.726895119418484, "grad_norm": 7.521075248718262, "learning_rate": 3.811893905768669e-06, "loss": 0.24444730579853058, "step": 2800 }, { "epoch": 0.7271547248182763, "grad_norm": 3.6372439861297607, "learning_rate": 3.811059787394133e-06, "loss": 0.31724613904953003, "step": 2801 }, { "epoch": 0.7274143302180686, "grad_norm": 8.106527328491211, "learning_rate": 3.8102254814485225e-06, "loss": 0.27662795782089233, "step": 2802 }, { "epoch": 0.7276739356178609, "grad_norm": 4.350475311279297, "learning_rate": 3.8093909880793223e-06, "loss": 0.28135257959365845, "step": 2803 }, { "epoch": 0.7279335410176532, "grad_norm": 3.4236292839050293, "learning_rate": 3.8085563074340513e-06, "loss": 0.33669790625572205, "step": 2804 }, { "epoch": 0.7281931464174455, "grad_norm": 10.165872573852539, "learning_rate": 3.8077214396602642e-06, "loss": 0.39830881357192993, "step": 2805 }, { "epoch": 0.7284527518172378, "grad_norm": 4.85352087020874, "learning_rate": 3.806886384905545e-06, "loss": 0.3267597556114197, "step": 2806 }, { "epoch": 0.7287123572170301, "grad_norm": 11.921640396118164, "learning_rate": 3.806051143317512e-06, "loss": 0.3462767004966736, "step": 2807 }, { "epoch": 0.7289719626168224, "grad_norm": 8.4683837890625, "learning_rate": 3.805215715043818e-06, "loss": 0.21409273147583008, "step": 2808 }, { "epoch": 0.7292315680166147, "grad_norm": 4.8008503913879395, "learning_rate": 3.8043801002321457e-06, "loss": 0.32453155517578125, "step": 2809 }, { "epoch": 0.729491173416407, "grad_norm": 10.872644424438477, "learning_rate": 3.8035442990302145e-06, "loss": 0.30166441202163696, "step": 2810 }, { "epoch": 0.7297507788161994, "grad_norm": 9.785642623901367, "learning_rate": 3.802708311585774e-06, "loss": 0.27905285358428955, "step": 2811 }, { "epoch": 0.7300103842159917, "grad_norm": 10.0725736618042, "learning_rate": 3.801872138046608e-06, "loss": 0.31270110607147217, "step": 2812 }, { "epoch": 0.730269989615784, "grad_norm": 4.480055809020996, "learning_rate": 3.801035778560532e-06, "loss": 0.32883894443511963, "step": 2813 }, { "epoch": 0.7305295950155763, "grad_norm": 8.175654411315918, "learning_rate": 3.800199233275397e-06, "loss": 0.22885552048683167, "step": 2814 }, { "epoch": 0.7307892004153687, "grad_norm": 11.140000343322754, "learning_rate": 3.7993625023390835e-06, "loss": 0.2501412332057953, "step": 2815 }, { "epoch": 0.731048805815161, "grad_norm": 10.608674049377441, "learning_rate": 3.7985255858995067e-06, "loss": 0.24144048988819122, "step": 2816 }, { "epoch": 0.7313084112149533, "grad_norm": 5.446510314941406, "learning_rate": 3.7976884841046135e-06, "loss": 0.3419486880302429, "step": 2817 }, { "epoch": 0.7315680166147456, "grad_norm": 7.765115737915039, "learning_rate": 3.7968511971023863e-06, "loss": 0.2562735974788666, "step": 2818 }, { "epoch": 0.7318276220145379, "grad_norm": 3.2051970958709717, "learning_rate": 3.7960137250408374e-06, "loss": 0.3485964238643646, "step": 2819 }, { "epoch": 0.7320872274143302, "grad_norm": 6.829794406890869, "learning_rate": 3.795176068068012e-06, "loss": 0.37019672989845276, "step": 2820 }, { "epoch": 0.7323468328141225, "grad_norm": 3.0794944763183594, "learning_rate": 3.794338226331989e-06, "loss": 0.316901296377182, "step": 2821 }, { "epoch": 0.7326064382139148, "grad_norm": 10.759210586547852, "learning_rate": 3.7935001999808796e-06, "loss": 0.3320199251174927, "step": 2822 }, { "epoch": 0.7328660436137072, "grad_norm": 5.3209967613220215, "learning_rate": 3.792661989162828e-06, "loss": 0.3334110379219055, "step": 2823 }, { "epoch": 0.7331256490134995, "grad_norm": 4.804259777069092, "learning_rate": 3.7918235940260108e-06, "loss": 0.33288443088531494, "step": 2824 }, { "epoch": 0.7333852544132918, "grad_norm": 4.011545181274414, "learning_rate": 3.790985014718636e-06, "loss": 0.33454370498657227, "step": 2825 }, { "epoch": 0.7336448598130841, "grad_norm": 4.274051666259766, "learning_rate": 3.790146251388947e-06, "loss": 0.32741495966911316, "step": 2826 }, { "epoch": 0.7339044652128764, "grad_norm": 6.47121000289917, "learning_rate": 3.789307304185216e-06, "loss": 0.36756032705307007, "step": 2827 }, { "epoch": 0.7341640706126688, "grad_norm": 7.908495903015137, "learning_rate": 3.7884681732557517e-06, "loss": 0.263630747795105, "step": 2828 }, { "epoch": 0.7344236760124611, "grad_norm": 8.532066345214844, "learning_rate": 3.7876288587488913e-06, "loss": 0.2471606284379959, "step": 2829 }, { "epoch": 0.7346832814122534, "grad_norm": 8.324673652648926, "learning_rate": 3.786789360813007e-06, "loss": 0.36425065994262695, "step": 2830 }, { "epoch": 0.7349428868120457, "grad_norm": 7.970616817474365, "learning_rate": 3.785949679596504e-06, "loss": 0.22006955742835999, "step": 2831 }, { "epoch": 0.735202492211838, "grad_norm": 2.4622316360473633, "learning_rate": 3.785109815247817e-06, "loss": 0.3226422667503357, "step": 2832 }, { "epoch": 0.7354620976116303, "grad_norm": 8.577398300170898, "learning_rate": 3.784269767915416e-06, "loss": 0.27213770151138306, "step": 2833 }, { "epoch": 0.7357217030114226, "grad_norm": 3.1258890628814697, "learning_rate": 3.7834295377478013e-06, "loss": 0.321897953748703, "step": 2834 }, { "epoch": 0.735981308411215, "grad_norm": 3.521677017211914, "learning_rate": 3.7825891248935066e-06, "loss": 0.2870967388153076, "step": 2835 }, { "epoch": 0.7362409138110073, "grad_norm": 4.631546974182129, "learning_rate": 3.7817485295010982e-06, "loss": 0.2548927664756775, "step": 2836 }, { "epoch": 0.7365005192107996, "grad_norm": 9.885430335998535, "learning_rate": 3.7809077517191733e-06, "loss": 0.32542136311531067, "step": 2837 }, { "epoch": 0.7367601246105919, "grad_norm": 4.0536723136901855, "learning_rate": 3.780066791696363e-06, "loss": 0.29654043912887573, "step": 2838 }, { "epoch": 0.7370197300103842, "grad_norm": 5.369431018829346, "learning_rate": 3.779225649581329e-06, "loss": 0.38696181774139404, "step": 2839 }, { "epoch": 0.7372793354101765, "grad_norm": 7.376279354095459, "learning_rate": 3.778384325522767e-06, "loss": 0.2136499136686325, "step": 2840 }, { "epoch": 0.7375389408099688, "grad_norm": 3.3128015995025635, "learning_rate": 3.7775428196694023e-06, "loss": 0.2987252473831177, "step": 2841 }, { "epoch": 0.7377985462097612, "grad_norm": 8.191816329956055, "learning_rate": 3.776701132169995e-06, "loss": 0.21511231362819672, "step": 2842 }, { "epoch": 0.7380581516095535, "grad_norm": 7.357722282409668, "learning_rate": 3.7758592631733354e-06, "loss": 0.3485018014907837, "step": 2843 }, { "epoch": 0.7383177570093458, "grad_norm": 5.713189125061035, "learning_rate": 3.775017212828248e-06, "loss": 0.325521320104599, "step": 2844 }, { "epoch": 0.7385773624091381, "grad_norm": 7.043890476226807, "learning_rate": 3.774174981283587e-06, "loss": 0.39279893040657043, "step": 2845 }, { "epoch": 0.7388369678089304, "grad_norm": 4.501875400543213, "learning_rate": 3.773332568688239e-06, "loss": 0.3052477240562439, "step": 2846 }, { "epoch": 0.7390965732087228, "grad_norm": 7.17415189743042, "learning_rate": 3.7724899751911254e-06, "loss": 0.2642841041088104, "step": 2847 }, { "epoch": 0.7393561786085151, "grad_norm": 4.781938076019287, "learning_rate": 3.7716472009411944e-06, "loss": 0.3178279995918274, "step": 2848 }, { "epoch": 0.7396157840083074, "grad_norm": 4.978259086608887, "learning_rate": 3.7708042460874315e-06, "loss": 0.307761549949646, "step": 2849 }, { "epoch": 0.7398753894080997, "grad_norm": 3.2677505016326904, "learning_rate": 3.769961110778852e-06, "loss": 0.33226191997528076, "step": 2850 }, { "epoch": 0.740134994807892, "grad_norm": 9.770633697509766, "learning_rate": 3.7691177951645018e-06, "loss": 0.3022145628929138, "step": 2851 }, { "epoch": 0.7403946002076843, "grad_norm": 5.520777702331543, "learning_rate": 3.7682742993934595e-06, "loss": 0.3389822840690613, "step": 2852 }, { "epoch": 0.7406542056074766, "grad_norm": 4.735177040100098, "learning_rate": 3.7674306236148374e-06, "loss": 0.33960074186325073, "step": 2853 }, { "epoch": 0.7409138110072689, "grad_norm": 5.83404016494751, "learning_rate": 3.7665867679777763e-06, "loss": 0.2974347472190857, "step": 2854 }, { "epoch": 0.7411734164070612, "grad_norm": 8.533098220825195, "learning_rate": 3.7657427326314523e-06, "loss": 0.27075228095054626, "step": 2855 }, { "epoch": 0.7414330218068536, "grad_norm": 5.127711772918701, "learning_rate": 3.7648985177250697e-06, "loss": 0.315197229385376, "step": 2856 }, { "epoch": 0.7416926272066459, "grad_norm": 9.949994087219238, "learning_rate": 3.764054123407867e-06, "loss": 0.25416743755340576, "step": 2857 }, { "epoch": 0.7419522326064382, "grad_norm": 7.054831504821777, "learning_rate": 3.763209549829115e-06, "loss": 0.2804223299026489, "step": 2858 }, { "epoch": 0.7422118380062306, "grad_norm": 6.381371974945068, "learning_rate": 3.7623647971381132e-06, "loss": 0.2939707338809967, "step": 2859 }, { "epoch": 0.7424714434060229, "grad_norm": 10.132739067077637, "learning_rate": 3.7615198654841957e-06, "loss": 0.2851818799972534, "step": 2860 }, { "epoch": 0.7427310488058152, "grad_norm": 7.777835369110107, "learning_rate": 3.760674755016727e-06, "loss": 0.3316361904144287, "step": 2861 }, { "epoch": 0.7429906542056075, "grad_norm": 6.248178005218506, "learning_rate": 3.7598294658851025e-06, "loss": 0.2850669026374817, "step": 2862 }, { "epoch": 0.7432502596053998, "grad_norm": 11.162178993225098, "learning_rate": 3.758983998238751e-06, "loss": 0.30991798639297485, "step": 2863 }, { "epoch": 0.7435098650051921, "grad_norm": 8.308171272277832, "learning_rate": 3.758138352227131e-06, "loss": 0.26999303698539734, "step": 2864 }, { "epoch": 0.7437694704049844, "grad_norm": 5.335605621337891, "learning_rate": 3.757292527999734e-06, "loss": 0.28884145617485046, "step": 2865 }, { "epoch": 0.7440290758047767, "grad_norm": 10.887803077697754, "learning_rate": 3.756446525706081e-06, "loss": 0.2290845811367035, "step": 2866 }, { "epoch": 0.744288681204569, "grad_norm": 8.773750305175781, "learning_rate": 3.7556003454957273e-06, "loss": 0.23594129085540771, "step": 2867 }, { "epoch": 0.7445482866043613, "grad_norm": 4.608088970184326, "learning_rate": 3.754753987518259e-06, "loss": 0.3125370144844055, "step": 2868 }, { "epoch": 0.7448078920041536, "grad_norm": 7.615936756134033, "learning_rate": 3.75390745192329e-06, "loss": 0.37561994791030884, "step": 2869 }, { "epoch": 0.745067497403946, "grad_norm": 6.093354225158691, "learning_rate": 3.75306073886047e-06, "loss": 0.2397112250328064, "step": 2870 }, { "epoch": 0.7453271028037384, "grad_norm": 8.666474342346191, "learning_rate": 3.752213848479479e-06, "loss": 0.3637480139732361, "step": 2871 }, { "epoch": 0.7455867082035307, "grad_norm": 5.96307373046875, "learning_rate": 3.751366780930027e-06, "loss": 0.25195997953414917, "step": 2872 }, { "epoch": 0.745846313603323, "grad_norm": 9.056300163269043, "learning_rate": 3.7505195363618563e-06, "loss": 0.32302916049957275, "step": 2873 }, { "epoch": 0.7461059190031153, "grad_norm": 4.709084510803223, "learning_rate": 3.7496721149247407e-06, "loss": 0.2936042547225952, "step": 2874 }, { "epoch": 0.7463655244029076, "grad_norm": 8.755414009094238, "learning_rate": 3.7488245167684846e-06, "loss": 0.266934871673584, "step": 2875 }, { "epoch": 0.7466251298026999, "grad_norm": 9.411989212036133, "learning_rate": 3.7479767420429235e-06, "loss": 0.2575356066226959, "step": 2876 }, { "epoch": 0.7468847352024922, "grad_norm": 2.8259081840515137, "learning_rate": 3.7471287908979254e-06, "loss": 0.34917259216308594, "step": 2877 }, { "epoch": 0.7471443406022845, "grad_norm": 9.508617401123047, "learning_rate": 3.746280663483389e-06, "loss": 0.2512911558151245, "step": 2878 }, { "epoch": 0.7474039460020768, "grad_norm": 5.588083744049072, "learning_rate": 3.7454323599492414e-06, "loss": 0.3082844018936157, "step": 2879 }, { "epoch": 0.7476635514018691, "grad_norm": 10.179658889770508, "learning_rate": 3.744583880445446e-06, "loss": 0.29418569803237915, "step": 2880 }, { "epoch": 0.7479231568016614, "grad_norm": 7.427023410797119, "learning_rate": 3.743735225121994e-06, "loss": 0.26475346088409424, "step": 2881 }, { "epoch": 0.7481827622014537, "grad_norm": 6.477266788482666, "learning_rate": 3.7428863941289067e-06, "loss": 0.24276408553123474, "step": 2882 }, { "epoch": 0.7484423676012462, "grad_norm": 8.34974479675293, "learning_rate": 3.742037387616239e-06, "loss": 0.17507758736610413, "step": 2883 }, { "epoch": 0.7487019730010385, "grad_norm": 9.899566650390625, "learning_rate": 3.7411882057340766e-06, "loss": 0.3092931807041168, "step": 2884 }, { "epoch": 0.7489615784008308, "grad_norm": 4.766524791717529, "learning_rate": 3.7403388486325345e-06, "loss": 0.3252788782119751, "step": 2885 }, { "epoch": 0.7492211838006231, "grad_norm": 12.211851119995117, "learning_rate": 3.739489316461759e-06, "loss": 0.2561694383621216, "step": 2886 }, { "epoch": 0.7494807892004154, "grad_norm": 5.364532947540283, "learning_rate": 3.7386396093719297e-06, "loss": 0.31701937317848206, "step": 2887 }, { "epoch": 0.7497403946002077, "grad_norm": 5.3278326988220215, "learning_rate": 3.7377897275132534e-06, "loss": 0.3159496784210205, "step": 2888 }, { "epoch": 0.75, "grad_norm": 9.780098915100098, "learning_rate": 3.736939671035971e-06, "loss": 0.3146677017211914, "step": 2889 }, { "epoch": 0.7502596053997923, "grad_norm": 9.869150161743164, "learning_rate": 3.736089440090353e-06, "loss": 0.2625213861465454, "step": 2890 }, { "epoch": 0.7505192107995846, "grad_norm": 7.070525646209717, "learning_rate": 3.7352390348266997e-06, "loss": 0.36952346563339233, "step": 2891 }, { "epoch": 0.7507788161993769, "grad_norm": 9.877591133117676, "learning_rate": 3.734388455395344e-06, "loss": 0.3021009862422943, "step": 2892 }, { "epoch": 0.7510384215991692, "grad_norm": 11.716475486755371, "learning_rate": 3.7335377019466497e-06, "loss": 0.23682285845279694, "step": 2893 }, { "epoch": 0.7512980269989615, "grad_norm": 10.878910064697266, "learning_rate": 3.73268677463101e-06, "loss": 0.22115670144557953, "step": 2894 }, { "epoch": 0.7515576323987538, "grad_norm": 6.173102855682373, "learning_rate": 3.731835673598848e-06, "loss": 0.2538667917251587, "step": 2895 }, { "epoch": 0.7518172377985463, "grad_norm": 4.011954307556152, "learning_rate": 3.7309843990006207e-06, "loss": 0.271697074174881, "step": 2896 }, { "epoch": 0.7520768431983386, "grad_norm": 8.417110443115234, "learning_rate": 3.7301329509868124e-06, "loss": 0.2442142367362976, "step": 2897 }, { "epoch": 0.7523364485981309, "grad_norm": 3.4438412189483643, "learning_rate": 3.7292813297079416e-06, "loss": 0.32248541712760925, "step": 2898 }, { "epoch": 0.7525960539979232, "grad_norm": 3.7950849533081055, "learning_rate": 3.728429535314554e-06, "loss": 0.2963203191757202, "step": 2899 }, { "epoch": 0.7528556593977155, "grad_norm": 3.376589775085449, "learning_rate": 3.727577567957227e-06, "loss": 0.32566213607788086, "step": 2900 }, { "epoch": 0.7531152647975078, "grad_norm": 8.507394790649414, "learning_rate": 3.72672542778657e-06, "loss": 0.27921921014785767, "step": 2901 }, { "epoch": 0.7533748701973001, "grad_norm": 7.946580410003662, "learning_rate": 3.7258731149532207e-06, "loss": 0.2067728340625763, "step": 2902 }, { "epoch": 0.7536344755970924, "grad_norm": 7.133813381195068, "learning_rate": 3.72502062960785e-06, "loss": 0.37483593821525574, "step": 2903 }, { "epoch": 0.7538940809968847, "grad_norm": 3.581087112426758, "learning_rate": 3.724167971901157e-06, "loss": 0.3359658718109131, "step": 2904 }, { "epoch": 0.754153686396677, "grad_norm": 4.702091693878174, "learning_rate": 3.7233151419838713e-06, "loss": 0.34912675619125366, "step": 2905 }, { "epoch": 0.7544132917964693, "grad_norm": 10.166646003723145, "learning_rate": 3.722462140006755e-06, "loss": 0.27266421914100647, "step": 2906 }, { "epoch": 0.7546728971962616, "grad_norm": 7.817196369171143, "learning_rate": 3.721608966120599e-06, "loss": 0.2307615429162979, "step": 2907 }, { "epoch": 0.754932502596054, "grad_norm": 4.8429365158081055, "learning_rate": 3.7207556204762248e-06, "loss": 0.35024112462997437, "step": 2908 }, { "epoch": 0.7551921079958464, "grad_norm": 4.274049758911133, "learning_rate": 3.7199021032244843e-06, "loss": 0.3070489764213562, "step": 2909 }, { "epoch": 0.7554517133956387, "grad_norm": 6.852060794830322, "learning_rate": 3.7190484145162585e-06, "loss": 0.2674396336078644, "step": 2910 }, { "epoch": 0.755711318795431, "grad_norm": 8.372601509094238, "learning_rate": 3.7181945545024622e-06, "loss": 0.21338872611522675, "step": 2911 }, { "epoch": 0.7559709241952233, "grad_norm": 10.281451225280762, "learning_rate": 3.717340523334037e-06, "loss": 0.2908163070678711, "step": 2912 }, { "epoch": 0.7562305295950156, "grad_norm": 4.711365699768066, "learning_rate": 3.716486321161957e-06, "loss": 0.30801358819007874, "step": 2913 }, { "epoch": 0.7564901349948079, "grad_norm": 2.466123104095459, "learning_rate": 3.7156319481372247e-06, "loss": 0.3166887164115906, "step": 2914 }, { "epoch": 0.7567497403946002, "grad_norm": 3.337231397628784, "learning_rate": 3.7147774044108743e-06, "loss": 0.33919858932495117, "step": 2915 }, { "epoch": 0.7570093457943925, "grad_norm": 8.827056884765625, "learning_rate": 3.7139226901339685e-06, "loss": 0.3332074284553528, "step": 2916 }, { "epoch": 0.7572689511941848, "grad_norm": 5.017797470092773, "learning_rate": 3.713067805457603e-06, "loss": 0.3412310481071472, "step": 2917 }, { "epoch": 0.7575285565939771, "grad_norm": 4.254548072814941, "learning_rate": 3.7122127505329003e-06, "loss": 0.26562026143074036, "step": 2918 }, { "epoch": 0.7577881619937694, "grad_norm": 6.024530410766602, "learning_rate": 3.7113575255110155e-06, "loss": 0.33011212944984436, "step": 2919 }, { "epoch": 0.7580477673935618, "grad_norm": 2.9198379516601562, "learning_rate": 3.7105021305431317e-06, "loss": 0.3526095151901245, "step": 2920 }, { "epoch": 0.7583073727933541, "grad_norm": 2.7876880168914795, "learning_rate": 3.709646565780464e-06, "loss": 0.35939544439315796, "step": 2921 }, { "epoch": 0.7585669781931464, "grad_norm": 9.511137962341309, "learning_rate": 3.708790831374257e-06, "loss": 0.20184236764907837, "step": 2922 }, { "epoch": 0.7588265835929388, "grad_norm": 5.693546772003174, "learning_rate": 3.7079349274757838e-06, "loss": 0.2801084518432617, "step": 2923 }, { "epoch": 0.7590861889927311, "grad_norm": 7.635338306427002, "learning_rate": 3.7070788542363495e-06, "loss": 0.3773394227027893, "step": 2924 }, { "epoch": 0.7593457943925234, "grad_norm": 10.569711685180664, "learning_rate": 3.706222611807288e-06, "loss": 0.25009816884994507, "step": 2925 }, { "epoch": 0.7596053997923157, "grad_norm": 8.301628112792969, "learning_rate": 3.705366200339964e-06, "loss": 0.3631451725959778, "step": 2926 }, { "epoch": 0.759865005192108, "grad_norm": 7.626810550689697, "learning_rate": 3.7045096199857694e-06, "loss": 0.2411917746067047, "step": 2927 }, { "epoch": 0.7601246105919003, "grad_norm": 4.4024338722229, "learning_rate": 3.7036528708961297e-06, "loss": 0.27464503049850464, "step": 2928 }, { "epoch": 0.7603842159916926, "grad_norm": 3.224409818649292, "learning_rate": 3.702795953222498e-06, "loss": 0.3520377576351166, "step": 2929 }, { "epoch": 0.7606438213914849, "grad_norm": 3.8748536109924316, "learning_rate": 3.7019388671163588e-06, "loss": 0.3151147961616516, "step": 2930 }, { "epoch": 0.7609034267912772, "grad_norm": 3.58064866065979, "learning_rate": 3.7010816127292245e-06, "loss": 0.3294232189655304, "step": 