{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.982278481012658, "eval_steps": 500, "global_step": 1230, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004050632911392405, "grad_norm": 7.462853012277802, "learning_rate": 3.2520325203252037e-07, "loss": 1.1694, "step": 1 }, { "epoch": 0.00810126582278481, "grad_norm": 6.25714857239286, "learning_rate": 6.504065040650407e-07, "loss": 1.0573, "step": 2 }, { "epoch": 0.012151898734177215, "grad_norm": 6.406308125709961, "learning_rate": 9.75609756097561e-07, "loss": 1.067, "step": 3 }, { "epoch": 0.01620253164556962, "grad_norm": 6.3219861037986105, "learning_rate": 1.3008130081300815e-06, "loss": 1.0578, "step": 4 }, { "epoch": 0.020253164556962026, "grad_norm": 5.949509674084552, "learning_rate": 1.6260162601626018e-06, "loss": 1.0422, "step": 5 }, { "epoch": 0.02430379746835443, "grad_norm": 5.951410979808134, "learning_rate": 1.951219512195122e-06, "loss": 1.0309, "step": 6 }, { "epoch": 0.028354430379746835, "grad_norm": 4.928720737749959, "learning_rate": 2.2764227642276426e-06, "loss": 1.0346, "step": 7 }, { "epoch": 0.03240506329113924, "grad_norm": 4.522149965019342, "learning_rate": 2.601626016260163e-06, "loss": 0.9772, "step": 8 }, { "epoch": 0.03645569620253165, "grad_norm": 2.448966233213755, "learning_rate": 2.926829268292683e-06, "loss": 0.9356, "step": 9 }, { "epoch": 0.04050632911392405, "grad_norm": 2.2440449151943858, "learning_rate": 3.2520325203252037e-06, "loss": 0.958, "step": 10 }, { "epoch": 0.044556962025316456, "grad_norm": 2.0990651890633347, "learning_rate": 3.577235772357724e-06, "loss": 0.9601, "step": 11 }, { "epoch": 0.04860759493670886, "grad_norm": 4.2879145686834494, "learning_rate": 3.902439024390244e-06, "loss": 0.9642, "step": 12 }, { "epoch": 0.052658227848101265, "grad_norm": 4.6217489740485584, "learning_rate": 4.227642276422765e-06, "loss": 0.9402, "step": 13 }, { "epoch": 0.05670886075949367, "grad_norm": 4.524083941039058, "learning_rate": 4.552845528455285e-06, "loss": 0.9328, "step": 14 }, { "epoch": 0.060759493670886074, "grad_norm": 4.360457125569118, "learning_rate": 4.8780487804878055e-06, "loss": 0.9272, "step": 15 }, { "epoch": 0.06481012658227848, "grad_norm": 3.2222323579690673, "learning_rate": 5.203252032520326e-06, "loss": 0.8689, "step": 16 }, { "epoch": 0.06886075949367089, "grad_norm": 3.082239360380718, "learning_rate": 5.528455284552846e-06, "loss": 0.8702, "step": 17 }, { "epoch": 0.0729113924050633, "grad_norm": 2.6719312501156036, "learning_rate": 5.853658536585366e-06, "loss": 0.8477, "step": 18 }, { "epoch": 0.0769620253164557, "grad_norm": 2.2828595543958277, "learning_rate": 6.178861788617887e-06, "loss": 0.8442, "step": 19 }, { "epoch": 0.0810126582278481, "grad_norm": 2.1950644137516524, "learning_rate": 6.504065040650407e-06, "loss": 0.8253, "step": 20 }, { "epoch": 0.08506329113924051, "grad_norm": 1.8105501912971411, "learning_rate": 6.829268292682928e-06, "loss": 0.8438, "step": 21 }, { "epoch": 0.08911392405063291, "grad_norm": 1.7893580223171528, "learning_rate": 7.154471544715448e-06, "loss": 0.8196, "step": 22 }, { "epoch": 0.09316455696202532, "grad_norm": 1.7483647912468308, "learning_rate": 7.4796747967479676e-06, "loss": 0.7839, "step": 23 }, { "epoch": 0.09721518987341772, "grad_norm": 1.8803840548961483, "learning_rate": 7.804878048780489e-06, "loss": 0.7967, "step": 24 }, { "epoch": 0.10126582278481013, "grad_norm": 1.7034267176261355, "learning_rate": 8.130081300813009e-06, "loss": 0.8111, "step": 25 }, { "epoch": 0.10531645569620253, "grad_norm": 1.4969171919686544, "learning_rate": 8.45528455284553e-06, "loss": 0.7989, "step": 26 }, { "epoch": 0.10936708860759493, "grad_norm": 1.5786726949221874, "learning_rate": 8.78048780487805e-06, "loss": 0.7867, "step": 27 }, { "epoch": 0.11341772151898734, "grad_norm": 1.4769044083554372, "learning_rate": 9.10569105691057e-06, "loss": 0.7712, "step": 28 }, { "epoch": 0.11746835443037974, "grad_norm": 1.2910543620178385, "learning_rate": 9.43089430894309e-06, "loss": 0.7908, "step": 29 }, { "epoch": 0.12151898734177215, "grad_norm": 1.1271624697951563, "learning_rate": 9.756097560975611e-06, "loss": 0.7873, "step": 30 }, { "epoch": 0.12556962025316457, "grad_norm": 1.0813390464152832, "learning_rate": 1.008130081300813e-05, "loss": 0.7601, "step": 31 }, { "epoch": 0.12962025316455697, "grad_norm": 1.1551102236794237, "learning_rate": 1.0406504065040652e-05, "loss": 0.781, "step": 32 }, { "epoch": 0.13367088607594937, "grad_norm": 1.073388423204837, "learning_rate": 1.0731707317073172e-05, "loss": 0.7597, "step": 33 }, { "epoch": 0.13772151898734178, "grad_norm": 1.3151201838058075, "learning_rate": 1.1056910569105692e-05, "loss": 0.7739, "step": 34 }, { "epoch": 0.14177215189873418, "grad_norm": 0.9662999888503995, "learning_rate": 1.1382113821138213e-05, "loss": 0.7383, "step": 35 }, { "epoch": 0.1458227848101266, "grad_norm": 0.8311890643807676, "learning_rate": 1.1707317073170731e-05, "loss": 0.7111, "step": 36 }, { "epoch": 0.149873417721519, "grad_norm": 0.8373110038996643, "learning_rate": 1.2032520325203254e-05, "loss": 0.7277, "step": 37 }, { "epoch": 0.1539240506329114, "grad_norm": 0.7576751978197261, "learning_rate": 1.2357723577235774e-05, "loss": 0.7525, "step": 38 }, { "epoch": 0.1579746835443038, "grad_norm": 0.7143412959785281, "learning_rate": 1.2682926829268294e-05, "loss": 0.7546, "step": 39 }, { "epoch": 0.1620253164556962, "grad_norm": 0.8330231432102801, "learning_rate": 1.3008130081300815e-05, "loss": 0.7414, "step": 40 }, { "epoch": 0.1660759493670886, "grad_norm": 0.7238480111667391, "learning_rate": 1.3333333333333333e-05, "loss": 0.7123, "step": 41 }, { "epoch": 0.17012658227848101, "grad_norm": 0.7897626099948587, "learning_rate": 1.3658536585365855e-05, "loss": 0.7218, "step": 42 }, { "epoch": 0.17417721518987342, "grad_norm": 0.9510948298988992, "learning_rate": 1.3983739837398376e-05, "loss": 0.7656, "step": 43 }, { "epoch": 0.17822784810126582, "grad_norm": 0.6523367733147618, "learning_rate": 1.4308943089430896e-05, "loss": 0.7166, "step": 44 }, { "epoch": 0.18227848101265823, "grad_norm": 0.6783916881981749, "learning_rate": 1.4634146341463415e-05, "loss": 0.6818, "step": 45 }, { "epoch": 0.18632911392405063, "grad_norm": 0.6816010559832797, "learning_rate": 1.4959349593495935e-05, "loss": 0.6869, "step": 46 }, { "epoch": 0.19037974683544304, "grad_norm": 0.6770404502821674, "learning_rate": 1.528455284552846e-05, "loss": 0.7129, "step": 47 }, { "epoch": 0.19443037974683544, "grad_norm": 0.685592562602747, "learning_rate": 1.5609756097560978e-05, "loss": 0.7124, "step": 48 }, { "epoch": 0.19848101265822785, "grad_norm": 0.6801967927832354, "learning_rate": 1.5934959349593496e-05, "loss": 0.7363, "step": 49 }, { "epoch": 0.20253164556962025, "grad_norm": 0.6857456392886703, "learning_rate": 1.6260162601626018e-05, "loss": 0.7103, "step": 50 }, { "epoch": 0.20658227848101265, "grad_norm": 0.6123610835766904, "learning_rate": 1.6585365853658537e-05, "loss": 0.6831, "step": 51 }, { "epoch": 0.21063291139240506, "grad_norm": 0.632540711504353, "learning_rate": 1.691056910569106e-05, "loss": 0.7063, "step": 52 }, { "epoch": 0.21468354430379746, "grad_norm": 0.7391966435924728, "learning_rate": 1.7235772357723578e-05, "loss": 0.7225, "step": 53 }, { "epoch": 0.21873417721518987, "grad_norm": 0.6259734408478311, "learning_rate": 1.75609756097561e-05, "loss": 0.6958, "step": 54 }, { "epoch": 0.22278481012658227, "grad_norm": 1.671815232149034, "learning_rate": 1.788617886178862e-05, "loss": 0.7572, "step": 55 }, { "epoch": 0.22683544303797468, "grad_norm": 0.9230659630010654, "learning_rate": 1.821138211382114e-05, "loss": 0.6996, "step": 56 }, { "epoch": 0.23088607594936708, "grad_norm": 0.703416151477436, "learning_rate": 1.8536585365853663e-05, "loss": 0.6891, "step": 57 }, { "epoch": 0.23493670886075949, "grad_norm": 0.8533799374419763, "learning_rate": 1.886178861788618e-05, "loss": 0.6905, "step": 58 }, { "epoch": 0.2389873417721519, "grad_norm": 0.8234230410698261, "learning_rate": 1.91869918699187e-05, "loss": 0.7095, "step": 59 }, { "epoch": 0.2430379746835443, "grad_norm": 0.658404848328806, "learning_rate": 1.9512195121951222e-05, "loss": 0.7038, "step": 60 }, { "epoch": 0.2470886075949367, "grad_norm": 0.7444184843368803, "learning_rate": 1.983739837398374e-05, "loss": 0.6778, "step": 61 }, { "epoch": 0.25113924050632913, "grad_norm": 0.7887872265642041, "learning_rate": 2.016260162601626e-05, "loss": 0.6704, "step": 62 }, { "epoch": 0.25518987341772154, "grad_norm": 0.6730677399977146, "learning_rate": 2.048780487804878e-05, "loss": 0.6982, "step": 63 }, { "epoch": 0.25924050632911394, "grad_norm": 0.829201695029833, "learning_rate": 2.0813008130081303e-05, "loss": 0.6814, "step": 64 }, { "epoch": 0.26329113924050634, "grad_norm": 0.6852971580272852, "learning_rate": 2.1138211382113822e-05, "loss": 0.6585, "step": 65 }, { "epoch": 0.26734177215189875, "grad_norm": 0.7043353779486311, "learning_rate": 2.1463414634146344e-05, "loss": 0.6707, "step": 66 }, { "epoch": 0.27139240506329115, "grad_norm": 0.7001106640013287, "learning_rate": 2.1788617886178863e-05, "loss": 0.7071, "step": 67 }, { "epoch": 0.27544303797468356, "grad_norm": 0.6690651604937112, "learning_rate": 2.2113821138211385e-05, "loss": 0.6839, "step": 68 }, { "epoch": 0.27949367088607596, "grad_norm": 1.2381626442406672, "learning_rate": 2.2439024390243907e-05, "loss": 0.6796, "step": 69 }, { "epoch": 0.28354430379746837, "grad_norm": 0.8656675311836918, "learning_rate": 2.2764227642276426e-05, "loss": 0.6916, "step": 70 }, { "epoch": 0.28759493670886077, "grad_norm": 0.7038175659861762, "learning_rate": 2.3089430894308948e-05, "loss": 0.6858, "step": 71 }, { "epoch": 0.2916455696202532, "grad_norm": 2.7930715455355046, "learning_rate": 2.3414634146341463e-05, "loss": 0.6843, "step": 72 }, { "epoch": 0.2956962025316456, "grad_norm": 1.1689833758534733, "learning_rate": 2.3739837398373985e-05, "loss": 0.7106, "step": 73 }, { "epoch": 0.299746835443038, "grad_norm": 1.2427554915500179, "learning_rate": 2.4065040650406507e-05, "loss": 0.6944, "step": 74 }, { "epoch": 0.3037974683544304, "grad_norm": 1.1819859904263557, "learning_rate": 2.4390243902439026e-05, "loss": 0.6922, "step": 75 }, { "epoch": 0.3078481012658228, "grad_norm": 1.1633126857133198, "learning_rate": 2.4715447154471548e-05, "loss": 0.6944, "step": 76 }, { "epoch": 0.3118987341772152, "grad_norm": 0.9162467885440315, "learning_rate": 2.5040650406504066e-05, "loss": 0.6866, "step": 77 }, { "epoch": 0.3159493670886076, "grad_norm": 1.1758540463683382, "learning_rate": 2.536585365853659e-05, "loss": 0.6671, "step": 78 }, { "epoch": 0.32, "grad_norm": 0.8646057197961597, "learning_rate": 2.569105691056911e-05, "loss": 0.6814, "step": 79 }, { "epoch": 0.3240506329113924, "grad_norm": 1.1607558365369646, "learning_rate": 2.601626016260163e-05, "loss": 0.7012, "step": 80 }, { "epoch": 0.3281012658227848, "grad_norm": 0.831750409658479, "learning_rate": 2.634146341463415e-05, "loss": 0.6734, "step": 81 }, { "epoch": 0.3321518987341772, "grad_norm": 1.143686634482531, "learning_rate": 2.6666666666666667e-05, "loss": 0.6645, "step": 82 }, { "epoch": 0.3362025316455696, "grad_norm": 0.7948857465766141, "learning_rate": 2.699186991869919e-05, "loss": 0.6769, "step": 83 }, { "epoch": 0.34025316455696203, "grad_norm": 0.9776401176022017, "learning_rate": 2.731707317073171e-05, "loss": 0.6718, "step": 84 }, { "epoch": 0.34430379746835443, "grad_norm": 1.3554584206682707, "learning_rate": 2.764227642276423e-05, "loss": 0.6973, "step": 85 }, { "epoch": 0.34835443037974684, "grad_norm": 1.0657466906351925, "learning_rate": 2.796747967479675e-05, "loss": 0.6804, "step": 86 }, { "epoch": 0.35240506329113924, "grad_norm": 0.833367510559818, "learning_rate": 2.829268292682927e-05, "loss": 0.6348, "step": 87 }, { "epoch": 0.35645569620253165, "grad_norm": 0.7896904428512026, "learning_rate": 2.8617886178861792e-05, "loss": 0.6752, "step": 88 }, { "epoch": 0.36050632911392405, "grad_norm": 0.8600565090557819, "learning_rate": 2.8943089430894314e-05, "loss": 0.6699, "step": 89 }, { "epoch": 0.36455696202531646, "grad_norm": 0.7419644723376186, "learning_rate": 2.926829268292683e-05, "loss": 0.6809, "step": 90 }, { "epoch": 0.36860759493670886, "grad_norm": 0.8441103426541376, "learning_rate": 2.959349593495935e-05, "loss": 0.6731, "step": 91 }, { "epoch": 0.37265822784810126, "grad_norm": 0.7722658228306852, "learning_rate": 2.991869918699187e-05, "loss": 0.6847, "step": 92 }, { "epoch": 0.37670886075949367, "grad_norm": 0.8908268996082084, "learning_rate": 3.0243902439024392e-05, "loss": 0.6613, "step": 93 }, { "epoch": 0.3807594936708861, "grad_norm": 0.7962503359027143, "learning_rate": 3.056910569105692e-05, "loss": 0.668, "step": 94 }, { "epoch": 0.3848101265822785, "grad_norm": 0.8186096152914857, "learning_rate": 3.089430894308943e-05, "loss": 0.6598, "step": 95 }, { "epoch": 0.3888607594936709, "grad_norm": 0.7536339807164599, "learning_rate": 3.1219512195121955e-05, "loss": 0.6661, "step": 96 }, { "epoch": 0.3929113924050633, "grad_norm": 0.8819461911254393, "learning_rate": 3.154471544715447e-05, "loss": 0.6235, "step": 97 }, { "epoch": 0.3969620253164557, "grad_norm": 0.8622318673871132, "learning_rate": 3.186991869918699e-05, "loss": 0.6724, "step": 98 }, { "epoch": 0.4010126582278481, "grad_norm": 1.5005218125776778, "learning_rate": 3.2195121951219514e-05, "loss": 0.675, "step": 99 }, { "epoch": 0.4050632911392405, "grad_norm": 0.8179782052843831, "learning_rate": 3.2520325203252037e-05, "loss": 0.6477, "step": 100 }, { "epoch": 0.4091139240506329, "grad_norm": 1.5477030814576047, "learning_rate": 3.284552845528456e-05, "loss": 0.6531, "step": 101 }, { "epoch": 0.4131645569620253, "grad_norm": 0.8766097080723768, "learning_rate": 3.3170731707317074e-05, "loss": 0.6667, "step": 102 }, { "epoch": 0.4172151898734177, "grad_norm": 1.714879125882602, "learning_rate": 3.3495934959349596e-05, "loss": 0.6753, "step": 103 }, { "epoch": 0.4212658227848101, "grad_norm": 1.0668183467061434, "learning_rate": 3.382113821138212e-05, "loss": 0.6675, "step": 104 }, { "epoch": 0.4253164556962025, "grad_norm": 1.6893479973086594, "learning_rate": 3.414634146341463e-05, "loss": 0.659, "step": 105 }, { "epoch": 0.4293670886075949, "grad_norm": 1.3711348892014652, "learning_rate": 3.4471544715447155e-05, "loss": 0.6657, "step": 106 }, { "epoch": 0.43341772151898733, "grad_norm": 1.1546272995650728, "learning_rate": 3.479674796747968e-05, "loss": 0.6449, "step": 107 }, { "epoch": 0.43746835443037974, "grad_norm": 1.1743818784260314, "learning_rate": 3.51219512195122e-05, "loss": 0.6443, "step": 108 }, { "epoch": 0.44151898734177214, "grad_norm": 1.0181468377644005, "learning_rate": 3.544715447154472e-05, "loss": 0.6426, "step": 109 }, { "epoch": 0.44556962025316454, "grad_norm": 1.2030954058747845, "learning_rate": 3.577235772357724e-05, "loss": 0.692, "step": 110 }, { "epoch": 0.44962025316455695, "grad_norm": 0.8706956995232112, "learning_rate": 3.609756097560976e-05, "loss": 0.6684, "step": 111 }, { "epoch": 0.45367088607594935, "grad_norm": 1.1231332237869054, "learning_rate": 3.642276422764228e-05, "loss": 0.6562, "step": 112 }, { "epoch": 0.45772151898734176, "grad_norm": 1.1143026151111883, "learning_rate": 3.67479674796748e-05, "loss": 0.6525, "step": 113 }, { "epoch": 0.46177215189873416, "grad_norm": 1.023794955667932, "learning_rate": 3.7073170731707325e-05, "loss": 0.6245, "step": 114 }, { "epoch": 0.46582278481012657, "grad_norm": 1.059245063091439, "learning_rate": 3.739837398373984e-05, "loss": 0.6445, "step": 115 }, { "epoch": 0.46987341772151897, "grad_norm": 0.8704328283680484, "learning_rate": 3.772357723577236e-05, "loss": 0.6568, "step": 116 }, { "epoch": 0.4739240506329114, "grad_norm": 0.948789293654258, "learning_rate": 3.804878048780488e-05, "loss": 0.6692, "step": 117 }, { "epoch": 0.4779746835443038, "grad_norm": 1.1781931606358895, "learning_rate": 3.83739837398374e-05, "loss": 0.6351, "step": 118 }, { "epoch": 0.4820253164556962, "grad_norm": 0.771461588504397, "learning_rate": 3.869918699186992e-05, "loss": 0.6662, "step": 119 }, { "epoch": 0.4860759493670886, "grad_norm": 1.4252848971575929, "learning_rate": 3.9024390243902444e-05, "loss": 0.6694, "step": 120 }, { "epoch": 0.490126582278481, "grad_norm": 0.7697774080357259, "learning_rate": 3.9349593495934966e-05, "loss": 0.6394, "step": 121 }, { "epoch": 0.4941772151898734, "grad_norm": 1.3822171569254176, "learning_rate": 3.967479674796748e-05, "loss": 0.6747, "step": 122 }, { "epoch": 0.4982278481012658, "grad_norm": 1.282090829585757, "learning_rate": 4e-05, "loss": 0.6479, "step": 123 }, { "epoch": 0.5022784810126583, "grad_norm": 1.0677064232210807, "learning_rate": 3.999991946137476e-05, "loss": 0.6692, "step": 124 }, { "epoch": 0.5063291139240507, "grad_norm": 0.9603340962895642, "learning_rate": 3.999967784614766e-05, "loss": 0.645, "step": 125 }, { "epoch": 0.5103797468354431, "grad_norm": 0.7818915248692372, "learning_rate": 3.9999275156264656e-05, "loss": 0.6325, "step": 126 }, { "epoch": 0.5144303797468355, "grad_norm": 1.1351403827600912, "learning_rate": 3.999871139496895e-05, "loss": 0.6633, "step": 127 }, { "epoch": 0.5184810126582279, "grad_norm": 0.6645737461230282, "learning_rate": 3.9997986566800995e-05, "loss": 0.6005, "step": 128 }, { "epoch": 0.5225316455696203, "grad_norm": 1.1522085228173642, "learning_rate": 3.999710067759846e-05, "loss": 0.6564, "step": 129 }, { "epoch": 0.5265822784810127, "grad_norm": 0.6597352271048318, "learning_rate": 3.999605373449617e-05, "loss": 0.6213, "step": 130 }, { "epoch": 0.5306329113924051, "grad_norm": 0.9514895041039322, "learning_rate": 3.9994845745926075e-05, "loss": 0.6381, "step": 131 }, { "epoch": 0.5346835443037975, "grad_norm": 1.2924852079569509, "learning_rate": 3.999347672161713e-05, "loss": 0.6765, "step": 132 }, { "epoch": 0.5387341772151899, "grad_norm": 0.6588448651962283, "learning_rate": 3.999194667259528e-05, "loss": 0.6599, "step": 133 }, { "epoch": 0.5427848101265823, "grad_norm": 1.1334288407053792, "learning_rate": 3.999025561118334e-05, "loss": 0.6634, "step": 134 }, { "epoch": 0.5468354430379747, "grad_norm": 0.6779663366332457, "learning_rate": 3.998840355100086e-05, "loss": 0.6173, "step": 135 }, { "epoch": 0.5508860759493671, "grad_norm": 0.8857879749875172, "learning_rate": 3.998639050696409e-05, "loss": 0.643, "step": 136 }, { "epoch": 0.5549367088607595, "grad_norm": 0.8448962814550993, "learning_rate": 3.998421649528582e-05, "loss": 0.6488, "step": 137 }, { "epoch": 0.5589873417721519, "grad_norm": 0.6421079406559727, "learning_rate": 3.9981881533475234e-05, "loss": 0.6399, "step": 138 }, { "epoch": 0.5630379746835443, "grad_norm": 1.0143914812882258, "learning_rate": 3.997938564033779e-05, "loss": 0.646, "step": 139 }, { "epoch": 0.5670886075949367, "grad_norm": 0.6220433364692863, "learning_rate": 3.9976728835975064e-05, "loss": 0.6408, "step": 140 }, { "epoch": 0.5711392405063291, "grad_norm": 0.8235519233561306, "learning_rate": 3.9973911141784605e-05, "loss": 0.6546, "step": 141 }, { "epoch": 0.5751898734177215, "grad_norm": 0.6542928196312121, "learning_rate": 3.997093258045973e-05, "loss": 0.6204, "step": 142 }, { "epoch": 0.579240506329114, "grad_norm": 0.762866076575407, "learning_rate": 3.996779317598936e-05, "loss": 0.6481, "step": 143 }, { "epoch": 0.5832911392405064, "grad_norm": 0.6125442623619621, "learning_rate": 3.996449295365782e-05, "loss": 0.627, "step": 144 }, { "epoch": 0.5873417721518988, "grad_norm": 0.6697973126208135, "learning_rate": 3.996103194004467e-05, "loss": 0.6292, "step": 145 }, { "epoch": 0.5913924050632912, "grad_norm": 0.7848885102042558, "learning_rate": 3.995741016302441e-05, "loss": 0.6681, "step": 146 }, { "epoch": 0.5954430379746836, "grad_norm": 0.6911211626662856, "learning_rate": 3.9953627651766364e-05, "loss": 0.6463, "step": 147 }, { "epoch": 0.599493670886076, "grad_norm": 0.6227390077209588, "learning_rate": 3.9949684436734325e-05, "loss": 0.6589, "step": 148 }, { "epoch": 0.6035443037974684, "grad_norm": 0.7513197280689199, "learning_rate": 3.994558054968643e-05, "loss": 0.6401, "step": 149 }, { "epoch": 0.6075949367088608, "grad_norm": 0.6318225432225943, "learning_rate": 3.994131602367481e-05, "loss": 0.6324, "step": 150 }, { "epoch": 0.6116455696202532, "grad_norm": 0.5516107544266493, "learning_rate": 3.9936890893045376e-05, "loss": 0.6147, "step": 151 }, { "epoch": 0.6156962025316456, "grad_norm": 0.6945406964847344, "learning_rate": 3.993230519343752e-05, "loss": 0.6256, "step": 152 }, { "epoch": 0.619746835443038, "grad_norm": 0.565954697263074, "learning_rate": 3.992755896178383e-05, "loss": 0.6632, "step": 153 }, { "epoch": 0.6237974683544304, "grad_norm": 0.8715440467475899, "learning_rate": 3.992265223630981e-05, "loss": 0.6527, "step": 154 }, { "epoch": 0.6278481012658228, "grad_norm": 0.5554810282231124, "learning_rate": 3.991758505653355e-05, "loss": 0.6339, "step": 155 }, { "epoch": 0.6318987341772152, "grad_norm": 0.7237173546593751, "learning_rate": 3.991235746326543e-05, "loss": 0.6049, "step": 156 }, { "epoch": 0.6359493670886076, "grad_norm": 0.6946281085186605, "learning_rate": 3.9906969498607745e-05, "loss": 0.6425, "step": 157 }, { "epoch": 0.64, "grad_norm": 0.5699266553376975, "learning_rate": 3.990142120595444e-05, "loss": 0.6501, "step": 158 }, { "epoch": 0.6440506329113924, "grad_norm": 0.5508702343643855, "learning_rate": 3.98957126299907e-05, "loss": 0.6289, "step": 159 }, { "epoch": 0.6481012658227848, "grad_norm": 0.6829405229203495, "learning_rate": 3.9889843816692596e-05, "loss": 0.6429, "step": 160 }, { "epoch": 0.6521518987341772, "grad_norm": 0.5197687467735633, "learning_rate": 3.9883814813326766e-05, "loss": 0.6311, "step": 161 }, { "epoch": 0.6562025316455696, "grad_norm": 0.6478178472864301, "learning_rate": 3.9877625668449956e-05, "loss": 0.5945, "step": 162 }, { "epoch": 0.660253164556962, "grad_norm": 0.5490707134925374, "learning_rate": 3.98712764319087e-05, "loss": 0.6297, "step": 163 }, { "epoch": 0.6643037974683544, "grad_norm": 0.8208523380374193, "learning_rate": 3.9864767154838864e-05, "loss": 0.6253, "step": 164 }, { "epoch": 0.6683544303797468, "grad_norm": 0.6033250223447137, "learning_rate": 3.9858097889665277e-05, "loss": 0.6222, "step": 165 }, { "epoch": 0.6724050632911392, "grad_norm": 0.5986098882717482, "learning_rate": 3.985126869010129e-05, "loss": 0.6142, "step": 166 }, { "epoch": 0.6764556962025317, "grad_norm": 0.7370928855617441, "learning_rate": 3.984427961114833e-05, "loss": 0.6035, "step": 167 }, { "epoch": 0.6805063291139241, "grad_norm": 0.5370586114706123, "learning_rate": 3.9837130709095475e-05, "loss": 0.6038, "step": 168 }, { "epoch": 0.6845569620253165, "grad_norm": 0.7384340843274683, "learning_rate": 3.982982204151901e-05, "loss": 0.6301, "step": 169 }, { "epoch": 0.6886075949367089, "grad_norm": 0.6308545484393953, "learning_rate": 3.982235366728193e-05, "loss": 0.6163, "step": 170 }, { "epoch": 0.6926582278481013, "grad_norm": 0.6774956858558794, "learning_rate": 3.9814725646533505e-05, "loss": 0.652, "step": 171 }, { "epoch": 0.6967088607594937, "grad_norm": 0.6240375696492806, "learning_rate": 3.9806938040708746e-05, "loss": 0.6074, "step": 172 }, { "epoch": 0.7007594936708861, "grad_norm": 0.6683112008667518, "learning_rate": 3.9798990912527976e-05, "loss": 0.6177, "step": 173 }, { "epoch": 0.7048101265822785, "grad_norm": 0.5719141425258613, "learning_rate": 3.979088432599627e-05, "loss": 0.6256, "step": 174 }, { "epoch": 0.7088607594936709, "grad_norm": 0.724372798425408, "learning_rate": 3.9782618346402964e-05, "loss": 0.6145, "step": 175 }, { "epoch": 0.7129113924050633, "grad_norm": 0.5785563145021232, "learning_rate": 3.977419304032111e-05, "loss": 0.5983, "step": 176 }, { "epoch": 0.7169620253164557, "grad_norm": 0.6844955865323347, "learning_rate": 3.976560847560697e-05, "loss": 0.6138, "step": 177 }, { "epoch": 0.7210126582278481, "grad_norm": 0.6464008540047615, "learning_rate": 3.9756864721399456e-05, "loss": 0.624, "step": 178 }, { "epoch": 0.7250632911392405, "grad_norm": 0.5978053246458565, "learning_rate": 3.974796184811956e-05, "loss": 0.6049, "step": 179 }, { "epoch": 0.7291139240506329, "grad_norm": 0.5916919270959142, "learning_rate": 3.973889992746979e-05, "loss": 0.6431, "step": 180 }, { "epoch": 0.7331645569620253, "grad_norm": 0.7052561258905004, "learning_rate": 3.972967903243361e-05, "loss": 0.6343, "step": 181 }, { "epoch": 0.7372151898734177, "grad_norm": 0.5414594769074579, "learning_rate": 3.972029923727486e-05, "loss": 0.6248, "step": 182 }, { "epoch": 0.7412658227848101, "grad_norm": 0.5656393151516913, "learning_rate": 3.971076061753709e-05, "loss": 0.6179, "step": 183 }, { "epoch": 0.7453164556962025, "grad_norm": 0.5212772596711286, "learning_rate": 3.9701063250043066e-05, "loss": 0.6163, "step": 184 }, { "epoch": 0.7493670886075949, "grad_norm": 0.5234543230285669, "learning_rate": 3.969120721289402e-05, "loss": 0.6115, "step": 185 }, { "epoch": 0.7534177215189873, "grad_norm": 0.6087902670988561, "learning_rate": 3.9681192585469146e-05, "loss": 0.6222, "step": 186 }, { "epoch": 0.7574683544303797, "grad_norm": 0.5769297248500831, "learning_rate": 3.9671019448424865e-05, "loss": 0.6037, "step": 187 }, { "epoch": 0.7615189873417721, "grad_norm": 0.6601193474288565, "learning_rate": 3.966068788369422e-05, "loss": 0.6103, "step": 188 }, { "epoch": 0.7655696202531646, "grad_norm": 0.5405692072575906, "learning_rate": 3.965019797448622e-05, "loss": 0.6178, "step": 189 }, { "epoch": 0.769620253164557, "grad_norm": 0.6824507503322881, "learning_rate": 3.963954980528515e-05, "loss": 0.6234, "step": 190 }, { "epoch": 0.7736708860759494, "grad_norm": 0.6284108097733041, "learning_rate": 3.9628743461849905e-05, "loss": 0.6076, "step": 191 }, { "epoch": 0.7777215189873418, "grad_norm": 0.5416681689608508, "learning_rate": 3.961777903121329e-05, "loss": 0.6052, "step": 192 }, { "epoch": 0.7817721518987342, "grad_norm": 0.6159077813823434, "learning_rate": 3.960665660168131e-05, "loss": 0.599, "step": 193 }, { "epoch": 0.7858227848101266, "grad_norm": 0.6114397737446657, "learning_rate": 3.9595376262832485e-05, "loss": 0.592, "step": 194 }, { "epoch": 0.789873417721519, "grad_norm": 0.5198435470733823, "learning_rate": 3.9583938105517127e-05, "loss": 0.617, "step": 195 }, { "epoch": 0.7939240506329114, "grad_norm": 0.6280162075452843, "learning_rate": 3.957234222185657e-05, "loss": 0.6032, "step": 196 }, { "epoch": 0.7979746835443038, "grad_norm": 0.6779983938911587, "learning_rate": 3.9560588705242474e-05, "loss": 0.5909, "step": 197 }, { "epoch": 0.8020253164556962, "grad_norm": 0.5721754522959519, "learning_rate": 3.954867765033605e-05, "loss": 0.6241, "step": 198 }, { "epoch": 0.8060759493670886, "grad_norm": 0.7069955268273154, "learning_rate": 3.953660915306728e-05, "loss": 0.6039, "step": 199 }, { "epoch": 0.810126582278481, "grad_norm": 0.5394498398557904, "learning_rate": 3.952438331063419e-05, "loss": 0.6275, "step": 200 }, { "epoch": 0.8141772151898734, "grad_norm": 0.5615988076660543, "learning_rate": 3.951200022150205e-05, "loss": 0.63, "step": 201 }, { "epoch": 0.8182278481012658, "grad_norm": 0.6451655366989583, "learning_rate": 3.949945998540253e-05, "loss": 0.5867, "step": 202 }, { "epoch": 0.8222784810126582, "grad_norm": 0.6160524712393104, "learning_rate": 3.9486762703332993e-05, "loss": 0.6079, "step": 203 }, { "epoch": 0.8263291139240506, "grad_norm": 0.741303842469956, "learning_rate": 3.947390847755559e-05, "loss": 0.6262, "step": 204 }, { "epoch": 0.830379746835443, "grad_norm": 0.5487032960824594, "learning_rate": 3.946089741159648e-05, "loss": 0.6014, "step": 205 }, { "epoch": 0.8344303797468354, "grad_norm": 0.6274558472516643, "learning_rate": 3.944772961024501e-05, "loss": 0.6284, "step": 206 }, { "epoch": 0.8384810126582278, "grad_norm": 0.6664006575416126, "learning_rate": 3.943440517955285e-05, "loss": 0.6226, "step": 207 }, { "epoch": 0.8425316455696202, "grad_norm": 0.5381554226537686, "learning_rate": 3.9420924226833126e-05, "loss": 0.5933, "step": 208 }, { "epoch": 0.8465822784810126, "grad_norm": 0.6542833368601223, "learning_rate": 3.9407286860659566e-05, "loss": 0.6097, "step": 209 }, { "epoch": 0.850632911392405, "grad_norm": 0.6380004985898825, "learning_rate": 3.9393493190865657e-05, "loss": 0.6443, "step": 210 }, { "epoch": 0.8546835443037974, "grad_norm": 0.6281260672722871, "learning_rate": 3.937954332854371e-05, "loss": 0.617, "step": 211 }, { "epoch": 0.8587341772151899, "grad_norm": 0.6789184582173966, "learning_rate": 3.9365437386044016e-05, "loss": 0.6266, "step": 212 }, { "epoch": 0.8627848101265823, "grad_norm": 0.5356678035603144, "learning_rate": 3.935117547697387e-05, "loss": 0.6311, "step": 213 }, { "epoch": 0.8668354430379747, "grad_norm": 0.6310055038109207, "learning_rate": 3.933675771619675e-05, "loss": 0.5838, "step": 214 }, { "epoch": 0.8708860759493671, "grad_norm": 0.6000711327182289, "learning_rate": 3.932218421983131e-05, "loss": 0.6148, "step": 215 }, { "epoch": 0.8749367088607595, "grad_norm": 0.5941642647137034, "learning_rate": 3.9307455105250484e-05, "loss": 0.6027, "step": 216 }, { "epoch": 0.8789873417721519, "grad_norm": 0.5474176431318294, "learning_rate": 3.929257049108054e-05, "loss": 0.6066, "step": 217 }, { "epoch": 0.8830379746835443, "grad_norm": 0.667435671083107, "learning_rate": 3.927753049720011e-05, "loss": 0.6186, "step": 218 }, { "epoch": 0.8870886075949367, "grad_norm": 0.6024911856247329, "learning_rate": 3.9262335244739234e-05, "loss": 0.6147, "step": 219 }, { "epoch": 0.8911392405063291, "grad_norm": 0.8317085947590184, "learning_rate": 3.92469848560784e-05, "loss": 0.6131, "step": 220 }, { "epoch": 0.8951898734177215, "grad_norm": 0.5161880497821377, "learning_rate": 3.923147945484751e-05, "loss": 0.6069, "step": 221 }, { "epoch": 0.8992405063291139, "grad_norm": 0.839115270548457, "learning_rate": 3.9215819165924956e-05, "loss": 0.589, "step": 222 }, { "epoch": 0.9032911392405063, "grad_norm": 0.5867429814443407, "learning_rate": 3.920000411543654e-05, "loss": 0.6199, "step": 223 }, { "epoch": 0.9073417721518987, "grad_norm": 0.623681197455042, "learning_rate": 3.9184034430754495e-05, "loss": 0.5809, "step": 224 }, { "epoch": 0.9113924050632911, "grad_norm": 0.7004307961791486, "learning_rate": 3.916791024049648e-05, "loss": 0.6084, "step": 225 }, { "epoch": 0.9154430379746835, "grad_norm": 0.5729868421602514, "learning_rate": 3.91516316745245e-05, "loss": 0.6164, "step": 226 }, { "epoch": 0.9194936708860759, "grad_norm": 0.5914433004306328, "learning_rate": 3.913519886394389e-05, "loss": 0.5855, "step": 227 }, { "epoch": 0.9235443037974683, "grad_norm": 0.560702167396111, "learning_rate": 3.911861194110225e-05, "loss": 0.5981, "step": 228 }, { "epoch": 0.9275949367088607, "grad_norm": 0.48722825271831, "learning_rate": 3.910187103958837e-05, "loss": 0.5953, "step": 229 }, { "epoch": 0.9316455696202531, "grad_norm": 0.5872183923759643, "learning_rate": 3.908497629423117e-05, "loss": 0.5939, "step": 230 }, { "epoch": 0.9356962025316455, "grad_norm": 0.5539447750798528, "learning_rate": 3.9067927841098614e-05, "loss": 0.6056, "step": 231 }, { "epoch": 0.9397468354430379, "grad_norm": 0.49959512434242814, "learning_rate": 3.9050725817496594e-05, "loss": 0.5875, "step": 232 }, { "epoch": 0.9437974683544303, "grad_norm": 0.5472733825236712, "learning_rate": 3.9033370361967844e-05, "loss": 0.588, "step": 233 }, { "epoch": 0.9478481012658228, "grad_norm": 0.5790881048565243, "learning_rate": 3.901586161429081e-05, "loss": 0.6025, "step": 234 }, { "epoch": 0.9518987341772152, "grad_norm": 0.5910325525470324, "learning_rate": 3.8998199715478545e-05, "loss": 0.6023, "step": 235 }, { "epoch": 0.9559493670886076, "grad_norm": 0.5505490686400791, "learning_rate": 3.8980384807777564e-05, "loss": 0.5951, "step": 236 }, { "epoch": 0.96, "grad_norm": 0.5386632161374434, "learning_rate": 3.896241703466667e-05, "loss": 0.603, "step": 237 }, { "epoch": 0.9640506329113924, "grad_norm": 0.5558915815651001, "learning_rate": 3.894429654085585e-05, "loss": 0.5969, "step": 238 }, { "epoch": 0.9681012658227848, "grad_norm": 0.4934978832055345, "learning_rate": 3.892602347228505e-05, "loss": 0.6114, "step": 239 }, { "epoch": 0.9721518987341772, "grad_norm": 0.5480287719728275, "learning_rate": 3.890759797612307e-05, "loss": 0.6229, "step": 240 }, { "epoch": 0.9762025316455696, "grad_norm": 0.5492906687933836, "learning_rate": 3.888902020076632e-05, "loss": 0.6075, "step": 241 }, { "epoch": 0.980253164556962, "grad_norm": 0.5554362767791582, "learning_rate": 3.887029029583764e-05, "loss": 0.6214, "step": 242 }, { "epoch": 0.9843037974683544, "grad_norm": 0.49628848228634115, "learning_rate": 3.8851408412185125e-05, "loss": 0.6055, "step": 243 }, { "epoch": 0.9883544303797468, "grad_norm": 0.5072948439754807, "learning_rate": 3.8832374701880855e-05, "loss": 0.6016, "step": 244 }, { "epoch": 0.9924050632911392, "grad_norm": 0.5956269041168486, "learning_rate": 3.881318931821972e-05, "loss": 0.5973, "step": 245 }, { "epoch": 0.9964556962025316, "grad_norm": 0.4705418623648784, "learning_rate": 3.879385241571817e-05, "loss": 0.6083, "step": 246 }, { "epoch": 1.000506329113924, "grad_norm": 0.5363346744403108, "learning_rate": 3.8774364150112955e-05, "loss": 0.5829, "step": 247 }, { "epoch": 1.0045569620253165, "grad_norm": 0.6369700202446721, "learning_rate": 3.8754724678359884e-05, "loss": 0.5074, "step": 248 }, { "epoch": 1.0086075949367088, "grad_norm": 0.526781249069065, "learning_rate": 3.873493415863256e-05, "loss": 0.5124, "step": 249 }, { "epoch": 1.0126582278481013, "grad_norm": 0.6688114870591695, "learning_rate": 3.871499275032111e-05, "loss": 0.4988, "step": 250 }, { "epoch": 1.0167088607594936, "grad_norm": 0.6120702127077573, "learning_rate": 3.869490061403091e-05, "loss": 0.5039, "step": 251 }, { "epoch": 1.0207594936708861, "grad_norm": 0.5749989952264982, "learning_rate": 3.867465791158124e-05, "loss": 0.4872, "step": 252 }, { "epoch": 1.0248101265822784, "grad_norm": 0.6298308171731668, "learning_rate": 3.865426480600407e-05, "loss": 0.4831, "step": 253 }, { "epoch": 1.028860759493671, "grad_norm": 0.5571407541503394, "learning_rate": 3.863372146154264e-05, "loss": 0.5195, "step": 254 }, { "epoch": 1.0329113924050632, "grad_norm": 0.6052062707182921, "learning_rate": 3.861302804365024e-05, "loss": 0.4966, "step": 255 }, { "epoch": 1.0369620253164558, "grad_norm": 0.504492659599492, "learning_rate": 3.85921847189888e-05, "loss": 0.4875, "step": 256 }, { "epoch": 1.041012658227848, "grad_norm": 0.5599977041244015, "learning_rate": 3.85711916554276e-05, "loss": 0.4934, "step": 257 }, { "epoch": 1.0450632911392406, "grad_norm": 0.553941972580479, "learning_rate": 3.85500490220419e-05, "loss": 0.4981, "step": 258 }, { "epoch": 1.0491139240506329, "grad_norm": 0.5749168218253881, "learning_rate": 3.852875698911154e-05, "loss": 0.4912, "step": 259 }, { "epoch": 1.0531645569620254, "grad_norm": 0.5176998698810582, "learning_rate": 3.850731572811963e-05, "loss": 0.4569, "step": 260 }, { "epoch": 1.0572151898734177, "grad_norm": 0.5684198455759452, "learning_rate": 3.848572541175116e-05, "loss": 0.5088, "step": 261 }, { "epoch": 1.0612658227848102, "grad_norm": 0.5059411422283082, "learning_rate": 3.846398621389154e-05, "loss": 0.5043, "step": 262 }, { "epoch": 1.0653164556962025, "grad_norm": 0.7035393508601439, "learning_rate": 3.84420983096253e-05, "loss": 0.5007, "step": 263 }, { "epoch": 1.069367088607595, "grad_norm": 0.5731017882914812, "learning_rate": 3.8420061875234606e-05, "loss": 0.4945, "step": 264 }, { "epoch": 1.0734177215189873, "grad_norm": 0.5334011918775026, "learning_rate": 3.839787708819787e-05, "loss": 0.5054, "step": 265 }, { "epoch": 1.0774683544303798, "grad_norm": 0.5912941474896775, "learning_rate": 3.8375544127188325e-05, "loss": 0.4923, "step": 266 }, { "epoch": 1.081518987341772, "grad_norm": 0.5092080954737511, "learning_rate": 3.8353063172072564e-05, "loss": 0.4908, "step": 267 }, { "epoch": 1.0855696202531646, "grad_norm": 0.6221744028467444, "learning_rate": 3.8330434403909105e-05, "loss": 0.4833, "step": 268 }, { "epoch": 1.089620253164557, "grad_norm": 0.6280882982516588, "learning_rate": 3.8307658004946934e-05, "loss": 0.5103, "step": 269 }, { "epoch": 1.0936708860759494, "grad_norm": 0.5881090547252823, "learning_rate": 3.8284734158624046e-05, "loss": 0.5017, "step": 270 }, { "epoch": 1.0977215189873417, "grad_norm": 0.6836884810579328, "learning_rate": 3.826166304956594e-05, "loss": 0.499, "step": 271 }, { "epoch": 1.1017721518987342, "grad_norm": 0.6157470724732549, "learning_rate": 3.8238444863584164e-05, "loss": 0.4859, "step": 272 }, { "epoch": 1.1058227848101265, "grad_norm": 0.6515902530280261, "learning_rate": 3.821507978767479e-05, "loss": 0.4802, "step": 