2931 }, { "epoch": 0.7611630321910696, "grad_norm": 4.5242438316345215, "learning_rate": 3.7002241902126366e-06, "loss": 0.23704464733600616, "step": 2932 }, { "epoch": 0.7614226375908619, "grad_norm": 5.373256206512451, "learning_rate": 3.6993665997181698e-06, "loss": 0.2780560851097107, "step": 2933 }, { "epoch": 0.7616822429906542, "grad_norm": 3.963287591934204, "learning_rate": 3.698508841397426e-06, "loss": 0.32844388484954834, "step": 2934 }, { "epoch": 0.7619418483904465, "grad_norm": 5.925235748291016, "learning_rate": 3.6976509154020375e-06, "loss": 0.26138633489608765, "step": 2935 }, { "epoch": 0.7622014537902388, "grad_norm": 2.580685615539551, "learning_rate": 3.6967928218836646e-06, "loss": 0.3526655435562134, "step": 2936 }, { "epoch": 0.7624610591900312, "grad_norm": 4.702685832977295, "learning_rate": 3.695934560993999e-06, "loss": 0.2789028286933899, "step": 2937 }, { "epoch": 0.7627206645898235, "grad_norm": 10.482868194580078, "learning_rate": 3.6950761328847634e-06, "loss": 0.26026129722595215, "step": 2938 }, { "epoch": 0.7629802699896158, "grad_norm": 8.957139015197754, "learning_rate": 3.694217537707706e-06, "loss": 0.2709147334098816, "step": 2939 }, { "epoch": 0.7632398753894081, "grad_norm": 9.104467391967773, "learning_rate": 3.6933587756146085e-06, "loss": 0.3078954219818115, "step": 2940 }, { "epoch": 0.7634994807892004, "grad_norm": 5.782392501831055, "learning_rate": 3.6924998467572782e-06, "loss": 0.3134614825248718, "step": 2941 }, { "epoch": 0.7637590861889927, "grad_norm": 2.793874979019165, "learning_rate": 3.6916407512875567e-06, "loss": 0.3667243719100952, "step": 2942 }, { "epoch": 0.764018691588785, "grad_norm": 10.2444429397583, "learning_rate": 3.6907814893573102e-06, "loss": 0.28476470708847046, "step": 2943 }, { "epoch": 0.7642782969885774, "grad_norm": 8.92273235321045, "learning_rate": 3.6899220611184384e-06, "loss": 0.3172229826450348, "step": 2944 }, { "epoch": 0.7645379023883697, "grad_norm": 7.889821529388428, "learning_rate": 3.6890624667228664e-06, "loss": 0.23559843003749847, "step": 2945 }, { "epoch": 0.764797507788162, "grad_norm": 6.384113311767578, "learning_rate": 3.6882027063225527e-06, "loss": 0.2608438730239868, "step": 2946 }, { "epoch": 0.7650571131879543, "grad_norm": 9.630766868591309, "learning_rate": 3.687342780069482e-06, "loss": 0.21317452192306519, "step": 2947 }, { "epoch": 0.7653167185877466, "grad_norm": 3.700125217437744, "learning_rate": 3.68648268811567e-06, "loss": 0.32318222522735596, "step": 2948 }, { "epoch": 0.7655763239875389, "grad_norm": 7.3538618087768555, "learning_rate": 3.6856224306131622e-06, "loss": 0.18229934573173523, "step": 2949 }, { "epoch": 0.7658359293873312, "grad_norm": 8.043879508972168, "learning_rate": 3.684762007714031e-06, "loss": 0.28192418813705444, "step": 2950 }, { "epoch": 0.7660955347871236, "grad_norm": 6.2796173095703125, "learning_rate": 3.68390141957038e-06, "loss": 0.2818089723587036, "step": 2951 }, { "epoch": 0.7663551401869159, "grad_norm": 2.5728564262390137, "learning_rate": 3.683040666334342e-06, "loss": 0.3200395703315735, "step": 2952 }, { "epoch": 0.7666147455867082, "grad_norm": 3.083400249481201, "learning_rate": 3.682179748158078e-06, "loss": 0.2934536635875702, "step": 2953 }, { "epoch": 0.7668743509865005, "grad_norm": 8.817089080810547, "learning_rate": 3.6813186651937775e-06, "loss": 0.24178621172904968, "step": 2954 }, { "epoch": 0.7671339563862928, "grad_norm": 9.505817413330078, "learning_rate": 3.6804574175936623e-06, "loss": 0.20899474620819092, "step": 2955 }, { "epoch": 0.7673935617860852, "grad_norm": 10.780226707458496, "learning_rate": 3.6795960055099804e-06, "loss": 0.22838467359542847, "step": 2956 }, { "epoch": 0.7676531671858775, "grad_norm": 4.654297351837158, "learning_rate": 3.6787344290950094e-06, "loss": 0.3403228223323822, "step": 2957 }, { "epoch": 0.7679127725856698, "grad_norm": 9.726863861083984, "learning_rate": 3.677872688501057e-06, "loss": 0.31365078687667847, "step": 2958 }, { "epoch": 0.7681723779854621, "grad_norm": 8.973569869995117, "learning_rate": 3.6770107838804577e-06, "loss": 0.3390156626701355, "step": 2959 }, { "epoch": 0.7684319833852544, "grad_norm": 4.114809036254883, "learning_rate": 3.676148715385578e-06, "loss": 0.30684518814086914, "step": 2960 }, { "epoch": 0.7686915887850467, "grad_norm": 8.690303802490234, "learning_rate": 3.6752864831688124e-06, "loss": 0.26104575395584106, "step": 2961 }, { "epoch": 0.768951194184839, "grad_norm": 10.155251502990723, "learning_rate": 3.6744240873825816e-06, "loss": 0.26484793424606323, "step": 2962 }, { "epoch": 0.7692107995846313, "grad_norm": 4.864884853363037, "learning_rate": 3.673561528179339e-06, "loss": 0.22152234613895416, "step": 2963 }, { "epoch": 0.7694704049844237, "grad_norm": 5.078694820404053, "learning_rate": 3.6726988057115646e-06, "loss": 0.3109809458255768, "step": 2964 }, { "epoch": 0.769730010384216, "grad_norm": 4.292663097381592, "learning_rate": 3.6718359201317695e-06, "loss": 0.3573298454284668, "step": 2965 }, { "epoch": 0.7699896157840083, "grad_norm": 11.93574047088623, "learning_rate": 3.67097287159249e-06, "loss": 0.2052847445011139, "step": 2966 }, { "epoch": 0.7702492211838006, "grad_norm": 5.151886463165283, "learning_rate": 3.6701096602462944e-06, "loss": 0.28009897470474243, "step": 2967 }, { "epoch": 0.770508826583593, "grad_norm": 9.38802719116211, "learning_rate": 3.6692462862457784e-06, "loss": 0.4011502265930176, "step": 2968 }, { "epoch": 0.7707684319833853, "grad_norm": 5.067757606506348, "learning_rate": 3.6683827497435678e-06, "loss": 0.3021196722984314, "step": 2969 }, { "epoch": 0.7710280373831776, "grad_norm": 3.8482277393341064, "learning_rate": 3.667519050892315e-06, "loss": 0.31302666664123535, "step": 2970 }, { "epoch": 0.7712876427829699, "grad_norm": 3.1489241123199463, "learning_rate": 3.666655189844701e-06, "loss": 0.3002598285675049, "step": 2971 }, { "epoch": 0.7715472481827622, "grad_norm": 8.474059104919434, "learning_rate": 3.6657911667534397e-06, "loss": 0.24313116073608398, "step": 2972 }, { "epoch": 0.7718068535825545, "grad_norm": 12.524016380310059, "learning_rate": 3.6649269817712686e-06, "loss": 0.22838571667671204, "step": 2973 }, { "epoch": 0.7720664589823468, "grad_norm": 9.160576820373535, "learning_rate": 3.6640626350509557e-06, "loss": 0.15385687351226807, "step": 2974 }, { "epoch": 0.7723260643821391, "grad_norm": 6.41375732421875, "learning_rate": 3.663198126745299e-06, "loss": 0.2928832173347473, "step": 2975 }, { "epoch": 0.7725856697819314, "grad_norm": 10.434319496154785, "learning_rate": 3.6623334570071216e-06, "loss": 0.17917564511299133, "step": 2976 }, { "epoch": 0.7728452751817237, "grad_norm": 5.994143009185791, "learning_rate": 3.6614686259892794e-06, "loss": 0.2986330986022949, "step": 2977 }, { "epoch": 0.773104880581516, "grad_norm": 7.906204700469971, "learning_rate": 3.660603633844654e-06, "loss": 0.1702122837305069, "step": 2978 }, { "epoch": 0.7733644859813084, "grad_norm": 6.073457717895508, "learning_rate": 3.6597384807261564e-06, "loss": 0.3341429829597473, "step": 2979 }, { "epoch": 0.7736240913811008, "grad_norm": 4.262717247009277, "learning_rate": 3.658873166786726e-06, "loss": 0.30057623982429504, "step": 2980 }, { "epoch": 0.7738836967808931, "grad_norm": 7.996879577636719, "learning_rate": 3.6580076921793295e-06, "loss": 0.19909997284412384, "step": 2981 }, { "epoch": 0.7741433021806854, "grad_norm": 9.61661148071289, "learning_rate": 3.6571420570569643e-06, "loss": 0.2604880928993225, "step": 2982 }, { "epoch": 0.7744029075804777, "grad_norm": 3.3117849826812744, "learning_rate": 3.6562762615726538e-06, "loss": 0.3234233260154724, "step": 2983 }, { "epoch": 0.77466251298027, "grad_norm": 9.143250465393066, "learning_rate": 3.6554103058794504e-06, "loss": 0.21598121523857117, "step": 2984 }, { "epoch": 0.7749221183800623, "grad_norm": 7.9351348876953125, "learning_rate": 3.6545441901304366e-06, "loss": 0.30787938833236694, "step": 2985 }, { "epoch": 0.7751817237798546, "grad_norm": 3.4962751865386963, "learning_rate": 3.6536779144787223e-06, "loss": 0.32465073466300964, "step": 2986 }, { "epoch": 0.7754413291796469, "grad_norm": 3.414926767349243, "learning_rate": 3.652811479077443e-06, "loss": 0.29200732707977295, "step": 2987 }, { "epoch": 0.7757009345794392, "grad_norm": 2.664829730987549, "learning_rate": 3.6519448840797667e-06, "loss": 0.31840449571609497, "step": 2988 }, { "epoch": 0.7759605399792315, "grad_norm": 9.584778785705566, "learning_rate": 3.651078129638886e-06, "loss": 0.27316638827323914, "step": 2989 }, { "epoch": 0.7762201453790238, "grad_norm": 11.306703567504883, "learning_rate": 3.6502112159080243e-06, "loss": 0.269653856754303, "step": 2990 }, { "epoch": 0.7764797507788161, "grad_norm": 6.723293781280518, "learning_rate": 3.6493441430404315e-06, "loss": 0.36877167224884033, "step": 2991 }, { "epoch": 0.7767393561786086, "grad_norm": 14.915096282958984, "learning_rate": 3.648476911189387e-06, "loss": 0.3227148652076721, "step": 2992 }, { "epoch": 0.7769989615784009, "grad_norm": 7.844959735870361, "learning_rate": 3.6476095205081963e-06, "loss": 0.31824254989624023, "step": 2993 }, { "epoch": 0.7772585669781932, "grad_norm": 3.472411870956421, "learning_rate": 3.646741971150195e-06, "loss": 0.3115321695804596, "step": 2994 }, { "epoch": 0.7775181723779855, "grad_norm": 7.090742111206055, "learning_rate": 3.6458742632687462e-06, "loss": 0.2897982597351074, "step": 2995 }, { "epoch": 0.7777777777777778, "grad_norm": 2.820052146911621, "learning_rate": 3.64500639701724e-06, "loss": 0.39785337448120117, "step": 2996 }, { "epoch": 0.7780373831775701, "grad_norm": 9.247444152832031, "learning_rate": 3.6441383725490957e-06, "loss": 0.25179699063301086, "step": 2997 }, { "epoch": 0.7782969885773624, "grad_norm": 7.893416881561279, "learning_rate": 3.643270190017761e-06, "loss": 0.3673664927482605, "step": 2998 }, { "epoch": 0.7785565939771547, "grad_norm": 7.412363529205322, "learning_rate": 3.642401849576709e-06, "loss": 0.35728657245635986, "step": 2999 }, { "epoch": 0.778816199376947, "grad_norm": 9.842689514160156, "learning_rate": 3.6415333513794442e-06, "loss": 0.2300199568271637, "step": 3000 }, { "epoch": 0.7790758047767393, "grad_norm": 3.8049700260162354, "learning_rate": 3.640664695579496e-06, "loss": 0.31781989336013794, "step": 3001 }, { "epoch": 0.7793354101765316, "grad_norm": 4.3356242179870605, "learning_rate": 3.639795882330423e-06, "loss": 0.3646215498447418, "step": 3002 }, { "epoch": 0.7795950155763239, "grad_norm": 3.6743381023406982, "learning_rate": 3.638926911785811e-06, "loss": 0.29767221212387085, "step": 3003 }, { "epoch": 0.7798546209761164, "grad_norm": 9.42989444732666, "learning_rate": 3.6380577840992758e-06, "loss": 0.2312011867761612, "step": 3004 }, { "epoch": 0.7801142263759087, "grad_norm": 3.3485281467437744, "learning_rate": 3.637188499424457e-06, "loss": 0.2634873390197754, "step": 3005 }, { "epoch": 0.780373831775701, "grad_norm": 7.403895378112793, "learning_rate": 3.636319057915027e-06, "loss": 0.3632820248603821, "step": 3006 }, { "epoch": 0.7806334371754933, "grad_norm": 3.9741084575653076, "learning_rate": 3.63544945972468e-06, "loss": 0.29011625051498413, "step": 3007 }, { "epoch": 0.7808930425752856, "grad_norm": 8.344226837158203, "learning_rate": 3.634579705007144e-06, "loss": 0.2354932427406311, "step": 3008 }, { "epoch": 0.7811526479750779, "grad_norm": 4.061411380767822, "learning_rate": 3.6337097939161698e-06, "loss": 0.37439611554145813, "step": 3009 }, { "epoch": 0.7814122533748702, "grad_norm": 7.013547420501709, "learning_rate": 3.632839726605538e-06, "loss": 0.1875610202550888, "step": 3010 }, { "epoch": 0.7816718587746625, "grad_norm": 12.407045364379883, "learning_rate": 3.6319695032290565e-06, "loss": 0.19548019766807556, "step": 3011 }, { "epoch": 0.7819314641744548, "grad_norm": 9.25439167022705, "learning_rate": 3.6310991239405625e-06, "loss": 0.26242971420288086, "step": 3012 }, { "epoch": 0.7821910695742471, "grad_norm": 8.347503662109375, "learning_rate": 3.630228588893917e-06, "loss": 0.2706696093082428, "step": 3013 }, { "epoch": 0.7824506749740394, "grad_norm": 9.202430725097656, "learning_rate": 3.629357898243011e-06, "loss": 0.3149803876876831, "step": 3014 }, { "epoch": 0.7827102803738317, "grad_norm": 13.486801147460938, "learning_rate": 3.6284870521417646e-06, "loss": 0.2783692479133606, "step": 3015 }, { "epoch": 0.7829698857736241, "grad_norm": 6.057895660400391, "learning_rate": 3.627616050744121e-06, "loss": 0.30196213722229004, "step": 3016 }, { "epoch": 0.7832294911734164, "grad_norm": 9.212732315063477, "learning_rate": 3.6267448942040553e-06, "loss": 0.20743364095687866, "step": 3017 }, { "epoch": 0.7834890965732088, "grad_norm": 10.85365104675293, "learning_rate": 3.6258735826755663e-06, "loss": 0.1269814372062683, "step": 3018 }, { "epoch": 0.7837487019730011, "grad_norm": 9.50033187866211, "learning_rate": 3.625002116312683e-06, "loss": 0.18951964378356934, "step": 3019 }, { "epoch": 0.7840083073727934, "grad_norm": 4.377427577972412, "learning_rate": 3.6241304952694606e-06, "loss": 0.3455716371536255, "step": 3020 }, { "epoch": 0.7842679127725857, "grad_norm": 8.483487129211426, "learning_rate": 3.623258719699982e-06, "loss": 0.28682661056518555, "step": 3021 }, { "epoch": 0.784527518172378, "grad_norm": 3.652576208114624, "learning_rate": 3.6223867897583555e-06, "loss": 0.3284294307231903, "step": 3022 }, { "epoch": 0.7847871235721703, "grad_norm": 10.49876880645752, "learning_rate": 3.6215147055987204e-06, "loss": 0.3562489151954651, "step": 3023 }, { "epoch": 0.7850467289719626, "grad_norm": 7.830203533172607, "learning_rate": 3.62064246737524e-06, "loss": 0.1719869077205658, "step": 3024 }, { "epoch": 0.7853063343717549, "grad_norm": 3.0669002532958984, "learning_rate": 3.6197700752421066e-06, "loss": 0.337488055229187, "step": 3025 }, { "epoch": 0.7855659397715472, "grad_norm": 9.391194343566895, "learning_rate": 3.6188975293535393e-06, "loss": 0.2700721025466919, "step": 3026 }, { "epoch": 0.7858255451713395, "grad_norm": 5.523684501647949, "learning_rate": 3.618024829863784e-06, "loss": 0.3262765407562256, "step": 3027 }, { "epoch": 0.7860851505711319, "grad_norm": 9.747648239135742, "learning_rate": 3.617151976927113e-06, "loss": 0.2258933037519455, "step": 3028 }, { "epoch": 0.7863447559709242, "grad_norm": 12.228838920593262, "learning_rate": 3.6162789706978287e-06, "loss": 0.20559683442115784, "step": 3029 }, { "epoch": 0.7866043613707165, "grad_norm": 8.321374893188477, "learning_rate": 3.6154058113302566e-06, "loss": 0.4320724308490753, "step": 3030 }, { "epoch": 0.7868639667705088, "grad_norm": 5.567972183227539, "learning_rate": 3.614532498978753e-06, "loss": 0.2693914771080017, "step": 3031 }, { "epoch": 0.7871235721703012, "grad_norm": 5.32216739654541, "learning_rate": 3.6136590337976985e-06, "loss": 0.2756160497665405, "step": 3032 }, { "epoch": 0.7873831775700935, "grad_norm": 5.462826251983643, "learning_rate": 3.6127854159415014e-06, "loss": 0.299660325050354, "step": 3033 }, { "epoch": 0.7876427829698858, "grad_norm": 4.68453311920166, "learning_rate": 3.611911645564599e-06, "loss": 0.3340112566947937, "step": 3034 }, { "epoch": 0.7879023883696781, "grad_norm": 8.107121467590332, "learning_rate": 3.611037722821452e-06, "loss": 0.14769649505615234, "step": 3035 }, { "epoch": 0.7881619937694704, "grad_norm": 7.786975860595703, "learning_rate": 3.610163647866552e-06, "loss": 0.30332183837890625, "step": 3036 }, { "epoch": 0.7884215991692627, "grad_norm": 7.332645893096924, "learning_rate": 3.6092894208544128e-06, "loss": 0.22601060569286346, "step": 3037 }, { "epoch": 0.788681204569055, "grad_norm": 3.8100972175598145, "learning_rate": 3.608415041939579e-06, "loss": 0.3191354274749756, "step": 3038 }, { "epoch": 0.7889408099688473, "grad_norm": 3.8073549270629883, "learning_rate": 3.6075405112766213e-06, "loss": 0.3392159640789032, "step": 3039 }, { "epoch": 0.7892004153686397, "grad_norm": 7.695495128631592, "learning_rate": 3.606665829020137e-06, "loss": 0.2980988919734955, "step": 3040 }, { "epoch": 0.789460020768432, "grad_norm": 7.4616804122924805, "learning_rate": 3.605790995324749e-06, "loss": 0.3166729211807251, "step": 3041 }, { "epoch": 0.7897196261682243, "grad_norm": 9.041600227355957, "learning_rate": 3.604916010345107e-06, "loss": 0.15033423900604248, "step": 3042 }, { "epoch": 0.7899792315680166, "grad_norm": 4.392211437225342, "learning_rate": 3.60404087423589e-06, "loss": 0.3082675337791443, "step": 3043 }, { "epoch": 0.7902388369678089, "grad_norm": 9.697943687438965, "learning_rate": 3.6031655871518017e-06, "loss": 0.2656199336051941, "step": 3044 }, { "epoch": 0.7904984423676013, "grad_norm": 5.179602146148682, "learning_rate": 3.602290149247572e-06, "loss": 0.29817816615104675, "step": 3045 }, { "epoch": 0.7907580477673936, "grad_norm": 4.8982343673706055, "learning_rate": 3.6014145606779586e-06, "loss": 0.2968280017375946, "step": 3046 }, { "epoch": 0.7910176531671859, "grad_norm": 8.817171096801758, "learning_rate": 3.600538821597746e-06, "loss": 0.10977563261985779, "step": 3047 }, { "epoch": 0.7912772585669782, "grad_norm": 9.748857498168945, "learning_rate": 3.599662932161745e-06, "loss": 0.27724677324295044, "step": 3048 }, { "epoch": 0.7915368639667705, "grad_norm": 11.61117172241211, "learning_rate": 3.5987868925247916e-06, "loss": 0.21900390088558197, "step": 3049 }, { "epoch": 0.7917964693665628, "grad_norm": 4.858984470367432, "learning_rate": 3.597910702841751e-06, "loss": 0.32524654269218445, "step": 3050 }, { "epoch": 0.7920560747663551, "grad_norm": 15.320073127746582, "learning_rate": 3.5970343632675115e-06, "loss": 0.1509595364332199, "step": 3051 }, { "epoch": 0.7923156801661475, "grad_norm": 8.543713569641113, "learning_rate": 3.5961578739569926e-06, "loss": 0.2895321846008301, "step": 3052 }, { "epoch": 0.7925752855659398, "grad_norm": 10.47764778137207, "learning_rate": 3.5952812350651346e-06, "loss": 0.2605660557746887, "step": 3053 }, { "epoch": 0.7928348909657321, "grad_norm": 5.936007499694824, "learning_rate": 3.5944044467469095e-06, "loss": 0.29426079988479614, "step": 3054 }, { "epoch": 0.7930944963655244, "grad_norm": 4.644794940948486, "learning_rate": 3.5935275091573124e-06, "loss": 0.31927403807640076, "step": 3055 }, { "epoch": 0.7933541017653167, "grad_norm": 3.742994546890259, "learning_rate": 3.5926504224513655e-06, "loss": 0.3184070587158203, "step": 3056 }, { "epoch": 0.793613707165109, "grad_norm": 6.981520652770996, "learning_rate": 3.591773186784118e-06, "loss": 0.31049418449401855, "step": 3057 }, { "epoch": 0.7938733125649013, "grad_norm": 15.250147819519043, "learning_rate": 3.590895802310646e-06, "loss": 0.2530636787414551, "step": 3058 }, { "epoch": 0.7941329179646937, "grad_norm": 6.850579738616943, "learning_rate": 3.590018269186049e-06, "loss": 0.2543288469314575, "step": 3059 }, { "epoch": 0.794392523364486, "grad_norm": 9.875079154968262, "learning_rate": 3.589140587565456e-06, "loss": 0.1710866242647171, "step": 3060 }, { "epoch": 0.7946521287642783, "grad_norm": 3.96242618560791, "learning_rate": 3.5882627576040212e-06, "loss": 0.28437063097953796, "step": 3061 }, { "epoch": 0.7949117341640706, "grad_norm": 8.989665985107422, "learning_rate": 3.587384779456925e-06, "loss": 0.3034898638725281, "step": 3062 }, { "epoch": 0.7951713395638629, "grad_norm": 2.9449493885040283, "learning_rate": 