273 }, { "epoch": 1.109873417721519, "grad_norm": 0.49494946045535443, "learning_rate": 3.819156801001693e-05, "loss": 0.4853, "step": 274 }, { "epoch": 1.1139240506329113, "grad_norm": 0.5756304691482019, "learning_rate": 3.816790971997121e-05, "loss": 0.4729, "step": 275 }, { "epoch": 1.1179746835443038, "grad_norm": 0.5143386466105113, "learning_rate": 3.8144105108078246e-05, "loss": 0.479, "step": 276 }, { "epoch": 1.1220253164556961, "grad_norm": 0.48001629930276846, "learning_rate": 3.81201543660571e-05, "loss": 0.4743, "step": 277 }, { "epoch": 1.1260759493670887, "grad_norm": 0.5298589659500469, "learning_rate": 3.809605768680377e-05, "loss": 0.4898, "step": 278 }, { "epoch": 1.130126582278481, "grad_norm": 0.48848045596589124, "learning_rate": 3.807181526438958e-05, "loss": 0.481, "step": 279 }, { "epoch": 1.1341772151898735, "grad_norm": 0.5458461930982174, "learning_rate": 3.8047427294059697e-05, "loss": 0.4853, "step": 280 }, { "epoch": 1.1382278481012658, "grad_norm": 0.5494454076594906, "learning_rate": 3.802289397223145e-05, "loss": 0.4956, "step": 281 }, { "epoch": 1.1422784810126583, "grad_norm": 0.47248687730118777, "learning_rate": 3.7998215496492854e-05, "loss": 0.4991, "step": 282 }, { "epoch": 1.1463291139240506, "grad_norm": 0.5190170906618122, "learning_rate": 3.797339206560096e-05, "loss": 0.4994, "step": 283 }, { "epoch": 1.150379746835443, "grad_norm": 0.5473347631083015, "learning_rate": 3.794842387948027e-05, "loss": 0.4925, "step": 284 }, { "epoch": 1.1544303797468354, "grad_norm": 0.5387960024747152, "learning_rate": 3.7923311139221114e-05, "loss": 0.4881, "step": 285 }, { "epoch": 1.158481012658228, "grad_norm": 0.5562087803180331, "learning_rate": 3.7898054047078054e-05, "loss": 0.4732, "step": 286 }, { "epoch": 1.1625316455696202, "grad_norm": 0.5214745379491722, "learning_rate": 3.787265280646825e-05, "loss": 0.5184, "step": 287 }, { "epoch": 1.1665822784810127, "grad_norm": 0.5190962477517732, "learning_rate": 3.7847107621969786e-05, "loss": 0.4779, "step": 288 }, { "epoch": 1.170632911392405, "grad_norm": 0.47530319003842925, "learning_rate": 3.7821418699320064e-05, "loss": 0.4925, "step": 289 }, { "epoch": 1.1746835443037975, "grad_norm": 0.5139005803017609, "learning_rate": 3.7795586245414145e-05, "loss": 0.5024, "step": 290 }, { "epoch": 1.1787341772151898, "grad_norm": 0.48655281820517204, "learning_rate": 3.776961046830306e-05, "loss": 0.4952, "step": 291 }, { "epoch": 1.1827848101265823, "grad_norm": 0.4964048116306404, "learning_rate": 3.774349157719215e-05, "loss": 0.5038, "step": 292 }, { "epoch": 1.1868354430379746, "grad_norm": 0.44189248451077967, "learning_rate": 3.7717229782439365e-05, "loss": 0.4916, "step": 293 }, { "epoch": 1.1908860759493671, "grad_norm": 0.47985084833361513, "learning_rate": 3.769082529555359e-05, "loss": 0.494, "step": 294 }, { "epoch": 1.1949367088607594, "grad_norm": 0.49783740121770353, "learning_rate": 3.766427832919294e-05, "loss": 0.4676, "step": 295 }, { "epoch": 1.198987341772152, "grad_norm": 0.46417317347105164, "learning_rate": 3.7637589097163024e-05, "loss": 0.5046, "step": 296 }, { "epoch": 1.2030379746835442, "grad_norm": 0.5104629697773866, "learning_rate": 3.761075781441526e-05, "loss": 0.5284, "step": 297 }, { "epoch": 1.2070886075949367, "grad_norm": 0.478786504873347, "learning_rate": 3.75837846970451e-05, "loss": 0.467, "step": 298 }, { "epoch": 1.211139240506329, "grad_norm": 0.5091309980312485, "learning_rate": 3.755666996229032e-05, "loss": 0.4937, "step": 299 }, { "epoch": 1.2151898734177216, "grad_norm": 0.4567877356746936, "learning_rate": 3.752941382852927e-05, "loss": 0.4935, "step": 300 }, { "epoch": 1.2192405063291138, "grad_norm": 0.514730109471005, "learning_rate": 3.7502016515279115e-05, "loss": 0.4643, "step": 301 }, { "epoch": 1.2232911392405064, "grad_norm": 0.45214529054325375, "learning_rate": 3.7474478243194043e-05, "loss": 0.4936, "step": 302 }, { "epoch": 1.2273417721518987, "grad_norm": 0.5652474132179435, "learning_rate": 3.744679923406351e-05, "loss": 0.5079, "step": 303 }, { "epoch": 1.2313924050632912, "grad_norm": 0.5219900557365896, "learning_rate": 3.741897971081043e-05, "loss": 0.4903, "step": 304 }, { "epoch": 1.2354430379746835, "grad_norm": 0.4888230737277604, "learning_rate": 3.739101989748946e-05, "loss": 0.5185, "step": 305 }, { "epoch": 1.239493670886076, "grad_norm": 0.6408729299829772, "learning_rate": 3.7362920019285066e-05, "loss": 0.4957, "step": 306 }, { "epoch": 1.2435443037974683, "grad_norm": 0.5176880230984034, "learning_rate": 3.73346803025098e-05, "loss": 0.5071, "step": 307 }, { "epoch": 1.2475949367088608, "grad_norm": 0.5418483794920186, "learning_rate": 3.730630097460247e-05, "loss": 0.4802, "step": 308 }, { "epoch": 1.251645569620253, "grad_norm": 0.5208433754648614, "learning_rate": 3.727778226412628e-05, "loss": 0.4844, "step": 309 }, { "epoch": 1.2556962025316456, "grad_norm": 0.5722726118274343, "learning_rate": 3.7249124400767006e-05, "loss": 0.5015, "step": 310 }, { "epoch": 1.259746835443038, "grad_norm": 0.5961794541723068, "learning_rate": 3.722032761533114e-05, "loss": 0.4988, "step": 311 }, { "epoch": 1.2637974683544304, "grad_norm": 0.5802329343710285, "learning_rate": 3.719139213974403e-05, "loss": 0.5004, "step": 312 }, { "epoch": 1.2678481012658227, "grad_norm": 0.5627216342131635, "learning_rate": 3.7162318207048006e-05, "loss": 0.4997, "step": 313 }, { "epoch": 1.2718987341772152, "grad_norm": 0.5833979486697212, "learning_rate": 3.713310605140055e-05, "loss": 0.5016, "step": 314 }, { "epoch": 1.2759493670886077, "grad_norm": 0.4829571266387927, "learning_rate": 3.710375590807233e-05, "loss": 0.4984, "step": 315 }, { "epoch": 1.28, "grad_norm": 0.5005180297328758, "learning_rate": 3.7074268013445365e-05, "loss": 0.4946, "step": 316 }, { "epoch": 1.2840506329113923, "grad_norm": 0.45588101195596287, "learning_rate": 3.7044642605011114e-05, "loss": 0.5104, "step": 317 }, { "epoch": 1.2881012658227848, "grad_norm": 0.5309054433633821, "learning_rate": 3.701487992136854e-05, "loss": 0.4972, "step": 318 }, { "epoch": 1.2921518987341774, "grad_norm": 0.43997737549350086, "learning_rate": 3.69849802022222e-05, "loss": 0.502, "step": 319 }, { "epoch": 1.2962025316455696, "grad_norm": 0.502607188857478, "learning_rate": 3.6954943688380334e-05, "loss": 0.4847, "step": 320 }, { "epoch": 1.300253164556962, "grad_norm": 0.45667669118113047, "learning_rate": 3.692477062175289e-05, "loss": 0.5052, "step": 321 }, { "epoch": 1.3043037974683545, "grad_norm": 0.4969817781875874, "learning_rate": 3.689446124534958e-05, "loss": 0.5121, "step": 322 }, { "epoch": 1.308354430379747, "grad_norm": 0.5056174208156867, "learning_rate": 3.686401580327799e-05, "loss": 0.4822, "step": 323 }, { "epoch": 1.3124050632911393, "grad_norm": 0.5106233862889605, "learning_rate": 3.683343454074149e-05, "loss": 0.5052, "step": 324 }, { "epoch": 1.3164556962025316, "grad_norm": 0.4479878638708429, "learning_rate": 3.6802717704037386e-05, "loss": 0.4864, "step": 325 }, { "epoch": 1.320506329113924, "grad_norm": 0.4864922491245442, "learning_rate": 3.6771865540554855e-05, "loss": 0.4864, "step": 326 }, { "epoch": 1.3245569620253166, "grad_norm": 0.44783464349523644, "learning_rate": 3.674087829877297e-05, "loss": 0.4819, "step": 327 }, { "epoch": 1.3286075949367089, "grad_norm": 0.4887952216254288, "learning_rate": 3.6709756228258735e-05, "loss": 0.4883, "step": 328 }, { "epoch": 1.3326582278481012, "grad_norm": 0.5358091193635394, "learning_rate": 3.667849957966501e-05, "loss": 0.4871, "step": 329 }, { "epoch": 1.3367088607594937, "grad_norm": 0.5359607426543558, "learning_rate": 3.6647108604728546e-05, "loss": 0.5072, "step": 330 }, { "epoch": 1.3407594936708862, "grad_norm": 0.5676392758798315, "learning_rate": 3.661558355626795e-05, "loss": 0.4977, "step": 331 }, { "epoch": 1.3448101265822785, "grad_norm": 0.5513764711545082, "learning_rate": 3.658392468818163e-05, "loss": 0.4875, "step": 332 }, { "epoch": 1.3488607594936708, "grad_norm": 0.6363312706663011, "learning_rate": 3.655213225544574e-05, "loss": 0.4792, "step": 333 }, { "epoch": 1.3529113924050633, "grad_norm": 0.4963854961982338, "learning_rate": 3.652020651411218e-05, "loss": 0.5035, "step": 334 }, { "epoch": 1.3569620253164558, "grad_norm": 0.5359895610278381, "learning_rate": 3.6488147721306474e-05, "loss": 0.5027, "step": 335 }, { "epoch": 1.3610126582278481, "grad_norm": 0.5494314608092599, "learning_rate": 3.645595613522574e-05, "loss": 0.4961, "step": 336 }, { "epoch": 1.3650632911392404, "grad_norm": 0.5597022769079281, "learning_rate": 3.642363201513657e-05, "loss": 0.4947, "step": 337 }, { "epoch": 1.369113924050633, "grad_norm": 0.503230810768043, "learning_rate": 3.6391175621373006e-05, "loss": 0.4886, "step": 338 }, { "epoch": 1.3731645569620254, "grad_norm": 0.5499778703185593, "learning_rate": 3.6358587215334355e-05, "loss": 0.4903, "step": 339 }, { "epoch": 1.3772151898734177, "grad_norm": 0.5298469480638328, "learning_rate": 3.632586705948318e-05, "loss": 0.4981, "step": 340 }, { "epoch": 1.38126582278481, "grad_norm": 0.4920395427054174, "learning_rate": 3.629301541734311e-05, "loss": 0.4808, "step": 341 }, { "epoch": 1.3853164556962025, "grad_norm": 0.5663956320584469, "learning_rate": 3.626003255349676e-05, "loss": 0.4921, "step": 342 }, { "epoch": 1.389367088607595, "grad_norm": 0.4517255986812466, "learning_rate": 3.622691873358357e-05, "loss": 0.5053, "step": 343 }, { "epoch": 1.3934177215189874, "grad_norm": 0.5039775809026127, "learning_rate": 3.61936742242977e-05, "loss": 0.4894, "step": 344 }, { "epoch": 1.3974683544303796, "grad_norm": 0.4847706813214993, "learning_rate": 3.6160299293385864e-05, "loss": 0.5148, "step": 345 }, { "epoch": 1.4015189873417722, "grad_norm": 0.48807871623185894, "learning_rate": 3.612679420964516e-05, "loss": 0.5004, "step": 346 }, { "epoch": 1.4055696202531647, "grad_norm": 0.46125556883818103, "learning_rate": 3.609315924292092e-05, "loss": 0.4971, "step": 347 }, { "epoch": 1.409620253164557, "grad_norm": 0.4764841975623861, "learning_rate": 3.6059394664104554e-05, "loss": 0.5006, "step": 348 }, { "epoch": 1.4136708860759493, "grad_norm": 0.5520060533625688, "learning_rate": 3.602550074513133e-05, "loss": 0.5027, "step": 349 }, { "epoch": 1.4177215189873418, "grad_norm": 0.4126619314426673, "learning_rate": 3.599147775897822e-05, "loss": 0.5015, "step": 350 }, { "epoch": 1.4217721518987343, "grad_norm": 0.5215900210306349, "learning_rate": 3.595732597966167e-05, "loss": 0.4857, "step": 351 }, { "epoch": 1.4258227848101266, "grad_norm": 0.45552692612776186, "learning_rate": 3.592304568223542e-05, "loss": 0.4925, "step": 352 }, { "epoch": 1.4298734177215189, "grad_norm": 0.5552413335226507, "learning_rate": 3.588863714278826e-05, "loss": 0.4793, "step": 353 }, { "epoch": 1.4339240506329114, "grad_norm": 0.49525629464578985, "learning_rate": 3.585410063844186e-05, "loss": 0.5084, "step": 354 }, { "epoch": 1.437974683544304, "grad_norm": 0.4855334369850481, "learning_rate": 3.581943644734846e-05, "loss": 0.4786, "step": 355 }, { "epoch": 1.4420253164556962, "grad_norm": 0.5537368933692945, "learning_rate": 3.578464484868869e-05, "loss": 0.4889, "step": 356 }, { "epoch": 1.4460759493670885, "grad_norm": 0.5031382502317597, "learning_rate": 3.5749726122669316e-05, "loss": 0.4961, "step": 357 }, { "epoch": 1.450126582278481, "grad_norm": 0.5392093277387463, "learning_rate": 3.5714680550520943e-05, "loss": 0.4807, "step": 358 }, { "epoch": 1.4541772151898735, "grad_norm": 0.5419929611231369, "learning_rate": 3.5679508414495794e-05, "loss": 0.4932, "step": 359 }, { "epoch": 1.4582278481012658, "grad_norm": 0.4720735991231182, "learning_rate": 3.564420999786543e-05, "loss": 0.5031, "step": 360 }, { "epoch": 1.4622784810126581, "grad_norm": 0.46506372835223286, "learning_rate": 3.560878558491842e-05, "loss": 0.4854, "step": 361 }, { "epoch": 1.4663291139240506, "grad_norm": 0.5159077590045953, "learning_rate": 3.5573235460958145e-05, "loss": 0.4943, "step": 362 }, { "epoch": 1.4703797468354431, "grad_norm": 0.4625296071812449, "learning_rate": 3.553755991230039e-05, "loss": 0.4905, "step": 363 }, { "epoch": 1.4744303797468354, "grad_norm": 0.5179846872361631, "learning_rate": 3.5501759226271144e-05, "loss": 0.4876, "step": 364 }, { "epoch": 1.4784810126582277, "grad_norm": 0.5133635108533725, "learning_rate": 3.546583369120419e-05, "loss": 0.4996, "step": 365 }, { "epoch": 1.4825316455696202, "grad_norm": 0.5045293684804901, "learning_rate": 3.5429783596438864e-05, "loss": 0.4887, "step": 366 }, { "epoch": 1.4865822784810128, "grad_norm": 0.5956995809071176, "learning_rate": 3.539360923231766e-05, "loss": 0.4973, "step": 367 }, { "epoch": 1.490632911392405, "grad_norm": 0.4734462733064546, "learning_rate": 3.535731089018394e-05, "loss": 0.5056, "step": 368 }, { "epoch": 1.4946835443037974, "grad_norm": 0.5293347811995639, "learning_rate": 3.532088886237956e-05, "loss": 0.4828, "step": 369 }, { "epoch": 1.4987341772151899, "grad_norm": 0.41816017235165814, "learning_rate": 3.528434344224253e-05, "loss": 0.4872, "step": 370 }, { "epoch": 1.5027848101265824, "grad_norm": 0.5403304387449043, "learning_rate": 3.524767492410464e-05, "loss": 0.5133, "step": 371 }, { "epoch": 1.5068354430379747, "grad_norm": 0.48689497561713513, "learning_rate": 3.521088360328908e-05, "loss": 0.4849, "step": 372 }, { "epoch": 1.510886075949367, "grad_norm": 0.5505544698326778, "learning_rate": 3.517396977610811e-05, "loss": 0.4811, "step": 373 }, { "epoch": 1.5149367088607595, "grad_norm": 0.4494508754945606, "learning_rate": 3.5136933739860595e-05, "loss": 0.4742, "step": 374 }, { "epoch": 1.518987341772152, "grad_norm": 0.4885198219284603, "learning_rate": 3.509977579282971e-05, "loss": 0.4724, "step": 375 }, { "epoch": 1.5230379746835443, "grad_norm": 0.468832726353249, "learning_rate": 3.5062496234280424e-05, "loss": 0.5023, "step": 376 }, { "epoch": 1.5270886075949366, "grad_norm": 0.49707165373134476, "learning_rate": 3.502509536445719e-05, "loss": 0.487, "step": 377 }, { "epoch": 1.531139240506329, "grad_norm": 0.5118804913346856, "learning_rate": 3.498757348458147e-05, "loss": 0.5035, "step": 378 }, { "epoch": 1.5351898734177216, "grad_norm": 0.5022092177715352, "learning_rate": 3.4949930896849324e-05, "loss": 0.5109, "step": 379 }, { "epoch": 1.539240506329114, "grad_norm": 0.49908280195746907, "learning_rate": 3.491216790442899e-05, "loss": 0.5011, "step": 380 }, { "epoch": 1.5432911392405062, "grad_norm": 0.4811907772376422, "learning_rate": 3.487428481145839e-05, "loss": 0.4803, "step": 381 }, { "epoch": 1.5473417721518987, "grad_norm": 0.4985577130617522, "learning_rate": 3.483628192304278e-05, "loss": 0.4774, "step": 382 }, { "epoch": 1.5513924050632912, "grad_norm": 0.5090760337995829, "learning_rate": 3.479815954525219e-05, "loss": 0.4862, "step": 383 }, { "epoch": 1.5554430379746835, "grad_norm": 0.4434289618004002, "learning_rate": 3.475991798511899e-05, "loss": 0.4975, "step": 384 }, { "epoch": 1.5594936708860758, "grad_norm": 0.46176155879993735, "learning_rate": 3.4721557550635464e-05, "loss": 0.4851, "step": 385 }, { "epoch": 1.5635443037974683, "grad_norm": 0.4778620478701114, "learning_rate": 3.468307855075128e-05, "loss": 0.5033, "step": 386 }, { "epoch": 1.5675949367088609, "grad_norm": 0.45850552655135696, "learning_rate": 3.4644481295371005e-05, "loss": 0.4945, "step": 387 }, { "epoch": 1.5716455696202531, "grad_norm": 0.5314019046361848, "learning_rate": 3.460576609535163e-05, "loss": 0.4919, "step": 388 }, { "epoch": 1.5756962025316454, "grad_norm": 0.4275417325233082, "learning_rate": 3.456693326250006e-05, "loss": 0.4891, "step": 389 }, { "epoch": 1.579746835443038, "grad_norm": 0.522574217032523, "learning_rate": 3.452798310957058e-05, "loss": 0.4893, "step": 390 }, { "epoch": 1.5837974683544305, "grad_norm": 0.48019400095890086, "learning_rate": 3.4488915950262386e-05, "loss": 0.4762, "step": 391 }, { "epoch": 1.5878481012658228, "grad_norm": 0.5220594600151185, "learning_rate": 3.4449732099216985e-05, "loss": 0.4858, "step": 392 }, { "epoch": 1.591898734177215, "grad_norm": 0.45964314458551847, "learning_rate": 3.441043187201574e-05, "loss": 0.4831, "step": 393 }, { "epoch": 1.5959493670886076, "grad_norm": 0.4526278698110787, "learning_rate": 3.437101558517728e-05, "loss": 0.4903, "step": 394 }, { "epoch": 1.6, "grad_norm": 0.4847656163359053, "learning_rate": 3.433148355615496e-05, "loss": 0.4908, "step": 395 }, { "epoch": 1.6040506329113924, "grad_norm": 0.4152718582382735, "learning_rate": 3.4291836103334294e-05, "loss": 0.4792, "step": 396 }, { "epoch": 1.6081012658227847, "grad_norm": 0.48978507886484357, "learning_rate": 3.425207354603043e-05, "loss": 0.5183, "step": 397 }, { "epoch": 1.6121518987341772, "grad_norm": 0.4728070857152709, "learning_rate": 3.421219620448553e-05, "loss": 0.4819, "step": 398 }, { "epoch": 1.6162025316455697, "grad_norm": 0.5412843216481626, "learning_rate": 3.417220439986623e-05, "loss": 0.4887, "step": 399 }, { "epoch": 1.620253164556962, "grad_norm": 0.5128722133389186, "learning_rate": 3.4132098454261024e-05, "loss": 0.497, "step": 400 }, { "epoch": 1.6243037974683543, "grad_norm": 0.45336334205384865, "learning_rate": 3.4091878690677676e-05, "loss": 0.4945, "step": 401 }, { "epoch": 1.6283544303797468, "grad_norm": 0.4627723190030034, "learning_rate": 3.405154543304065e-05, "loss": 0.5029, "step": 402 }, { "epoch": 1.6324050632911393, "grad_norm": 0.5042540455490365, "learning_rate": 3.401109900618843e-05, "loss": 0.4998, "step": 403 }, { "epoch": 1.6364556962025316, "grad_norm": 0.4463213094176671, "learning_rate": 3.3970539735870996e-05, "loss": 0.4854, "step": 404 }, { "epoch": 1.640506329113924, "grad_norm": 0.42785221083160496, "learning_rate": 3.392986794874714e-05, "loss": 0.4987, "step": 405 }, { "epoch": 1.6445569620253164, "grad_norm": 0.45984428109456743, "learning_rate": 3.388908397238184e-05, "loss": 0.4787, "step": 406 }, { "epoch": 1.648607594936709, "grad_norm": 0.4468123926258551, "learning_rate": 3.384818813524362e-05, "loss": 0.4988, "step": 407 }, { "epoch": 1.6526582278481012, "grad_norm": 0.47953821359287335, "learning_rate": 3.380718076670195e-05, "loss": 0.4729, "step": 408 }, { "epoch": 1.6567088607594935, "grad_norm": 0.4308135214711306, "learning_rate": 3.376606219702454e-05, "loss": 0.506, "step": 409 }, { "epoch": 1.660759493670886, "grad_norm": 0.445761227574612, "learning_rate": 3.372483275737468e-05, "loss": 