3.5865066532793737e-06, "loss": 0.28709813952445984, "step": 3063 }, { "epoch": 0.7954309449636553, "grad_norm": 8.57004451751709, "learning_rate": 3.5856283792265984e-06, "loss": 0.3083856701850891, "step": 3064 }, { "epoch": 0.7956905503634476, "grad_norm": 6.187835216522217, "learning_rate": 3.5847499574538598e-06, "loss": 0.33410367369651794, "step": 3065 }, { "epoch": 0.7959501557632399, "grad_norm": 8.702141761779785, "learning_rate": 3.5838713881164413e-06, "loss": 0.27501344680786133, "step": 3066 }, { "epoch": 0.7962097611630322, "grad_norm": 2.837932586669922, "learning_rate": 3.582992671369655e-06, "loss": 0.34634530544281006, "step": 3067 }, { "epoch": 0.7964693665628245, "grad_norm": 8.61501407623291, "learning_rate": 3.5821138073688373e-06, "loss": 0.18477210402488708, "step": 3068 }, { "epoch": 0.7967289719626168, "grad_norm": 3.823798894882202, "learning_rate": 3.581234796269351e-06, "loss": 0.26454049348831177, "step": 3069 }, { "epoch": 0.7969885773624091, "grad_norm": 8.92734146118164, "learning_rate": 3.5803556382265854e-06, "loss": 0.20883017778396606, "step": 3070 }, { "epoch": 0.7972481827622014, "grad_norm": 10.007524490356445, "learning_rate": 3.5794763333959564e-06, "loss": 0.27912232279777527, "step": 3071 }, { "epoch": 0.7975077881619937, "grad_norm": 4.475005626678467, "learning_rate": 3.578596881932904e-06, "loss": 0.3574344515800476, "step": 3072 }, { "epoch": 0.797767393561786, "grad_norm": 10.200873374938965, "learning_rate": 3.5777172839928943e-06, "loss": 0.3221530318260193, "step": 3073 }, { "epoch": 0.7980269989615784, "grad_norm": 7.206223487854004, "learning_rate": 3.5768375397314215e-06, "loss": 0.18871715664863586, "step": 3074 }, { "epoch": 0.7982866043613707, "grad_norm": 7.914945602416992, "learning_rate": 3.5759576493040045e-06, "loss": 0.27894270420074463, "step": 3075 }, { "epoch": 0.7985462097611631, "grad_norm": 3.1185121536254883, "learning_rate": 3.5750776128661865e-06, "loss": 0.3274461328983307, "step": 3076 }, { "epoch": 0.7988058151609554, "grad_norm": 6.819393634796143, "learning_rate": 3.5741974305735377e-06, "loss": 0.3287877142429352, "step": 3077 }, { "epoch": 0.7990654205607477, "grad_norm": 7.579362392425537, "learning_rate": 3.5733171025816547e-06, "loss": 0.26942408084869385, "step": 3078 }, { "epoch": 0.79932502596054, "grad_norm": 3.844980239868164, "learning_rate": 3.5724366290461604e-06, "loss": 0.29927563667297363, "step": 3079 }, { "epoch": 0.7995846313603323, "grad_norm": 9.57211971282959, "learning_rate": 3.5715560101227013e-06, "loss": 0.20057092607021332, "step": 3080 }, { "epoch": 0.7998442367601246, "grad_norm": 5.289236545562744, "learning_rate": 3.5706752459669506e-06, "loss": 0.33881452679634094, "step": 3081 }, { "epoch": 0.8001038421599169, "grad_norm": 6.26256799697876, "learning_rate": 3.5697943367346066e-06, "loss": 0.3737446367740631, "step": 3082 }, { "epoch": 0.8003634475597092, "grad_norm": 2.822279930114746, "learning_rate": 3.5689132825813953e-06, "loss": 0.3405984044075012, "step": 3083 }, { "epoch": 0.8006230529595015, "grad_norm": 8.881982803344727, "learning_rate": 3.5680320836630667e-06, "loss": 0.2632264196872711, "step": 3084 }, { "epoch": 0.8008826583592938, "grad_norm": 5.649953365325928, "learning_rate": 3.567150740135396e-06, "loss": 0.24726247787475586, "step": 3085 }, { "epoch": 0.8011422637590861, "grad_norm": 5.4874348640441895, "learning_rate": 3.566269252154184e-06, "loss": 0.27745798230171204, "step": 3086 }, { "epoch": 0.8014018691588785, "grad_norm": 4.570885181427002, "learning_rate": 3.565387619875259e-06, "loss": 0.27087685465812683, "step": 3087 }, { "epoch": 0.8016614745586709, "grad_norm": 10.221424102783203, "learning_rate": 3.564505843454472e-06, "loss": 0.4202551543712616, "step": 3088 }, { "epoch": 0.8019210799584632, "grad_norm": 9.966785430908203, "learning_rate": 3.5636239230477025e-06, "loss": 0.1476435661315918, "step": 3089 }, { "epoch": 0.8021806853582555, "grad_norm": 7.986683368682861, "learning_rate": 3.562741858810852e-06, "loss": 0.24295443296432495, "step": 3090 }, { "epoch": 0.8024402907580478, "grad_norm": 11.019425392150879, "learning_rate": 3.561859650899851e-06, "loss": 0.21644769608974457, "step": 3091 }, { "epoch": 0.8026998961578401, "grad_norm": 10.97170352935791, "learning_rate": 3.560977299470653e-06, "loss": 0.15845215320587158, "step": 3092 }, { "epoch": 0.8029595015576324, "grad_norm": 6.258111000061035, "learning_rate": 3.560094804679237e-06, "loss": 0.2944721579551697, "step": 3093 }, { "epoch": 0.8032191069574247, "grad_norm": 4.926252365112305, "learning_rate": 3.5592121666816083e-06, "loss": 0.3382223844528198, "step": 3094 }, { "epoch": 0.803478712357217, "grad_norm": 5.970461368560791, "learning_rate": 3.5583293856337963e-06, "loss": 0.2827860116958618, "step": 3095 }, { "epoch": 0.8037383177570093, "grad_norm": 6.84689474105835, "learning_rate": 3.557446461691858e-06, "loss": 0.19088220596313477, "step": 3096 }, { "epoch": 0.8039979231568016, "grad_norm": 7.271081447601318, "learning_rate": 3.5565633950118727e-06, "loss": 0.2236240655183792, "step": 3097 }, { "epoch": 0.8042575285565939, "grad_norm": 9.48151969909668, "learning_rate": 3.5556801857499474e-06, "loss": 0.2593458294868469, "step": 3098 }, { "epoch": 0.8045171339563862, "grad_norm": 3.1350879669189453, "learning_rate": 3.554796834062213e-06, "loss": 0.3431103527545929, "step": 3099 }, { "epoch": 0.8047767393561787, "grad_norm": 4.920793533325195, "learning_rate": 3.553913340104826e-06, "loss": 0.27894747257232666, "step": 3100 }, { "epoch": 0.805036344755971, "grad_norm": 14.542646408081055, "learning_rate": 3.5530297040339667e-06, "loss": 0.2531014382839203, "step": 3101 }, { "epoch": 0.8052959501557633, "grad_norm": 7.55456018447876, "learning_rate": 3.5521459260058435e-06, "loss": 0.14876516163349152, "step": 3102 }, { "epoch": 0.8055555555555556, "grad_norm": 4.921143531799316, "learning_rate": 3.5512620061766866e-06, "loss": 0.31762659549713135, "step": 3103 }, { "epoch": 0.8058151609553479, "grad_norm": 6.822137355804443, "learning_rate": 3.550377944702755e-06, "loss": 0.28441137075424194, "step": 3104 }, { "epoch": 0.8060747663551402, "grad_norm": 6.948608875274658, "learning_rate": 3.549493741740327e-06, "loss": 0.28784337639808655, "step": 3105 }, { "epoch": 0.8063343717549325, "grad_norm": 7.476720809936523, "learning_rate": 3.5486093974457133e-06, "loss": 0.285200297832489, "step": 3106 }, { "epoch": 0.8065939771547248, "grad_norm": 6.808506011962891, "learning_rate": 3.5477249119752426e-06, "loss": 0.3041353225708008, "step": 3107 }, { "epoch": 0.8068535825545171, "grad_norm": 7.957334041595459, "learning_rate": 3.546840285485273e-06, "loss": 0.3141871392726898, "step": 3108 }, { "epoch": 0.8071131879543094, "grad_norm": 6.006409168243408, "learning_rate": 3.5459555181321856e-06, "loss": 0.2712518572807312, "step": 3109 }, { "epoch": 0.8073727933541017, "grad_norm": 4.596513271331787, "learning_rate": 3.545070610072389e-06, "loss": 0.2840758264064789, "step": 3110 }, { "epoch": 0.807632398753894, "grad_norm": 5.328555107116699, "learning_rate": 3.5441855614623126e-06, "loss": 0.356050968170166, "step": 3111 }, { "epoch": 0.8078920041536864, "grad_norm": 9.40754508972168, "learning_rate": 3.5433003724584143e-06, "loss": 0.29955756664276123, "step": 3112 }, { "epoch": 0.8081516095534788, "grad_norm": 8.026220321655273, "learning_rate": 3.5424150432171727e-06, "loss": 0.27560922503471375, "step": 3113 }, { "epoch": 0.8084112149532711, "grad_norm": 10.86638355255127, "learning_rate": 3.5415295738950965e-06, "loss": 0.24457159638404846, "step": 3114 }, { "epoch": 0.8086708203530634, "grad_norm": 7.233248233795166, "learning_rate": 3.5406439646487144e-06, "loss": 0.2586037516593933, "step": 3115 }, { "epoch": 0.8089304257528557, "grad_norm": 10.048213005065918, "learning_rate": 3.539758215634584e-06, "loss": 0.2508518099784851, "step": 3116 }, { "epoch": 0.809190031152648, "grad_norm": 3.4757983684539795, "learning_rate": 3.5388723270092824e-06, "loss": 0.31769782304763794, "step": 3117 }, { "epoch": 0.8094496365524403, "grad_norm": 10.214476585388184, "learning_rate": 3.5379862989294174e-06, "loss": 0.2563425898551941, "step": 3118 }, { "epoch": 0.8097092419522326, "grad_norm": 6.8774027824401855, "learning_rate": 3.537100131551617e-06, "loss": 0.28402435779571533, "step": 3119 }, { "epoch": 0.8099688473520249, "grad_norm": 8.40041446685791, "learning_rate": 3.536213825032535e-06, "loss": 0.24835066497325897, "step": 3120 }, { "epoch": 0.8102284527518172, "grad_norm": 7.960394859313965, "learning_rate": 3.535327379528851e-06, "loss": 0.26655638217926025, "step": 3121 }, { "epoch": 0.8104880581516095, "grad_norm": 5.924786567687988, "learning_rate": 3.5344407951972687e-06, "loss": 0.2651018500328064, "step": 3122 }, { "epoch": 0.8107476635514018, "grad_norm": 9.358762741088867, "learning_rate": 3.5335540721945145e-06, "loss": 0.37923839688301086, "step": 3123 }, { "epoch": 0.8110072689511942, "grad_norm": 10.767473220825195, "learning_rate": 3.532667210677341e-06, "loss": 0.2879551351070404, "step": 3124 }, { "epoch": 0.8112668743509865, "grad_norm": 11.2582368850708, "learning_rate": 3.531780210802526e-06, "loss": 0.207722008228302, "step": 3125 }, { "epoch": 0.8115264797507789, "grad_norm": 3.439652442932129, "learning_rate": 3.5308930727268693e-06, "loss": 0.3158087730407715, "step": 3126 }, { "epoch": 0.8117860851505712, "grad_norm": 13.547183990478516, "learning_rate": 3.530005796607198e-06, "loss": 0.31632113456726074, "step": 3127 }, { "epoch": 0.8120456905503635, "grad_norm": 17.467456817626953, "learning_rate": 3.529118382600361e-06, "loss": 0.32181209325790405, "step": 3128 }, { "epoch": 0.8123052959501558, "grad_norm": 3.6920084953308105, "learning_rate": 3.5282308308632348e-06, "loss": 0.3167700171470642, "step": 3129 }, { "epoch": 0.8125649013499481, "grad_norm": 10.555238723754883, "learning_rate": 3.527343141552715e-06, "loss": 0.1877814084291458, "step": 3130 }, { "epoch": 0.8128245067497404, "grad_norm": 4.736701011657715, "learning_rate": 3.526455314825728e-06, "loss": 0.32227376103401184, "step": 3131 }, { "epoch": 0.8130841121495327, "grad_norm": 4.25869083404541, "learning_rate": 3.525567350839219e-06, "loss": 0.28963956236839294, "step": 3132 }, { "epoch": 0.813343717549325, "grad_norm": 8.262420654296875, "learning_rate": 3.5246792497501615e-06, "loss": 0.321269690990448, "step": 3133 }, { "epoch": 0.8136033229491173, "grad_norm": 9.131514549255371, "learning_rate": 3.5237910117155494e-06, "loss": 0.23981349170207977, "step": 3134 }, { "epoch": 0.8138629283489096, "grad_norm": 9.474514961242676, "learning_rate": 3.5229026368924043e-06, "loss": 0.25282493233680725, "step": 3135 }, { "epoch": 0.814122533748702, "grad_norm": 7.003528594970703, "learning_rate": 3.5220141254377697e-06, "loss": 0.11103606224060059, "step": 3136 }, { "epoch": 0.8143821391484943, "grad_norm": 4.080542087554932, "learning_rate": 3.521125477508715e-06, "loss": 0.32472050189971924, "step": 3137 }, { "epoch": 0.8146417445482866, "grad_norm": 4.542934417724609, "learning_rate": 3.5202366932623327e-06, "loss": 0.3078048825263977, "step": 3138 }, { "epoch": 0.814901349948079, "grad_norm": 2.6997485160827637, "learning_rate": 3.519347772855738e-06, "loss": 0.3076353669166565, "step": 3139 }, { "epoch": 0.8151609553478713, "grad_norm": 9.1556396484375, "learning_rate": 3.518458716446074e-06, "loss": 0.2598796486854553, "step": 3140 }, { "epoch": 0.8154205607476636, "grad_norm": 4.875513553619385, "learning_rate": 3.517569524190503e-06, "loss": 0.29178309440612793, "step": 3141 }, { "epoch": 0.8156801661474559, "grad_norm": 8.71745491027832, "learning_rate": 3.516680196246216e-06, "loss": 0.3097529411315918, "step": 3142 }, { "epoch": 0.8159397715472482, "grad_norm": 5.325420379638672, "learning_rate": 3.5157907327704244e-06, "loss": 0.31502774357795715, "step": 3143 }, { "epoch": 0.8161993769470405, "grad_norm": 13.72249698638916, "learning_rate": 3.514901133920366e-06, "loss": 0.3137661814689636, "step": 3144 }, { "epoch": 0.8164589823468328, "grad_norm": 3.571040630340576, "learning_rate": 3.5140113998533015e-06, "loss": 0.3378813862800598, "step": 3145 }, { "epoch": 0.8167185877466251, "grad_norm": 5.001646995544434, "learning_rate": 3.513121530726515e-06, "loss": 0.3211561441421509, "step": 3146 }, { "epoch": 0.8169781931464174, "grad_norm": 4.424001216888428, "learning_rate": 3.5122315266973146e-06, "loss": 0.3450816869735718, "step": 3147 }, { "epoch": 0.8172377985462098, "grad_norm": 10.051835060119629, "learning_rate": 3.511341387923032e-06, "loss": 0.1940820962190628, "step": 3148 }, { "epoch": 0.8174974039460021, "grad_norm": 11.892212867736816, "learning_rate": 3.5104511145610255e-06, "loss": 0.3876020312309265, "step": 3149 }, { "epoch": 0.8177570093457944, "grad_norm": 9.763969421386719, "learning_rate": 3.509560706768674e-06, "loss": 0.31696781516075134, "step": 3150 }, { "epoch": 0.8180166147455867, "grad_norm": 3.274080991744995, "learning_rate": 3.508670164703382e-06, "loss": 0.3134767413139343, "step": 3151 }, { "epoch": 0.818276220145379, "grad_norm": 4.71979284286499, "learning_rate": 3.5077794885225747e-06, "loss": 0.2826882004737854, "step": 3152 }, { "epoch": 0.8185358255451713, "grad_norm": 6.742734909057617, "learning_rate": 3.5068886783837047e-06, "loss": 0.27695780992507935, "step": 3153 }, { "epoch": 0.8187954309449637, "grad_norm": 7.433505535125732, "learning_rate": 3.505997734444248e-06, "loss": 0.1540253609418869, "step": 3154 }, { "epoch": 0.819055036344756, "grad_norm": 9.3214111328125, "learning_rate": 3.505106656861701e-06, "loss": 0.27144092321395874, "step": 3155 }, { "epoch": 0.8193146417445483, "grad_norm": 7.062599182128906, "learning_rate": 3.5042154457935867e-06, "loss": 0.2915653586387634, "step": 3156 }, { "epoch": 0.8195742471443406, "grad_norm": 8.608109474182129, "learning_rate": 3.5033241013974512e-06, "loss": 0.18122202157974243, "step": 3157 }, { "epoch": 0.8198338525441329, "grad_norm": 9.205632209777832, "learning_rate": 3.502432623830863e-06, "loss": 0.3292325735092163, "step": 3158 }, { "epoch": 0.8200934579439252, "grad_norm": 7.495359420776367, "learning_rate": 3.5015410132514153e-06, "loss": 0.2149992287158966, "step": 3159 }, { "epoch": 0.8203530633437176, "grad_norm": 3.0016582012176514, "learning_rate": 3.5006492698167256e-06, "loss": 0.3210694491863251, "step": 3160 }, { "epoch": 0.8206126687435099, "grad_norm": 5.100093841552734, "learning_rate": 3.499757393684431e-06, "loss": 0.2586045265197754, "step": 3161 }, { "epoch": 0.8208722741433022, "grad_norm": 3.5867719650268555, "learning_rate": 3.4988653850121975e-06, "loss": 0.33682650327682495, "step": 3162 }, { "epoch": 0.8211318795430945, "grad_norm": 3.0943644046783447, "learning_rate": 3.4979732439577103e-06, "loss": 0.3469085097312927, "step": 3163 }, { "epoch": 0.8213914849428868, "grad_norm": 6.147197723388672, "learning_rate": 3.4970809706786802e-06, "loss": 0.361294150352478, "step": 3164 }, { "epoch": 0.8216510903426791, "grad_norm": 5.659784317016602, "learning_rate": 3.49618856533284e-06, "loss": 0.2495267391204834, "step": 3165 }, { "epoch": 0.8219106957424714, "grad_norm": 8.430194854736328, "learning_rate": 3.4952960280779463e-06, "loss": 0.1704530566930771, "step": 3166 }, { "epoch": 0.8221703011422637, "grad_norm": 5.158522129058838, "learning_rate": 3.494403359071781e-06, "loss": 0.3168485164642334, "step": 3167 }, { "epoch": 0.822429906542056, "grad_norm": 11.707586288452148, "learning_rate": 3.4935105584721455e-06, "loss": 0.3189131021499634, "step": 3168 }, { "epoch": 0.8226895119418484, "grad_norm": 7.69419002532959, "learning_rate": 3.4926176264368683e-06, "loss": 0.2824154496192932, "step": 3169 }, { "epoch": 0.8229491173416407, "grad_norm": 8.478104591369629, "learning_rate": 3.491724563123798e-06, "loss": 0.17359107732772827, "step": 3170 }, { "epoch": 0.823208722741433, "grad_norm": 3.0869874954223633, "learning_rate": 3.4908313686908074e-06, "loss": 0.3205142319202423, "step": 3171 }, { "epoch": 0.8234683281412254, "grad_norm": 2.8702588081359863, "learning_rate": 3.4899380432957948e-06, "loss": 0.29799196124076843, "step": 3172 }, { "epoch": 0.8237279335410177, "grad_norm": 4.0334272384643555, "learning_rate": 3.4890445870966783e-06, "loss": 0.3127686679363251, "step": 3173 }, { "epoch": 0.82398753894081, "grad_norm": 8.610658645629883, "learning_rate": 3.4881510002514e-06, "loss": 0.18521234393119812, "step": 3174 }, { "epoch": 0.8242471443406023, "grad_norm": 2.861084461212158, "learning_rate": 3.487257282917927e-06, "loss": 0.30608734488487244, "step": 3175 }, { "epoch": 0.8245067497403946, "grad_norm": 3.8056704998016357, "learning_rate": 3.4863634352542465e-06, "loss": 0.3011285662651062, "step": 3176 }, { "epoch": 0.8247663551401869, "grad_norm": 8.440982818603516, "learning_rate": 3.4854694574183716e-06, "loss": 0.22571344673633575, "step": 3177 }, { "epoch": 0.8250259605399792, "grad_norm": 3.5909814834594727, "learning_rate": 3.4845753495683366e-06, "loss": 0.2798970341682434, "step": 3178 }, { "epoch": 0.8252855659397715, "grad_norm": 3.394047260284424, "learning_rate": 3.4836811118621995e-06, "loss": 0.3260036110877991, "step": 3179 }, { "epoch": 0.8255451713395638, "grad_norm": 8.412894248962402, "learning_rate": 3.482786744458041e-06, "loss": 0.1875709593296051, "step": 3180 }, { "epoch": 0.8258047767393562, "grad_norm": 6.343113899230957, "learning_rate": 3.4818922475139643e-06, "loss": 0.2583107352256775, "step": 3181 }, { "epoch": 0.8260643821391485, "grad_norm": 10.646626472473145, "learning_rate": 3.4809976211880963e-06, "loss": 0.2602383494377136, "step": 3182 }, { "epoch": 0.8263239875389408, "grad_norm": 4.588613986968994, "learning_rate": 3.4801028656385867e-06, "loss": 0.28943800926208496, "step": 3183 }, { "epoch": 0.8265835929387332, "grad_norm": 13.029390335083008, "learning_rate": 3.4792079810236078e-06, "loss": 0.21999657154083252, "step": 3184 }, { "epoch": 0.8268431983385255, "grad_norm": 3.8344995975494385, "learning_rate": 3.4783129675013545e-06, "loss": 0.295820027589798, "step": 3185 }, { "epoch": 0.8271028037383178, "grad_norm": 5.348873615264893, "learning_rate": 3.4774178252300445e-06, "loss": 0.3353201150894165, "step": 3186 }, { "epoch": 0.8273624091381101, "grad_norm": 5.310141563415527, "learning_rate": 3.476522554367918e-06, "loss": 0.31299465894699097, "step": 3187 }, { "epoch": 0.8276220145379024, "grad_norm": 8.199601173400879, "learning_rate": 3.4756271550732397e-06, "loss": 0.23933987319469452, "step": 3188 }, { "epoch": 0.8278816199376947, "grad_norm": 5.316598415374756, "learning_rate": 3.474731627504296e-06, "loss": 0.3086685240268707, "step": 3189 }, { "epoch": 0.828141225337487, "grad_norm": 9.593762397766113, "learning_rate": 3.4738359718193932e-06, "loss": 0.24469657242298126, "step": 3190 }, { "epoch": 0.8284008307372793, "grad_norm": 4.657723426818848, "learning_rate": 3.4729401881768655e-06, "loss": 0.29507356882095337, "step": 3191 }, { "epoch": 0.8286604361370716, "grad_norm": 5.13503360748291, "learning_rate": 3.4720442767350637e-06, "loss": 0.2717358469963074, "step": 3192 }, { "epoch": 0.8289200415368639, "grad_norm": 10.72988224029541, "learning_rate": 3.4711482376523687e-06, "loss": 0.25442811846733093, "step": 3193 }, { "epoch": 0.8291796469366562, "grad_norm": 6.156895637512207, "learning_rate": 3.4702520710871757e-06, "loss": 0.26132577657699585, "step": 3194 }, { "epoch": 0.8294392523364486, "grad_norm": 5.145753383636475, "learning_rate": 3.469355777197909e-06, "loss": 0.29449933767318726, "step": 3195 }, { "epoch": 0.829698857736241, "grad_norm": 6.483043193817139, "learning_rate": 3.468459356143012e-06, "loss": 0.3067525029182434, "step": 3196 }, { "epoch": 0.8299584631360333, "grad_norm": 3.7186169624328613, "learning_rate": 3.4675628080809508e-06, "loss": 0.3222750723361969, "step": 3197 }, { "epoch": 0.8302180685358256, "grad_norm": 7.922921657562256, "learning_rate": 3.466666133170215e-06, "loss": 0.2706645131111145, "step": 3198 }, { "epoch": 0.8304776739356179, "grad_norm": 10.226441383361816, "learning_rate": 3.4657693315693177e-06, "loss": 0.22443152964115143, "step": 3199 }, { "epoch": 0.8307372793354102, "grad_norm": 9.846485137939453, "learning_rate": 3.4648724034367903e-06, "loss": 0.22878171503543854, "step": 3200 }, { "epoch": 0.8309968847352025, "grad_norm": 11.649839401245117, "learning_rate": 3.4639753489311905e-06, "loss": 0.18447169661521912, "step": 3201 }, { "epoch": 0.8312564901349948, "grad_norm": 10.625434875488281, "learning_rate": 3.4630781682110975e-06, "loss": 0.16902974247932434, "step": 3202 }, { "epoch": 0.8315160955347871, "grad_norm": 9.525106430053711, "learning_rate": 3.462180861435111e-06, "loss": 0.20111875236034393, "step": 3203 }, { "epoch": 0.8317757009345794, "grad_norm": 9.754728317260742, "learning_rate": 3.4612834287618556e-06, "loss": 0.30443504452705383, "step": 3204 }, { "epoch": 0.8320353063343717, "grad_norm": 6.025335788726807, "learning_rate": 3.4603858703499747e-06, "loss": 0.3454056978225708, "step": 3205 }, { "epoch": 0.832294911734164, "grad_norm": 4.461131572723389, "learning_rate": 3.4594881863581397e-06, "loss": 0.3395601809024811, "step": 3206 }, { "epoch": 0.8325545171339563, "grad_norm": 3.5420985221862793, "learning_rate": 3.4585903769450372e-06, "loss": 0.3171788156032562, "step": 3207 }, { "epoch": 0.8328141225337488, "grad_norm": 9.32202434539795, "learning_rate": 3.4576924422693813e-06, "loss": 0.3000454902648926, "step": 3208 }, { "epoch": 0.8330737279335411, "grad_norm": 10.96294116973877, "learning_rate": 3.4567943824899055e-06, "loss": 0.1580657958984375, "step": 3209 }, { "epoch": 0.8333333333333334, "grad_norm": 4.370983123779297, "learning_rate": 3.455896197765366e-06, "loss": 0.279951274394989, "step": 3210 }, { "epoch": 0.8335929387331257, "grad_norm": 10.662561416625977, "learning_rate": 3.454997888254541e-06, "loss": 0.27031272649765015, "step": 3211 }, { "epoch": 0.833852544132918, "grad_norm": 11.763964653015137, "learning_rate": 3.4540994541162333e-06, "loss": 0.18833932280540466, "step": 3212 }, { "epoch": 0.8341121495327103, "grad_norm": 8.59557819366455, "learning_rate": 3.4532008955092627e-06, "loss": 0.17439591884613037, "step": 3213 }, { "epoch": 0.8343717549325026, "grad_norm": 4.778911113739014, "learning_rate": 3.452302212592475e-06, "loss": 0.32710087299346924, "step": 3214 }, { "epoch": 0.8346313603322949, "grad_norm": 6.787949085235596, "learning_rate": 3.4514034055247366e-06, "loss": 0.2916264235973358, "step": 3215 }, { "epoch": 0.8348909657320872, "grad_norm": 7.5274338722229, "learning_rate": 3.450504474464937e-06, "loss": 0.15641270577907562, "step": 3216 }, { "epoch": 0.8351505711318795, "grad_norm": 7.3893866539001465, "learning_rate": 3.4496054195719847e-06, "loss": 0.30229490995407104, "step": 3217 }, { "epoch": 0.8354101765316718, "grad_norm": 9.721466064453125, "learning_rate": 3.4487062410048135e-06, "loss": 0.27984899282455444, "step": 3218 }, { "epoch": 0.8356697819314641, "grad_norm": 7.365912437438965, "learning_rate": 3.447806938922377e-06, "loss": 0.2514254152774811, "step": 3219 }, { "epoch": 0.8359293873312564, "grad_norm": 8.495997428894043, "learning_rate": 3.4469075134836516e-06, "loss": 0.3557590842247009, "step": 3220 }, { "epoch": 0.8361889927310489, "grad_norm": 9.655848503112793, "learning_rate": 3.4460079648476354e-06, "loss": 0.27682605385780334, "step": 3221 }, { "epoch": 0.8364485981308412, "grad_norm": 8.116880416870117, "learning_rate": 3.4451082931733463e-06, "loss": 0.1814446896314621, "step": 3222 }, { "epoch": 0.8367082035306335, "grad_norm": 6.979934215545654, "learning_rate": 3.444208498619827e-06, "loss": 0.26615509390830994, "step": 3223 }, { "epoch": 0.8369678089304258, "grad_norm": 4.419520378112793, "learning_rate": 3.4433085813461407e-06, "loss": 0.32360345125198364, "step": 3224 }, { "epoch": 0.8372274143302181, "grad_norm": 4.798161506652832, "learning_rate": 3.4424085415113722e-06, "loss": 0.2846439480781555, "step": 3225 }, { "epoch": 0.8374870197300104, "grad_norm": 3.135420322418213, "learning_rate": 3.4415083792746284e-06, "loss": 0.3067951500415802, "step": 3226 }, { "epoch": 0.8377466251298027, "grad_norm": 4.383477687835693, "learning_rate": 3.440608094795035e-06, "loss": 0.27737122774124146, "step": 3227 }, { "epoch": 0.838006230529595, "grad_norm": 6.957740306854248, "learning_rate": 3.4397076882317438e-06, "loss": 0.20247814059257507, "step": 3228 }, { "epoch": 0.8382658359293873, "grad_norm": 5.725429058074951, "learning_rate": 3.438807159743926e-06, "loss": 0.2203439176082611, "step": 3229 }, { "epoch": 0.8385254413291796, "grad_norm": 4.071192741394043, "learning_rate": 3.4379065094907734e-06, "loss": 0.3091985285282135, "step": 3230 }, { "epoch": 0.8387850467289719, "grad_norm": 5.297783374786377, "learning_rate": 3.4370057376315e-06, "loss": 0.35023200511932373, "step": 3231 }, { "epoch": 0.8390446521287642, "grad_norm": 9.132401466369629, "learning_rate": 3.4361048443253443e-06, "loss": 0.23462949693202972, "step": 3232 }, { "epoch": 0.8393042575285566, "grad_norm": 8.819626808166504, "learning_rate": 3.4352038297315616e-06, "loss": 0.26045355200767517, "step": 3233 }, { "epoch": 0.839563862928349, "grad_norm": 7.783332824707031, "learning_rate": 3.4343026940094297e-06, "loss": 0.20210061967372894, "step": 3234 }, { "epoch": 0.8398234683281413, "grad_norm": 10.6542387008667, "learning_rate": 3.433401437318251e-06, "loss": 0.3809974193572998, "step": 3235 }, { "epoch": 0.8400830737279336, "grad_norm": 5.228852272033691, "learning_rate": 3.4325000598173454e-06, "loss": 0.28319087624549866, "step": 3236 }, { "epoch": 0.8403426791277259, "grad_norm": 2.9239909648895264, "learning_rate": 3.4315985616660572e-06, "loss": 0.322517991065979, "step": 3237 }, { "epoch": 0.8406022845275182, "grad_norm": 10.43567180633545, "learning_rate": 3.430696943023749e-06, "loss": 0.2770457863807678, "step": 3238 }, { "epoch": 0.8408618899273105, "grad_norm": 9.922743797302246, "learning_rate": 3.429795204049808e-06, "loss": 0.30047139525413513, "step": 3239 }, { "epoch": 0.8411214953271028, "grad_norm": 8.140556335449219, "learning_rate": 3.428893344903639e-06, "loss": 0.22942490875720978, "step": 3240 }, { "epoch": 0.8413811007268951, "grad_norm": 13.086823463439941, "learning_rate": 3.427991365744672e-06, "loss": 0.1579139232635498, "step": 3241 }, { "epoch": 0.8416407061266874, "grad_norm": 9.08492660522461, "learning_rate": 3.4270892667323553e-06, "loss": 0.28699398040771484, "step": 3242 }, { "epoch": 0.8419003115264797, "grad_norm": 8.192752838134766, "learning_rate": 3.42618704802616e-06, "loss": 0.28503483533859253, "step": 3243 }, { "epoch": 0.842159916926272, "grad_norm": 6.960997104644775, "learning_rate": 3.4252847097855764e-06, "loss": 0.3004365563392639, "step": 3244 }, { "epoch": 0.8424195223260644, "grad_norm": 10.2034912109375, "learning_rate": 3.4243822521701183e-06, "loss": 0.18297719955444336, "step": 3245 }, { "epoch": 0.8426791277258567, "grad_norm": 5.5126729011535645, "learning_rate": 3.4234796753393197e-06, "loss": 0.280644953250885, "step": 3246 }, { "epoch": 0.842938733125649, "grad_norm": 5.7516255378723145, "learning_rate": 3.4225769794527354e-06, "loss": 0.26049667596817017, "step": 3247 }, { "epoch": 0.8431983385254413, "grad_norm": 6.34517240524292, "learning_rate": 3.4216741646699396e-06, "loss": 0.2650902569293976, "step": 3248 }, { "epoch": 0.8434579439252337, "grad_norm": 13.603130340576172, "learning_rate": 3.420771231150532e-06, "loss": 0.18259161710739136, "step": 3249 }, { "epoch": 0.843717549325026, "grad_norm": 8.47137451171875, "learning_rate": 3.4198681790541296e-06, "loss": 0.23521706461906433, "step": 3250 }, { "epoch": 0.8439771547248183, "grad_norm": 9.86083984375, "learning_rate": 3.418965008540371e-06, "loss": 0.26235097646713257, "step": 3251 }, { "epoch": 0.8442367601246106, "grad_norm": 5.705347061157227, "learning_rate": 3.418061719768916e-06, "loss": 0.2813965976238251, "step": 3252 }, { "epoch": 0.8444963655244029, "grad_norm": 9.52481746673584, "learning_rate": 3.4171583128994453e-06, "loss": 0.22513900697231293, "step": 3253 }, { "epoch": 0.8447559709241952, "grad_norm": 3.9038584232330322, "learning_rate": 3.41625478809166e-06, "loss": 0.33068355917930603, "step": 3254 }, { "epoch": 0.8450155763239875, "grad_norm": 9.021575927734375, "learning_rate": 3.4153511455052844e-06, "loss": 0.32971328496932983, "step": 3255 }, { "epoch": 0.8452751817237798, "grad_norm": 5.2115397453308105, "learning_rate": 3.414447385300061e-06, "loss": 0.3013721704483032, "step": 3256 }, { "epoch": 0.8455347871235722, "grad_norm": 10.804703712463379, "learning_rate": 3.4135435076357537e-06, "loss": 0.2677058279514313, "step": 3257 }, { "epoch": 0.8457943925233645, "grad_norm": 8.150985717773438, "learning_rate": 3.412639512672147e-06, "loss": 0.17044945061206818, "step": 3258 }, { "epoch": 0.8460539979231568, "grad_norm": 6.9929046630859375, "learning_rate": 3.411735400569046e-06, "loss": 0.3109116554260254, "step": 3259 }, { "epoch": 0.8463136033229491, "grad_norm": 5.574970722198486, "learning_rate": 3.41083117148628e-06, "loss": 0.32946205139160156, "step": 3260 }, { "epoch": 0.8465732087227414, "grad_norm": 9.226449012756348, "learning_rate": 3.409926825583692e-06, "loss": 0.23861879110336304, "step": 3261 }, { "epoch": 0.8468328141225338, "grad_norm": 10.704353332519531, "learning_rate": 3.4090223630211523e-06, "loss": 0.18831953406333923, "step": 3262 }, { "epoch": 0.8470924195223261, "grad_norm": 5.245989799499512, "learning_rate": 3.4081177839585485e-06, "loss": 0.3359377682209015, "step": 3263 }, { "epoch": 0.8473520249221184, "grad_norm": 5.041751861572266, "learning_rate": 3.407213088555789e-06, "loss": 0.26192983984947205, "step": 3264 }, { "epoch": 0.8476116303219107, "grad_norm": 6.491723537445068, "learning_rate": 3.4063082769728045e-06, "loss": 0.19228598475456238, "step": 3265 }, { "epoch": 0.847871235721703, "grad_norm": 12.46094036102295, "learning_rate": 3.405403349369544e-06, "loss": 0.19657589495182037, "step": 3266 }, { "epoch": 0.8481308411214953, "grad_norm": 8.803661346435547, "learning_rate": 3.4044983059059766e-06, "loss": 0.19999918341636658, "step": 3267 }, { "epoch": 0.8483904465212876, "grad_norm": 6.022563457489014, "learning_rate": 3.4035931467420964e-06, "loss": 0.36015188694000244, "step": 3268 }, { "epoch": 0.84865005192108, "grad_norm": 7.631641864776611, "learning_rate": 3.402687872037912e-06, "loss": 0.2544587254524231, "step": 3269 }, { "epoch": 0.8489096573208723, "grad_norm": 9.269041061401367, "learning_rate": 3.401782481953457e-06, "loss": 0.13658609986305237, "step": 3270 }, { "epoch": 0.8491692627206646, "grad_norm": 5.768779277801514, "learning_rate": 3.4008769766487826e-06, "loss": 0.2945604920387268, "step": 3271 }, { "epoch": 0.8494288681204569, "grad_norm": 4.321394443511963, "learning_rate": 3.399971356283963e-06, "loss": 0.3234243392944336, "step": 3272 }, { "epoch": 0.8496884735202492, "grad_norm": 10.621495246887207, "learning_rate": 3.399065621019089e-06, "loss": 0.17059513926506042, "step": 3273 }, { "epoch": 0.8499480789200415, "grad_norm": 7.865368366241455, "learning_rate": 3.3981597710142757e-06, "loss": 0.22289274632930756, "step": 3274 }, { "epoch": 0.8502076843198338, "grad_norm": 5.5510687828063965, "learning_rate": 3.3972538064296545e-06, "loss": 0.304837703704834, "step": 3275 }, { "epoch": 0.8504672897196262, "grad_norm": 4.9162797927856445, "learning_rate": 3.396347727425381e-06, "loss": 0.3113331198692322, "step": 3276 }, { "epoch": 0.8507268951194185, "grad_norm": 6.320882320404053, "learning_rate": 3.3954415341616285e-06, "loss": 0.3165271282196045, "step": 3277 }, { "epoch": 0.8509865005192108, "grad_norm": 9.43779182434082, "learning_rate": 3.394535226798592e-06, "loss": 0.13337819278240204, "step": 3278 }, { "epoch": 0.8512461059190031, "grad_norm": 12.21671199798584, "learning_rate": 3.393628805496485e-06, "loss": 0.22363102436065674, "step": 3279 }, { "epoch": 0.8515057113187954, "grad_norm": 3.2687296867370605, "learning_rate": 3.3927222704155415e-06, "loss": 0.34359490871429443, "step": 3280 }, { "epoch": 0.8517653167185878, "grad_norm": 5.919684410095215, "learning_rate": 3.3918156217160182e-06, "loss": 0.26591432094573975, "step": 3281 }, { "epoch": 0.8520249221183801, "grad_norm": 7.4159159660339355, "learning_rate": 3.3909088595581884e-06, "loss": 0.32546383142471313, "step": 3282 }, { "epoch": 0.8522845275181724, "grad_norm": 6.437912464141846, "learning_rate": 3.3900019841023476e-06, "loss": 0.2553894817829132, "step": 3283 }, { "epoch": 0.8525441329179647, "grad_norm": 4.554826736450195, "learning_rate": 3.389094995508809e-06, "loss": 0.2604043185710907, "step": 3284 }, { "epoch": 0.852803738317757, "grad_norm": 11.538936614990234, "learning_rate": 3.3881878939379086e-06, "loss": 0.22239141166210175, "step": 3285 }, { "epoch": 0.8530633437175493, "grad_norm": 11.966357231140137, "learning_rate": 3.3872806795500014e-06, "loss": 0.16284093260765076, "step": 3286 }, { "epoch": 0.8533229491173416, "grad_norm": 8.190706253051758, "learning_rate": 3.386373352505462e-06, "loss": 0.2461293637752533, "step": 3287 }, { "epoch": 0.8535825545171339, "grad_norm": 3.7965989112854004, "learning_rate": 3.385465912964685e-06, "loss": 0.35072895884513855, "step": 3288 }, { "epoch": 0.8538421599169262, "grad_norm": 11.536164283752441, "learning_rate": 3.3845583610880844e-06, "loss": 0.21775315701961517, "step": 3289 }, { "epoch": 0.8541017653167186, "grad_norm": 10.653242111206055, "learning_rate": 3.383650697036095e-06, "loss": 0.1547721028327942, "step": 3290 }, { "epoch": 0.8543613707165109, "grad_norm": 3.568159580230713, "learning_rate": 3.3827429209691722e-06, "loss": 0.32104766368865967, "step": 3291 }, { "epoch": 0.8546209761163032, "grad_norm": 6.5399489402771, "learning_rate": 3.3818350330477874e-06, "loss": 0.29987502098083496, "step": 3292 }, { "epoch": 0.8548805815160956, "grad_norm": 7.089338779449463, "learning_rate": 3.3809270334324364e-06, "loss": 0.3173566460609436, "step": 3293 }, { "epoch": 0.8551401869158879, "grad_norm": 6.551617622375488, "learning_rate": 3.3800189222836316e-06, "loss": 0.24963554739952087, "step": 3294 }, { "epoch": 0.8553997923156802, "grad_norm": 6.4391608238220215, "learning_rate": 3.3791106997619078e-06, "loss": 0.23778221011161804, "step": 3295 }, { "epoch": 0.8556593977154725, "grad_norm": 6.704909801483154, "learning_rate": 3.378202366027817e-06, "loss": 0.31964436173439026, "step": 3296 }, { "epoch": 0.8559190031152648, "grad_norm": 8.18769645690918, "learning_rate": 3.3772939212419314e-06, "loss": 0.3159995675086975, "step": 3297 }, { "epoch": 0.8561786085150571, "grad_norm": 8.724250793457031, "learning_rate": 3.3763853655648436e-06, "loss": 0.18857789039611816, "step": 3298 }, { "epoch": 0.8564382139148494, "grad_norm": 10.957064628601074, "learning_rate": 3.3754766991571657e-06, "loss": 0.15006187558174133, "step": 3299 }, { "epoch": 0.8566978193146417, "grad_norm": 11.265565872192383, "learning_rate": 3.3745679221795284e-06, "loss": 0.2422826588153839, "step": 3300 }, { "epoch": 0.856957424714434, "grad_norm": 4.29692268371582, "learning_rate": 3.3736590347925842e-06, "loss": 0.29470717906951904, "step": 3301 }, { "epoch": 0.8572170301142263, "grad_norm": 5.191999435424805, "learning_rate": 3.3727500371570014e-06, "loss": 0.23659351468086243, "step": 3302 }, { "epoch": 0.8574766355140186, "grad_norm": 4.155877113342285, "learning_rate": 3.371840929433472e-06, "loss": 0.3936411738395691, "step": 3303 }, { "epoch": 0.857736240913811, "grad_norm": 7.100390434265137, "learning_rate": 3.370931711782704e-06, "loss": 0.26964110136032104, "step": 3304 }, { "epoch": 0.8579958463136034, "grad_norm": 5.4872050285339355, "learning_rate": 3.370022384365427e-06, "loss": 0.2720520496368408, "step": 3305 }, { "epoch": 0.8582554517133957, "grad_norm": 4.795141220092773, "learning_rate": 3.3691129473423895e-06, "loss": 0.3009631335735321, "step": 3306 }, { "epoch": 0.858515057113188, "grad_norm": 11.68492603302002, "learning_rate": 3.368203400874358e-06, "loss": 0.2731561064720154, "step": 3307 }, { "epoch": 0.8587746625129803, "grad_norm": 5.348812580108643, "learning_rate": 3.3672937451221206e-06, "loss": 0.2542460262775421, "step": 3308 }, { "epoch": 0.8590342679127726, "grad_norm": 14.568070411682129, "learning_rate": 3.366383980246483e-06, "loss": 0.18590694665908813, "step": 3309 }, { "epoch": 0.8592938733125649, "grad_norm": 12.536148071289062, "learning_rate": 3.3654741064082712e-06, "loss": 0.17590391635894775, "step": 3310 }, { "epoch": 0.8595534787123572, "grad_norm": 4.912477016448975, "learning_rate": 3.3645641237683295e-06, "loss": 0.2935693860054016, "step": 3311 }, { "epoch": 0.8598130841121495, "grad_norm": 8.889856338500977, "learning_rate": 3.363654032487523e-06, "loss": 0.26715609431266785, "step": 3312 }, { "epoch": 0.8600726895119418, "grad_norm": 4.183051109313965, "learning_rate": 3.362743832726735e-06, "loss": 0.2740701138973236, "step": 3313 }, { "epoch": 0.8603322949117341, "grad_norm": 11.625319480895996, "learning_rate": 3.3618335246468657e-06, "loss": 0.17105108499526978, "step": 3314 }, { "epoch": 0.8605919003115264, "grad_norm": 9.998305320739746, "learning_rate": 3.360923108408839e-06, "loss": 0.20728367567062378, "step": 3315 }, { "epoch": 0.8608515057113187, "grad_norm": 4.098561763763428, "learning_rate": 3.3600125841735955e-06, "loss": 0.3444480299949646, "step": 3316 }, { "epoch": 0.8611111111111112, "grad_norm": 6.115469932556152, "learning_rate": 3.359101952102094e-06, "loss": 0.3009290099143982, "step": 3317 }, { "epoch": 0.8613707165109035, "grad_norm": 10.234269142150879, "learning_rate": 3.3581912123553144e-06, "loss": 0.21396750211715698, "step": 3318 }, { "epoch": 0.8616303219106958, "grad_norm": 9.193540573120117, "learning_rate": 3.357280365094254e-06, "loss": 0.34177613258361816, "step": 3319 }, { "epoch": 0.8618899273104881, "grad_norm": 4.115030765533447, "learning_rate": 3.3563694104799292e-06, "loss": 0.31425416469573975, "step": 3320 }, { "epoch": 0.8621495327102804, "grad_norm": 10.263819694519043, "learning_rate": 3.3554583486733776e-06, "loss": 0.26706868410110474, "step": 3321 }, { "epoch": 0.8624091381100727, "grad_norm": 4.950944900512695, "learning_rate": 3.3545471798356526e-06, "loss": 0.23817817866802216, "step": 3322 }, { "epoch": 0.862668743509865, "grad_norm": 8.983583450317383, "learning_rate": 3.353635904127829e-06, "loss": 0.21694687008857727, "step": 3323 }, { "epoch": 0.8629283489096573, "grad_norm": 4.579959392547607, "learning_rate": 3.3527245217109986e-06, "loss": 0.2632017731666565, "step": 3324 }, { "epoch": 0.8631879543094496, "grad_norm": 5.133302211761475, "learning_rate": 3.3518130327462734e-06, "loss": 0.32506683468818665, "step": 3325 }, { "epoch": 0.8634475597092419, "grad_norm": 3.855862855911255, "learning_rate": 3.3509014373947834e-06, "loss": 0.31317269802093506, "step": 