0.5057, "step": 410 }, { "epoch": 1.6648101265822786, "grad_norm": 0.4963333466116854, "learning_rate": 3.368349277980861e-05, "loss": 0.4867, "step": 411 }, { "epoch": 1.6688607594936709, "grad_norm": 0.4436991943935751, "learning_rate": 3.3642042597272844e-05, "loss": 0.4878, "step": 412 }, { "epoch": 1.6729113924050631, "grad_norm": 0.49221804372938144, "learning_rate": 3.360048254360144e-05, "loss": 0.4797, "step": 413 }, { "epoch": 1.6769620253164557, "grad_norm": 0.49436032801119995, "learning_rate": 3.355881295351336e-05, "loss": 0.4832, "step": 414 }, { "epoch": 1.6810126582278482, "grad_norm": 0.4613228992105084, "learning_rate": 3.351703416260975e-05, "loss": 0.5036, "step": 415 }, { "epoch": 1.6850632911392405, "grad_norm": 0.4530976641281682, "learning_rate": 3.347514650737126e-05, "loss": 0.4969, "step": 416 }, { "epoch": 1.6891139240506328, "grad_norm": 0.43145963085495714, "learning_rate": 3.3433150325155295e-05, "loss": 0.4665, "step": 417 }, { "epoch": 1.6931645569620253, "grad_norm": 0.5319923637609211, "learning_rate": 3.339104595419334e-05, "loss": 0.4928, "step": 418 }, { "epoch": 1.6972151898734178, "grad_norm": 0.4184927305297104, "learning_rate": 3.3348833733588204e-05, "loss": 0.5092, "step": 419 }, { "epoch": 1.70126582278481, "grad_norm": 0.4437481913303361, "learning_rate": 3.3306514003311305e-05, "loss": 0.4728, "step": 420 }, { "epoch": 1.7053164556962024, "grad_norm": 0.39595902212962963, "learning_rate": 3.326408710419996e-05, "loss": 0.4785, "step": 421 }, { "epoch": 1.709367088607595, "grad_norm": 0.4173963899596858, "learning_rate": 3.322155337795454e-05, "loss": 0.4936, "step": 422 }, { "epoch": 1.7134177215189874, "grad_norm": 0.4321950499571264, "learning_rate": 3.317891316713587e-05, "loss": 0.4906, "step": 423 }, { "epoch": 1.7174683544303797, "grad_norm": 0.40872275708333866, "learning_rate": 3.313616681516231e-05, "loss": 0.4802, "step": 424 }, { "epoch": 1.721518987341772, "grad_norm": 0.4891255097800129, "learning_rate": 3.309331466630713e-05, "loss": 0.5011, "step": 425 }, { "epoch": 1.7255696202531645, "grad_norm": 0.4528517700006589, "learning_rate": 3.305035706569563e-05, "loss": 0.4968, "step": 426 }, { "epoch": 1.729620253164557, "grad_norm": 0.5765809460654442, "learning_rate": 3.3007294359302433e-05, "loss": 0.4844, "step": 427 }, { "epoch": 1.7336708860759493, "grad_norm": 0.4463358215204884, "learning_rate": 3.296412689394864e-05, "loss": 0.4863, "step": 428 }, { "epoch": 1.7377215189873416, "grad_norm": 0.5829178776930466, "learning_rate": 3.292085501729909e-05, "loss": 0.4837, "step": 429 }, { "epoch": 1.7417721518987341, "grad_norm": 0.43302274021401954, "learning_rate": 3.2877479077859534e-05, "loss": 0.4919, "step": 430 }, { "epoch": 1.7458227848101266, "grad_norm": 0.5070585081072507, "learning_rate": 3.283399942497381e-05, "loss": 0.4879, "step": 431 }, { "epoch": 1.749873417721519, "grad_norm": 0.41982808929139936, "learning_rate": 3.279041640882108e-05, "loss": 0.4711, "step": 432 }, { "epoch": 1.7539240506329112, "grad_norm": 0.5203159610458518, "learning_rate": 3.2746730380412964e-05, "loss": 0.4849, "step": 433 }, { "epoch": 1.7579746835443038, "grad_norm": 0.42119621698522786, "learning_rate": 3.2702941691590726e-05, "loss": 0.5005, "step": 434 }, { "epoch": 1.7620253164556963, "grad_norm": 0.545815722837325, "learning_rate": 3.265905069502244e-05, "loss": 0.4782, "step": 435 }, { "epoch": 1.7660759493670886, "grad_norm": 0.43604890485873105, "learning_rate": 3.261505774420016e-05, "loss": 0.4643, "step": 436 }, { "epoch": 1.7701265822784809, "grad_norm": 0.4973645109321658, "learning_rate": 3.257096319343707e-05, "loss": 0.4863, "step": 437 }, { "epoch": 1.7741772151898734, "grad_norm": 0.48240722724587637, "learning_rate": 3.2526767397864614e-05, "loss": 0.4826, "step": 438 }, { "epoch": 1.7782278481012659, "grad_norm": 0.42181012919532795, "learning_rate": 3.248247071342966e-05, "loss": 0.4916, "step": 439 }, { "epoch": 1.7822784810126582, "grad_norm": 0.42246480279829945, "learning_rate": 3.243807349689161e-05, "loss": 0.5, "step": 440 }, { "epoch": 1.7863291139240505, "grad_norm": 0.45009239764387227, "learning_rate": 3.2393576105819544e-05, "loss": 0.4835, "step": 441 }, { "epoch": 1.790379746835443, "grad_norm": 0.43560445509775064, "learning_rate": 3.2348978898589333e-05, "loss": 0.4854, "step": 442 }, { "epoch": 1.7944303797468355, "grad_norm": 0.5838595293197341, "learning_rate": 3.230428223438075e-05, "loss": 0.491, "step": 443 }, { "epoch": 1.7984810126582278, "grad_norm": 0.5007624076609164, "learning_rate": 3.225948647317459e-05, "loss": 0.4954, "step": 444 }, { "epoch": 1.80253164556962, "grad_norm": 0.4725921065841419, "learning_rate": 3.2214591975749745e-05, "loss": 0.5116, "step": 445 }, { "epoch": 1.8065822784810126, "grad_norm": 0.5141525316293205, "learning_rate": 3.216959910368034e-05, "loss": 0.4899, "step": 446 }, { "epoch": 1.8106329113924051, "grad_norm": 0.40076629992771684, "learning_rate": 3.212450821933277e-05, "loss": 0.478, "step": 447 }, { "epoch": 1.8146835443037974, "grad_norm": 0.46302316367714696, "learning_rate": 3.207931968586281e-05, "loss": 0.494, "step": 448 }, { "epoch": 1.81873417721519, "grad_norm": 0.4411812828528412, "learning_rate": 3.203403386721272e-05, "loss": 0.4578, "step": 449 }, { "epoch": 1.8227848101265822, "grad_norm": 0.46675238155985316, "learning_rate": 3.1988651128108245e-05, "loss": 0.479, "step": 450 }, { "epoch": 1.8268354430379747, "grad_norm": 0.4403916056684223, "learning_rate": 3.194317183405573e-05, "loss": 0.4944, "step": 451 }, { "epoch": 1.8308860759493673, "grad_norm": 0.5112987260955735, "learning_rate": 3.189759635133914e-05, "loss": 0.5146, "step": 452 }, { "epoch": 1.8349367088607595, "grad_norm": 1.4442582069401269, "learning_rate": 3.185192504701718e-05, "loss": 0.4701, "step": 453 }, { "epoch": 1.8389873417721518, "grad_norm": 0.5328162436266618, "learning_rate": 3.1806158288920234e-05, "loss": 0.4975, "step": 454 }, { "epoch": 1.8430379746835444, "grad_norm": 0.40652984325241676, "learning_rate": 3.1760296445647477e-05, "loss": 0.4935, "step": 455 }, { "epoch": 1.8470886075949369, "grad_norm": 0.5735103679366411, "learning_rate": 3.1714339886563896e-05, "loss": 0.5018, "step": 456 }, { "epoch": 1.8511392405063292, "grad_norm": 0.46273029611858585, "learning_rate": 3.166828898179731e-05, "loss": 0.481, "step": 457 }, { "epoch": 1.8551898734177215, "grad_norm": 0.5009081998220901, "learning_rate": 3.162214410223536e-05, "loss": 0.483, "step": 458 }, { "epoch": 1.859240506329114, "grad_norm": 0.49520010971547584, "learning_rate": 3.157590561952257e-05, "loss": 0.4607, "step": 459 }, { "epoch": 1.8632911392405065, "grad_norm": 0.42908171131718376, "learning_rate": 3.152957390605732e-05, "loss": 0.4879, "step": 460 }, { "epoch": 1.8673417721518988, "grad_norm": 0.5563597587745458, "learning_rate": 3.148314933498886e-05, "loss": 0.4876, "step": 461 }, { "epoch": 1.871392405063291, "grad_norm": 0.4080103615055227, "learning_rate": 3.143663228021431e-05, "loss": 0.482, "step": 462 }, { "epoch": 1.8754430379746836, "grad_norm": 0.45071042222525987, "learning_rate": 3.1390023116375624e-05, "loss": 0.4858, "step": 463 }, { "epoch": 1.879493670886076, "grad_norm": 0.4273785973153673, "learning_rate": 3.134332221885661e-05, "loss": 0.4738, "step": 464 }, { "epoch": 1.8835443037974684, "grad_norm": 0.42326144108290154, "learning_rate": 3.129652996377987e-05, "loss": 0.5003, "step": 465 }, { "epoch": 1.8875949367088607, "grad_norm": 0.4534481933744949, "learning_rate": 3.12496467280038e-05, "loss": 0.509, "step": 466 }, { "epoch": 1.8916455696202532, "grad_norm": 0.4075383602178575, "learning_rate": 3.120267288911952e-05, "loss": 0.4791, "step": 467 }, { "epoch": 1.8956962025316457, "grad_norm": 0.469575267549545, "learning_rate": 3.11556088254479e-05, "loss": 0.5015, "step": 468 }, { "epoch": 1.899746835443038, "grad_norm": 0.4411317914388956, "learning_rate": 3.11084549160364e-05, "loss": 0.5003, "step": 469 }, { "epoch": 1.9037974683544303, "grad_norm": 0.41895436209321796, "learning_rate": 3.106121154065615e-05, "loss": 0.4758, "step": 470 }, { "epoch": 1.9078481012658228, "grad_norm": 0.701374276163425, "learning_rate": 3.1013879079798805e-05, "loss": 0.4644, "step": 471 }, { "epoch": 1.9118987341772153, "grad_norm": 0.4462066039588728, "learning_rate": 3.096645791467348e-05, "loss": 0.4922, "step": 472 }, { "epoch": 1.9159493670886076, "grad_norm": 0.47150188860609477, "learning_rate": 3.091894842720373e-05, "loss": 0.4874, "step": 473 }, { "epoch": 1.92, "grad_norm": 0.44495808670319587, "learning_rate": 3.0871351000024425e-05, "loss": 0.4869, "step": 474 }, { "epoch": 1.9240506329113924, "grad_norm": 0.43347869018909924, "learning_rate": 3.0823666016478716e-05, "loss": 0.4708, "step": 475 }, { "epoch": 1.928101265822785, "grad_norm": 0.4035655854053392, "learning_rate": 3.0775893860614896e-05, "loss": 0.4767, "step": 476 }, { "epoch": 1.9321518987341773, "grad_norm": 0.4347781093770362, "learning_rate": 3.0728034917183336e-05, "loss": 0.4842, "step": 477 }, { "epoch": 1.9362025316455695, "grad_norm": 0.4319108882902854, "learning_rate": 3.06800895716334e-05, "loss": 0.4809, "step": 478 }, { "epoch": 1.940253164556962, "grad_norm": 0.411625944575659, "learning_rate": 3.063205821011029e-05, "loss": 0.4756, "step": 479 }, { "epoch": 1.9443037974683546, "grad_norm": 0.41651299401965497, "learning_rate": 3.0583941219452016e-05, "loss": 0.4763, "step": 480 }, { "epoch": 1.9483544303797469, "grad_norm": 0.4898432045658191, "learning_rate": 3.053573898718618e-05, "loss": 0.4813, "step": 481 }, { "epoch": 1.9524050632911392, "grad_norm": 1.0649245486041987, "learning_rate": 3.0487451901526956e-05, "loss": 0.502, "step": 482 }, { "epoch": 1.9564556962025317, "grad_norm": 0.4184902275429508, "learning_rate": 3.0439080351371875e-05, "loss": 0.4824, "step": 483 }, { "epoch": 1.9605063291139242, "grad_norm": 0.4149059917484562, "learning_rate": 3.0390624726298764e-05, "loss": 0.4867, "step": 484 }, { "epoch": 1.9645569620253165, "grad_norm": 0.44410502688926834, "learning_rate": 3.034208541656255e-05, "loss": 0.4927, "step": 485 }, { "epoch": 1.9686075949367088, "grad_norm": 0.4177455442819199, "learning_rate": 3.029346281309218e-05, "loss": 0.4762, "step": 486 }, { "epoch": 1.9726582278481013, "grad_norm": 1.8522219937145947, "learning_rate": 3.0244757307487415e-05, "loss": 0.4963, "step": 487 }, { "epoch": 1.9767088607594938, "grad_norm": 1.88152793009122, "learning_rate": 3.019596929201569e-05, "loss": 0.5148, "step": 488 }, { "epoch": 1.980759493670886, "grad_norm": 0.4598722171457815, "learning_rate": 3.0147099159608985e-05, "loss": 0.4773, "step": 489 }, { "epoch": 1.9848101265822784, "grad_norm": 0.41320708538147866, "learning_rate": 3.0098147303860616e-05, "loss": 0.48, "step": 490 }, { "epoch": 1.988860759493671, "grad_norm": 0.4849084732431047, "learning_rate": 3.0049114119022117e-05, "loss": 0.4785, "step": 491 }, { "epoch": 1.9929113924050634, "grad_norm": 0.4127152582734995, "learning_rate": 3.0000000000000004e-05, "loss": 0.4593, "step": 492 }, { "epoch": 1.9969620253164557, "grad_norm": 0.4335941151781117, "learning_rate": 2.995080534235264e-05, "loss": 0.4908, "step": 493 }, { "epoch": 2.001012658227848, "grad_norm": 0.48310450282739664, "learning_rate": 2.9901530542287044e-05, "loss": 0.4711, "step": 494 }, { "epoch": 2.0050632911392405, "grad_norm": 0.6396450242045277, "learning_rate": 2.9852175996655676e-05, "loss": 0.362, "step": 495 }, { "epoch": 2.009113924050633, "grad_norm": 0.8592640748854415, "learning_rate": 2.980274210295326e-05, "loss": 0.355, "step": 496 }, { "epoch": 2.013164556962025, "grad_norm": 0.9813066393929778, "learning_rate": 2.9753229259313578e-05, "loss": 0.3705, "step": 497 }, { "epoch": 2.0172151898734176, "grad_norm": 0.9681992659898294, "learning_rate": 2.9703637864506274e-05, "loss": 0.3446, "step": 498 }, { "epoch": 2.02126582278481, "grad_norm": 0.5200636898000063, "learning_rate": 2.965396831793362e-05, "loss": 0.3661, "step": 499 }, { "epoch": 2.0253164556962027, "grad_norm": 0.5843827328838295, "learning_rate": 2.9604221019627316e-05, "loss": 0.3563, "step": 500 }, { "epoch": 2.0293670886075947, "grad_norm": 0.4529392950265646, "learning_rate": 2.955439637024526e-05, "loss": 0.3545, "step": 501 }, { "epoch": 2.0334177215189873, "grad_norm": 0.5398718669049895, "learning_rate": 2.9504494771068334e-05, "loss": 0.3596, "step": 502 }, { "epoch": 2.0374683544303798, "grad_norm": 0.4823421368339781, "learning_rate": 2.9454516623997156e-05, "loss": 0.3445, "step": 503 }, { "epoch": 2.0415189873417723, "grad_norm": 0.45905801526328943, "learning_rate": 2.9404462331548847e-05, "loss": 0.3489, "step": 504 }, { "epoch": 2.0455696202531644, "grad_norm": 0.48598009640232304, "learning_rate": 2.93543322968538e-05, "loss": 0.3502, "step": 505 }, { "epoch": 2.049620253164557, "grad_norm": 0.4310794161930802, "learning_rate": 2.9304126923652428e-05, "loss": 0.3387, "step": 506 }, { "epoch": 2.0536708860759494, "grad_norm": 0.4582432118919477, "learning_rate": 2.9253846616291896e-05, "loss": 0.3629, "step": 507 }, { "epoch": 2.057721518987342, "grad_norm": 0.5392515604146502, "learning_rate": 2.9203491779722896e-05, "loss": 0.3691, "step": 508 }, { "epoch": 2.061772151898734, "grad_norm": 0.46478893694563717, "learning_rate": 2.9153062819496357e-05, "loss": 0.3315, "step": 509 }, { "epoch": 2.0658227848101265, "grad_norm": 0.42718406057045094, "learning_rate": 2.9102560141760178e-05, "loss": 0.3589, "step": 510 }, { "epoch": 2.069873417721519, "grad_norm": 0.46912515945269284, "learning_rate": 2.9051984153256004e-05, "loss": 0.3509, "step": 511 }, { "epoch": 2.0739240506329115, "grad_norm": 0.40475964359433303, "learning_rate": 2.900133526131588e-05, "loss": 0.3455, "step": 512 }, { "epoch": 2.0779746835443036, "grad_norm": 0.8843942998370797, "learning_rate": 2.8950613873859025e-05, "loss": 0.3465, "step": 513 }, { "epoch": 2.082025316455696, "grad_norm": 0.3993614346217456, "learning_rate": 2.8899820399388515e-05, "loss": 0.3375, "step": 514 }, { "epoch": 2.0860759493670886, "grad_norm": 0.45007293527636044, "learning_rate": 2.8848955246988012e-05, "loss": 0.3424, "step": 515 }, { "epoch": 2.090126582278481, "grad_norm": 0.39713132839389326, "learning_rate": 2.879801882631847e-05, "loss": 0.3467, "step": 516 }, { "epoch": 2.094177215189873, "grad_norm": 0.4478056962784838, "learning_rate": 2.8747011547614808e-05, "loss": 0.365, "step": 517 }, { "epoch": 2.0982278481012657, "grad_norm": 0.4104933642878909, "learning_rate": 2.8695933821682635e-05, "loss": 0.3636, "step": 518 }, { "epoch": 2.1022784810126582, "grad_norm": 0.4011885619406475, "learning_rate": 2.864478605989494e-05, "loss": 0.3644, "step": 519 }, { "epoch": 2.1063291139240508, "grad_norm": 0.41567844059941006, "learning_rate": 2.8593568674188765e-05, "loss": 0.361, "step": 520 }, { "epoch": 2.110379746835443, "grad_norm": 0.435348379437705, "learning_rate": 2.8542282077061892e-05, "loss": 0.3646, "step": 521 }, { "epoch": 2.1144303797468353, "grad_norm": 0.42378829736352774, "learning_rate": 2.8490926681569523e-05, "loss": 0.3524, "step": 522 }, { "epoch": 2.118481012658228, "grad_norm": 0.38879432623307175, "learning_rate": 2.8439502901320956e-05, "loss": 0.3645, "step": 523 }, { "epoch": 2.1225316455696204, "grad_norm": 0.45486156062634964, "learning_rate": 2.8388011150476237e-05, "loss": 0.3386, "step": 524 }, { "epoch": 2.1265822784810124, "grad_norm": 0.4170534055004539, "learning_rate": 2.8336451843742866e-05, "loss": 0.3587, "step": 525 }, { "epoch": 2.130632911392405, "grad_norm": 0.4372273662989678, "learning_rate": 2.8284825396372387e-05, "loss": 0.3514, "step": 526 }, { "epoch": 2.1346835443037975, "grad_norm": 0.434795096587829, "learning_rate": 2.8233132224157132e-05, "loss": 0.3447, "step": 527 }, { "epoch": 2.13873417721519, "grad_norm": 0.4406277414502166, "learning_rate": 2.8181372743426805e-05, "loss": 0.3567, "step": 528 }, { "epoch": 2.1427848101265825, "grad_norm": 0.3988010456693515, "learning_rate": 2.8129547371045128e-05, "loss": 0.3447, "step": 529 }, { "epoch": 2.1468354430379746, "grad_norm": 0.437819167781582, "learning_rate": 2.8077656524406534e-05, "loss": 0.3699, "step": 530 }, { "epoch": 2.150886075949367, "grad_norm": 0.42778030133729594, "learning_rate": 2.802570062143278e-05, "loss": 0.3682, "step": 531 }, { "epoch": 2.1549367088607596, "grad_norm": 0.4131605405150727, "learning_rate": 2.7973680080569555e-05, "loss": 0.3408, "step": 532 }, { "epoch": 2.1589873417721517, "grad_norm": 0.6618105991155985, "learning_rate": 2.792159532078314e-05, "loss": 0.3676, "step": 533 }, { "epoch": 2.163037974683544, "grad_norm": 0.37929875384799194, "learning_rate": 2.7869446761557033e-05, "loss": 0.3546, "step": 534 }, { "epoch": 2.1670886075949367, "grad_norm": 0.447356818609384, "learning_rate": 2.781723482288857e-05, "loss": 0.3486, "step": 535 }, { "epoch": 2.1711392405063292, "grad_norm": 0.38311981163201436, "learning_rate": 2.7764959925285517e-05, "loss": 0.3705, "step": 536 }, { "epoch": 2.1751898734177217, "grad_norm": 0.38110287751787497, "learning_rate": 2.771262248976272e-05, "loss": 0.3524, "step": 537 }, { "epoch": 2.179240506329114, "grad_norm": 0.42951053596970734, "learning_rate": 2.7660222937838677e-05, "loss": 0.3479, "step": 538 }, { "epoch": 2.1832911392405063, "grad_norm": 0.4061430535325171, "learning_rate": 2.7607761691532186e-05, "loss": 0.3518, "step": 539 }, { "epoch": 2.187341772151899, "grad_norm": 0.42844079998169365, "learning_rate": 2.7555239173358916e-05, "loss": 0.3519, "step": 540 }, { "epoch": 2.191392405063291, "grad_norm": 0.4042475757469009, "learning_rate": 2.7502655806328e-05, "loss": 0.3694, "step": 541 }, { "epoch": 2.1954430379746834, "grad_norm": 0.4261089699849046, "learning_rate": 2.7450012013938648e-05, "loss": 0.3494, "step": 542 }, { "epoch": 2.199493670886076, "grad_norm": 0.40490176865283384, "learning_rate": 2.739730822017673e-05, "loss": 0.3467, "step": 543 }, { "epoch": 2.2035443037974685, "grad_norm": 0.4173891193331155, "learning_rate": 2.7344544849511355e-05, "loss": 0.3576, "step": 544 }, { "epoch": 2.207594936708861, "grad_norm": 0.567216122711215, "learning_rate": 2.7291722326891456e-05, "loss": 0.3617, "step": 545 }, { "epoch": 2.211645569620253, "grad_norm": 0.4549569831179454, "learning_rate": 2.723884107774236e-05, "loss": 0.3666, "step": 546 }, { "epoch": 2.2156962025316456, "grad_norm": 0.41475202340739814, "learning_rate": 2.718590152796239e-05, "loss": 0.3543, "step": 547 }, { "epoch": 2.219746835443038, "grad_norm": 0.45809013306263036, "learning_rate": 2.71329041039194e-05, "loss": 0.3476, "step": 548 }, { "epoch": 2.22379746835443, "grad_norm": 0.4111401384802064, "learning_rate": 2.7079849232447357e-05, "loss": 0.3578, "step": 549 }, { "epoch": 2.2278481012658227, "grad_norm": 0.44872196848414897, "learning_rate": 2.7026737340842895e-05, "loss": 0.3716, "step": 550 }, { "epoch": 2.231898734177215, "grad_norm": 0.403571281649303, "learning_rate": 2.697356885686189e-05, "loss": 0.3584, "step": 551 }, { "epoch": 2.2359493670886077, "grad_norm": 0.4075265151135991, "learning_rate": 2.6920344208716014e-05, "loss": 0.3511, "step": 552 }, { "epoch": 2.24, "grad_norm": 0.3854545005566597, "learning_rate": 2.6867063825069252e-05, "loss": 0.3508, "step": 553 }, { "epoch": 2.2440506329113923, "grad_norm": 0.4187516152410682, "learning_rate": 2.6813728135034494e-05, "loss": 0.3483, "step": 554 }, { "epoch": 2.248101265822785, "grad_norm": 0.40854878836696784, "learning_rate": 2.6760337568170056e-05, "loss": 0.3568, "step": 555 }, { "epoch": 2.2521518987341773, "grad_norm": 0.42647735994377667, "learning_rate": 2.6706892554476226e-05, "loss": 0.3625, "step": 556 }, { "epoch": 2.2562025316455694, "grad_norm": 0.40306790035434437, "learning_rate": 2.6653393524391795e-05, "loss": 0.353, "step": 557 }, { "epoch": 2.260253164556962, "grad_norm": 0.4596693752813578, "learning_rate": 2.6599840908790592e-05, "loss": 0.3532, "step": 558 }, { "epoch": 2.2643037974683544, "grad_norm": 0.3918138653358397, "learning_rate": 2.6546235138978028e-05, "loss": 0.3456, "step": 559 }, { "epoch": 2.268354430379747, "grad_norm": 0.5254890299227827, "learning_rate": 2.6492576646687597e-05, "loss": 0.3472, "step": 560 }, { "epoch": 2.2724050632911394, "grad_norm": 0.82785901327937, "learning_rate": 2.6438865864077425e-05, "loss": 0.3599, "step": 561 }, { "epoch": 2.2764556962025315, "grad_norm": 0.4789420995112133, "learning_rate": 2.6385103223726766e-05, "loss": 0.3506, "step": 562 }, { "epoch": 2.280506329113924, "grad_norm": 0.44116956636231874, "learning_rate": 2.6331289158632537e-05, "loss": 0.3472, "step": 563 }, { "epoch": 2.2845569620253166, "grad_norm": 0.3976796281206817, "learning_rate": 2.6277424102205817e-05, "loss": 0.3573, "step": 564 }, { "epoch": 2.2886075949367086, "grad_norm": 0.41239543566069925, "learning_rate": 2.6223508488268374e-05, "loss": 0.3522, "step": 565 }, { "epoch": 2.292658227848101, "grad_norm": 0.42116045426249216, "learning_rate": 2.6169542751049148e-05, "loss": 0.3561, "step": 566 }, { "epoch": 2.2967088607594937, "grad_norm": 0.36542499152556784, "learning_rate": 2.6115527325180754e-05, "loss": 0.3652, "step": 567 }, { "epoch": 2.300759493670886, "grad_norm": 0.38281627149184183, "learning_rate": 2.606146264569603e-05, "loss": 0.3562, "step": 568 }, { "epoch": 2.3048101265822787, "grad_norm": 0.39500371746571833, "learning_rate": 2.6007349148024447e-05, "loss": 0.3721, "step": 569 }, { "epoch": 2.3088607594936708, "grad_norm": 0.39405604929337984, "learning_rate": 2.5953187267988694e-05, "loss": 0.3412, "step": 570 }, { "epoch": 2.3129113924050633, "grad_norm": 0.3933086866821294, "learning_rate": 2.5898977441801097e-05, "loss": 0.3622, "step": 571 }, { "epoch": 2.316962025316456, "grad_norm": 0.3904919485335808, "learning_rate": 2.584472010606015e-05, "loss": 0.3485, "step": 572 }, { "epoch": 2.321012658227848, "grad_norm": 0.38545742694121843, "learning_rate": 2.5790415697746976e-05, "loss": 0.3562, "step": 573 }, { "epoch": 2.3250632911392404, "grad_norm": 0.5444223314121409, "learning_rate": 2.5736064654221808e-05, "loss": 0.3636, "step": 574 }, { "epoch": 2.329113924050633, "grad_norm": 0.4185911267094969, "learning_rate": 2.568166741322048e-05, "loss": 0.3556, "step": 575 }, { "epoch": 2.3331645569620254, "grad_norm": 0.3966853692269029, "learning_rate": 2.56272244128509e-05, "loss": 0.363, "step": 576 }, { "epoch": 2.337215189873418, "grad_norm": 0.36870743676242895, "learning_rate": 2.55727360915895e-05, "loss": 0.3468, "step": 577 }, { "epoch": 2.34126582278481, "grad_norm": 0.3972033646172607, "learning_rate": 2.5518202888277734e-05, "loss": 0.3535, "step": 578 }, { "epoch": 2.3453164556962025, "grad_norm": 0.381940655536523, "learning_rate": 2.5463625242118523e-05, "loss": 0.3612, "step": 579 }, { "epoch": 2.349367088607595, "grad_norm": 0.3888036505592139, "learning_rate": 2.5409003592672723e-05, "loss": 0.353, "step": 580 }, { "epoch": 2.353417721518987, "grad_norm": 0.4007645151243008, "learning_rate": 2.535433837985559e-05, "loss": 0.3756, "step": 581 }, { "epoch": 2.3574683544303796, "grad_norm": 0.3817963286283231, "learning_rate": 2.529963004393324e-05, "loss": 0.3567, "step": 582 }, { "epoch": 2.361518987341772, "grad_norm": 0.37296224152480134, "learning_rate": 2.524487902551908e-05, "loss": 0.3557, "step": 583 }, { "epoch": 2.3655696202531646, "grad_norm": 0.40566136752957427, "learning_rate": 2.519008576557029e-05, "loss": 0.3507, "step": 584 }, { "epoch": 2.369620253164557, "grad_norm": 0.436087413612293, "learning_rate": 2.5135250705384254e-05, "loss": 0.3738, "step": 585 }, { "epoch": 2.3736708860759492, "grad_norm": 0.3800204422540479, "learning_rate": 2.5080374286595007e-05, "loss": 0.3726, "step": 586 }, { "epoch": 2.3777215189873417, "grad_norm": 0.41272226957658975, "learning_rate": 2.5025456951169677e-05, "loss": 0.3478, "step": 587 }, { "epoch": 2.3817721518987343, "grad_norm": 0.4137460969571554, "learning_rate": 2.4970499141404942e-05, "loss": 0.3595, "step": 588 }, { "epoch": 2.3858227848101268, "grad_norm": 0.38695595387952364, "learning_rate": 2.491550129992345e-05, "loss": 0.3791, "step": 589 }, { "epoch": 2.389873417721519, "grad_norm": 0.6674508967975743, "learning_rate": 2.486046386967024e-05, "loss": 0.3959, "step": 590 }, { "epoch": 2.3939240506329114, "grad_norm": 0.37292560186516965, "learning_rate": 2.4805387293909214e-05, "loss": 0.3518, "step": 591 }, { "epoch": 2.397974683544304, "grad_norm": 0.380552760258254, "learning_rate": 2.4750272016219552e-05, "loss": 0.3741, "step": 592 }, { "epoch": 2.4020253164556964, "grad_norm": 0.3792003550948465, "learning_rate": 2.4695118480492114e-05, "loss": 0.3439, "step": 593 }, { "epoch": 2.4060759493670885, "grad_norm": 0.4368661028992637, "learning_rate": 2.4639927130925898e-05, "loss": 0.3447, "step": 594 }, { "epoch": 2.410126582278481, "grad_norm": 0.3892845311365053, "learning_rate": 2.458469841202444e-05, "loss": 0.3547, "step": 595 }, { "epoch": 2.4141772151898735, "grad_norm": 0.3453277573527043, "learning_rate": 2.452943276859226e-05, "loss": 0.3647, "step": 596 }, { "epoch": 2.418227848101266, "grad_norm": 0.4167975050251109, "learning_rate": 2.447413064573125e-05, "loss": 0.3433, "step": 597 }, { "epoch": 2.422278481012658, "grad_norm": 0.4358933574059834, "learning_rate": 2.4418792488837095e-05, "loss": 0.3755, "step": 598 }, { "epoch": 2.4263291139240506, "grad_norm": 0.3930205919228338, "learning_rate": 2.4363418743595713e-05, "loss": 0.3619, "step": 599 }, { "epoch": 2.430379746835443, "grad_norm": 0.40147197470217827, "learning_rate": 2.430800985597963e-05, "loss": 0.3512, "step": 600 }, { "epoch": 2.4344303797468356, "grad_norm": 0.36578681026226084, "learning_rate": 2.4252566272244415e-05, "loss": 0.353, "step": 601 }, { "epoch": 2.4384810126582277, "grad_norm": 0.38719894520654424, "learning_rate": 2.4197088438925063e-05, "loss": 0.3342, "step": 602 }, { "epoch": 2.44253164556962, "grad_norm": 0.40038342339750865, "learning_rate": 2.4141576802832417e-05, "loss": 0.3603, "step": 603 }, { "epoch": 2.4465822784810127, "grad_norm": 0.36756929410596545, "learning_rate": 2.408603181104957e-05, "loss": 0.3705, "step": 604 }, { "epoch": 2.4506329113924052, "grad_norm": 0.40005707635306353, "learning_rate": 2.4030453910928245e-05, "loss": 0.3624, "step": 605 }, { "epoch": 2.4546835443037973, "grad_norm": 0.39170720293479644, "learning_rate": 2.397484355008521e-05, "loss": 0.3578, "step": 606 }, { "epoch": 2.45873417721519, "grad_norm": 0.37578036737073284, "learning_rate": 2.3919201176398662e-05, "loss": 0.3521, "step": 607 }, { "epoch": 2.4627848101265823, "grad_norm": 0.41658101899371736, "learning_rate": 2.3863527238004633e-05, "loss": 0.3619, "step": 608 }, { "epoch": 2.466835443037975, "grad_norm": 0.3635401446180164, "learning_rate": 2.380782218329337e-05, "loss": 0.342, "step": 609 }, { "epoch": 2.470886075949367, "grad_norm": 0.40468764530889145, "learning_rate": 2.3752086460905725e-05, "loss": 0.3376, "step": 610 }, { "epoch": 2.4749367088607594, "grad_norm": 0.40871545286449346, "learning_rate": 2.3696320519729544e-05, "loss": 0.347, "step": 611 }, { "epoch": 2.478987341772152, "grad_norm": 0.3670933594512628, "learning_rate": 2.3640524808896045e-05, "loss": 0.3786, "step": 612 }, { "epoch": 2.4830379746835445, "grad_norm": 0.7695641237143664, "learning_rate": 2.3584699777776222e-05, "loss": 0.3457, "step": 613 }, { "epoch": 2.4870886075949366, "grad_norm": 0.35860672046115316, "learning_rate": 2.3528845875977195e-05, "loss": 0.3572, "step": 614 }, { "epoch": 2.491139240506329, "grad_norm": 0.38510672443784416, "learning_rate": 2.3472963553338614e-05, "loss": 0.3458, "step": 615 }, { "epoch": 2.4951898734177216, "grad_norm": 0.3445057126973361, "learning_rate": 2.341705325992901e-05, "loss": 0.3477, "step": 616 }, { "epoch": 2.499240506329114, "grad_norm": 0.3463322139226352, "learning_rate": 2.336111544604222e-05, "loss": 0.3541, "step": 617 }, { "epoch": 2.503291139240506, "grad_norm": 0.3699646697612228, "learning_rate": 2.33051505621937e-05, "loss": 0.3523, "step": 618 }, { "epoch": 2.5073417721518987, "grad_norm": 0.3792737962371367, "learning_rate": 2.324915905911693e-05, "loss": 0.3438, "step": 619 }, { "epoch": 2.511392405063291, "grad_norm": 0.3751260669983934, "learning_rate": 2.319314138775977e-05, "loss": 0.3657, "step": 620 }, { "epoch": 2.5154430379746833, "grad_norm": 0.3815364013179364, "learning_rate": 2.3137097999280856e-05, "loss": 0.3553, "step": 621 }, { "epoch": 2.519493670886076, "grad_norm": 0.4653621146595721, "learning_rate": 2.308102934504593e-05, "loss": 0.3407, "step": 622 }, { "epoch": 2.5235443037974683, "grad_norm": 0.3871142578233712, "learning_rate": 2.3024935876624222e-05, "loss": 0.36, "step": 623 }, { "epoch": 2.527594936708861, "grad_norm": 0.3892570325609824, "learning_rate": 2.2968818045784813e-05, "loss": 0.3721, "step": 624 }, { "epoch": 2.5316455696202533, "grad_norm": 0.3667646442779527, "learning_rate": 2.2912676304493006e-05, "loss": 0.368, "step": 625 }, { "epoch": 2.5356962025316454, "grad_norm": 0.37650887634527974, "learning_rate": 2.2856511104906668e-05, "loss": 0.3642, "step": 626 }, { "epoch": 2.539746835443038, "grad_norm": 0.3795336341607874, "learning_rate": 2.2800322899372586e-05, "loss": 0.3624, "step": 627 }, { "epoch": 2.5437974683544304, "grad_norm": 0.3897907347563641, "learning_rate": 2.2744112140422844e-05, "loss": 0.3665, "step": 628 }, { "epoch": 2.547848101265823, "grad_norm": 0.3558176845610719, "learning_rate": 2.2687879280771177e-05, "loss": 0.3672, "step": 629 }, { "epoch": 2.5518987341772155, "grad_norm": 0.3960962066664535, "learning_rate": 2.26316247733093e-05, "loss": 0.3597, "step": 630 }, { "epoch": 2.5559493670886075, "grad_norm": 0.3570113349250364, "learning_rate": 2.257534907110328e-05, "loss": 0.3478, "step": 631 }, { "epoch": 2.56, "grad_norm": 0.419429673445133, "learning_rate": 2.2519052627389882e-05, "loss": 0.3373, "step": 632 }, { "epoch": 2.5640506329113926, "grad_norm": 0.3839923083955588, "learning_rate": 2.246273589557294e-05, "loss": 0.3674, "step": 633 }, { "epoch": 2.5681012658227846, "grad_norm": 0.3914248145629139, "learning_rate": 2.240639932921966e-05, "loss": 0.3394, "step": 634 }, { "epoch": 2.572151898734177, "grad_norm": 0.39836814378071866, "learning_rate": 2.2350043382056995e-05, "loss": 0.356, "step": 635 }, { "epoch": 2.5762025316455697, "grad_norm": 0.38986888385730795, "learning_rate": 2.2293668507968015e-05, "loss": 0.3548, "step": 636 }, { "epoch": 2.580253164556962, "grad_norm": 0.3806996009342088, "learning_rate": 2.2237275160988186e-05, "loss": 0.3589, "step": 637 }, { "epoch": 2.5843037974683547, "grad_norm": 0.3902419025251199, "learning_rate": 2.2180863795301787e-05, "loss": 0.3426, "step": 638 }, { "epoch": 2.5883544303797468, "grad_norm": 0.3900803216756185, "learning_rate": 2.212443486523819e-05, "loss": 0.3517, "step": 639 }, { "epoch": 2.5924050632911393, "grad_norm": 0.37889233758338914, "learning_rate": 2.2067988825268243e-05, "loss": 0.3576, "step": 640 }, { "epoch": 2.596455696202532, "grad_norm": 0.40459204900357326, "learning_rate": 2.2011526130000596e-05, "loss": 0.354, "step": 641 }, { "epoch": 2.600506329113924, "grad_norm": 0.36392697000499946, "learning_rate": 2.1955047234178038e-05, "loss": 0.3522, "step": 642 }, { "epoch": 2.6045569620253164, "grad_norm": 0.39333708690701047, "learning_rate": 2.1898552592673825e-05, "loss": 0.3598, "step": 643 }, { "epoch": 2.608607594936709, "grad_norm": 0.3543426768748365, "learning_rate": 2.184204266048803e-05, "loss": 0.3566, "step": 644 }, { "epoch": 2.6126582278481014, "grad_norm": 0.381330240339846, "learning_rate": 2.1785517892743887e-05, "loss": 0.3597, "step": 645 }, { "epoch": 2.616708860759494, "grad_norm": 0.3699832003088976, "learning_rate": 2.17289787446841e-05, "loss": 0.3408, "step": 646 }, { "epoch": 2.620759493670886, "grad_norm": 0.3587795887622992, "learning_rate": 2.1672425671667198e-05, "loss": 0.3506, "step": 647 }, { "epoch": 2.6248101265822785, "grad_norm": 0.39771207416538973, "learning_rate": 2.161585912916385e-05, "loss": 0.3591, "step": 648 }, { "epoch": 2.628860759493671, "grad_norm": 0.3669778469018335, "learning_rate": 2.1559279572753214e-05, "loss": 0.3578, "step": 649 }, { "epoch": 2.632911392405063, "grad_norm": 0.37975771100947614, "learning_rate": 2.1502687458119268e-05, "loss": 0.367, "step": 650 }, { "epoch": 2.6369620253164556, "grad_norm": 0.3559370989572412, "learning_rate": 2.1446083241047116e-05, "loss": 0.358, "step": 651 }, { "epoch": 2.641012658227848, "grad_norm": 0.3816670689416468, "learning_rate": 2.1389467377419333e-05, "loss": 0.3525, "step": 652 }, { "epoch": 2.6450632911392407, "grad_norm": 0.3735981962006779, "learning_rate": 2.133284032321232e-05, "loss": 0.3549, "step": 653 }, { "epoch": 2.649113924050633, "grad_norm": 0.4070065482462672, "learning_rate": 2.1276202534492566e-05, "loss": 0.3389, "step": 654 }, { "epoch": 2.6531645569620252, "grad_norm": 0.37151327220365676, "learning_rate": 2.121955446741306e-05, "loss": 0.3688, "step": 655 }, { "epoch": 2.6572151898734178, "grad_norm": 0.3775479686197029, "learning_rate": 2.1162896578209517e-05, "loss": 0.3581, "step": 656 }, { "epoch": 2.6612658227848103, "grad_norm": 0.3679440076086958, "learning_rate": 2.1106229323196813e-05, "loss": 0.3731, "step": 657 }, { "epoch": 2.6653164556962023, "grad_norm": 0.3563263013251416, "learning_rate": 2.1049553158765214e-05, "loss": 0.3411, "step": 658 }, { "epoch": 2.669367088607595, "grad_norm": 0.3699600037341244, "learning_rate": 2.0992868541376764e-05, "loss": 0.363, "step": 659 }, { "epoch": 2.6734177215189874, "grad_norm": 0.37503417126331295, "learning_rate": 2.093617592756158e-05, "loss": 0.3401, "step": 660 }, { "epoch": 2.67746835443038, "grad_norm": 0.381844499885597, "learning_rate": 2.0879475773914167e-05, "loss": 0.3353, "step": 661 }, { "epoch": 2.6815189873417724, "grad_norm": 0.39700291555788253, "learning_rate": 2.082276853708978e-05, "loss": 0.3374, "step": 662 }, { "epoch": 2.6855696202531645, "grad_norm": 0.38449412957274953, "learning_rate": 2.076605467380071e-05, "loss": 0.3275, "step": 663 }, { "epoch": 2.689620253164557, "grad_norm": 2.7478952497617697, "learning_rate": 2.0709334640812613e-05, "loss": 0.3718, "step": 664 }, { "epoch": 2.6936708860759495, "grad_norm": 0.505160861356048, "learning_rate": 2.0652608894940824e-05, "loss": 0.3585, "step": 665 }, { "epoch": 2.6977215189873416, "grad_norm": 0.3617816081842201, "learning_rate": 2.0595877893046722e-05, "loss": 0.3695, "step": 666 }, { "epoch": 2.701772151898734, "grad_norm": 0.3904846187343071, "learning_rate": 2.0539142092033985e-05, "loss": 0.3602, "step": 667 }, { "epoch": 2.7058227848101266, "grad_norm": 0.42847583468698497, "learning_rate": 2.048240194884496e-05, "loss": 0.3353, "step": 668 }, { "epoch": 2.709873417721519, "grad_norm": 0.3865848150466836, "learning_rate": 2.042565792045695e-05, "loss": 0.3526, "step": 669 }, { "epoch": 2.7139240506329116, "grad_norm": 0.38238067590616914, "learning_rate": 2.036891046387857e-05, "loss": 0.3614, "step": 670 }, { "epoch": 2.7179746835443037, "grad_norm": 0.46982499516730686, "learning_rate": 2.0312160036146036e-05, "loss": 0.3698, "step": 671 }, { "epoch": 2.7220253164556962, "grad_norm": 0.3679814961150859, "learning_rate": 2.025540709431948e-05, "loss": 0.3735, "step": 672 }, { "epoch": 2.7260759493670887, "grad_norm": 0.38070602165431977, "learning_rate": 2.0198652095479298e-05, "loss": 0.3546, "step": 673 }, { "epoch": 2.730126582278481, "grad_norm": 0.3868465236842662, "learning_rate": 2.014189549672245e-05, "loss": 0.3546, "step": 674 }, { "epoch": 2.7341772151898733, "grad_norm": 0.38381159726488445, "learning_rate": 2.0085137755158776e-05, "loss": 0.3572, "step": 675 }, { "epoch": 2.738227848101266, "grad_norm": 0.3854877489991777, "learning_rate": 2.0028379327907327e-05, "loss": 0.3605, "step": 676 }, { "epoch": 2.7422784810126584, "grad_norm": 0.3899940617641495, "learning_rate": 1.9971620672092676e-05, "loss": 0.3527, "step": 677 }, { "epoch": 2.746329113924051, "grad_norm": 0.6497335194950734, "learning_rate": 1.991486224484123e-05, "loss": 0.3695, "step": 678 }, { "epoch": 2.750379746835443, "grad_norm": 0.4944613233737503, "learning_rate": 1.985810450327756e-05, "loss": 0.3689, "step": 679 }, { "epoch": 2.7544303797468355, "grad_norm": 0.4040380276165527, "learning_rate": 1.9801347904520706e-05, "loss": 0.3441, "step": 680 }, { "epoch": 2.758481012658228, "grad_norm": 0.3959493434901651, "learning_rate": 1.974459290568053e-05, "loss": 0.364, "step": 681 }, { "epoch": 2.76253164556962, "grad_norm": 0.46260549659291295, "learning_rate": 1.968783996385397e-05, "loss": 0.3493, "step": 682 }, { "epoch": 2.7665822784810126, "grad_norm": 0.377599027828365, "learning_rate": 1.963108953612143e-05, "loss": 0.3569, "step": 683 }, { "epoch": 2.770632911392405, "grad_norm": 0.36337581820142173, "learning_rate": 1.9574342079543056e-05, "loss": 0.3297, "step": 684 }, { "epoch": 2.7746835443037976, "grad_norm": 0.38366361769127605, "learning_rate": 1.9517598051155046e-05, "loss": 0.3713, "step": 685 }, { "epoch": 2.77873417721519, "grad_norm": 0.3988278600661032, "learning_rate": 1.9460857907966025e-05, "loss": 0.3545, "step": 686 }, { "epoch": 2.782784810126582, "grad_norm": 0.42608599291995475, "learning_rate": 1.9404122106953285e-05, "loss": 0.367, "step": 687 }, { "epoch": 2.7868354430379747, "grad_norm": 0.43073648577474793, "learning_rate": 1.9347391105059176e-05, "loss": 0.3593, "step": 688 }, { "epoch": 2.790886075949367, "grad_norm": 0.41510880450714, "learning_rate": 1.92906653591874e-05, "loss": 0.3547, "step": 689 }, { "epoch": 2.7949367088607593, "grad_norm": 0.37190054450432364, "learning_rate": 1.9233945326199295e-05, "loss": 0.3654, "step": 690 }, { "epoch": 2.798987341772152, "grad_norm": 0.38757944734566585, "learning_rate": 1.917723146291022e-05, "loss": 0.362, "step": 691 }, { "epoch": 2.8030379746835443, "grad_norm": 0.4228217502198484, "learning_rate": 1.912052422608584e-05, "loss": 0.3748, "step": 692 }, { "epoch": 2.807088607594937, "grad_norm": 0.37905255761245393, "learning_rate": 1.9063824072438428e-05, "loss": 0.3433, "step": 693 }, { "epoch": 2.8111392405063294, "grad_norm": 0.38666476510686726, "learning_rate": 1.9007131458623246e-05, "loss": 0.3256, "step": 694 }, { "epoch": 2.8151898734177214, "grad_norm": 0.3464456600617518, "learning_rate": 1.895044684123479e-05, "loss": 0.3532, "step": 695 }, { "epoch": 2.819240506329114, "grad_norm": 0.3784754425065164, "learning_rate": 1.8893770676803194e-05, "loss": 0.3649, "step": 696 }, { "epoch": 2.8232911392405065, "grad_norm": 0.3724366402759857, "learning_rate": 1.8837103421790486e-05, "loss": 0.3408, "step": 697 }, { "epoch": 2.8273417721518985, "grad_norm": 0.37017740582994274, "learning_rate": 1.8780445532586952e-05, "loss": 0.3543, "step": 698 }, { "epoch": 2.831392405063291, "grad_norm": 0.3567075798863208, "learning_rate": 1.872379746550743e-05, "loss": 0.3551, "step": 699 }, { "epoch": 2.8354430379746836, "grad_norm": 0.40136693332767215, "learning_rate": 1.866715967678769e-05, "loss": 0.3565, "step": 700 }, { "epoch": 2.839493670886076, "grad_norm": 0.3685238002977323, "learning_rate": 1.861053262258067e-05, "loss": 0.3556, "step": 701 }, { "epoch": 2.8435443037974686, "grad_norm": 0.3607059398975028, "learning_rate": 1.8553916758952897e-05, "loss": 0.363, "step": 702 }, { "epoch": 2.8475949367088607, "grad_norm": 0.37325519321021144, "learning_rate": 1.8497312541880735e-05, "loss": 0.3526, "step": 703 }, { "epoch": 2.851645569620253, "grad_norm": 0.36900852822213986, "learning_rate": 1.8440720427246786e-05, "loss": 0.3632, "step": 704 }, { "epoch": 2.8556962025316457, "grad_norm": 0.39501960150131354, "learning_rate": 1.8384140870836157e-05, "loss": 0.3529, "step": 705 }, { "epoch": 2.8597468354430378, "grad_norm": 0.35853382771777614, "learning_rate": 1.8327574328332806e-05, "loss": 0.3573, "step": 706 }, { "epoch": 2.8637974683544303, "grad_norm": 0.35021867756239905, "learning_rate": 1.8271021255315906e-05, "loss": 0.3628, "step": 707 }, { "epoch": 2.867848101265823, "grad_norm": 0.40937514997036106, "learning_rate": 1.8214482107256117e-05, "loss": 0.3378, "step": 708 }, { "epoch": 2.8718987341772153, "grad_norm": 0.3862490718319656, "learning_rate": 1.8157957339511968e-05, "loss": 0.3519, "step": 709 }, { "epoch": 2.875949367088608, "grad_norm": 0.3614109905806213, "learning_rate": 1.8101447407326182e-05, "loss": 0.3449, "step": 710 }, { "epoch": 2.88, "grad_norm": 0.39904077686984224, "learning_rate": 1.8044952765821966e-05, "loss": 0.3519, "step": 711 }, { "epoch": 2.8840506329113924, "grad_norm": 0.3998283432192742, "learning_rate": 1.7988473869999407e-05, "loss": 0.3237, "step": 712 }, { "epoch": 2.888101265822785, "grad_norm": 0.3712244300153937, "learning_rate": 1.7932011174731764e-05, "loss": 0.3543, "step": 713 }, { "epoch": 2.892151898734177, "grad_norm": 0.3883179575062461, "learning_rate": 1.7875565134761817e-05, "loss": 0.3694, "step": 714 }, { "epoch": 2.8962025316455695, "grad_norm": 0.3985124443612759, "learning_rate": 1.7819136204698226e-05, "loss": 0.3625, "step": 715 }, { "epoch": 2.900253164556962, "grad_norm": 0.349315588254954, "learning_rate": 1.776272483901182e-05, "loss": 0.3398, "step": 716 }, { "epoch": 2.9043037974683545, "grad_norm": 0.3647962900099536, "learning_rate": 1.7706331492031995e-05, "loss": 0.3501, "step": 717 }, { "epoch": 2.908354430379747, "grad_norm": 0.425888447617012, "learning_rate": 1.764995661794301e-05, "loss": 0.3474, "step": 718 }, { "epoch": 2.912405063291139, "grad_norm": 0.349133810157936, "learning_rate": 1.759360067078035e-05, "loss": 0.3666, "step": 719 }, { "epoch": 2.9164556962025316, "grad_norm": 0.33614661487859854, "learning_rate": 1.7537264104427064e-05, "loss": 0.3376, "step": 720 }, { "epoch": 2.920506329113924, "grad_norm": 0.401855035700003, "learning_rate": 1.748094737261012e-05, "loss": 0.3503, "step": 721 }, { "epoch": 2.9245569620253162, "grad_norm": 0.3934371523972986, "learning_rate": 1.7424650928896726e-05, "loss": 0.3623, "step": 722 }, { "epoch": 2.9286075949367087, "grad_norm": 0.3735419859826372, "learning_rate": 1.7368375226690712e-05, "loss": 0.3426, "step": 723 }, { "epoch": 2.9326582278481013, "grad_norm": 0.3496172250688338, "learning_rate": 1.731212071922883e-05, "loss": 0.338, "step": 724 }, { "epoch": 2.9367088607594938, "grad_norm": 0.4009848902336462, "learning_rate": 1.7255887859577156e-05, "loss": 0.351, "step": 725 }, { "epoch": 2.9407594936708863, "grad_norm": 0.40688095563081594, "learning_rate": 1.7199677100627427e-05, "loss": 0.3568, "step": 726 }, { "epoch": 2.9448101265822784, "grad_norm": 0.34053802745084344, "learning_rate": 1.7143488895093343e-05, "loss": 0.3627, "step": 727 }, { "epoch": 2.948860759493671, "grad_norm": 0.4066704059476737, "learning_rate": 1.7087323695506994e-05, "loss": 0.3479, "step": 728 }, { "epoch": 2.9529113924050634, "grad_norm": 0.37979445474748885, "learning_rate": 1.7031181954215194e-05, "loss": 0.3586, "step": 729 }, { "epoch": 2.9569620253164555, "grad_norm": 0.3465528729873324, "learning_rate": 1.6975064123375788e-05, "loss": 0.3607, "step": 730 }, { "epoch": 2.961012658227848, "grad_norm": 0.3561036580951355, "learning_rate": 1.6918970654954084e-05, "loss": 0.3656, "step": 731 }, { "epoch": 2.9650632911392405, "grad_norm": 0.3460469544706407, "learning_rate": 1.686290200071915e-05, "loss": 0.3479, "step": 732 }, { "epoch": 2.969113924050633, "grad_norm": 0.33220390511888354, "learning_rate": 1.6806858612240234e-05, "loss": 0.3364, "step": 733 }, { "epoch": 2.9731645569620255, "grad_norm": 0.3716032712981138, "learning_rate": 1.6750840940883078e-05, "loss": 0.3274, "step": 734 }, { "epoch": 2.9772151898734176, "grad_norm": 0.3577431920832846, "learning_rate": 1.6694849437806305e-05, "loss": 0.3507, "step": 735 }, { "epoch": 2.98126582278481, "grad_norm": 0.33078762733155553, "learning_rate": 1.663888455395778e-05, "loss": 0.3448, "step": 736 }, { "epoch": 2.9853164556962026, "grad_norm": 0.32407345636647766, "learning_rate": 1.6582946740070995e-05, "loss": 0.345, "step": 737 }, { "epoch": 2.9893670886075947, "grad_norm": 0.35374507247157444, "learning_rate": 1.6527036446661396e-05, "loss": 0.3537, "step": 738 }, { "epoch": 2.993417721518987, "grad_norm": 0.3675173275090233, "learning_rate": 1.6471154124022818e-05, "loss": 0.3262, "step": 739 }, { "epoch": 2.9974683544303797, "grad_norm": 0.34808301654391727, "learning_rate": 1.6415300222223788e-05, "loss": 0.3507, "step": 740 }, { "epoch": 3.0015189873417722, "grad_norm": 0.4057511525268783, "learning_rate": 1.6359475191103958e-05, "loss": 0.3072, "step": 741 }, { "epoch": 3.0055696202531648, "grad_norm": 0.4722248811068361, "learning_rate": 1.6303679480270466e-05, "loss": 0.2539, "step": 742 }, { "epoch": 3.009620253164557, "grad_norm": 0.339418122617376, "learning_rate": 1.624791353909428e-05, "loss": 0.2727, "step": 743 }, { "epoch": 3.0136708860759494, "grad_norm": 0.5506278112978007, "learning_rate": 1.619217781670663e-05, "loss": 0.2616, "step": 744 }, { "epoch": 3.017721518987342, "grad_norm": 0.5764557722567786, "learning_rate": 1.6136472761995373e-05, "loss": 0.2444, "step": 745 }, { "epoch": 3.0217721518987344, "grad_norm": 0.4233392944522442, "learning_rate": 1.608079882360134e-05, "loss": 0.2605, "step": 746 }, { "epoch": 3.0258227848101265, "grad_norm": 0.45936510675395975, "learning_rate": 1.60251564499148e-05, "loss": 0.2704, "step": 747 }, { "epoch": 3.029873417721519, "grad_norm": 0.4482723328193524, "learning_rate": 1.596954608907176e-05, "loss": 0.2533, "step": 748 }, { "epoch": 3.0339240506329115, "grad_norm": 0.3807571316268612, "learning_rate": 1.591396818895043e-05, "loss": 0.256, "step": 749 }, { "epoch": 3.037974683544304, "grad_norm": 0.41726786268222504, "learning_rate": 1.585842319716759e-05, "loss": 0.2548, "step": 750 }, { "epoch": 3.042025316455696, "grad_norm": 0.4375346267505827, "learning_rate": 1.5802911561074944e-05, "loss": 0.2272, "step": 751 }, { "epoch": 3.0460759493670886, "grad_norm": 0.3771077696623335, "learning_rate": 1.5747433727755595e-05, "loss": 0.2644, "step": 752 }, { "epoch": 3.050126582278481, "grad_norm": 0.3725862145537581, "learning_rate": 1.5691990144020376e-05, "loss": 0.2444, "step": 753 }, { "epoch": 3.0541772151898736, "grad_norm": 0.40211100902437635, "learning_rate": 1.5636581256404297e-05, "loss": 0.2668, "step": 754 }, { "epoch": 3.0582278481012657, "grad_norm": 0.37507636270440514, "learning_rate": 1.558120751116291e-05, "loss": 0.2211, "step": 755 }, { "epoch": 3.062278481012658, "grad_norm": 0.3848810673883114, "learning_rate": 1.552586935426876e-05, "loss": 0.2401, "step": 756 }, { "epoch": 3.0663291139240507, "grad_norm": 0.36661581484201955, "learning_rate": 1.547056723140774e-05, "loss": 0.2277, "step": 757 }, { "epoch": 3.0703797468354432, "grad_norm": 0.3614310556730798, "learning_rate": 1.5415301587975565e-05, "loss": 0.2481, "step": 758 }, { "epoch": 3.0744303797468353, "grad_norm": 0.33825365479107405, "learning_rate": 1.536007286907411e-05, "loss": 0.2354, "step": 759 }, { "epoch": 3.078481012658228, "grad_norm": 0.340253659910146, "learning_rate": 1.5304881519507896e-05, "loss": 0.2486, "step": 760 }, { "epoch": 3.0825316455696203, "grad_norm": 0.3441939461869194, "learning_rate": 1.5249727983780453e-05, "loss": 0.2469, "step": 761 }, { "epoch": 3.086582278481013, "grad_norm": 0.30936692388568443, "learning_rate": 1.5194612706090786e-05, "loss": 0.2367, "step": 762 }, { "epoch": 3.090632911392405, "grad_norm": 0.354440183849083, "learning_rate": 1.5139536130329771e-05, "loss": 0.2461, "step": 763 }, { "epoch": 3.0946835443037974, "grad_norm": 0.33575947227204267, "learning_rate": 1.508449870007656e-05, "loss": 0.2442, "step": 764 }, { "epoch": 3.09873417721519, "grad_norm": 0.31638209247163707, "learning_rate": 1.5029500858595056e-05, "loss": 0.231, "step": 765 }, { "epoch": 3.1027848101265825, "grad_norm": 0.3345410034468005, "learning_rate": 1.4974543048830328e-05, "loss": 0.249, "step": 766 }, { "epoch": 3.1068354430379745, "grad_norm": 0.31125405064210215, "learning_rate": 1.4919625713405e-05, "loss": 0.2448, "step": 767 }, { "epoch": 3.110886075949367, "grad_norm": 0.33019761218231636, "learning_rate": 1.4864749294615756e-05, "loss": 0.2713, "step": 768 }, { "epoch": 3.1149367088607596, "grad_norm": 0.32250199632171817, "learning_rate": 1.4809914234429716e-05, "loss": 0.2409, "step": 769 }, { "epoch": 3.118987341772152, "grad_norm": 0.3494172549541519, "learning_rate": 1.4755120974480923e-05, "loss": 0.237, "step": 770 }, { "epoch": 3.123037974683544, "grad_norm": 0.3196618886961228, "learning_rate": 1.4700369956066771e-05, "loss": 0.25, "step": 771 }, { "epoch": 3.1270886075949367, "grad_norm": 0.3372159855666134, "learning_rate": 1.4645661620144413e-05, "loss": 0.2463, "step": 772 }, { "epoch": 3.131139240506329, "grad_norm": 0.3194109036027576, "learning_rate": 1.4590996407327284e-05, "loss": 0.253, "step": 773 }, { "epoch": 3.1351898734177217, "grad_norm": 0.319580387497776, "learning_rate": 1.4536374757881487e-05, "loss": 0.2422, "step": 774 }, { "epoch": 3.1392405063291138, "grad_norm": 0.32411490997405973, "learning_rate": 1.4481797111722271e-05, "loss": 0.2343, "step": 775 }, { "epoch": 3.1432911392405063, "grad_norm": 0.3264670802924616, "learning_rate": 1.4427263908410507e-05, "loss": 0.2279, "step": 776 }, { "epoch": 3.147341772151899, "grad_norm": 0.3454585470742877, "learning_rate": 1.4372775587149108e-05, "loss": 0.2493, "step": 777 }, { "epoch": 3.1513924050632913, "grad_norm": 0.3109896100216924, "learning_rate": 1.4318332586779522e-05, "loss": 0.2638, "step": 778 }, { "epoch": 3.1554430379746834, "grad_norm": 0.33302974982016603, "learning_rate": 1.4263935345778202e-05, "loss": 0.2472, "step": 779 }, { "epoch": 3.159493670886076, "grad_norm": 0.3250738666524847, "learning_rate": 1.420958430225303e-05, "loss": 0.2467, "step": 780 }, { "epoch": 3.1635443037974684, "grad_norm": 0.30576939319413965, "learning_rate": 1.415527989393985e-05, "loss": 0.2698, "step": 781 }, { "epoch": 3.167594936708861, "grad_norm": 0.3217653995702274, "learning_rate": 1.410102255819891e-05, "loss": 0.2488, "step": 782 }, { "epoch": 3.171645569620253, "grad_norm": 0.3235333707743536, "learning_rate": 1.404681273201131e-05, "loss": 0.2682, "step": 783 }, { "epoch": 3.1756962025316455, "grad_norm": 0.33295180709111166, "learning_rate": 1.399265085197556e-05, "loss": 0.2414, "step": 784 }, { "epoch": 3.179746835443038, "grad_norm": 0.3184324983610456, "learning_rate": 1.393853735430398e-05, "loss": 0.2468, "step": 785 }, { "epoch": 3.1837974683544306, "grad_norm": 0.31786739311390344, "learning_rate": 1.3884472674819246e-05, "loss": 0.2465, "step": 786 }, { "epoch": 3.1878481012658226, "grad_norm": 0.3120999464572437, "learning_rate": 1.3830457248950864e-05, "loss": 0.2503, "step": 787 }, { "epoch": 3.191898734177215, "grad_norm": 0.32112823499396576, "learning_rate": 1.377649151173163e-05, "loss": 0.2472, "step": 788 }, { "epoch": 3.1959493670886077, "grad_norm": 0.3203434572985807, "learning_rate": 1.3722575897794181e-05, "loss": 0.2305, "step": 789 }, { "epoch": 3.2, "grad_norm": 0.3256790940887963, "learning_rate": 1.3668710841367472e-05, "loss": 0.2473, "step": 790 }, { "epoch": 3.2040506329113922, "grad_norm": 0.3077339074227137, "learning_rate": 1.361489677627324e-05, "loss": 0.2566, "step": 791 }, { "epoch": 3.2081012658227848, "grad_norm": 0.3185784711374213, "learning_rate": 1.3561134135922585e-05, "loss": 0.2368, "step": 792 }, { "epoch": 3.2121518987341773, "grad_norm": 0.3274770207427437, "learning_rate": 1.350742335331241e-05, "loss": 0.2456, "step": 793 }, { "epoch": 3.21620253164557, "grad_norm": 0.30430672582871343, "learning_rate": 1.345376486102198e-05, "loss": 0.235, "step": 794 }, { "epoch": 3.220253164556962, "grad_norm": 0.3339460402223005, "learning_rate": 1.3400159091209414e-05, "loss": 0.2626, "step": 795 }, { "epoch": 3.2243037974683544, "grad_norm": 0.7376039550017484, "learning_rate": 1.3346606475608216e-05, "loss": 0.2816, "step": 796 }, { "epoch": 3.228354430379747, "grad_norm": 0.32049615283878385, "learning_rate": 1.3293107445523781e-05, "loss": 0.221, "step": 797 }, { "epoch": 3.2324050632911394, "grad_norm": 0.3935109425606821, "learning_rate": 1.3239662431829949e-05, "loss": 0.2441, "step": 798 }, { "epoch": 3.2364556962025315, "grad_norm": 0.31107080231452694, "learning_rate": 1.3186271864965509e-05, "loss": 0.2424, "step": 799 }, { "epoch": 3.240506329113924, "grad_norm": 0.31602565958064427, "learning_rate": 1.3132936174930756e-05, "loss": 0.2487, "step": 800 }, { "epoch": 3.2445569620253165, "grad_norm": 0.33408361569919237, "learning_rate": 1.3079655791283995e-05, "loss": 0.2454, "step": 801 }, { "epoch": 3.248607594936709, "grad_norm": 0.3312206096452522, "learning_rate": 1.3026431143138108e-05, "loss": 0.2517, "step": 802 }, { "epoch": 3.252658227848101, "grad_norm": 0.31687868738916375, "learning_rate": 1.2973262659157114e-05, "loss": 0.2465, "step": 803 }, { "epoch": 3.2567088607594936, "grad_norm": 0.32367888526527483, "learning_rate": 1.2920150767552651e-05, "loss": 0.2432, "step": 804 }, { "epoch": 3.260759493670886, "grad_norm": 0.3464112934064315, "learning_rate": 1.2867095896080607e-05, "loss": 0.2378, "step": 805 }, { "epoch": 3.2648101265822786, "grad_norm": 0.3174508228441782, "learning_rate": 1.2814098472037612e-05, "loss": 0.2584, "step": 806 }, { "epoch": 3.2688607594936707, "grad_norm": 0.3245756026417169, "learning_rate": 1.276115892225764e-05, "loss": 0.2653, "step": 807 }, { "epoch": 3.2729113924050632, "grad_norm": 0.3196987836480971, "learning_rate": 1.2708277673108555e-05, "loss": 0.2416, "step": 808 }, { "epoch": 3.2769620253164558, "grad_norm": 0.3157849690703753, "learning_rate": 1.2655455150488649e-05, "loss": 0.2452, "step": 809 }, { "epoch": 3.2810126582278483, "grad_norm": 0.34069463974787356, "learning_rate": 1.2602691779823272e-05, "loss": 0.2602, "step": 810 }, { "epoch": 3.2850632911392403, "grad_norm": 0.3408025699035478, "learning_rate": 1.2549987986061355e-05, "loss": 0.23, "step": 811 }, { "epoch": 3.289113924050633, "grad_norm": 0.3262297818182896, "learning_rate": 1.2497344193672005e-05, "loss": 0.2261, "step": 812 }, { "epoch": 3.2931645569620254, "grad_norm": 0.3369717613824077, "learning_rate": 1.2444760826641092e-05, "loss": 0.2327, "step": 813 }, { "epoch": 3.297215189873418, "grad_norm": 0.32880026123571976, "learning_rate": 1.2392238308467817e-05, "loss": 0.238, "step": 814 }, { "epoch": 3.30126582278481, "grad_norm": 0.3270437893930841, "learning_rate": 1.2339777062161326e-05, "loss": 0.2673, "step": 815 }, { "epoch": 3.3053164556962025, "grad_norm": 0.32481747214266216, "learning_rate": 1.2287377510237293e-05, "loss": 0.2577, "step": 816 }, { "epoch": 3.309367088607595, "grad_norm": 0.33392482042329197, "learning_rate": 1.2235040074714488e-05, "loss": 0.2546, "step": 817 }, { "epoch": 3.3134177215189875, "grad_norm": 0.3159783782171445, "learning_rate": 1.2182765177111434e-05, "loss": 0.2458, "step": 818 }, { "epoch": 3.3174683544303796, "grad_norm": 0.33022929739689677, "learning_rate": 1.213055323844297e-05, "loss": 0.244, "step": 819 }, { "epoch": 3.321518987341772, "grad_norm": 0.3245770130848048, "learning_rate": 