3326 }, { "epoch": 0.8637071651090342, "grad_norm": 4.487433910369873, "learning_rate": 3.3499897358176793e-06, "loss": 0.30648621916770935, "step": 3327 }, { "epoch": 0.8639667705088265, "grad_norm": 7.404778003692627, "learning_rate": 3.349077928176126e-06, "loss": 0.24009060859680176, "step": 3328 }, { "epoch": 0.864226375908619, "grad_norm": 7.672855854034424, "learning_rate": 3.3481660146313133e-06, "loss": 0.14735056459903717, "step": 3329 }, { "epoch": 0.8644859813084113, "grad_norm": 9.81471061706543, "learning_rate": 3.3472539953444453e-06, "loss": 0.22247225046157837, "step": 3330 }, { "epoch": 0.8647455867082036, "grad_norm": 10.632919311523438, "learning_rate": 3.346341870476746e-06, "loss": 0.15367138385772705, "step": 3331 }, { "epoch": 0.8650051921079959, "grad_norm": 9.05982494354248, "learning_rate": 3.3454296401894585e-06, "loss": 0.20652835071086884, "step": 3332 }, { "epoch": 0.8652647975077882, "grad_norm": 6.769678115844727, "learning_rate": 3.344517304643844e-06, "loss": 0.2655715346336365, "step": 3333 }, { "epoch": 0.8655244029075805, "grad_norm": 11.743613243103027, "learning_rate": 3.3436048640011832e-06, "loss": 0.2572195529937744, "step": 3334 }, { "epoch": 0.8657840083073728, "grad_norm": 7.0060601234436035, "learning_rate": 3.342692318422773e-06, "loss": 0.30613839626312256, "step": 3335 }, { "epoch": 0.8660436137071651, "grad_norm": 5.5456719398498535, "learning_rate": 3.3417796680699334e-06, "loss": 0.3142770528793335, "step": 3336 }, { "epoch": 0.8663032191069574, "grad_norm": 11.45893383026123, "learning_rate": 3.3408669131039972e-06, "loss": 0.23566916584968567, "step": 3337 }, { "epoch": 0.8665628245067497, "grad_norm": 9.452194213867188, "learning_rate": 3.33995405368632e-06, "loss": 0.2900446057319641, "step": 3338 }, { "epoch": 0.866822429906542, "grad_norm": 5.103531360626221, "learning_rate": 3.3390410899782748e-06, "loss": 0.2997591197490692, "step": 3339 }, { "epoch": 0.8670820353063343, "grad_norm": 4.590688228607178, "learning_rate": 3.3381280221412517e-06, "loss": 0.33945149183273315, "step": 3340 }, { "epoch": 0.8673416407061267, "grad_norm": 9.28467845916748, "learning_rate": 3.3372148503366607e-06, "loss": 0.10412970185279846, "step": 3341 }, { "epoch": 0.867601246105919, "grad_norm": 7.643020153045654, "learning_rate": 3.3363015747259294e-06, "loss": 0.309054434299469, "step": 3342 }, { "epoch": 0.8678608515057114, "grad_norm": 7.409242153167725, "learning_rate": 3.3353881954705047e-06, "loss": 0.2707344889640808, "step": 3343 }, { "epoch": 0.8681204569055037, "grad_norm": 6.76283073425293, "learning_rate": 3.3344747127318506e-06, "loss": 0.2884918749332428, "step": 3344 }, { "epoch": 0.868380062305296, "grad_norm": 14.945289611816406, "learning_rate": 3.33356112667145e-06, "loss": 0.18852102756500244, "step": 3345 }, { "epoch": 0.8686396677050883, "grad_norm": 8.666985511779785, "learning_rate": 3.332647437450803e-06, "loss": 0.20602717995643616, "step": 3346 }, { "epoch": 0.8688992731048806, "grad_norm": 10.341415405273438, "learning_rate": 3.3317336452314308e-06, "loss": 0.26861482858657837, "step": 3347 }, { "epoch": 0.8691588785046729, "grad_norm": 4.513097763061523, "learning_rate": 3.33081975017487e-06, "loss": 0.29399389028549194, "step": 3348 }, { "epoch": 0.8694184839044652, "grad_norm": 3.926178216934204, "learning_rate": 3.329905752442677e-06, "loss": 0.30769529938697815, "step": 3349 }, { "epoch": 0.8696780893042575, "grad_norm": 6.442591667175293, "learning_rate": 3.328991652196424e-06, "loss": 0.3132849335670471, "step": 3350 }, { "epoch": 0.8699376947040498, "grad_norm": 5.672098159790039, "learning_rate": 3.3280774495977048e-06, "loss": 0.26291123032569885, "step": 3351 }, { "epoch": 0.8701973001038421, "grad_norm": 7.450997352600098, "learning_rate": 3.3271631448081277e-06, "loss": 0.15740421414375305, "step": 3352 }, { "epoch": 0.8704569055036345, "grad_norm": 5.108365058898926, "learning_rate": 3.3262487379893227e-06, "loss": 0.26365116238594055, "step": 3353 }, { "epoch": 0.8707165109034268, "grad_norm": 4.759271144866943, "learning_rate": 3.325334229302935e-06, "loss": 0.3094634413719177, "step": 3354 }, { "epoch": 0.8709761163032191, "grad_norm": 8.587971687316895, "learning_rate": 3.3244196189106287e-06, "loss": 0.27449193596839905, "step": 3355 }, { "epoch": 0.8712357217030114, "grad_norm": 14.204000473022461, "learning_rate": 3.3235049069740864e-06, "loss": 0.21495799720287323, "step": 3356 }, { "epoch": 0.8714953271028038, "grad_norm": 7.856698036193848, "learning_rate": 3.3225900936550094e-06, "loss": 0.18094107508659363, "step": 3357 }, { "epoch": 0.8717549325025961, "grad_norm": 3.6069488525390625, "learning_rate": 3.3216751791151124e-06, "loss": 0.2875344753265381, "step": 3358 }, { "epoch": 0.8720145379023884, "grad_norm": 14.362724304199219, "learning_rate": 3.320760163516134e-06, "loss": 0.2135678082704544, "step": 3359 }, { "epoch": 0.8722741433021807, "grad_norm": 3.768664598464966, "learning_rate": 3.3198450470198273e-06, "loss": 0.32476913928985596, "step": 3360 }, { "epoch": 0.872533748701973, "grad_norm": 5.715640544891357, "learning_rate": 3.3189298297879653e-06, "loss": 0.25708845257759094, "step": 3361 }, { "epoch": 0.8727933541017653, "grad_norm": 6.3815226554870605, "learning_rate": 3.3180145119823347e-06, "loss": 0.25375208258628845, "step": 3362 }, { "epoch": 0.8730529595015576, "grad_norm": 10.068909645080566, "learning_rate": 3.3170990937647445e-06, "loss": 0.2085573524236679, "step": 3363 }, { "epoch": 0.8733125649013499, "grad_norm": 4.009922504425049, "learning_rate": 3.316183575297019e-06, "loss": 0.2883650064468384, "step": 3364 }, { "epoch": 0.8735721703011423, "grad_norm": 3.5308175086975098, "learning_rate": 3.3152679567410023e-06, "loss": 0.32812434434890747, "step": 3365 }, { "epoch": 0.8738317757009346, "grad_norm": 9.266546249389648, "learning_rate": 3.3143522382585536e-06, "loss": 0.23008903861045837, "step": 3366 }, { "epoch": 0.8740913811007269, "grad_norm": 8.244917869567871, "learning_rate": 3.3134364200115504e-06, "loss": 0.28532156348228455, "step": 3367 }, { "epoch": 0.8743509865005192, "grad_norm": 4.332717418670654, "learning_rate": 3.3125205021618893e-06, "loss": 0.3027380704879761, "step": 3368 }, { "epoch": 0.8746105919003115, "grad_norm": 8.915938377380371, "learning_rate": 3.3116044848714833e-06, "loss": 0.17640388011932373, "step": 3369 }, { "epoch": 0.8748701973001038, "grad_norm": 9.668608665466309, "learning_rate": 3.3106883683022646e-06, "loss": 0.22430770099163055, "step": 3370 }, { "epoch": 0.8751298026998962, "grad_norm": 3.911221742630005, "learning_rate": 3.309772152616179e-06, "loss": 0.3126119375228882, "step": 3371 }, { "epoch": 0.8753894080996885, "grad_norm": 3.549042224884033, "learning_rate": 3.3088558379751945e-06, "loss": 0.32026562094688416, "step": 3372 }, { "epoch": 0.8756490134994808, "grad_norm": 4.103643894195557, "learning_rate": 3.307939424541294e-06, "loss": 0.3031999468803406, "step": 3373 }, { "epoch": 0.8759086188992731, "grad_norm": 11.400967597961426, "learning_rate": 3.3070229124764784e-06, "loss": 0.2157503068447113, "step": 3374 }, { "epoch": 0.8761682242990654, "grad_norm": 11.847726821899414, "learning_rate": 3.3061063019427653e-06, "loss": 0.3221629858016968, "step": 3375 }, { "epoch": 0.8764278296988577, "grad_norm": 2.9941954612731934, "learning_rate": 3.305189593102192e-06, "loss": 0.305564284324646, "step": 3376 }, { "epoch": 0.8766874350986501, "grad_norm": 5.692251205444336, "learning_rate": 3.30427278611681e-06, "loss": 0.2728239595890045, "step": 3377 }, { "epoch": 0.8769470404984424, "grad_norm": 8.234871864318848, "learning_rate": 3.3033558811486915e-06, "loss": 0.2618536353111267, "step": 3378 }, { "epoch": 0.8772066458982347, "grad_norm": 9.485240936279297, "learning_rate": 3.302438878359923e-06, "loss": 0.2024955451488495, "step": 3379 }, { "epoch": 0.877466251298027, "grad_norm": 6.691384792327881, "learning_rate": 3.30152177791261e-06, "loss": 0.2504940629005432, "step": 3380 }, { "epoch": 0.8777258566978193, "grad_norm": 3.690040111541748, "learning_rate": 3.300604579968875e-06, "loss": 0.27827826142311096, "step": 3381 }, { "epoch": 0.8779854620976116, "grad_norm": 3.3432419300079346, "learning_rate": 3.2996872846908574e-06, "loss": 0.2883632481098175, "step": 3382 }, { "epoch": 0.8782450674974039, "grad_norm": 17.010066986083984, "learning_rate": 3.298769892240713e-06, "loss": 0.19515933096408844, "step": 3383 }, { "epoch": 0.8785046728971962, "grad_norm": 13.264678001403809, "learning_rate": 3.2978524027806185e-06, "loss": 0.19693708419799805, "step": 3384 }, { "epoch": 0.8787642782969886, "grad_norm": 4.424168586730957, "learning_rate": 3.2969348164727624e-06, "loss": 0.2645060420036316, "step": 3385 }, { "epoch": 0.8790238836967809, "grad_norm": 9.87037181854248, "learning_rate": 3.296017133479354e-06, "loss": 0.15928912162780762, "step": 3386 }, { "epoch": 0.8792834890965732, "grad_norm": 9.689916610717773, "learning_rate": 3.295099353962618e-06, "loss": 0.30358946323394775, "step": 3387 }, { "epoch": 0.8795430944963655, "grad_norm": 6.7747907638549805, "learning_rate": 3.2941814780847987e-06, "loss": 0.279344379901886, "step": 3388 }, { "epoch": 0.8798026998961579, "grad_norm": 11.809818267822266, "learning_rate": 3.293263506008153e-06, "loss": 0.16252358257770538, "step": 3389 }, { "epoch": 0.8800623052959502, "grad_norm": 10.988349914550781, "learning_rate": 3.2923454378949587e-06, "loss": 0.2335195541381836, "step": 3390 }, { "epoch": 0.8803219106957425, "grad_norm": 6.631229400634766, "learning_rate": 3.291427273907509e-06, "loss": 0.26741546392440796, "step": 3391 }, { "epoch": 0.8805815160955348, "grad_norm": 9.817219734191895, "learning_rate": 3.2905090142081147e-06, "loss": 0.2555844783782959, "step": 3392 }, { "epoch": 0.8808411214953271, "grad_norm": 5.2583327293396, "learning_rate": 3.289590658959103e-06, "loss": 0.2582080662250519, "step": 3393 }, { "epoch": 0.8811007268951194, "grad_norm": 9.25303840637207, "learning_rate": 3.2886722083228177e-06, "loss": 0.16421276330947876, "step": 3394 }, { "epoch": 0.8813603322949117, "grad_norm": 10.076031684875488, "learning_rate": 3.2877536624616198e-06, "loss": 0.2802702784538269, "step": 3395 }, { "epoch": 0.881619937694704, "grad_norm": 9.230013847351074, "learning_rate": 3.286835021537886e-06, "loss": 0.14194735884666443, "step": 3396 }, { "epoch": 0.8818795430944963, "grad_norm": 7.550843238830566, "learning_rate": 3.2859162857140143e-06, "loss": 0.355927050113678, "step": 3397 }, { "epoch": 0.8821391484942886, "grad_norm": 9.470573425292969, "learning_rate": 3.2849974551524135e-06, "loss": 0.13054457306861877, "step": 3398 }, { "epoch": 0.882398753894081, "grad_norm": 3.6056318283081055, "learning_rate": 3.284078530015512e-06, "loss": 0.29835814237594604, "step": 3399 }, { "epoch": 0.8826583592938733, "grad_norm": 7.097720146179199, "learning_rate": 3.2831595104657547e-06, "loss": 0.22074095904827118, "step": 3400 }, { "epoch": 0.8829179646936657, "grad_norm": 15.417861938476562, "learning_rate": 3.2822403966656045e-06, "loss": 0.2186710089445114, "step": 3401 }, { "epoch": 0.883177570093458, "grad_norm": 3.2723984718322754, "learning_rate": 3.2813211887775386e-06, "loss": 0.3105984330177307, "step": 3402 }, { "epoch": 0.8834371754932503, "grad_norm": 7.023527145385742, "learning_rate": 3.2804018869640525e-06, "loss": 0.26443952322006226, "step": 3403 }, { "epoch": 0.8836967808930426, "grad_norm": 5.686655044555664, "learning_rate": 3.279482491387657e-06, "loss": 0.3091106712818146, "step": 3404 }, { "epoch": 0.8839563862928349, "grad_norm": 8.427488327026367, "learning_rate": 3.2785630022108804e-06, "loss": 0.351144403219223, "step": 3405 }, { "epoch": 0.8842159916926272, "grad_norm": 8.446015357971191, "learning_rate": 3.2776434195962682e-06, "loss": 0.17824658751487732, "step": 3406 }, { "epoch": 0.8844755970924195, "grad_norm": 3.452984094619751, "learning_rate": 3.2767237437063803e-06, "loss": 0.3375275731086731, "step": 3407 }, { "epoch": 0.8847352024922118, "grad_norm": 8.875057220458984, "learning_rate": 3.2758039747037944e-06, "loss": 0.18152616918087006, "step": 3408 }, { "epoch": 0.8849948078920041, "grad_norm": 3.730839490890503, "learning_rate": 3.274884112751106e-06, "loss": 0.2968023419380188, "step": 3409 }, { "epoch": 0.8852544132917964, "grad_norm": 10.793548583984375, "learning_rate": 3.2739641580109243e-06, "loss": 0.24593427777290344, "step": 3410 }, { "epoch": 0.8855140186915887, "grad_norm": 10.22158145904541, "learning_rate": 3.273044110645878e-06, "loss": 0.3008277118206024, "step": 3411 }, { "epoch": 0.885773624091381, "grad_norm": 8.028698921203613, "learning_rate": 3.2721239708186077e-06, "loss": 0.19338637590408325, "step": 3412 }, { "epoch": 0.8860332294911735, "grad_norm": 5.901490688323975, "learning_rate": 3.271203738691774e-06, "loss": 0.2422260344028473, "step": 3413 }, { "epoch": 0.8862928348909658, "grad_norm": 4.4840240478515625, "learning_rate": 3.2702834144280536e-06, "loss": 0.3117758631706238, "step": 3414 }, { "epoch": 0.8865524402907581, "grad_norm": 4.896306037902832, "learning_rate": 3.2693629981901392e-06, "loss": 0.307345449924469, "step": 3415 }, { "epoch": 0.8868120456905504, "grad_norm": 4.541911602020264, "learning_rate": 3.268442490140738e-06, "loss": 0.27973324060440063, "step": 3416 }, { "epoch": 0.8870716510903427, "grad_norm": 3.6485395431518555, "learning_rate": 3.2675218904425748e-06, "loss": 0.27817338705062866, "step": 3417 }, { "epoch": 0.887331256490135, "grad_norm": 7.1854248046875, "learning_rate": 3.266601199258391e-06, "loss": 0.2654880881309509, "step": 3418 }, { "epoch": 0.8875908618899273, "grad_norm": 7.295029640197754, "learning_rate": 3.2656804167509456e-06, "loss": 0.240975022315979, "step": 3419 }, { "epoch": 0.8878504672897196, "grad_norm": 3.966637372970581, "learning_rate": 3.264759543083009e-06, "loss": 0.28381285071372986, "step": 3420 }, { "epoch": 0.8881100726895119, "grad_norm": 8.894929885864258, "learning_rate": 3.2638385784173704e-06, "loss": 0.23712538182735443, "step": 3421 }, { "epoch": 0.8883696780893042, "grad_norm": 5.539900779724121, "learning_rate": 3.262917522916838e-06, "loss": 0.3345686197280884, "step": 3422 }, { "epoch": 0.8886292834890965, "grad_norm": 10.729443550109863, "learning_rate": 3.2619963767442314e-06, "loss": 0.20733314752578735, "step": 3423 }, { "epoch": 0.8888888888888888, "grad_norm": 12.117618560791016, "learning_rate": 3.2610751400623887e-06, "loss": 0.21852925419807434, "step": 3424 }, { "epoch": 0.8891484942886813, "grad_norm": 12.216233253479004, "learning_rate": 3.2601538130341627e-06, "loss": 0.1634184718132019, "step": 3425 }, { "epoch": 0.8894080996884736, "grad_norm": 6.742727756500244, "learning_rate": 3.2592323958224236e-06, "loss": 0.22049862146377563, "step": 3426 }, { "epoch": 0.8896677050882659, "grad_norm": 12.121562957763672, "learning_rate": 3.258310888590058e-06, "loss": 0.12247808277606964, "step": 3427 }, { "epoch": 0.8899273104880582, "grad_norm": 4.030780792236328, "learning_rate": 3.257389291499965e-06, "loss": 0.32255345582962036, "step": 3428 }, { "epoch": 0.8901869158878505, "grad_norm": 6.715838432312012, "learning_rate": 3.256467604715062e-06, "loss": 0.34741145372390747, "step": 3429 }, { "epoch": 0.8904465212876428, "grad_norm": 6.235073566436768, "learning_rate": 3.255545828398285e-06, "loss": 0.25708895921707153, "step": 3430 }, { "epoch": 0.8907061266874351, "grad_norm": 11.18893051147461, "learning_rate": 3.2546239627125796e-06, "loss": 0.3231753706932068, "step": 3431 }, { "epoch": 0.8909657320872274, "grad_norm": 10.892372131347656, "learning_rate": 3.2537020078209126e-06, "loss": 0.16800394654273987, "step": 3432 }, { "epoch": 0.8912253374870197, "grad_norm": 5.065823078155518, "learning_rate": 3.252779963886264e-06, "loss": 0.25736868381500244, "step": 3433 }, { "epoch": 0.891484942886812, "grad_norm": 8.718746185302734, "learning_rate": 3.25185783107163e-06, "loss": 0.1689431369304657, "step": 3434 }, { "epoch": 0.8917445482866043, "grad_norm": 11.377795219421387, "learning_rate": 3.250935609540021e-06, "loss": 0.32102030515670776, "step": 3435 }, { "epoch": 0.8920041536863966, "grad_norm": 13.473759651184082, "learning_rate": 3.250013299454468e-06, "loss": 0.22399680316448212, "step": 3436 }, { "epoch": 0.892263759086189, "grad_norm": 3.465585470199585, "learning_rate": 3.2490909009780117e-06, "loss": 0.2973029315471649, "step": 3437 }, { "epoch": 0.8925233644859814, "grad_norm": 4.593074798583984, "learning_rate": 3.248168414273712e-06, "loss": 0.28391802310943604, "step": 3438 }, { "epoch": 0.8927829698857737, "grad_norm": 11.436718940734863, "learning_rate": 3.2472458395046423e-06, "loss": 0.1844031810760498, "step": 3439 }, { "epoch": 0.893042575285566, "grad_norm": 10.124654769897461, "learning_rate": 3.2463231768338954e-06, "loss": 0.3350117802619934, "step": 3440 }, { "epoch": 0.8933021806853583, "grad_norm": 6.581059455871582, "learning_rate": 3.2454004264245735e-06, "loss": 0.23701392114162445, "step": 3441 }, { "epoch": 0.8935617860851506, "grad_norm": 8.525303840637207, "learning_rate": 3.2444775884398e-06, "loss": 0.19644856452941895, "step": 3442 }, { "epoch": 0.8938213914849429, "grad_norm": 5.23052978515625, "learning_rate": 3.2435546630427105e-06, "loss": 0.2662343978881836, "step": 3443 }, { "epoch": 0.8940809968847352, "grad_norm": 6.667723655700684, "learning_rate": 3.2426316503964583e-06, "loss": 0.21365417540073395, "step": 3444 }, { "epoch": 0.8943406022845275, "grad_norm": 3.931253671646118, "learning_rate": 3.2417085506642095e-06, "loss": 0.2966335415840149, "step": 3445 }, { "epoch": 0.8946002076843198, "grad_norm": 7.902840614318848, "learning_rate": 3.240785364009148e-06, "loss": 0.25424936413764954, "step": 3446 }, { "epoch": 0.8948598130841121, "grad_norm": 5.9382710456848145, "learning_rate": 3.239862090594471e-06, "loss": 0.26823845505714417, "step": 3447 }, { "epoch": 0.8951194184839044, "grad_norm": 4.785794258117676, "learning_rate": 3.2389387305833932e-06, "loss": 0.3069922924041748, "step": 3448 }, { "epoch": 0.8953790238836968, "grad_norm": 7.566030025482178, "learning_rate": 3.238015284139143e-06, "loss": 0.1900220811367035, "step": 3449 }, { "epoch": 0.8956386292834891, "grad_norm": 7.083916664123535, "learning_rate": 3.2370917514249646e-06, "loss": 0.31084197759628296, "step": 3450 }, { "epoch": 0.8958982346832814, "grad_norm": 5.074721813201904, "learning_rate": 3.2361681326041167e-06, "loss": 0.2824740409851074, "step": 3451 }, { "epoch": 0.8961578400830738, "grad_norm": 9.345532417297363, "learning_rate": 3.2352444278398754e-06, "loss": 0.22466181218624115, "step": 3452 }, { "epoch": 0.8964174454828661, "grad_norm": 8.904326438903809, "learning_rate": 3.2343206372955305e-06, "loss": 0.1986542046070099, "step": 3453 }, { "epoch": 0.8966770508826584, "grad_norm": 5.740591049194336, "learning_rate": 3.2333967611343854e-06, "loss": 0.3121699392795563, "step": 3454 }, { "epoch": 0.8969366562824507, "grad_norm": 7.6248908042907715, "learning_rate": 3.232472799519762e-06, "loss": 0.34174028038978577, "step": 3455 }, { "epoch": 0.897196261682243, "grad_norm": 10.263611793518066, "learning_rate": 3.231548752614994e-06, "loss": 0.24685800075531006, "step": 3456 }, { "epoch": 0.8974558670820353, "grad_norm": 11.06263542175293, "learning_rate": 3.2306246205834333e-06, "loss": 0.2898288071155548, "step": 3457 }, { "epoch": 0.8977154724818276, "grad_norm": 5.649982929229736, "learning_rate": 