1.2078404679216864e-05, "loss": 0.2562, "step": 820 }, { "epoch": 3.3255696202531646, "grad_norm": 0.3192846513564221, "learning_rate": 1.2026319919430458e-05, "loss": 0.2506, "step": 821 }, { "epoch": 3.329620253164557, "grad_norm": 0.3277396790752462, "learning_rate": 1.1974299378567227e-05, "loss": 0.2402, "step": 822 }, { "epoch": 3.333670886075949, "grad_norm": 0.31213298535552425, "learning_rate": 1.1922343475593462e-05, "loss": 0.2574, "step": 823 }, { "epoch": 3.3377215189873417, "grad_norm": 0.31638674111945203, "learning_rate": 1.187045262895488e-05, "loss": 0.2296, "step": 824 }, { "epoch": 3.3417721518987342, "grad_norm": 0.31896334505570884, "learning_rate": 1.1818627256573203e-05, "loss": 0.2463, "step": 825 }, { "epoch": 3.3458227848101267, "grad_norm": 0.3200475690083679, "learning_rate": 1.1766867775842864e-05, "loss": 0.2335, "step": 826 }, { "epoch": 3.349873417721519, "grad_norm": 0.331987167421697, "learning_rate": 1.1715174603627615e-05, "loss": 0.2364, "step": 827 }, { "epoch": 3.3539240506329113, "grad_norm": 0.32101530806877526, "learning_rate": 1.1663548156257147e-05, "loss": 0.2468, "step": 828 }, { "epoch": 3.357974683544304, "grad_norm": 0.3346879068422618, "learning_rate": 1.161198884952377e-05, "loss": 0.2419, "step": 829 }, { "epoch": 3.3620253164556964, "grad_norm": 0.33351936628368123, "learning_rate": 1.1560497098679056e-05, "loss": 0.2258, "step": 830 }, { "epoch": 3.3660759493670884, "grad_norm": 0.3558053356645586, "learning_rate": 1.1509073318430479e-05, "loss": 0.2639, "step": 831 }, { "epoch": 3.370126582278481, "grad_norm": 0.3235016976049688, "learning_rate": 1.1457717922938116e-05, "loss": 0.2334, "step": 832 }, { "epoch": 3.3741772151898735, "grad_norm": 0.3229016051960621, "learning_rate": 1.1406431325811233e-05, "loss": 0.2481, "step": 833 }, { "epoch": 3.378227848101266, "grad_norm": 0.32802508629856686, "learning_rate": 1.135521394010506e-05, "loss": 0.2568, "step": 834 }, { "epoch": 3.382278481012658, "grad_norm": 0.31771026074741926, "learning_rate": 1.1304066178317367e-05, "loss": 0.2512, "step": 835 }, { "epoch": 3.3863291139240506, "grad_norm": 0.32523990398409086, "learning_rate": 1.1252988452385199e-05, "loss": 0.2317, "step": 836 }, { "epoch": 3.390379746835443, "grad_norm": 0.3436271665259347, "learning_rate": 1.1201981173681536e-05, "loss": 0.2517, "step": 837 }, { "epoch": 3.3944303797468356, "grad_norm": 0.32058856790122126, "learning_rate": 1.1151044753011991e-05, "loss": 0.2212, "step": 838 }, { "epoch": 3.3984810126582277, "grad_norm": 0.31357499150097246, "learning_rate": 1.1100179600611491e-05, "loss": 0.2411, "step": 839 }, { "epoch": 3.40253164556962, "grad_norm": 0.31014317063082514, "learning_rate": 1.1049386126140985e-05, "loss": 0.2483, "step": 840 }, { "epoch": 3.4065822784810127, "grad_norm": 0.32110366622820224, "learning_rate": 1.0998664738684128e-05, "loss": 0.2481, "step": 841 }, { "epoch": 3.410632911392405, "grad_norm": 0.31599630005548357, "learning_rate": 1.0948015846744e-05, "loss": 0.2438, "step": 842 }, { "epoch": 3.4146835443037973, "grad_norm": 0.31181542568542026, "learning_rate": 1.0897439858239832e-05, "loss": 0.2598, "step": 843 }, { "epoch": 3.41873417721519, "grad_norm": 0.31070045526059886, "learning_rate": 1.0846937180503652e-05, "loss": 0.2477, "step": 844 }, { "epoch": 3.4227848101265823, "grad_norm": 0.32015750211962174, "learning_rate": 1.0796508220277117e-05, "loss": 0.2411, "step": 845 }, { "epoch": 3.426835443037975, "grad_norm": 0.306870064091358, "learning_rate": 1.0746153383708107e-05, "loss": 0.265, "step": 846 }, { "epoch": 3.430886075949367, "grad_norm": 0.32098564533686136, "learning_rate": 1.0695873076347579e-05, "loss": 0.274, "step": 847 }, { "epoch": 3.4349367088607594, "grad_norm": 0.4059409785001321, "learning_rate": 1.0645667703146205e-05, "loss": 0.2431, "step": 848 }, { "epoch": 3.438987341772152, "grad_norm": 0.31458579157513733, "learning_rate": 1.0595537668451161e-05, "loss": 0.2496, "step": 849 }, { "epoch": 3.4430379746835444, "grad_norm": 0.32383314398148194, "learning_rate": 1.0545483376002854e-05, "loss": 0.2274, "step": 850 }, { "epoch": 3.4470886075949365, "grad_norm": 0.3171855860716723, "learning_rate": 1.0495505228931676e-05, "loss": 0.2541, "step": 851 }, { "epoch": 3.451139240506329, "grad_norm": 0.32935312977711667, "learning_rate": 1.044560362975474e-05, "loss": 0.2369, "step": 852 }, { "epoch": 3.4551898734177215, "grad_norm": 0.2992436564033801, "learning_rate": 1.0395778980372695e-05, "loss": 0.2522, "step": 853 }, { "epoch": 3.459240506329114, "grad_norm": 0.2970939133449401, "learning_rate": 1.0346031682066381e-05, "loss": 0.2589, "step": 854 }, { "epoch": 3.463291139240506, "grad_norm": 0.3199289815370357, "learning_rate": 1.0296362135493724e-05, "loss": 0.239, "step": 855 }, { "epoch": 3.4673417721518986, "grad_norm": 0.3112264758660539, "learning_rate": 1.0246770740686422e-05, "loss": 0.2433, "step": 856 }, { "epoch": 3.471392405063291, "grad_norm": 0.3288076369240393, "learning_rate": 1.0197257897046743e-05, "loss": 0.2412, "step": 857 }, { "epoch": 3.4754430379746837, "grad_norm": 0.3330519036995509, "learning_rate": 1.014782400334433e-05, "loss": 0.2272, "step": 858 }, { "epoch": 3.479493670886076, "grad_norm": 0.31839904521555984, "learning_rate": 1.009846945771296e-05, "loss": 0.2396, "step": 859 }, { "epoch": 3.4835443037974683, "grad_norm": 0.33714203308412477, "learning_rate": 1.0049194657647363e-05, "loss": 0.2506, "step": 860 }, { "epoch": 3.487594936708861, "grad_norm": 0.29823554132584806, "learning_rate": 1.0000000000000006e-05, "loss": 0.2539, "step": 861 }, { "epoch": 3.4916455696202533, "grad_norm": 0.30635824589017635, "learning_rate": 9.950885880977891e-06, "loss": 0.2428, "step": 862 }, { "epoch": 3.4956962025316454, "grad_norm": 0.3064293784218176, "learning_rate": 9.901852696139382e-06, "loss": 0.2552, "step": 863 }, { "epoch": 3.499746835443038, "grad_norm": 0.3334038420093838, "learning_rate": 9.852900840391027e-06, "loss": 0.2303, "step": 864 }, { "epoch": 3.5037974683544304, "grad_norm": 0.32218676736189217, "learning_rate": 9.804030707984313e-06, "loss": 0.2268, "step": 865 }, { "epoch": 3.507848101265823, "grad_norm": 0.3095327354852826, "learning_rate": 9.755242692512599e-06, "loss": 0.2384, "step": 866 }, { "epoch": 3.5118987341772154, "grad_norm": 0.3249804129452969, "learning_rate": 9.70653718690782e-06, "loss": 0.2226, "step": 867 }, { "epoch": 3.5159493670886075, "grad_norm": 0.3101835726816176, "learning_rate": 9.657914583437454e-06, "loss": 0.2466, "step": 868 }, { "epoch": 3.52, "grad_norm": 0.3183987476194242, "learning_rate": 9.609375273701246e-06, "loss": 0.2353, "step": 869 }, { "epoch": 3.5240506329113925, "grad_norm": 0.3312235171689143, "learning_rate": 9.560919648628133e-06, "loss": 0.226, "step": 870 }, { "epoch": 3.5281012658227846, "grad_norm": 0.3096702614017446, "learning_rate": 9.512548098473047e-06, "loss": 0.2368, "step": 871 }, { "epoch": 3.532151898734177, "grad_norm": 0.3143091125559158, "learning_rate": 9.464261012813825e-06, "loss": 0.2473, "step": 872 }, { "epoch": 3.5362025316455696, "grad_norm": 0.3006790869278435, "learning_rate": 9.416058780547987e-06, "loss": 0.251, "step": 873 }, { "epoch": 3.540253164556962, "grad_norm": 0.30459027473069983, "learning_rate": 9.367941789889714e-06, "loss": 0.2507, "step": 874 }, { "epoch": 3.5443037974683547, "grad_norm": 0.3147661524038504, "learning_rate": 9.319910428366607e-06, "loss": 0.2322, "step": 875 }, { "epoch": 3.5483544303797467, "grad_norm": 0.30522624430763834, "learning_rate": 9.271965082816667e-06, "loss": 0.2548, "step": 876 }, { "epoch": 3.5524050632911393, "grad_norm": 0.323887421295693, "learning_rate": 9.224106139385111e-06, "loss": 0.243, "step": 877 }, { "epoch": 3.5564556962025318, "grad_norm": 0.3042566770208906, "learning_rate": 9.176333983521291e-06, "loss": 0.2512, "step": 878 }, { "epoch": 3.560506329113924, "grad_norm": 0.3233888760205825, "learning_rate": 9.12864899997558e-06, "loss": 0.2222, "step": 879 }, { "epoch": 3.5645569620253164, "grad_norm": 0.30356420304771564, "learning_rate": 9.08105157279628e-06, "loss": 0.2345, "step": 880 }, { "epoch": 3.568607594936709, "grad_norm": 0.29465064512642014, "learning_rate": 9.03354208532653e-06, "loss": 0.2474, "step": 881 }, { "epoch": 3.5726582278481014, "grad_norm": 0.3289225785646361, "learning_rate": 8.986120920201205e-06, "loss": 0.2325, "step": 882 }, { "epoch": 3.576708860759494, "grad_norm": 0.31597618714589465, "learning_rate": 8.938788459343852e-06, "loss": 0.2408, "step": 883 }, { "epoch": 3.580759493670886, "grad_norm": 0.3012075985628806, "learning_rate": 8.8915450839636e-06, "loss": 0.2408, "step": 884 }, { "epoch": 3.5848101265822785, "grad_norm": 0.31874508170917343, "learning_rate": 8.844391174552116e-06, "loss": 0.2433, "step": 885 }, { "epoch": 3.588860759493671, "grad_norm": 0.31796651871706577, "learning_rate": 8.797327110880479e-06, "loss": 0.2367, "step": 886 }, { "epoch": 3.592911392405063, "grad_norm": 0.31097889381345983, "learning_rate": 8.750353271996206e-06, "loss": 0.2513, "step": 887 }, { "epoch": 3.5969620253164556, "grad_norm": 0.3222946735363269, "learning_rate": 8.703470036220132e-06, "loss": 0.2364, "step": 888 }, { "epoch": 3.601012658227848, "grad_norm": 0.3061784082611962, "learning_rate": 8.656677781143394e-06, "loss": 0.2577, "step": 889 }, { "epoch": 3.6050632911392406, "grad_norm": 0.3007063917176603, "learning_rate": 8.609976883624377e-06, "loss": 0.2543, "step": 890 }, { "epoch": 3.609113924050633, "grad_norm": 0.3043512455447562, "learning_rate": 8.563367719785698e-06, "loss": 0.2379, "step": 891 }, { "epoch": 3.613164556962025, "grad_norm": 0.30796776682090105, "learning_rate": 8.516850665011138e-06, "loss": 0.2179, "step": 892 }, { "epoch": 3.6172151898734177, "grad_norm": 0.30105249934638517, "learning_rate": 8.47042609394269e-06, "loss": 0.2598, "step": 893 }, { "epoch": 3.6212658227848102, "grad_norm": 0.31396802550590197, "learning_rate": 8.424094380477432e-06, "loss": 0.2536, "step": 894 }, { "epoch": 3.6253164556962023, "grad_norm": 0.3093263217808231, "learning_rate": 8.37785589776465e-06, "loss": 0.2446, "step": 895 }, { "epoch": 3.629367088607595, "grad_norm": 0.3107120191339328, "learning_rate": 8.331711018202694e-06, "loss": 0.2232, "step": 896 }, { "epoch": 3.6334177215189873, "grad_norm": 0.3040438395813236, "learning_rate": 8.285660113436104e-06, "loss": 0.2547, "step": 897 }, { "epoch": 3.63746835443038, "grad_norm": 0.31797732487036545, "learning_rate": 8.239703554352527e-06, "loss": 0.2334, "step": 898 }, { "epoch": 3.6415189873417724, "grad_norm": 0.3039888266031975, "learning_rate": 8.193841711079775e-06, "loss": 0.2306, "step": 899 }, { "epoch": 3.6455696202531644, "grad_norm": 0.3229507276714819, "learning_rate": 8.148074952982828e-06, "loss": 0.2105, "step": 900 }, { "epoch": 3.649620253164557, "grad_norm": 0.31371210624206153, "learning_rate": 8.102403648660859e-06, "loss": 0.2478, "step": 901 }, { "epoch": 3.6536708860759495, "grad_norm": 0.3046106419926285, "learning_rate": 8.056828165944282e-06, "loss": 0.2268, "step": 902 }, { "epoch": 3.6577215189873415, "grad_norm": 0.30067947826637087, "learning_rate": 8.011348871891762e-06, "loss": 0.2488, "step": 903 }, { "epoch": 3.661772151898734, "grad_norm": 0.39145351198112865, "learning_rate": 7.965966132787287e-06, "loss": 0.2532, "step": 904 }, { "epoch": 3.6658227848101266, "grad_norm": 1.8806574145901034, "learning_rate": 7.920680314137189e-06, "loss": 0.291, "step": 905 }, { "epoch": 3.669873417721519, "grad_norm": 0.30266604921000756, "learning_rate": 7.875491780667246e-06, "loss": 0.259, "step": 906 }, { "epoch": 3.6739240506329116, "grad_norm": 0.3039830979507333, "learning_rate": 7.830400896319667e-06, "loss": 0.2316, "step": 907 }, { "epoch": 3.6779746835443037, "grad_norm": 0.3069157966361694, "learning_rate": 7.785408024250259e-06, "loss": 0.2267, "step": 908 }, { "epoch": 3.682025316455696, "grad_norm": 0.310061243732615, "learning_rate": 7.74051352682542e-06, "loss": 0.2405, "step": 909 }, { "epoch": 3.6860759493670887, "grad_norm": 0.3187298825908714, "learning_rate": 7.695717765619257e-06, "loss": 0.2253, "step": 910 }, { "epoch": 3.690126582278481, "grad_norm": 0.31098155970685654, "learning_rate": 7.651021101410673e-06, "loss": 0.2327, "step": 911 }, { "epoch": 3.6941772151898733, "grad_norm": 0.29037865377624666, "learning_rate": 7.606423894180464e-06, "loss": 0.2646, "step": 912 }, { "epoch": 3.698227848101266, "grad_norm": 0.3073330726213045, "learning_rate": 7.56192650310839e-06, "loss": 0.2401, "step": 913 }, { "epoch": 3.7022784810126583, "grad_norm": 0.3045277626997075, "learning_rate": 7.517529286570349e-06, "loss": 0.2269, "step": 914 }, { "epoch": 3.706329113924051, "grad_norm": 0.30127770698383344, "learning_rate": 7.473232602135387e-06, "loss": 0.2487, "step": 915 }, { "epoch": 3.710379746835443, "grad_norm": 0.3002943172333402, "learning_rate": 7.429036806562935e-06, "loss": 0.2421, "step": 916 }, { "epoch": 3.7144303797468354, "grad_norm": 0.31019113038494744, "learning_rate": 7.3849422557998455e-06, "loss": 0.2438, "step": 917 }, { "epoch": 3.718481012658228, "grad_norm": 0.31377899792317004, "learning_rate": 7.340949304977567e-06, "loss": 0.2446, "step": 918 }, { "epoch": 3.72253164556962, "grad_norm": 0.3075026881522266, "learning_rate": 7.297058308409282e-06, "loss": 0.2424, "step": 919 }, { "epoch": 3.7265822784810125, "grad_norm": 0.31662558786238915, "learning_rate": 7.25326961958704e-06, "loss": 0.2421, "step": 920 }, { "epoch": 3.730632911392405, "grad_norm": 0.3184439496499938, "learning_rate": 7.209583591178921e-06, "loss": 0.2342, "step": 921 }, { "epoch": 3.7346835443037976, "grad_norm": 0.3003367266414243, "learning_rate": 7.1660005750261925e-06, "loss": 0.2447, "step": 922 }, { "epoch": 3.73873417721519, "grad_norm": 0.3179681506791899, "learning_rate": 7.1225209221404765e-06, "loss": 0.2534, "step": 923 }, { "epoch": 3.742784810126582, "grad_norm": 0.30300586318036377, "learning_rate": 7.079144982700909e-06, "loss": 0.2396, "step": 924 }, { "epoch": 3.7468354430379747, "grad_norm": 0.3147737611624677, "learning_rate": 7.0358731060513695e-06, "loss": 0.2585, "step": 925 }, { "epoch": 3.750886075949367, "grad_norm": 0.3092326523744661, "learning_rate": 6.99270564069757e-06, "loss": 0.2223, "step": 926 }, { "epoch": 3.7549367088607593, "grad_norm": 0.31158722749506246, "learning_rate": 6.949642934304375e-06, "loss": 0.2391, "step": 927 }, { "epoch": 3.7589873417721518, "grad_norm": 0.2950718758842213, "learning_rate": 6.906685333692871e-06, "loss": 0.258, "step": 928 }, { "epoch": 3.7630379746835443, "grad_norm": 0.31370212835562405, "learning_rate": 6.86383318483769e-06, "loss": 0.2299, "step": 929 }, { "epoch": 3.767088607594937, "grad_norm": 0.30888131975766, "learning_rate": 6.821086832864139e-06, "loss": 0.2346, "step": 930 }, { "epoch": 3.7711392405063293, "grad_norm": 0.3075121583429046, "learning_rate": 6.77844662204546e-06, "loss": 0.2341, "step": 931 }, { "epoch": 3.7751898734177214, "grad_norm": 0.3148219428301103, "learning_rate": 6.7359128958000455e-06, "loss": 0.2508, "step": 932 }, { "epoch": 3.779240506329114, "grad_norm": 0.3144681538313573, "learning_rate": 6.693485996688695e-06, "loss": 0.2477, "step": 933 }, { "epoch": 3.7832911392405064, "grad_norm": 0.3100013109548358, "learning_rate": 6.651166266411801e-06, "loss": 0.2369, "step": 934 }, { "epoch": 3.7873417721518985, "grad_norm": 0.3043055803953971, "learning_rate": 6.6089540458066725e-06, "loss": 0.2358, "step": 935 }, { "epoch": 3.791392405063291, "grad_norm": 0.29308001486399843, "learning_rate": 6.566849674844711e-06, "loss": 0.2416, "step": 936 }, { "epoch": 3.7954430379746835, "grad_norm": 0.29732236195673506, "learning_rate": 6.524853492628747e-06, "loss": 0.2341, "step": 937 }, { "epoch": 3.799493670886076, "grad_norm": 0.31186799847202223, "learning_rate": 6.4829658373902536e-06, "loss": 0.2444, "step": 938 }, { "epoch": 3.8035443037974686, "grad_norm": 0.30718418112243495, "learning_rate": 6.441187046486648e-06, "loss": 0.2575, "step": 939 }, { "epoch": 3.8075949367088606, "grad_norm": 0.29338147791598423, "learning_rate": 6.399517456398567e-06, "loss": 0.2457, "step": 940 }, { "epoch": 3.811645569620253, "grad_norm": 0.3109290552282426, "learning_rate": 6.357957402727164e-06, "loss": 0.2306, "step": 941 }, { "epoch": 3.8156962025316457, "grad_norm": 0.31862778290657023, "learning_rate": 6.316507220191395e-06, "loss": 0.2665, "step": 942 }, { "epoch": 3.8197468354430377, "grad_norm": 0.30032686928819896, "learning_rate": 6.275167242625331e-06, "loss": 0.2434, "step": 943 }, { "epoch": 3.8237974683544302, "grad_norm": 0.3037893147085854, "learning_rate": 6.233937802975471e-06, "loss": 0.2214, "step": 944 }, { "epoch": 3.8278481012658228, "grad_norm": 0.315440912208986, "learning_rate": 6.192819233298046e-06, "loss": 0.2446, "step": 945 }, { "epoch": 3.8318987341772153, "grad_norm": 0.30470397155361395, "learning_rate": 6.151811864756383e-06, "loss": 0.2225, "step": 946 }, { "epoch": 3.835949367088608, "grad_norm": 0.30108443552062264, "learning_rate": 6.1109160276181655e-06, "loss": 0.2538, "step": 947 }, { "epoch": 3.84, "grad_norm": 0.33641532470638824, "learning_rate": 6.070132051252868e-06, "loss": 0.2294, "step": 948 }, { "epoch": 3.8440506329113924, "grad_norm": 0.3009955792016808, "learning_rate": 6.0294602641290034e-06, "loss": 0.2203, "step": 949 }, { "epoch": 3.848101265822785, "grad_norm": 0.2984805119557601, "learning_rate": 5.988900993811575e-06, "loss": 0.248, "step": 950 }, { "epoch": 3.852151898734177, "grad_norm": 0.3253806597082246, "learning_rate": 5.948454566959363e-06, "loss": 0.24, "step": 951 }, { "epoch": 3.8562025316455695, "grad_norm": 0.3036668656774255, "learning_rate": 5.908121309322328e-06, "loss": 0.2323, "step": 952 }, { "epoch": 3.860253164556962, "grad_norm": 0.30365504037936963, "learning_rate": 5.867901545738976e-06, "loss": 0.2426, "step": 953 }, { "epoch": 3.8643037974683545, "grad_norm": 0.30233363741100244, "learning_rate": 5.827795600133774e-06, "loss": 0.2357, "step": 954 }, { "epoch": 3.868354430379747, "grad_norm": 0.30902685751088665, "learning_rate": 5.787803795514466e-06, "loss": 0.2367, "step": 955 }, { "epoch": 3.872405063291139, "grad_norm": 0.3089385805030145, "learning_rate": 5.747926453969576e-06, "loss": 0.2425, "step": 956 }, { "epoch": 3.8764556962025316, "grad_norm": 0.29764428614839655, "learning_rate": 