3.229700403588444e-06, "loss": 0.3077869415283203, "step": 3458 }, { "epoch": 0.8979750778816199, "grad_norm": 9.634500503540039, "learning_rate": 3.2287761017934076e-06, "loss": 0.24713711440563202, "step": 3459 }, { "epoch": 0.8982346832814122, "grad_norm": 11.104369163513184, "learning_rate": 3.2278517153617186e-06, "loss": 0.21587234735488892, "step": 3460 }, { "epoch": 0.8984942886812046, "grad_norm": 9.141768455505371, "learning_rate": 3.226927244456788e-06, "loss": 0.16627033054828644, "step": 3461 }, { "epoch": 0.8987538940809969, "grad_norm": 5.129382610321045, "learning_rate": 3.2260026892420397e-06, "loss": 0.2937810719013214, "step": 3462 }, { "epoch": 0.8990134994807892, "grad_norm": 12.906494140625, "learning_rate": 3.2250780498809157e-06, "loss": 0.2031383514404297, "step": 3463 }, { "epoch": 0.8992731048805815, "grad_norm": 3.273242950439453, "learning_rate": 3.22415332653687e-06, "loss": 0.2832852303981781, "step": 3464 }, { "epoch": 0.8995327102803738, "grad_norm": 3.2635602951049805, "learning_rate": 3.2232285193733735e-06, "loss": 0.3130720257759094, "step": 3465 }, { "epoch": 0.8997923156801662, "grad_norm": 6.894681453704834, "learning_rate": 3.2223036285539092e-06, "loss": 0.25511759519577026, "step": 3466 }, { "epoch": 0.9000519210799585, "grad_norm": 8.391773223876953, "learning_rate": 3.2213786542419796e-06, "loss": 0.17464831471443176, "step": 3467 }, { "epoch": 0.9003115264797508, "grad_norm": 4.563185214996338, "learning_rate": 3.220453596601096e-06, "loss": 0.295016348361969, "step": 3468 }, { "epoch": 0.9005711318795431, "grad_norm": 3.7181320190429688, "learning_rate": 3.219528455794788e-06, "loss": 0.3061586618423462, "step": 3469 }, { "epoch": 0.9008307372793354, "grad_norm": 8.79765796661377, "learning_rate": 3.2186032319866e-06, "loss": 0.20488327741622925, "step": 3470 }, { "epoch": 0.9010903426791277, "grad_norm": 8.732748985290527, "learning_rate": 3.217677925340091e-06, "loss": 0.141297847032547, "step": 3471 }, { "epoch": 0.90134994807892, "grad_norm": 3.1747188568115234, "learning_rate": 3.2167525360188317e-06, "loss": 0.2908972501754761, "step": 3472 }, { "epoch": 0.9016095534787124, "grad_norm": 5.9368438720703125, "learning_rate": 3.2158270641864126e-06, "loss": 0.26062721014022827, "step": 3473 }, { "epoch": 0.9018691588785047, "grad_norm": 9.236042976379395, "learning_rate": 3.2149015100064333e-06, "loss": 0.2801753282546997, "step": 3474 }, { "epoch": 0.902128764278297, "grad_norm": 10.868489265441895, "learning_rate": 3.213975873642513e-06, "loss": 0.2657746970653534, "step": 3475 }, { "epoch": 0.9023883696780893, "grad_norm": 13.375566482543945, "learning_rate": 3.2130501552582823e-06, "loss": 0.18421998620033264, "step": 3476 }, { "epoch": 0.9026479750778816, "grad_norm": 8.567865371704102, "learning_rate": 3.2121243550173854e-06, "loss": 0.32174161076545715, "step": 3477 }, { "epoch": 0.9029075804776739, "grad_norm": 5.640242576599121, "learning_rate": 3.2111984730834837e-06, "loss": 0.2553877830505371, "step": 3478 }, { "epoch": 0.9031671858774662, "grad_norm": 4.128000736236572, "learning_rate": 3.2102725096202527e-06, "loss": 0.29601532220840454, "step": 3479 }, { "epoch": 0.9034267912772586, "grad_norm": 8.09372329711914, "learning_rate": 3.2093464647913815e-06, "loss": 0.25978022813796997, "step": 3480 }, { "epoch": 0.9036863966770509, "grad_norm": 3.996187448501587, "learning_rate": 3.2084203387605716e-06, "loss": 0.3392415940761566, "step": 3481 }, { "epoch": 0.9039460020768432, "grad_norm": 6.8313164710998535, "learning_rate": 3.207494131691542e-06, "loss": 0.2588716745376587, "step": 3482 }, { "epoch": 0.9042056074766355, "grad_norm": 9.491840362548828, "learning_rate": 3.2065678437480265e-06, "loss": 0.25890201330184937, "step": 3483 }, { "epoch": 0.9044652128764278, "grad_norm": 9.110453605651855, "learning_rate": 3.2056414750937696e-06, "loss": 0.19943267107009888, "step": 3484 }, { "epoch": 0.9047248182762202, "grad_norm": 13.038575172424316, "learning_rate": 3.2047150258925324e-06, "loss": 0.19497942924499512, "step": 3485 }, { "epoch": 0.9049844236760125, "grad_norm": 8.330951690673828, "learning_rate": 3.203788496308091e-06, "loss": 0.2527843117713928, "step": 3486 }, { "epoch": 0.9052440290758048, "grad_norm": 4.692961692810059, "learning_rate": 3.2028618865042327e-06, "loss": 0.30485254526138306, "step": 3487 }, { "epoch": 0.9055036344755971, "grad_norm": 12.51753044128418, "learning_rate": 3.201935196644763e-06, "loss": 0.22879989445209503, "step": 3488 }, { "epoch": 0.9057632398753894, "grad_norm": 4.634182929992676, "learning_rate": 3.2010084268934984e-06, "loss": 0.32364994287490845, "step": 3489 }, { "epoch": 0.9060228452751817, "grad_norm": 7.081748008728027, "learning_rate": 3.2000815774142703e-06, "loss": 0.2896748483181, "step": 3490 }, { "epoch": 0.906282450674974, "grad_norm": 11.449047088623047, "learning_rate": 3.199154648370925e-06, "loss": 0.22186730802059174, "step": 3491 }, { "epoch": 0.9065420560747663, "grad_norm": 8.925627708435059, "learning_rate": 3.198227639927322e-06, "loss": 0.11272353678941727, "step": 3492 }, { "epoch": 0.9068016614745587, "grad_norm": 8.736189842224121, "learning_rate": 3.1973005522473355e-06, "loss": 0.10767650604248047, "step": 3493 }, { "epoch": 0.907061266874351, "grad_norm": 11.455095291137695, "learning_rate": 3.196373385494853e-06, "loss": 0.21145543456077576, "step": 3494 }, { "epoch": 0.9073208722741433, "grad_norm": 3.788050413131714, "learning_rate": 3.1954461398337766e-06, "loss": 0.33383285999298096, "step": 3495 }, { "epoch": 0.9075804776739356, "grad_norm": 5.048506259918213, "learning_rate": 3.194518815428022e-06, "loss": 0.2550642490386963, "step": 3496 }, { "epoch": 0.907840083073728, "grad_norm": 5.418405532836914, "learning_rate": 3.193591412441519e-06, "loss": 0.3344937562942505, "step": 3497 }, { "epoch": 0.9080996884735203, "grad_norm": 3.6881349086761475, "learning_rate": 3.1926639310382114e-06, "loss": 0.2654833197593689, "step": 3498 }, { "epoch": 0.9083592938733126, "grad_norm": 8.245292663574219, "learning_rate": 3.1917363713820565e-06, "loss": 0.14443150162696838, "step": 3499 }, { "epoch": 0.9086188992731049, "grad_norm": 4.065424919128418, "learning_rate": 3.1908087336370245e-06, "loss": 0.32842177152633667, "step": 3500 }, { "epoch": 0.9088785046728972, "grad_norm": 8.67591667175293, "learning_rate": 3.189881017967103e-06, "loss": 0.23303431272506714, "step": 3501 }, { "epoch": 0.9091381100726895, "grad_norm": 8.566359519958496, "learning_rate": 3.188953224536289e-06, "loss": 0.2574171721935272, "step": 3502 }, { "epoch": 0.9093977154724818, "grad_norm": 10.134953498840332, "learning_rate": 3.188025353508595e-06, "loss": 0.2064601629972458, "step": 3503 }, { "epoch": 0.9096573208722741, "grad_norm": 12.207365036010742, "learning_rate": 3.187097405048049e-06, "loss": 0.2641141414642334, "step": 3504 }, { "epoch": 0.9099169262720664, "grad_norm": 10.543349266052246, "learning_rate": 3.18616937931869e-06, "loss": 0.20194822549819946, "step": 3505 }, { "epoch": 0.9101765316718587, "grad_norm": 4.603213787078857, "learning_rate": 3.1852412764845704e-06, "loss": 0.3281129002571106, "step": 3506 }, { "epoch": 0.910436137071651, "grad_norm": 8.62265396118164, "learning_rate": 3.1843130967097596e-06, "loss": 0.17762739956378937, "step": 3507 }, { "epoch": 0.9106957424714434, "grad_norm": 6.609915733337402, "learning_rate": 3.183384840158338e-06, "loss": 0.2118730992078781, "step": 3508 }, { "epoch": 0.9109553478712358, "grad_norm": 7.188663005828857, "learning_rate": 3.1824565069943993e-06, "loss": 0.19709864258766174, "step": 3509 }, { "epoch": 0.9112149532710281, "grad_norm": 5.021056175231934, "learning_rate": 3.181528097382052e-06, "loss": 0.2891753911972046, "step": 3510 }, { "epoch": 0.9114745586708204, "grad_norm": 7.620799541473389, "learning_rate": 3.180599611485418e-06, "loss": 0.1942238062620163, "step": 3511 }, { "epoch": 0.9117341640706127, "grad_norm": 4.089792251586914, "learning_rate": 3.179671049468632e-06, "loss": 0.2816833257675171, "step": 3512 }, { "epoch": 0.911993769470405, "grad_norm": 7.518945693969727, "learning_rate": 3.1787424114958433e-06, "loss": 0.23276978731155396, "step": 3513 }, { "epoch": 0.9122533748701973, "grad_norm": 6.244469165802002, "learning_rate": 3.1778136977312125e-06, "loss": 0.30709215998649597, "step": 3514 }, { "epoch": 0.9125129802699896, "grad_norm": 5.637384414672852, "learning_rate": 3.1768849083389164e-06, "loss": 0.29115039110183716, "step": 3515 }, { "epoch": 0.9127725856697819, "grad_norm": 7.243411064147949, "learning_rate": 3.175956043483142e-06, "loss": 0.22616387903690338, "step": 3516 }, { "epoch": 0.9130321910695742, "grad_norm": 7.609091758728027, "learning_rate": 3.1750271033280925e-06, "loss": 0.30210766196250916, "step": 3517 }, { "epoch": 0.9132917964693665, "grad_norm": 5.612334728240967, "learning_rate": 3.1740980880379823e-06, "loss": 0.24446293711662292, "step": 3518 }, { "epoch": 0.9135514018691588, "grad_norm": 8.163936614990234, "learning_rate": 3.1731689977770414e-06, "loss": 0.247921422123909, "step": 3519 }, { "epoch": 0.9138110072689511, "grad_norm": 4.094721794128418, "learning_rate": 3.172239832709511e-06, "loss": 0.31509485840797424, "step": 3520 }, { "epoch": 0.9140706126687436, "grad_norm": 6.75026798248291, "learning_rate": 3.171310592999646e-06, "loss": 0.28007203340530396, "step": 3521 }, { "epoch": 0.9143302180685359, "grad_norm": 10.516005516052246, "learning_rate": 3.1703812788117157e-06, "loss": 0.33967500925064087, "step": 3522 }, { "epoch": 0.9145898234683282, "grad_norm": 10.89179515838623, "learning_rate": 3.1694518903099993e-06, "loss": 0.1749405860900879, "step": 3523 }, { "epoch": 0.9148494288681205, "grad_norm": 11.135866165161133, "learning_rate": 3.168522427658794e-06, "loss": 0.18371625244617462, "step": 3524 }, { "epoch": 0.9151090342679128, "grad_norm": 4.057887077331543, "learning_rate": 3.1675928910224063e-06, "loss": 0.3007049858570099, "step": 3525 }, { "epoch": 0.9153686396677051, "grad_norm": 11.245889663696289, "learning_rate": 3.1666632805651564e-06, "loss": 0.2164909392595291, "step": 3526 }, { "epoch": 0.9156282450674974, "grad_norm": 9.259434700012207, "learning_rate": 3.165733596451379e-06, "loss": 0.31874990463256836, "step": 3527 }, { "epoch": 0.9158878504672897, "grad_norm": 6.021206378936768, "learning_rate": 3.164803838845421e-06, "loss": 0.2900860905647278, "step": 3528 }, { "epoch": 0.916147455867082, "grad_norm": 4.577595233917236, "learning_rate": 3.1638740079116427e-06, "loss": 0.30870985984802246, "step": 3529 }, { "epoch": 0.9164070612668743, "grad_norm": 4.81682014465332, "learning_rate": 3.1629441038144152e-06, "loss": 0.2905752658843994, "step": 3530 }, { "epoch": 0.9166666666666666, "grad_norm": 8.34030818939209, "learning_rate": 3.1620141267181253e-06, "loss": 0.2840850353240967, "step": 3531 }, { "epoch": 0.9169262720664589, "grad_norm": 8.856947898864746, "learning_rate": 3.1610840767871726e-06, "loss": 0.1700141429901123, "step": 3532 }, { "epoch": 0.9171858774662512, "grad_norm": 4.263039588928223, "learning_rate": 3.160153954185967e-06, "loss": 0.2785175144672394, "step": 3533 }, { "epoch": 0.9174454828660437, "grad_norm": 4.090432643890381, "learning_rate": 3.159223759078934e-06, "loss": 0.28608229756355286, "step": 3534 }, { "epoch": 0.917705088265836, "grad_norm": 6.929190158843994, "learning_rate": 3.15829349163051e-06, "loss": 0.10669369250535965, "step": 3535 }, { "epoch": 0.9179646936656283, "grad_norm": 7.299758434295654, "learning_rate": 3.157363152005145e-06, "loss": 0.2682587206363678, "step": 3536 }, { "epoch": 0.9182242990654206, "grad_norm": 10.161051750183105, "learning_rate": 3.1564327403673024e-06, "loss": 0.21717548370361328, "step": 3537 }, { "epoch": 0.9184839044652129, "grad_norm": 10.688912391662598, "learning_rate": 3.155502256881458e-06, "loss": 0.15174856781959534, "step": 3538 }, { "epoch": 0.9187435098650052, "grad_norm": 4.126636028289795, "learning_rate": 3.1545717017120993e-06, "loss": 0.29652029275894165, "step": 3539 }, { "epoch": 0.9190031152647975, "grad_norm": 9.235064506530762, "learning_rate": 3.153641075023726e-06, "loss": 0.20613041520118713, "step": 3540 }, { "epoch": 0.9192627206645898, "grad_norm": 11.033463478088379, "learning_rate": 3.152710376980854e-06, "loss": 0.16848978400230408, "step": 3541 }, { "epoch": 0.9195223260643821, "grad_norm": 6.125524520874023, "learning_rate": 3.151779607748008e-06, "loss": 0.2910448908805847, "step": 3542 }, { "epoch": 0.9197819314641744, "grad_norm": 7.015234470367432, "learning_rate": 3.150848767489726e-06, "loss": 0.2969554662704468, "step": 3543 }, { "epoch": 0.9200415368639667, "grad_norm": 4.143373489379883, "learning_rate": 3.1499178563705605e-06, "loss": 0.3012382686138153, "step": 3544 }, { "epoch": 0.920301142263759, "grad_norm": 10.433137893676758, "learning_rate": 3.1489868745550754e-06, "loss": 0.26430290937423706, "step": 3545 }, { "epoch": 0.9205607476635514, "grad_norm": 4.824069499969482, "learning_rate": 3.1480558222078467e-06, "loss": 0.32892847061157227, "step": 3546 }, { "epoch": 0.9208203530633438, "grad_norm": 5.044724464416504, "learning_rate": 3.147124699493462e-06, "loss": 0.30935531854629517, "step": 3547 }, { "epoch": 0.9210799584631361, "grad_norm": 3.4113852977752686, "learning_rate": 3.146193506576524e-06, "loss": 0.29256612062454224, "step": 3548 }, { "epoch": 0.9213395638629284, "grad_norm": 9.17577838897705, "learning_rate": 3.1452622436216452e-06, "loss": 0.22252336144447327, "step": 3549 }, { "epoch": 0.9215991692627207, "grad_norm": 3.8668782711029053, "learning_rate": 3.144330910793453e-06, "loss": 0.3284856975078583, "step": 3550 }, { "epoch": 0.921858774662513, "grad_norm": 10.045150756835938, "learning_rate": 3.143399508256584e-06, "loss": 0.1482170969247818, "step": 3551 }, { "epoch": 0.9221183800623053, "grad_norm": 5.491549968719482, "learning_rate": 3.14246803617569e-06, "loss": 0.20679637789726257, "step": 3552 }, { "epoch": 0.9223779854620976, "grad_norm": 4.433149337768555, "learning_rate": 3.1415364947154323e-06, "loss": 0.32452520728111267, "step": 3553 }, { "epoch": 0.9226375908618899, "grad_norm": 4.838845729827881, "learning_rate": 3.1406048840404886e-06, "loss": 0.2583881616592407, "step": 3554 }, { "epoch": 0.9228971962616822, "grad_norm": 11.219839096069336, "learning_rate": 3.1396732043155447e-06, "loss": 0.13017326593399048, "step": 3555 }, { "epoch": 0.9231568016614745, "grad_norm": 10.536406517028809, "learning_rate": 3.1387414557053013e-06, "loss": 0.18632547557353973, "step": 3556 }, { "epoch": 0.9234164070612668, "grad_norm": 3.7389650344848633, "learning_rate": 3.1378096383744685e-06, "loss": 0.3019016981124878, "step": 3557 }, { "epoch": 0.9236760124610592, "grad_norm": 10.639749526977539, "learning_rate": 3.1368777524877713e-06, "loss": 0.22877828776836395, "step": 3558 }, { "epoch": 0.9239356178608515, "grad_norm": 8.442267417907715, "learning_rate": 3.1359457982099467e-06, "loss": 0.3158905804157257, "step": 3559 }, { "epoch": 0.9241952232606438, "grad_norm": 7.807366371154785, "learning_rate": 3.1350137757057412e-06, "loss": 0.23091855645179749, "step": 3560 }, { "epoch": 0.9244548286604362, "grad_norm": 4.586600303649902, "learning_rate": 3.1340816851399164e-06, "loss": 0.28657805919647217, "step": 3561 }, { "epoch": 0.9247144340602285, "grad_norm": 7.220985412597656, "learning_rate": 3.133149526677243e-06, "loss": 0.2927861213684082, "step": 3562 }, { "epoch": 0.9249740394600208, "grad_norm": 4.222777843475342, "learning_rate": 3.1322173004825076e-06, "loss": 0.31249451637268066, "step": 3563 }, { "epoch": 0.9252336448598131, "grad_norm": 10.914297103881836, "learning_rate": 3.1312850067205036e-06, "loss": 0.2971801161766052, "step": 3564 }, { "epoch": 0.9254932502596054, "grad_norm": 11.158512115478516, "learning_rate": 3.130352645556042e-06, "loss": 0.14894038438796997, "step": 3565 }, { "epoch": 0.9257528556593977, "grad_norm": 3.9668684005737305, "learning_rate": 3.1294202171539406e-06, "loss": 0.2548668384552002, "step": 3566 }, { "epoch": 0.92601246105919, "grad_norm": 3.923417568206787, "learning_rate": 3.128487721679033e-06, "loss": 0.3143361210823059, "step": 3567 }, { "epoch": 0.9262720664589823, "grad_norm": 4.738210678100586, "learning_rate": 3.1275551592961617e-06, "loss": 0.25283727049827576, "step": 3568 }, { "epoch": 0.9265316718587746, "grad_norm": 6.212704181671143, "learning_rate": 3.1266225301701842e-06, "loss": 0.26875168085098267, "step": 3569 }, { "epoch": 0.926791277258567, "grad_norm": 10.649785041809082, "learning_rate": 3.1256898344659657e-06, "loss": 0.2174609899520874, "step": 3570 }, { "epoch": 0.9270508826583593, "grad_norm": 9.340436935424805, "learning_rate": 3.124757072348388e-06, "loss": 0.19955772161483765, "step": 3571 }, { "epoch": 0.9273104880581516, "grad_norm": 3.9514524936676025, "learning_rate": 3.1238242439823393e-06, "loss": 0.301871120929718, "step": 3572 }, { "epoch": 0.927570093457944, "grad_norm": 9.75559139251709, "learning_rate": 3.1228913495327245e-06, "loss": 0.20415273308753967, "step": 3573 }, { "epoch": 0.9278296988577363, "grad_norm": 8.615458488464355, "learning_rate": 3.1219583891644574e-06, "loss": 0.16739916801452637, "step": 3574 }, { "epoch": 0.9280893042575286, "grad_norm": 6.667629241943359, "learning_rate": 3.121025363042463e-06, "loss": 0.22971123456954956, "step": 3575 }, { "epoch": 0.9283489096573209, "grad_norm": 9.378822326660156, "learning_rate": 3.12009227133168e-06, "loss": 0.2589693069458008, "step": 3576 }, { "epoch": 0.9286085150571132, "grad_norm": 10.6253080368042, "learning_rate": 3.119159114197058e-06, "loss": 0.149723082780838, "step": 3577 }, { "epoch": 0.9288681204569055, "grad_norm": 13.436205863952637, "learning_rate": 3.118225891803556e-06, "loss": 0.20711418986320496, "step": 3578 }, { "epoch": 0.9291277258566978, "grad_norm": 5.853994846343994, "learning_rate": 3.1172926043161496e-06, "loss": 0.2572420835494995, "step": 3579 }, { "epoch": 0.9293873312564901, "grad_norm": 9.855886459350586, "learning_rate": 3.116359251899819e-06, "loss": 0.2165345698595047, "step": 3580 }, { "epoch": 0.9296469366562824, "grad_norm": 4.42074728012085, "learning_rate": 3.1154258347195614e-06, "loss": 0.32461661100387573, "step": 3581 }, { "epoch": 0.9299065420560748, "grad_norm": 5.419365406036377, "learning_rate": 3.114492352940384e-06, "loss": 0.3197803497314453, "step": 3582 }, { "epoch": 0.9301661474558671, "grad_norm": 11.562695503234863, "learning_rate": 3.1135588067273044e-06, "loss": 0.23959232866764069, "step": 3583 }, { "epoch": 0.9304257528556594, "grad_norm": 6.993086814880371, "learning_rate": 3.1126251962453507e-06, "loss": 0.27795299887657166, "step": 3584 }, { "epoch": 0.9306853582554517, "grad_norm": 6.114516735076904, "learning_rate": 3.111691521659567e-06, "loss": 0.25345367193222046, "step": 3585 }, { "epoch": 0.930944963655244, "grad_norm": 3.8970253467559814, "learning_rate": 3.1107577831350033e-06, "loss": 0.30936264991760254, "step": 3586 }, { "epoch": 0.9312045690550363, "grad_norm": 11.570589065551758, "learning_rate": 3.1098239808367237e-06, "loss": 0.16551822423934937, "step": 3587 }, { "epoch": 0.9314641744548287, "grad_norm": 10.716724395751953, "learning_rate": 3.108890114929803e-06, "loss": 0.1473482996225357, "step": 3588 }, { "epoch": 0.931723779854621, "grad_norm": 12.935463905334473, "learning_rate": 3.1079561855793277e-06, "loss": 0.3376919627189636, "step": 3589 }, { "epoch": 0.9319833852544133, "grad_norm": 14.5278959274292, "learning_rate": 3.107022192950395e-06, "loss": 0.1267126053571701, "step": 3590 }, { "epoch": 0.9322429906542056, "grad_norm": 7.4245710372924805, "learning_rate": 3.106088137208113e-06, "loss": 0.23667459189891815, "step": 3591 }, { "epoch": 0.9325025960539979, "grad_norm": 10.616569519042969, "learning_rate": 3.105154018517602e-06, "loss": 0.2812075912952423, "step": 3592 }, { "epoch": 0.9327622014537902, "grad_norm": 10.083906173706055, "learning_rate": 3.1042198370439925e-06, "loss": 0.26347312331199646, "step": 3593 }, { "epoch": 0.9330218068535826, "grad_norm": 4.460453033447266, "learning_rate": 3.103285592952427e-06, "loss": 0.2920541763305664, "step": 3594 }, { "epoch": 0.9332814122533749, "grad_norm": 6.716248035430908, "learning_rate": 3.1023512864080563e-06, "loss": 0.22029003500938416, "step": 3595 }, { "epoch": 0.9335410176531672, "grad_norm": 7.761069297790527, "learning_rate": 3.101416917576047e-06, "loss": 0.21248233318328857, "step": 3596 }, { "epoch": 0.9338006230529595, "grad_norm": 4.488590240478516, "learning_rate": 3.1004824866215723e-06, "loss": 0.29907089471817017, "step": 3597 }, { "epoch": 0.9340602284527518, "grad_norm": 6.394941806793213, "learning_rate": 3.09954799370982e-06, "loss": 0.18636411428451538, "step": 3598 }, { "epoch": 0.9343198338525441, "grad_norm": 10.406386375427246, "learning_rate": 3.0986134390059847e-06, "loss": 0.18603545427322388, "step": 3599 }, { "epoch": 0.9345794392523364, "grad_norm": 5.101747989654541, "learning_rate": 3.0976788226752767e-06, "loss": 0.3048912286758423, "step": 3600 }, { "epoch": 0.9348390446521287, "grad_norm": 5.867343425750732, "learning_rate": 3.0967441448829132e-06, "loss": 0.33318662643432617, "step": 3601 }, { "epoch": 0.935098650051921, "grad_norm": 7.221153259277344, "learning_rate": 3.0958094057941245e-06, "loss": 0.29164811968803406, "step": 3602 }, { "epoch": 0.9353582554517134, "grad_norm": 3.5315520763397217, "learning_rate": 3.09487460557415e-06, "loss": 0.27930575609207153, "step": 3603 }, { "epoch": 0.9356178608515057, "grad_norm": 10.498655319213867, "learning_rate": 3.093939744388243e-06, "loss": 0.18577860295772552, "step": 3604 }, { "epoch": 0.935877466251298, "grad_norm": 13.543808937072754, "learning_rate": 3.093004822401664e-06, "loss": 0.27698633074760437, "step": 3605 }, { "epoch": 0.9361370716510904, "grad_norm": 4.921100616455078, "learning_rate": 3.092069839779686e-06, "loss": 0.2057969570159912, "step": 3606 }, { "epoch": 0.9363966770508827, "grad_norm": 8.8208646774292, "learning_rate": 3.0911347966875925e-06, "loss": 0.17093652486801147, "step": 3607 }, { "epoch": 0.936656282450675, "grad_norm": 10.167202949523926, "learning_rate": 3.090199693290678e-06, "loss": 0.1845812201499939, "step": 3608 }, { "epoch": 0.9369158878504673, "grad_norm": 11.626579284667969, "learning_rate": 3.0892645297542475e-06, "loss": 0.18700875341892242, "step": 3609 }, { "epoch": 0.9371754932502596, "grad_norm": 4.615846633911133, "learning_rate": 3.088329306243616e-06, "loss": 0.23918013274669647, "step": 3610 }, { "epoch": 0.9374350986500519, "grad_norm": 8.343182563781738, "learning_rate": 3.0873940229241095e-06, "loss": 0.2214278280735016, "step": 3611 }, { "epoch": 0.9376947040498442, "grad_norm": 7.4614644050598145, "learning_rate": 3.086458679961066e-06, "loss": 0.053552113473415375, "step": 3612 }, { "epoch": 0.9379543094496365, "grad_norm": 10.522090911865234, "learning_rate": 3.0855232775198317e-06, "loss": 0.08646832406520844, "step": 3613 }, { "epoch": 0.9382139148494288, "grad_norm": 9.787062644958496, "learning_rate": 3.084587815765764e-06, "loss": 0.23182737827301025, "step": 3614 }, { "epoch": 0.9384735202492211, "grad_norm": 10.539982795715332, "learning_rate": 3.0836522948642317e-06, "loss": 0.1960417926311493, "step": 3615 }, { "epoch": 0.9387331256490135, "grad_norm": 6.18471622467041, "learning_rate": 3.0827167149806126e-06, "loss": 0.2477879375219345, "step": 3616 }, { "epoch": 0.9389927310488058, "grad_norm": 5.181695938110352, "learning_rate": 3.0817810762802974e-06, "loss": 0.28384819626808167, "step": 3617 }, { "epoch": 0.9392523364485982, "grad_norm": 4.822947025299072, "learning_rate": 3.0808453789286842e-06, "loss": 0.35875898599624634, "step": 3618 }, { "epoch": 0.9395119418483905, "grad_norm": 7.3008880615234375, "learning_rate": 3.079909623091183e-06, "loss": 0.23051925003528595, "step": 3619 }, { "epoch": 0.9397715472481828, "grad_norm": 13.784490585327148, "learning_rate": 3.078973808933215e-06, "loss": 0.2108420729637146, "step": 3620 }, { "epoch": 0.9400311526479751, "grad_norm": 11.399375915527344, "learning_rate": 3.0780379366202106e-06, "loss": 0.15035350620746613, "step": 3621 }, { "epoch": 0.9402907580477674, "grad_norm": 8.70748519897461, "learning_rate": 3.077102006317609e-06, "loss": 0.1264955699443817, "step": 3622 }, { "epoch": 0.9405503634475597, "grad_norm": 10.680647850036621, "learning_rate": 3.0761660181908624e-06, "loss": 0.251271516084671, "step": 3623 }, { "epoch": 0.940809968847352, "grad_norm": 10.18744945526123, "learning_rate": 3.0752299724054324e-06, "loss": 0.14009059965610504, "step": 3624 }, { "epoch": 0.9410695742471443, "grad_norm": 8.225380897521973, "learning_rate": 3.0742938691267903e-06, "loss": 0.2396208941936493, "step": 3625 }, { "epoch": 0.9413291796469366, "grad_norm": 10.8668851852417, "learning_rate": 3.073357708520417e-06, "loss": 0.14791613817214966, "step": 3626 }, { "epoch": 0.9415887850467289, "grad_norm": 5.623111248016357, "learning_rate": 3.072421490751805e-06, "loss": 0.2802349030971527, "step": 3627 }, { "epoch": 0.9418483904465212, "grad_norm": 6.498407363891602, "learning_rate": 3.071485215986455e-06, "loss": 0.2199035882949829, "step": 3628 }, { "epoch": 0.9421079958463136, "grad_norm": 10.5452299118042, "learning_rate": 3.0705488843898816e-06, "loss": 0.2099052220582962, "step": 3629 }, { "epoch": 0.942367601246106, "grad_norm": 8.742781639099121, "learning_rate": 3.0696124961276036e-06, "loss": 0.2276293933391571, "step": 3630 }, { "epoch": 0.9426272066458983, "grad_norm": 10.559974670410156, "learning_rate": 3.0686760513651555e-06, "loss": 0.11401204019784927, "step": 3631 }, { "epoch": 0.9428868120456906, "grad_norm": 12.592544555664062, "learning_rate": 3.0677395502680774e-06, "loss": 0.14255118370056152, "step": 3632 }, { "epoch": 0.9431464174454829, "grad_norm": 5.479316711425781, "learning_rate": 3.066802993001922e-06, "loss": 0.23847153782844543, "step": 3633 }, { "epoch": 0.9434060228452752, "grad_norm": 10.854850769042969, "learning_rate": 3.0658663797322518e-06, "loss": 0.30861762166023254, "step": 3634 }, { "epoch": 0.9436656282450675, "grad_norm": 9.289156913757324, "learning_rate": 3.0649297106246386e-06, "loss": 0.29195326566696167, "step": 3635 }, { "epoch": 0.9439252336448598, "grad_norm": 5.44953727722168, "learning_rate": 3.0639929858446626e-06, "loss": 0.2322527915239334, "step": 3636 }, { "epoch": 0.9441848390446521, "grad_norm": 4.878546237945557, "learning_rate": 3.0630562055579154e-06, "loss": 0.2760196328163147, "step": 3637 }, { "epoch": 0.9444444444444444, "grad_norm": 5.380941390991211, "learning_rate": 3.0621193699300004e-06, "loss": 0.28066033124923706, "step": 3638 }, { "epoch": 0.9447040498442367, "grad_norm": 7.314034461975098, "learning_rate": 3.0611824791265278e-06, "loss": 0.27554231882095337, "step": 3639 }, { "epoch": 0.944963655244029, "grad_norm": 10.090003967285156, "learning_rate": 3.060245533313117e-06, "loss": 0.2864498496055603, "step": 3640 }, { "epoch": 0.9452232606438213, "grad_norm": 10.654471397399902, "learning_rate": 3.0593085326553995e-06, "loss": 0.22133873403072357, "step": 3641 }, { "epoch": 0.9454828660436138, "grad_norm": 4.868962287902832, "learning_rate": 3.058371477319016e-06, "loss": 0.27498018741607666, "step": 3642 }, { "epoch": 0.9457424714434061, "grad_norm": 12.833569526672363, "learning_rate": 3.0574343674696162e-06, "loss": 0.20967072248458862, "step": 3643 }, { "epoch": 0.9460020768431984, "grad_norm": 12.91003704071045, "learning_rate": 3.05649720327286e-06, "loss": 0.20077455043792725, "step": 3644 }, { "epoch": 0.9462616822429907, "grad_norm": 6.283634662628174, "learning_rate": 3.0555599848944152e-06, "loss": 0.3397507071495056, "step": 3645 }, { "epoch": 0.946521287642783, "grad_norm": 9.338624000549316, "learning_rate": 3.054622712499962e-06, "loss": 0.2917410135269165, "step": 3646 }, { "epoch": 0.9467808930425753, "grad_norm": 7.314364433288574, "learning_rate": 3.0536853862551875e-06, "loss": 0.29632800817489624, "step": 3647 }, { "epoch": 0.9470404984423676, "grad_norm": 10.91680908203125, "learning_rate": 3.0527480063257908e-06, "loss": 0.19089847803115845, "step": 3648 }, { "epoch": 0.9473001038421599, "grad_norm": 6.336851596832275, "learning_rate": 3.0518105728774782e-06, "loss": 0.23774799704551697, "step": 3649 }, { "epoch": 0.9475597092419522, "grad_norm": 14.939940452575684, "learning_rate": 3.0508730860759673e-06, "loss": 0.2163410633802414, "step": 3650 }, { "epoch": 0.9478193146417445, "grad_norm": 6.131736755371094, "learning_rate": 3.0499355460869833e-06, "loss": 0.2546122670173645, "step": 3651 }, { "epoch": 0.9480789200415368, "grad_norm": 16.509050369262695, "learning_rate": 3.048997953076263e-06, "loss": 0.156518816947937, "step": 3652 }, { "epoch": 0.9483385254413291, "grad_norm": 11.44095230102539, "learning_rate": 3.0480603072095507e-06, "loss": 0.15714646875858307, "step": 3653 }, { "epoch": 0.9485981308411215, "grad_norm": 4.89985990524292, "learning_rate": 3.0471226086526e-06, "loss": 0.27000612020492554, "step": 3654 }, { "epoch": 0.9488577362409139, "grad_norm": 10.078652381896973, "learning_rate": 3.046184857571176e-06, "loss": 0.0999942496418953, "step": 3655 }, { "epoch": 0.9491173416407062, "grad_norm": 3.772799491882324, "learning_rate": 3.0452470541310507e-06, "loss": 0.26823583245277405, "step": 3656 }, { "epoch": 0.9493769470404985, "grad_norm": 11.28650951385498, "learning_rate": 3.0443091984980066e-06, "loss": 0.18190905451774597, "step": 3657 }, { "epoch": 0.9496365524402908, "grad_norm": 7.010106563568115, "learning_rate": 3.0433712908378356e-06, "loss": 0.2432282567024231, "step": 3658 }, { "epoch": 0.9498961578400831, "grad_norm": 8.180177688598633, "learning_rate": 3.042433331316336e-06, "loss": 0.1626715213060379, "step": 3659 }, { "epoch": 0.9501557632398754, "grad_norm": 9.170376777648926, "learning_rate": 3.04149532009932e-06, "loss": 0.2561432719230652, "step": 3660 }, { "epoch": 0.9504153686396677, "grad_norm": 10.735122680664062, "learning_rate": 3.0405572573526067e-06, "loss": 0.16253899037837982, "step": 3661 }, { "epoch": 0.95067497403946, "grad_norm": 11.92684555053711, "learning_rate": 3.0396191432420225e-06, "loss": 0.19706027209758759, "step": 3662 }, { "epoch": 0.9509345794392523, "grad_norm": 5.202094078063965, "learning_rate": 3.0386809779334055e-06, "loss": 0.2607690691947937, "step": 3663 }, { "epoch": 0.9511941848390446, "grad_norm": 4.910449981689453, "learning_rate": 3.037742761592601e-06, "loss": 0.26356393098831177, "step": 3664 }, { "epoch": 0.9514537902388369, "grad_norm": 9.29149055480957, "learning_rate": 3.0368044943854647e-06, "loss": 0.18732208013534546, "step": 3665 }, { "epoch": 0.9517133956386293, "grad_norm": 10.435144424438477, "learning_rate": 3.0358661764778614e-06, "loss": 0.3016788959503174, "step": 3666 }, { "epoch": 0.9519730010384216, "grad_norm": 5.769700527191162, "learning_rate": 3.0349278080356626e-06, "loss": 0.27797457575798035, "step": 3667 }, { "epoch": 0.952232606438214, "grad_norm": 11.497552871704102, "learning_rate": 3.0339893892247518e-06, "loss": 0.179361954331398, "step": 3668 }, { "epoch": 0.9524922118380063, "grad_norm": 5.488044738769531, "learning_rate": 3.0330509202110197e-06, "loss": 0.2444954216480255, "step": 3669 }, { "epoch": 0.9527518172377986, "grad_norm": 5.0022358894348145, "learning_rate": 3.032112401160366e-06, "loss": 0.24949359893798828, "step": 3670 }, { "epoch": 0.9530114226375909, "grad_norm": 10.951900482177734, "learning_rate": 3.0311738322386996e-06, "loss": 0.20848561823368073, "step": 3671 }, { "epoch": 0.9532710280373832, "grad_norm": 4.022185325622559, "learning_rate": 3.0302352136119364e-06, "loss": 0.3436815142631531, "step": 3672 }, { "epoch": 0.9535306334371755, "grad_norm": 6.589463233947754, "learning_rate": 3.029296545446005e-06, "loss": 0.23505899310112, "step": 3673 }, { "epoch": 0.9537902388369678, "grad_norm": 7.957144260406494, "learning_rate": 3.0283578279068387e-06, "loss": 0.18555417656898499, "step": 3674 }, { "epoch": 0.9540498442367601, "grad_norm": 10.298297882080078, "learning_rate": 3.027419061160383e-06, "loss": 0.2585494816303253, "step": 3675 }, { "epoch": 0.9543094496365524, "grad_norm": 11.029706954956055, "learning_rate": 3.026480245372588e-06, "loss": 0.18718750774860382, "step": 3676 }, { "epoch": 0.9545690550363447, "grad_norm": 10.284143447875977, "learning_rate": 3.025541380709417e-06, "loss": 0.22763431072235107, "step": 3677 }, { "epoch": 0.9548286604361371, "grad_norm": 10.745635032653809, "learning_rate": 3.024602467336839e-06, "loss": 0.2667670249938965, "step": 3678 }, { "epoch": 0.9550882658359294, "grad_norm": 5.4048871994018555, "learning_rate": 3.0236635054208322e-06, "loss": 0.2823408246040344, "step": 3679 }, { "epoch": 0.9553478712357217, "grad_norm": 13.759919166564941, "learning_rate": 3.022724495127384e-06, "loss": 0.21503445506095886, "step": 3680 }, { "epoch": 0.955607476635514, "grad_norm": 5.510026931762695, "learning_rate": 3.0217854366224885e-06, "loss": 0.3161278963088989, "step": 3681 }, { "epoch": 0.9558670820353063, "grad_norm": 7.351826190948486, "learning_rate": 3.020846330072152e-06, "loss": 0.1800992786884308, "step": 3682 }, { "epoch": 0.9561266874350987, "grad_norm": 9.849350929260254, "learning_rate": 3.019907175642386e-06, "loss": 0.18220114707946777, "step": 3683 }, { "epoch": 0.956386292834891, "grad_norm": 10.944167137145996, "learning_rate": 3.0189679734992107e-06, "loss": 0.15824447572231293, "step": 3684 }, { "epoch": 0.9566458982346833, "grad_norm": 12.456371307373047, "learning_rate": 3.0180287238086563e-06, "loss": 0.22153975069522858, "step": 3685 }, { "epoch": 0.9569055036344756, "grad_norm": 4.651195049285889, "learning_rate": 3.0170894267367605e-06, "loss": 0.2975856065750122, "step": 3686 }, { "epoch": 0.9571651090342679, "grad_norm": 17.257078170776367, "learning_rate": 3.0161500824495704e-06, "loss": 0.22217464447021484, "step": 3687 }, { "epoch": 0.9574247144340602, "grad_norm": 10.792510986328125, "learning_rate": 3.015210691113139e-06, "loss": 0.14125101268291473, "step": 3688 }, { "epoch": 0.9576843198338525, "grad_norm": 4.116085529327393, "learning_rate": 3.014271252893531e-06, "loss": 0.2729570269584656, "step": 3689 }, { "epoch": 0.9579439252336449, "grad_norm": 10.82171630859375, "learning_rate": 3.0133317679568145e-06, "loss": 0.18051686882972717, "step": 3690 }, { "epoch": 0.9582035306334372, "grad_norm": 5.235945224761963, "learning_rate": 3.012392236469073e-06, "loss": 0.25770050287246704, "step": 3691 }, { "epoch": 0.9584631360332295, "grad_norm": 5.034853935241699, "learning_rate": 3.0114526585963903e-06, "loss": 0.2449193000793457, "step": 3692 }, { "epoch": 0.9587227414330218, "grad_norm": 6.531943321228027, "learning_rate": 3.0105130345048654e-06, "loss": 0.24749968945980072, "step": 3693 }, { "epoch": 0.9589823468328141, "grad_norm": 5.169016361236572, "learning_rate": 3.0095733643606005e-06, "loss": 0.2644535303115845, "step": 3694 }, { "epoch": 0.9592419522326064, "grad_norm": 6.9723310470581055, "learning_rate": 3.0086336483297084e-06, "loss": 0.2566864490509033, "step": 3695 }, { "epoch": 0.9595015576323987, "grad_norm": 5.434572696685791, "learning_rate": 3.007693886578309e-06, "loss": 0.2739381492137909, "step": 3696 }, { "epoch": 0.9597611630321911, "grad_norm": 10.161314010620117, "learning_rate": 3.0067540792725304e-06, "loss": 0.29151690006256104, "step": 3697 }, { "epoch": 0.9600207684319834, "grad_norm": 14.077884674072266, "learning_rate": 3.00581422657851e-06, "loss": 0.19666403532028198, "step": 3698 }, { "epoch": 0.9602803738317757, "grad_norm": 4.10066556930542, "learning_rate": 3.004874328662391e-06, "loss": 0.34251612424850464, "step": 3699 }, { "epoch": 0.960539979231568, "grad_norm": 8.429536819458008, "learning_rate": 3.003934385690328e-06, "loss": 0.09432175755500793, "step": 3700 }, { "epoch": 0.9607995846313603, "grad_norm": 12.499581336975098, "learning_rate": 3.002994397828479e-06, "loss": 0.12508513033390045, "step": 3701 }, { "epoch": 0.9610591900311527, "grad_norm": 11.531586647033691, "learning_rate": 3.002054365243014e-06, "loss": 0.1316324770450592, "step": 3702 }, { "epoch": 0.961318795430945, "grad_norm": 6.8101677894592285, "learning_rate": 3.001114288100107e-06, "loss": 0.2687312364578247, "step": 3703 }, { "epoch": 0.9615784008307373, "grad_norm": 10.348197937011719, "learning_rate": 3.0001741665659444e-06, "loss": 0.146964430809021, "step": 3704 }, { "epoch": 0.9618380062305296, "grad_norm": 8.059664726257324, "learning_rate": 2.9992340008067177e-06, "loss": 0.22030065953731537, "step": 3705 }, { "epoch": 0.9620976116303219, "grad_norm": 6.552878379821777, "learning_rate": 2.9982937909886267e-06, "loss": 0.23127317428588867, "step": 3706 }, { "epoch": 0.9623572170301142, "grad_norm": 8.794499397277832, "learning_rate": 2.997353537277878e-06, "loss": 0.20834439992904663, "step": 3707 }, { "epoch": 0.9626168224299065, "grad_norm": 9.82459545135498, "learning_rate": 2.996413239840687e-06, "loss": 0.29712870717048645, "step": 3708 }, { "epoch": 0.9628764278296988, "grad_norm": 5.3872809410095215, "learning_rate": 2.995472898843278e-06, "loss": 0.24081560969352722, "step": 3709 }, { "epoch": 0.9631360332294912, "grad_norm": 10.25644588470459, "learning_rate": 2.994532514451881e-06, "loss": 0.2230270653963089, "step": 3710 }, { "epoch": 0.9633956386292835, "grad_norm": 10.867944717407227, "learning_rate": 2.9935920868327345e-06, "loss": 0.16368483006954193, "step": 3711 }, { "epoch": 0.9636552440290758, "grad_norm": 10.203400611877441, "learning_rate": 2.9926516161520848e-06, "loss": 0.2297462522983551, "step": 3712 }, { "epoch": 0.9639148494288681, "grad_norm": 5.935476779937744, "learning_rate": 2.9917111025761848e-06, "loss": 0.2997325360774994, "step": 3713 }, { "epoch": 0.9641744548286605, "grad_norm": 7.816823482513428, "learning_rate": 2.9907705462712974e-06, "loss": 0.17500193417072296, "step": 3714 }, { "epoch": 0.9644340602284528, "grad_norm": 10.330283164978027, "learning_rate": 2.989829947403689e-06, "loss": 0.15441757440567017, "step": 3715 }, { "epoch": 0.9646936656282451, "grad_norm": 5.316339015960693, "learning_rate": 2.9888893061396375e-06, "loss": 0.3048705458641052, "step": 3716 }, { "epoch": 0.9649532710280374, "grad_norm": 13.445021629333496, "learning_rate": 2.987948622645427e-06, "loss": 0.10395358502864838, "step": 3717 }, { "epoch": 0.9652128764278297, "grad_norm": 5.027703762054443, "learning_rate": 2.9870078970873483e-06, "loss": 0.27485090494155884, "step": 3718 }, { "epoch": 0.965472481827622, "grad_norm": 9.703306198120117, "learning_rate": 2.9860671296317e-06, "loss": 0.2642529606819153, "step": 3719 }, { "epoch": 0.9657320872274143, "grad_norm": 5.36785364151001, "learning_rate": 2.985126320444789e-06, "loss": 0.27375519275665283, "step": 3720 }, { "epoch": 0.9659916926272066, "grad_norm": 6.186294078826904, "learning_rate": 2.9841854696929266e-06, "loss": 0.3140251040458679, "step": 3721 }, { "epoch": 0.9662512980269989, "grad_norm": 10.753216743469238, "learning_rate": 2.983244577542437e-06, "loss": 0.2316429615020752, "step": 3722 }, { "epoch": 0.9665109034267912, "grad_norm": 12.825013160705566, "learning_rate": 2.9823036441596465e-06, "loss": 0.15275350213050842, "step": 3723 }, { "epoch": 0.9667705088265836, "grad_norm": 5.416148662567139, "learning_rate": 2.98136266971089e-06, "loss": 0.2756756544113159, "step": 3724 }, { "epoch": 0.9670301142263759, "grad_norm": 4.1704254150390625, "learning_rate": 2.980421654362511e-06, "loss": 0.34782883524894714, "step": 3725 }, { "epoch": 0.9672897196261683, "grad_norm": 9.652115821838379, "learning_rate": 2.97948059828086e-06, "loss": 0.2314286231994629, "step": 3726 }, { "epoch": 0.9675493250259606, "grad_norm": 8.778816223144531, "learning_rate": 2.978539501632293e-06, "loss": 0.20206904411315918, "step": 3727 }, { "epoch": 0.9678089304257529, "grad_norm": 11.378121376037598, "learning_rate": 2.977598364583176e-06, "loss": 0.1438664197921753, "step": 3728 }, { "epoch": 0.9680685358255452, "grad_norm": 7.148344039916992, "learning_rate": 2.9766571872998777e-06, "loss": 0.24091196060180664, "step": 3729 }, { "epoch": 0.9683281412253375, "grad_norm": 8.839755058288574, "learning_rate": 2.9757159699487798e-06, "loss": 0.19608402252197266, "step": 3730 }, { "epoch": 0.9685877466251298, "grad_norm": 9.617384910583496, "learning_rate": 2.9747747126962666e-06, "loss": 0.14707016944885254, "step": 3731 }, { "epoch": 0.9688473520249221, "grad_norm": 5.28636360168457, "learning_rate": 2.9738334157087307e-06, "loss": 0.2917492091655731, "step": 3732 }, { "epoch": 0.9691069574247144, "grad_norm": 9.64216423034668, "learning_rate": 2.9728920791525724e-06, "loss": 0.23172476887702942, "step": 3733 }, { "epoch": 0.9693665628245067, "grad_norm": 8.903884887695312, "learning_rate": 2.971950703194197e-06, "loss": 0.20262065529823303, "step": 3734 }, { "epoch": 0.969626168224299, "grad_norm": 13.675958633422852, "learning_rate": 2.97100928800002e-06, "loss": 0.12669487297534943, "step": 3735 }, { "epoch": 0.9698857736240913, "grad_norm": 11.000950813293457, "learning_rate": 2.9700678337364615e-06, "loss": 0.2661615014076233, "step": 3736 }, { "epoch": 0.9701453790238836, "grad_norm": 12.129880905151367, "learning_rate": 2.9691263405699485e-06, "loss": 0.14903190732002258, "step": 3737 }, { "epoch": 0.9704049844236761, "grad_norm": 10.893779754638672, "learning_rate": 2.968184808666916e-06, "loss": 0.1566028892993927, "step": 3738 }, { "epoch": 0.9706645898234684, "grad_norm": 11.717377662658691, "learning_rate": 2.967243238193805e-06, "loss": 0.19596387445926666, "step": 3739 }, { "epoch": 0.9709241952232607, "grad_norm": 6.827475070953369, "learning_rate": 2.9663016293170632e-06, "loss": 0.24991370737552643, "step": 3740 }, { "epoch": 0.971183800623053, "grad_norm": 9.726764678955078, "learning_rate": 2.965359982203147e-06, "loss": 0.11794072389602661, "step": 3741 }, { "epoch": 0.9714434060228453, "grad_norm": 10.399826049804688, "learning_rate": 2.9644182970185163e-06, "loss": 0.11910035461187363, "step": 3742 }, { "epoch": 0.9717030114226376, "grad_norm": 10.429961204528809, "learning_rate": 2.96347657392964e-06, "loss": 0.13153338432312012, "step": 3743 }, { "epoch": 0.9719626168224299, "grad_norm": 4.1194281578063965, "learning_rate": 2.962534813102994e-06, "loss": 0.36814266443252563, "step": 3744 }, { "epoch": 0.9722222222222222, "grad_norm": 6.058714866638184, "learning_rate": 2.9615930147050597e-06, "loss": 0.29136690497398376, "step": 3745 }, { "epoch": 0.9724818276220145, "grad_norm": 6.845612049102783, "learning_rate": 2.9606511789023247e-06, "loss": 0.2158629596233368, "step": 3746 }, { "epoch": 0.9727414330218068, "grad_norm": 13.63595199584961, "learning_rate": 2.9597093058612843e-06, "loss": 0.12465198338031769, "step": 3747 }, { "epoch": 0.9730010384215991, "grad_norm": 10.37671947479248, "learning_rate": 2.958767395748441e-06, "loss": 0.23264756798744202, "step": 3748 }, { "epoch": 0.9732606438213914, "grad_norm": 11.05109691619873, "learning_rate": 2.957825448730302e-06, "loss": 0.2766701579093933, "step": 3749 }, { "epoch": 0.9735202492211839, "grad_norm": 6.299674987792969, "learning_rate": 2.9568834649733825e-06, "loss": 0.29146608710289, "step": 3750 }, { "epoch": 0.9737798546209762, "grad_norm": 10.820966720581055, "learning_rate": 2.9559414446442024e-06, "loss": 0.15695875883102417, "step": 3751 }, { "epoch": 0.9740394600207685, "grad_norm": 11.00458812713623, "learning_rate": 2.9549993879092912e-06, "loss": 0.10569745302200317, "step": 3752 }, { "epoch": 0.9742990654205608, "grad_norm": 6.646376609802246, "learning_rate": 2.954057294935182e-06, "loss": 0.2350914478302002, "step": 3753 }, { "epoch": 0.9745586708203531, "grad_norm": 9.409003257751465, "learning_rate": 2.9531151658884156e-06, "loss": 0.21021248400211334, "step": 3754 }, { "epoch": 0.9748182762201454, "grad_norm": 9.868096351623535, "learning_rate": 2.9521730009355383e-06, "loss": 0.2285819947719574, "step": 3755 }, { "epoch": 0.9750778816199377, "grad_norm": 11.42153263092041, "learning_rate": 2.951230800243103e-06, "loss": 0.14152508974075317, "step": 3756 }, { "epoch": 0.97533748701973, "grad_norm": 15.597848892211914, "learning_rate": 2.95028856397767e-06, "loss": 0.19179800152778625, "step": 3757 }, { "epoch": 0.9755970924195223, "grad_norm": 14.87777328491211, "learning_rate": 2.9493462923058057e-06, "loss": 0.13431821763515472, "step": 3758 }, { "epoch": 0.9758566978193146, "grad_norm": 9.607752799987793, "learning_rate": 2.948403985394081e-06, "loss": 0.23479802906513214, "step": 3759 }, { "epoch": 0.9761163032191069, "grad_norm": 6.061253547668457, "learning_rate": 2.9474616434090737e-06, "loss": 0.25139009952545166, "step": 3760 }, { "epoch": 0.9763759086188992, "grad_norm": 7.76071834564209, "learning_rate": 2.9465192665173697e-06, "loss": 0.3458169102668762, "step": 3761 }, { "epoch": 0.9766355140186916, "grad_norm": 10.217557907104492, "learning_rate": 2.9455768548855597e-06, "loss": 0.1574929654598236, "step": 3762 }, { "epoch": 0.976895119418484, "grad_norm": 5.030606746673584, "learning_rate": 2.944634408680239e-06, "loss": 0.3038440942764282, "step": 3763 }, { "epoch": 0.9771547248182763, "grad_norm": 4.660086154937744, "learning_rate": 2.9436919280680115e-06, "loss": 0.3138462007045746, "step": 3764 }, { "epoch": 0.9774143302180686, "grad_norm": 4.2771687507629395, "learning_rate": 2.942749413215486e-06, "loss": 0.2816585898399353, "step": 3765 }, { "epoch": 0.9776739356178609, "grad_norm": 3.6313059329986572, "learning_rate": 2.941806864289279e-06, "loss": 0.3159228563308716, "step": 3766 }, { "epoch": 0.9779335410176532, "grad_norm": 8.026812553405762, "learning_rate": 2.9408642814560082e-06, "loss": 0.22541256248950958, "step": 3767 }, { "epoch": 0.9781931464174455, "grad_norm": 9.805988311767578, "learning_rate": 2.939921664882304e-06, "loss": 0.14005538821220398, "step": 3768 }, { "epoch": 0.9784527518172378, "grad_norm": 12.81390380859375, "learning_rate": 2.9389790147347973e-06, "loss": 0.202900230884552, "step": 3769 }, { "epoch": 0.9787123572170301, "grad_norm": 16.967710494995117, "learning_rate": 2.9380363311801286e-06, "loss": 0.17715886235237122, "step": 3770 }, { "epoch": 0.9789719626168224, "grad_norm": 9.633113861083984, "learning_rate": 2.9370936143849415e-06, "loss": 0.17317701876163483, "step": 3771 }, { "epoch": 0.9792315680166147, "grad_norm": 7.698917388916016, "learning_rate": 2.9361508645158875e-06, "loss": 0.27160415053367615, "step": 3772 }, { "epoch": 0.979491173416407, "grad_norm": 9.994514465332031, "learning_rate": 2.9352080817396227e-06, "loss": 0.22615033388137817, "step": 3773 }, { "epoch": 0.9797507788161994, "grad_norm": 11.342794418334961, "learning_rate": 2.93426526622281e-06, "loss": 0.1181417778134346, "step": 3774 }, { "epoch": 0.9800103842159917, "grad_norm": 4.3334059715271, "learning_rate": 2.933322418132117e-06, "loss": 0.33162909746170044, "step": 3775 }, { "epoch": 0.980269989615784, "grad_norm": 5.714271068572998, "learning_rate": 2.932379537634218e-06, "loss": 0.16392916440963745, "step": 3776 }, { "epoch": 0.9805295950155763, "grad_norm": 10.376428604125977, "learning_rate": 2.9314366248957927e-06, "loss": 0.12816692888736725, "step": 3777 }, { "epoch": 0.9807892004153687, "grad_norm": 9.386340141296387, "learning_rate": 2.9304936800835264e-06, "loss": 0.18911705911159515, "step": 3778 }, { "epoch": 0.981048805815161, "grad_norm": 8.999969482421875, "learning_rate": 2.9295507033641105e-06, "loss": 0.14155028760433197, "step": 3779 }, { "epoch": 0.9813084112149533, "grad_norm": 4.28767204284668, "learning_rate": 2.9286076949042415e-06, "loss": 0.2999233305454254, "step": 3780 }, { "epoch": 0.9815680166147456, "grad_norm": 5.48783540725708, "learning_rate": 2.9276646548706222e-06, "loss": 0.2923530638217926, "step": 3781 }, { "epoch": 0.9818276220145379, "grad_norm": 3.704979181289673, "learning_rate": 2.9267215834299585e-06, "loss": 0.2945787012577057, "step": 3782 }, { "epoch": 0.9820872274143302, "grad_norm": 11.523344039916992, "learning_rate": 2.9257784807489663e-06, "loss": 0.1334608495235443, "step": 3783 }, { "epoch": 0.9823468328141225, "grad_norm": 12.929825782775879, "learning_rate": 2.924835346994363e-06, "loss": 0.10858595371246338, "step": 3784 }, { "epoch": 0.9826064382139148, "grad_norm": 4.03508186340332, "learning_rate": 2.9238921823328737e-06, "loss": 0.302152544260025, "step": 3785 }, { "epoch": 0.9828660436137072, "grad_norm": 4.950933933258057, "learning_rate": 2.9229489869312276e-06, "loss": 0.27505046129226685, "step": 3786 }, { "epoch": 0.9831256490134995, "grad_norm": 6.0228986740112305, "learning_rate": 2.9220057609561616e-06, "loss": 0.21044570207595825, "step": 3787 }, { "epoch": 0.9833852544132918, "grad_norm": 9.792251586914062, "learning_rate": 2.9210625045744143e-06, "loss": 0.22314314544200897, "step": 3788 }, { "epoch": 0.9836448598130841, "grad_norm": 4.897313594818115, "learning_rate": 2.920119217952735e-06, "loss": 0.28934934735298157, "step": 3789 }, { "epoch": 0.9839044652128764, "grad_norm": 10.47598934173584, "learning_rate": 2.9191759012578712e-06, "loss": 0.13875453174114227, "step": 3790 }, { "epoch": 0.9841640706126688, "grad_norm": 4.388350009918213, "learning_rate": 2.9182325546565822e-06, "loss": 0.2960510849952698, "step": 3791 }, { "epoch": 0.9844236760124611, "grad_norm": 4.087414264678955, "learning_rate": 2.91728917831563e-06, "loss": 0.2944518029689789, "step": 3792 }, { "epoch": 0.9846832814122534, "grad_norm": 9.056915283203125, "learning_rate": 2.916345772401781e-06, "loss": 0.2783612608909607, "step": 3793 }, { "epoch": 0.9849428868120457, "grad_norm": 3.455981492996216, "learning_rate": 2.9154023370818085e-06, "loss": 0.35497164726257324, "step": 3794 }, { "epoch": 0.985202492211838, "grad_norm": 7.073854923248291, "learning_rate": 2.91445887252249e-06, "loss": 0.19746652245521545, "step": 3795 }, { "epoch": 0.9854620976116303, "grad_norm": 6.917984962463379, "learning_rate": 2.9135153788906084e-06, "loss": 0.287864089012146, "step": 3796 }, { "epoch": 0.9857217030114226, "grad_norm": 4.809249401092529, "learning_rate": 2.912571856352952e-06, "loss": 0.2577003240585327, "step": 3797 }, { "epoch": 0.985981308411215, "grad_norm": 9.4518461227417, "learning_rate": 2.9116283050763137e-06, "loss": 0.18082383275032043, "step": 3798 }, { "epoch": 0.9862409138110073, "grad_norm": 7.865875244140625, "learning_rate": 2.910684725227492e-06, "loss": 0.22945080697536469, "step": 3799 }, { "epoch": 0.9865005192107996, "grad_norm": 8.650885581970215, "learning_rate": 2.909741116973289e-06, "loss": 0.21542900800704956, "step": 3800 }, { "epoch": 0.9867601246105919, "grad_norm": 11.000784873962402, "learning_rate": 2.908797480480515e-06, "loss": 0.1918497085571289, "step": 3801 }, { "epoch": 0.9870197300103842, "grad_norm": 10.504959106445312, "learning_rate": 2.9078538159159823e-06, "loss": 0.15470802783966064, "step": 3802 }, { "epoch": 0.9872793354101765, "grad_norm": 11.963495254516602, "learning_rate": 2.90691012344651e-06, "loss": 0.11995426565408707, "step": 3803 }, { "epoch": 0.9875389408099688, "grad_norm": 9.673391342163086, "learning_rate": 2.90596640323892e-06, "loss": 0.23597116768360138, "step": 3804 }, { "epoch": 0.9877985462097612, "grad_norm": 7.561262607574463, "learning_rate": 2.905022655460041e-06, "loss": 0.26588356494903564, "step": 3805 }, { "epoch": 0.9880581516095535, "grad_norm": 5.878683090209961, "learning_rate": 2.9040788802767065e-06, "loss": 0.2478150576353073, "step": 3806 }, { "epoch": 0.9883177570093458, "grad_norm": 5.001433372497559, "learning_rate": 2.903135077855754e-06, "loss": 0.3194965720176697, "step": 3807 }, { "epoch": 0.9885773624091381, "grad_norm": 9.142009735107422, "learning_rate": 2.902191248364025e-06, "loss": 0.17182406783103943, "step": 3808 }, { "epoch": 0.9888369678089304, "grad_norm": 8.697787284851074, "learning_rate": 2.9012473919683686e-06, "loss": 0.285457044839859, "step": 3809 }, { "epoch": 0.9890965732087228, "grad_norm": 4.509493350982666, "learning_rate": 2.900303508835637e-06, "loss": 0.31133031845092773, "step": 3810 }, { "epoch": 0.9893561786085151, "grad_norm": 6.920726299285889, "learning_rate": 2.8993595991326854e-06, "loss": 0.0963435173034668, "step": 3811 }, { "epoch": 0.9896157840083074, "grad_norm": 14.20353889465332, "learning_rate": 2.8984156630263777e-06, "loss": 0.16899625957012177, "step": 3812 }, { "epoch": 0.9898753894080997, "grad_norm": 8.735241889953613, "learning_rate": 2.8974717006835785e-06, "loss": 0.21270841360092163, "step": 3813 }, { "epoch": 0.990134994807892, "grad_norm": 9.924942016601562, "learning_rate": 2.8965277122711593e-06, "loss": 0.22001001238822937, "step": 3814 }, { "epoch": 0.9903946002076843, "grad_norm": 9.26751708984375, "learning_rate": 2.895583697955995e-06, "loss": 0.26072874665260315, "step": 3815 }, { "epoch": 0.9906542056074766, "grad_norm": 7.9449462890625, "learning_rate": 2.8946396579049674e-06, "loss": 0.28442567586898804, "step": 3816 }, { "epoch": 0.9909138110072689, "grad_norm": 4.448879718780518, "learning_rate": 2.8936955922849597e-06, "loss": 0.266884446144104, "step": 3817 }, { "epoch": 0.9911734164070612, "grad_norm": 10.34524154663086, "learning_rate": 2.8927515012628616e-06, "loss": 0.18924571573734283, "step": 3818 }, { "epoch": 0.9914330218068536, "grad_norm": 8.229374885559082, "learning_rate": 2.8918073850055663e-06, "loss": 0.26267871260643005, "step": 3819 }, { "epoch": 0.9916926272066459, "grad_norm": 5.545716762542725, "learning_rate": 2.8908632436799725e-06, "loss": 0.3084987998008728, "step": 3820 }, { "epoch": 0.9919522326064382, "grad_norm": 9.738302230834961, "learning_rate": 2.8899190774529823e-06, "loss": 0.18660226464271545, "step": 3821 }, { "epoch": 0.9922118380062306, "grad_norm": 11.730121612548828, "learning_rate": 2.888974886491503e-06, "loss": 0.2237657606601715, "step": 3822 }, { "epoch": 0.9924714434060229, "grad_norm": 10.223653793334961, "learning_rate": 2.888030670962446e-06, "loss": 0.15164953470230103, "step": 3823 }, { "epoch": 0.9927310488058152, "grad_norm": 9.51854419708252, "learning_rate": 2.8870864310327267e-06, "loss": 0.11375536024570465, "step": 3824 }, { "epoch": 0.9929906542056075, "grad_norm": 3.7768187522888184, "learning_rate": 2.886142166869265e-06, "loss": 0.3108120560646057, "step": 3825 }, { "epoch": 0.9932502596053998, "grad_norm": 7.650893211364746, "learning_rate": 2.885197878638986e-06, "loss": 0.2407875657081604, "step": 3826 }, { "epoch": 0.9935098650051921, "grad_norm": 9.008810043334961, "learning_rate": 2.8842535665088177e-06, "loss": 0.09182798117399216, "step": 3827 }, { "epoch": 0.9937694704049844, "grad_norm": 8.770661354064941, "learning_rate": 2.8833092306456934e-06, "loss": 0.17655442655086517, "step": 3828 }, { "epoch": 0.9940290758047767, "grad_norm": 9.434622764587402, "learning_rate": 2.882364871216548e-06, "loss": 0.1771126538515091, "step": 3829 }, { "epoch": 0.994288681204569, "grad_norm": 6.7543864250183105, "learning_rate": 2.881420488388325e-06, "loss": 0.30983176827430725, "step": 3830 }, { "epoch": 0.9945482866043613, "grad_norm": 3.8453214168548584, "learning_rate": 2.8804760823279687e-06, "loss": 0.2860226035118103, "step": 3831 }, { "epoch": 0.9948078920041536, "grad_norm": 11.100578308105469, "learning_rate": 2.8795316532024287e-06, "loss": 0.20019808411598206, "step": 3832 }, { "epoch": 0.995067497403946, "grad_norm": 7.517978191375732, "learning_rate": 2.878587201178658e-06, "loss": 0.2850990295410156, "step": 3833 }, { "epoch": 0.9953271028037384, "grad_norm": 10.147064208984375, "learning_rate": 2.8776427264236147e-06, "loss": 0.22327497601509094, "step": 3834 }, { "epoch": 0.9955867082035307, "grad_norm": 10.790189743041992, "learning_rate": 2.8766982291042593e-06, "loss": 0.15496984124183655, "step": 3835 }, { "epoch": 0.995846313603323, "grad_norm": 6.587928295135498, "learning_rate": 2.875753709387559e-06, "loss": 0.2655125856399536, "step": 3836 }, { "epoch": 0.9961059190031153, "grad_norm": 10.9763765335083, "learning_rate": 2.8748091674404816e-06, "loss": 0.1660509556531906, "step": 3837 }, { "epoch": 0.9963655244029076, "grad_norm": 9.827515602111816, "learning_rate": 2.8738646034300015e-06, "loss": 0.1474134922027588, "step": 3838 }, { "epoch": 0.9966251298026999, "grad_norm": 11.318853378295898, "learning_rate": 2.8729200175230955e-06, "loss": 0.26357659697532654, "step": 3839 }, { "epoch": 0.9968847352024922, "grad_norm": 14.037447929382324, "learning_rate": 2.8719754098867446e-06, "loss": 0.11433225125074387, "step": 3840 }, { "epoch": 0.9971443406022845, "grad_norm": 7.696038722991943, "learning_rate": 2.8710307806879343e-06, "loss": 0.21729855239391327, "step": 3841 }, { "epoch": 0.9974039460020768, "grad_norm": 11.07708740234375, "learning_rate": 2.870086130093653e-06, "loss": 0.13361720740795135, "step": 3842 }, { "epoch": 0.9976635514018691, "grad_norm": 12.338125228881836, "learning_rate": 2.8691414582708943e-06, "loss": 0.18271683156490326, "step": 3843 }, { "epoch": 0.9979231568016614, "grad_norm": 10.52668571472168, "learning_rate": 2.8681967653866527e-06, "loss": 0.08668416738510132, "step": 3844 }, { "epoch": 0.9981827622014537, "grad_norm": 5.174844264984131, "learning_rate": 2.86725205160793e-06, "loss": 0.2924373745918274, "step": 3845 }, { "epoch": 0.9984423676012462, "grad_norm": 8.034540176391602, "learning_rate": 2.8663073171017284e-06, "loss": 0.13918250799179077, "step": 3846 }, { "epoch": 0.9987019730010385, "grad_norm": 10.045344352722168, "learning_rate": 2.865362562035058e-06, "loss": 0.118327297270298, "step": 3847 }, { "epoch": 0.9989615784008308, "grad_norm": 9.53662395477295, "learning_rate": 2.8644177865749266e-06, "loss": 0.1660504937171936, "step": 3848 }, { "epoch": 0.9992211838006231, "grad_norm": 12.555435180664062, "learning_rate": 2.8634729908883506e-06, "loss": 0.22495916485786438, "step": 3849 }, { "epoch": 0.9994807892004154, "grad_norm": 11.948518753051758, "learning_rate": 2.8625281751423485e-06, "loss": 0.2428867220878601, "step": 3850 }, { "epoch": 0.9997403946002077, "grad_norm": 8.319740295410156, "learning_rate": 2.861583339503941e-06, "loss": 0.2200310230255127, "step": 3851 }, { "epoch": 1.0, "grad_norm": 12.897453308105469, "learning_rate": 2.8606384841401548e-06, "loss": 0.18619275093078613, "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 }