5.708163896665708e-06, "loss": 0.237, "step": 957 }, { "epoch": 3.880506329113924, "grad_norm": 0.3130547096032053, "learning_rate": 5.668516443845047e-06, "loss": 0.2433, "step": 958 }, { "epoch": 3.884556962025316, "grad_norm": 0.3094557303268805, "learning_rate": 5.6289844148227225e-06, "loss": 0.224, "step": 959 }, { "epoch": 3.8886075949367087, "grad_norm": 0.28271292346406407, "learning_rate": 5.5895681279842615e-06, "loss": 0.2464, "step": 960 }, { "epoch": 3.8926582278481012, "grad_norm": 0.30491737738965285, "learning_rate": 5.550267900783019e-06, "loss": 0.2238, "step": 961 }, { "epoch": 3.8967088607594937, "grad_norm": 0.28956233831957634, "learning_rate": 5.511084049737623e-06, "loss": 0.2369, "step": 962 }, { "epoch": 3.9007594936708863, "grad_norm": 0.30546708437205244, "learning_rate": 5.4720168904294215e-06, "loss": 0.2392, "step": 963 }, { "epoch": 3.9048101265822783, "grad_norm": 0.3123736211524849, "learning_rate": 5.433066737499948e-06, "loss": 0.2221, "step": 964 }, { "epoch": 3.908860759493671, "grad_norm": 0.2934181520388775, "learning_rate": 5.394233904648376e-06, "loss": 0.2479, "step": 965 }, { "epoch": 3.9129113924050634, "grad_norm": 0.29277982310733164, "learning_rate": 5.355518704628997e-06, "loss": 0.2507, "step": 966 }, { "epoch": 3.9169620253164554, "grad_norm": 0.3031938653380239, "learning_rate": 5.316921449248731e-06, "loss": 0.236, "step": 967 }, { "epoch": 3.921012658227848, "grad_norm": 0.2947020583586829, "learning_rate": 5.278442449364538e-06, "loss": 0.2405, "step": 968 }, { "epoch": 3.9250632911392405, "grad_norm": 0.30973345209164554, "learning_rate": 5.240082014881016e-06, "loss": 0.2383, "step": 969 }, { "epoch": 3.929113924050633, "grad_norm": 0.2937957676810797, "learning_rate": 5.201840454747822e-06, "loss": 0.2581, "step": 970 }, { "epoch": 3.9331645569620255, "grad_norm": 0.29603293319238155, "learning_rate": 5.163718076957223e-06, "loss": 0.2411, "step": 971 }, { "epoch": 3.9372151898734176, "grad_norm": 0.29289232413755767, "learning_rate": 5.125715188541609e-06, "loss": 0.2584, "step": 972 }, { "epoch": 3.94126582278481, "grad_norm": 0.3019638639569826, "learning_rate": 5.087832095571021e-06, "loss": 0.2289, "step": 973 }, { "epoch": 3.9453164556962026, "grad_norm": 0.2938888228966732, "learning_rate": 5.0500691031506766e-06, "loss": 0.2393, "step": 974 }, { "epoch": 3.9493670886075947, "grad_norm": 0.2857634543142544, "learning_rate": 5.01242651541854e-06, "loss": 0.2505, "step": 975 }, { "epoch": 3.953417721518987, "grad_norm": 0.2932675925102707, "learning_rate": 4.974904635542815e-06, "loss": 0.2374, "step": 976 }, { "epoch": 3.9574683544303797, "grad_norm": 0.2946786820027245, "learning_rate": 4.937503765719582e-06, "loss": 0.2289, "step": 977 }, { "epoch": 3.961518987341772, "grad_norm": 0.30359077487219005, "learning_rate": 4.900224207170299e-06, "loss": 0.2501, "step": 978 }, { "epoch": 3.9655696202531647, "grad_norm": 0.3002844802585082, "learning_rate": 4.8630662601394065e-06, "loss": 0.2296, "step": 979 }, { "epoch": 3.969620253164557, "grad_norm": 0.3158735422842598, "learning_rate": 4.8260302238918995e-06, "loss": 0.225, "step": 980 }, { "epoch": 3.9736708860759493, "grad_norm": 0.3070558681777055, "learning_rate": 4.789116396710924e-06, "loss": 0.2498, "step": 981 }, { "epoch": 3.977721518987342, "grad_norm": 0.29004332923448867, "learning_rate": 4.752325075895368e-06, "loss": 0.253, "step": 982 }, { "epoch": 3.981772151898734, "grad_norm": 0.2914746675381524, "learning_rate": 4.715656557757473e-06, "loss": 0.2525, "step": 983 }, { "epoch": 3.9858227848101264, "grad_norm": 0.2963830232744561, "learning_rate": 4.679111137620442e-06, "loss": 0.2529, "step": 984 }, { "epoch": 3.989873417721519, "grad_norm": 0.30788665361319495, "learning_rate": 4.6426891098160585e-06, "loss": 0.2249, "step": 985 }, { "epoch": 3.9939240506329114, "grad_norm": 0.29798314529982667, "learning_rate": 4.6063907676823474e-06, "loss": 0.2695, "step": 986 }, { "epoch": 3.997974683544304, "grad_norm": 0.29461554492924535, "learning_rate": 4.570216403561141e-06, "loss": 0.2377, "step": 987 }, { "epoch": 4.002025316455696, "grad_norm": 0.3433476617339371, "learning_rate": 4.534166308795815e-06, "loss": 0.2245, "step": 988 }, { "epoch": 4.006075949367089, "grad_norm": 0.39477380042491766, "learning_rate": 4.498240773728859e-06, "loss": 0.2023, "step": 989 }, { "epoch": 4.010126582278481, "grad_norm": 0.3416572983551114, "learning_rate": 4.462440087699609e-06, "loss": 0.1872, "step": 990 }, { "epoch": 4.014177215189873, "grad_norm": 0.27086279284582615, "learning_rate": 4.426764539041861e-06, "loss": 0.182, "step": 991 }, { "epoch": 4.018227848101266, "grad_norm": 0.3299631736574285, "learning_rate": 4.391214415081582e-06, "loss": 0.1904, "step": 992 }, { "epoch": 4.022278481012658, "grad_norm": 0.43696469929109155, "learning_rate": 4.355790002134579e-06, "loss": 0.1883, "step": 993 }, { "epoch": 4.02632911392405, "grad_norm": 0.4282165934112863, "learning_rate": 4.320491585504207e-06, "loss": 0.2022, "step": 994 }, { "epoch": 4.030379746835443, "grad_norm": 0.35279966572650634, "learning_rate": 4.2853194494790615e-06, "loss": 0.189, "step": 995 }, { "epoch": 4.034430379746835, "grad_norm": 0.30982683466205646, "learning_rate": 4.250273877330691e-06, "loss": 0.1695, "step": 996 }, { "epoch": 4.038481012658228, "grad_norm": 0.3949568336960241, "learning_rate": 4.215355151311313e-06, "loss": 0.1933, "step": 997 }, { "epoch": 4.04253164556962, "grad_norm": 0.3465129223108251, "learning_rate": 4.180563552651542e-06, "loss": 0.1915, "step": 998 }, { "epoch": 4.046582278481012, "grad_norm": 0.32023012903315756, "learning_rate": 4.145899361558147e-06, "loss": 0.1768, "step": 999 }, { "epoch": 4.050632911392405, "grad_norm": 0.2876932766140867, "learning_rate": 4.111362857211738e-06, "loss": 0.1759, "step": 1000 }, { "epoch": 4.054683544303797, "grad_norm": 0.2693890848383889, "learning_rate": 4.076954317764592e-06, "loss": 0.1742, "step": 1001 }, { "epoch": 4.0587341772151895, "grad_norm": 0.31854312166378485, "learning_rate": 4.042674020338335e-06, "loss": 0.1848, "step": 1002 }, { "epoch": 4.062784810126582, "grad_norm": 0.3039419538769003, "learning_rate": 4.0085222410217835e-06, "loss": 0.1732, "step": 1003 }, { "epoch": 4.0668354430379745, "grad_norm": 0.3132214546697805, "learning_rate": 3.974499254868674e-06, "loss": 0.2003, "step": 1004 }, { "epoch": 4.0708860759493675, "grad_norm": 0.28012336999769843, "learning_rate": 3.940605335895451e-06, "loss": 0.1731, "step": 1005 }, { "epoch": 4.0749367088607595, "grad_norm": 0.27204686128174654, "learning_rate": 3.90684075707908e-06, "loss": 0.1905, "step": 1006 }, { "epoch": 4.078987341772152, "grad_norm": 0.27842652827982467, "learning_rate": 3.8732057903548505e-06, "loss": 0.186, "step": 1007 }, { "epoch": 4.083037974683545, "grad_norm": 0.28273760049911684, "learning_rate": 3.8397007066141375e-06, "loss": 0.1818, "step": 1008 }, { "epoch": 4.087088607594937, "grad_norm": 0.28403856832634516, "learning_rate": 3.806325775702304e-06, "loss": 0.1917, "step": 1009 }, { "epoch": 4.091139240506329, "grad_norm": 0.2891849041889394, "learning_rate": 3.773081266416434e-06, "loss": 0.2013, "step": 1010 }, { "epoch": 4.095189873417722, "grad_norm": 0.270326130291634, "learning_rate": 3.739967446503245e-06, "loss": 0.2094, "step": 1011 }, { "epoch": 4.099240506329114, "grad_norm": 0.25195639473577985, "learning_rate": 3.706984582656894e-06, "loss": 0.1892, "step": 1012 }, { "epoch": 4.103291139240507, "grad_norm": 0.32634347516441536, "learning_rate": 3.6741329405168237e-06, "loss": 0.1894, "step": 1013 }, { "epoch": 4.107341772151899, "grad_norm": 0.2508899734724215, "learning_rate": 3.641412784665648e-06, "loss": 0.1636, "step": 1014 }, { "epoch": 4.111392405063291, "grad_norm": 0.2681161634947097, "learning_rate": 3.608824378627005e-06, "loss": 0.1941, "step": 1015 }, { "epoch": 4.115443037974684, "grad_norm": 0.25742671040516607, "learning_rate": 3.5763679848634337e-06, "loss": 0.1951, "step": 1016 }, { "epoch": 4.119493670886076, "grad_norm": 0.25724483366868933, "learning_rate": 3.544043864774269e-06, "loss": 0.1887, "step": 1017 }, { "epoch": 4.123544303797468, "grad_norm": 0.2593826490734755, "learning_rate": 3.5118522786935282e-06, "loss": 0.1806, "step": 1018 }, { "epoch": 4.127594936708861, "grad_norm": 0.2647355498234883, "learning_rate": 3.479793485887819e-06, "loss": 0.1729, "step": 1019 }, { "epoch": 4.131645569620253, "grad_norm": 0.2609451437201767, "learning_rate": 3.4478677445542653e-06, "loss": 0.1731, "step": 1020 }, { "epoch": 4.135696202531646, "grad_norm": 0.2606492571356536, "learning_rate": 3.4160753118183767e-06, "loss": 0.1667, "step": 1021 }, { "epoch": 4.139746835443038, "grad_norm": 0.25947269814837565, "learning_rate": 3.3844164437320527e-06, "loss": 0.1637, "step": 1022 }, { "epoch": 4.14379746835443, "grad_norm": 0.2571615358423336, "learning_rate": 3.3528913952714558e-06, "loss": 0.1696, "step": 1023 }, { "epoch": 4.147848101265823, "grad_norm": 0.271337327495063, "learning_rate": 3.321500420335e-06, "loss": 0.1666, "step": 1024 }, { "epoch": 4.151898734177215, "grad_norm": 0.2660410025240525, "learning_rate": 3.290243771741275e-06, "loss": 0.1721, "step": 1025 }, { "epoch": 4.155949367088607, "grad_norm": 0.2647415985407072, "learning_rate": 3.2591217012270325e-06, "loss": 0.18, "step": 1026 }, { "epoch": 4.16, "grad_norm": 0.26113078067461537, "learning_rate": 3.228134459445149e-06, "loss": 0.1692, "step": 1027 }, { "epoch": 4.164050632911392, "grad_norm": 0.2517806509851525, "learning_rate": 3.1972822959626205e-06, "loss": 0.1662, "step": 1028 }, { "epoch": 4.168101265822785, "grad_norm": 0.26094052558198866, "learning_rate": 3.166565459258513e-06, "loss": 0.1563, "step": 1029 }, { "epoch": 4.172151898734177, "grad_norm": 0.2597014443831941, "learning_rate": 3.1359841967220193e-06, "loss": 0.1864, "step": 1030 }, { "epoch": 4.176202531645569, "grad_norm": 0.2642150082085343, "learning_rate": 3.105538754650419e-06, "loss": 0.1757, "step": 1031 }, { "epoch": 4.180253164556962, "grad_norm": 0.2588267266932311, "learning_rate": 3.07522937824712e-06, "loss": 0.1745, "step": 1032 }, { "epoch": 4.184303797468354, "grad_norm": 0.27908799947780455, "learning_rate": 3.0450563116196697e-06, "loss": 0.1731, "step": 1033 }, { "epoch": 4.188354430379746, "grad_norm": 0.26355237759340855, "learning_rate": 3.0150197977778008e-06, "loss": 0.1945, "step": 1034 }, { "epoch": 4.192405063291139, "grad_norm": 0.25941819231507274, "learning_rate": 2.985120078631465e-06, "loss": 0.1973, "step": 1035 }, { "epoch": 4.1964556962025314, "grad_norm": 0.262939256696287, "learning_rate": 2.9553573949888893e-06, "loss": 0.1863, "step": 1036 }, { "epoch": 4.200506329113924, "grad_norm": 0.264452551952493, "learning_rate": 2.9257319865546384e-06, "loss": 0.1812, "step": 1037 }, { "epoch": 4.2045569620253165, "grad_norm": 0.26647146667961413, "learning_rate": 2.896244091927678e-06, "loss": 0.1867, "step": 1038 }, { "epoch": 4.2086075949367086, "grad_norm": 0.25740364412435796, "learning_rate": 2.8668939485994584e-06, "loss": 0.1887, "step": 1039 }, { "epoch": 4.2126582278481015, "grad_norm": 0.265991902766249, "learning_rate": 2.837681792951994e-06, "loss": 0.1801, "step": 1040 }, { "epoch": 4.216708860759494, "grad_norm": 0.2582571079986072, "learning_rate": 2.808607860255981e-06, "loss": 0.1845, "step": 1041 }, { "epoch": 4.220759493670886, "grad_norm": 0.2526206317948277, "learning_rate": 2.7796723846688634e-06, "loss": 0.175, "step": 1042 }, { "epoch": 4.224810126582279, "grad_norm": 0.2577473758708396, "learning_rate": 2.7508755992329937e-06, "loss": 0.1965, "step": 1043 }, { "epoch": 4.228860759493671, "grad_norm": 0.25875142701031045, "learning_rate": 2.722217735873718e-06, "loss": 0.1841, "step": 1044 }, { "epoch": 4.232911392405064, "grad_norm": 0.24948861125616853, "learning_rate": 2.6936990253975315e-06, "loss": 0.1773, "step": 1045 }, { "epoch": 4.236962025316456, "grad_norm": 0.2507696014620098, "learning_rate": 2.665319697490205e-06, "loss": 0.1773, "step": 1046 }, { "epoch": 4.241012658227848, "grad_norm": 0.2384534738118452, "learning_rate": 2.637079980714945e-06, "loss": 0.166, "step": 1047 }, { "epoch": 4.245063291139241, "grad_norm": 0.2593506035712687, "learning_rate": 2.6089801025105453e-06, "loss": 0.1754, "step": 1048 }, { "epoch": 4.249113924050633, "grad_norm": 0.2746971217801571, "learning_rate": 2.581020289189571e-06, "loss": 0.1834, "step": 1049 }, { "epoch": 4.253164556962025, "grad_norm": 0.2560387866615909, "learning_rate": 2.553200765936501e-06, "loss": 0.189, "step": 1050 }, { "epoch": 4.257215189873418, "grad_norm": 0.2581104968437682, "learning_rate": 2.525521756805962e-06, "loss": 0.1941, "step": 1051 }, { "epoch": 4.26126582278481, "grad_norm": 0.2535774910117627, "learning_rate": 2.497983484720885e-06, "loss": 0.1765, "step": 1052 }, { "epoch": 4.265316455696203, "grad_norm": 0.25831261066313754, "learning_rate": 2.470586171470728e-06, "loss": 0.1743, "step": 1053 }, { "epoch": 4.269367088607595, "grad_norm": 0.2539843440291694, "learning_rate": 2.4433300377096836e-06, "loss": 0.1821, "step": 1054 }, { "epoch": 4.273417721518987, "grad_norm": 0.25638091007771696, "learning_rate": 2.4162153029549073e-06, "loss": 0.1929, "step": 1055 }, { "epoch": 4.27746835443038, "grad_norm": 0.252854331947617, "learning_rate": 2.3892421855847458e-06, "loss": 0.1894, "step": 1056 }, { "epoch": 4.281518987341772, "grad_norm": 0.24922238762735385, "learning_rate": 2.362410902836978e-06, "loss": 0.2063, "step": 1057 }, { "epoch": 4.285569620253165, "grad_norm": 0.25268769778412037, "learning_rate": 2.3357216708070653e-06, "loss": 0.1811, "step": 1058 }, { "epoch": 4.289620253164557, "grad_norm": 0.24942611565853484, "learning_rate": 2.309174704446411e-06, "loss": 0.1877, "step": 1059 }, { "epoch": 4.293670886075949, "grad_norm": 0.24758656412776153, "learning_rate": 2.2827702175606437e-06, "loss": 0.1931, "step": 1060 }, { "epoch": 4.297721518987342, "grad_norm": 0.25854012123759845, "learning_rate": 2.256508422807855e-06, "loss": 0.1818, "step": 1061 }, { "epoch": 4.301772151898734, "grad_norm": 0.25551767512526, "learning_rate": 2.230389531696946e-06, "loss": 0.186, "step": 1062 }, { "epoch": 4.305822784810126, "grad_norm": 0.25391204695047404, "learning_rate": 2.204413754585857e-06, "loss": 0.1772, "step": 1063 }, { "epoch": 4.309873417721519, "grad_norm": 0.24770776271083783, "learning_rate": 2.1785813006799406e-06, "loss": 0.1849, "step": 1064 }, { "epoch": 4.313924050632911, "grad_norm": 0.2539940638855678, "learning_rate": 2.1528923780302224e-06, "loss": 0.1542, "step": 1065 }, { "epoch": 4.317974683544303, "grad_norm": 0.26423183577040515, "learning_rate": 2.127347193531757e-06, "loss": 0.1946, "step": 1066 }, { "epoch": 4.322025316455696, "grad_norm": 0.2581448722020038, "learning_rate": 2.101945952921942e-06, "loss": 0.1953, "step": 1067 }, { "epoch": 4.326075949367088, "grad_norm": 0.25234829738313247, "learning_rate": 2.0766888607788906e-06, "loss": 0.2104, "step": 1068 }, { "epoch": 4.330126582278481, "grad_norm": 0.26077584353302025, "learning_rate": 2.0515761205197337e-06, "loss": 0.1891, "step": 1069 }, { "epoch": 4.334177215189873, "grad_norm": 0.2552155177295496, "learning_rate": 2.0266079343990453e-06, "loss": 0.1803, "step": 1070 }, { "epoch": 4.3382278481012655, "grad_norm": 0.25642667718844175, "learning_rate": 2.0017845035071494e-06, "loss": 0.1719, "step": 1071 }, { "epoch": 4.3422784810126585, "grad_norm": 0.2623548725854853, "learning_rate": 1.9771060277685537e-06, "loss": 0.1488, "step": 1072 }, { "epoch": 4.3463291139240505, "grad_norm": 0.24648849275140336, "learning_rate": 1.95257270594031e-06, "loss": 0.1771, "step": 1073 }, { "epoch": 4.3503797468354435, "grad_norm": 0.25079917922897516, "learning_rate": 1.9281847356104188e-06, "loss": 0.1942, "step": 1074 }, { "epoch": 4.3544303797468356, "grad_norm": 0.25037573473911306, "learning_rate": 1.9039423131962365e-06, "loss": 0.1934, "step": 1075 }, { "epoch": 4.358481012658228, "grad_norm": 0.2493423236470893, "learning_rate": 1.8798456339429027e-06, "loss": 0.165, "step": 1076 }, { "epoch": 4.362531645569621, "grad_norm": 0.25989891925059283, "learning_rate": 1.8558948919217612e-06, "loss": 0.2139, "step": 1077 }, { "epoch": 4.366582278481013, "grad_norm": 0.2502482088038383, "learning_rate": 1.8320902800287954e-06, "loss": 0.1749, "step": 1078 }, { "epoch": 4.370632911392405, "grad_norm": 0.2493045095971663, "learning_rate": 1.8084319899830726e-06, "loss": 0.1754, "step": 1079 }, { "epoch": 4.374683544303798, "grad_norm": 0.2475545058732061, "learning_rate": 1.7849202123252097e-06, "loss": 0.1658, "step": 1080 }, { "epoch": 4.37873417721519, "grad_norm": 0.25887372335821945, "learning_rate": 1.7615551364158401e-06, "loss": 0.1839, "step": 1081 }, { "epoch": 4.382784810126582, "grad_norm": 0.25422325036301846, "learning_rate": 1.738336950434061e-06, "loss": 0.1876, "step": 1082 }, { "epoch": 4.386835443037975, "grad_norm": 0.25354396064928536, "learning_rate": 1.715265841375957e-06, "loss": 0.1812, "step": 1083 }, { "epoch": 4.390886075949367, "grad_norm": 0.26542911122546586, "learning_rate": 1.6923419950530684e-06, "loss": 0.1904, "step": 1084 }, { "epoch": 4.39493670886076, "grad_norm": 0.25216127853709736, "learning_rate": 1.6695655960909008e-06, "loss": 0.19, "step": 1085 }, { "epoch": 4.398987341772152, "grad_norm": 0.25158792660873025, "learning_rate": 1.646936827927441e-06, "loss": 0.1674, "step": 1086 }, { "epoch": 4.403037974683544, "grad_norm": 0.26044100756906885, "learning_rate": 1.6244558728116766e-06, "loss": 0.1622, "step": 1087 }, { "epoch": 4.407088607594937, "grad_norm": 0.25039676447344333, "learning_rate": 1.6021229118021265e-06, "loss": 0.1813, "step": 1088 }, { "epoch": 4.411139240506329, "grad_norm": 0.24923938200706788, "learning_rate": 1.5799381247653967e-06, "loss": 0.1902, "step": 1089 }, { "epoch": 4.415189873417722, "grad_norm": 0.24926546730185994, "learning_rate": 1.5579016903747013e-06, "loss": 0.1897, "step": 1090 }, { "epoch": 4.419240506329114, "grad_norm": 0.25904475270350147, "learning_rate": 1.5360137861084656e-06, "loss": 0.1892, "step": 1091 }, { "epoch": 4.423291139240506, "grad_norm": 0.2592052805848598, "learning_rate": 1.5142745882488475e-06, "loss": 0.1903, "step": 1092 }, { "epoch": 4.427341772151899, "grad_norm": 0.2527859877549928, "learning_rate": 1.4926842718803691e-06, "loss": 0.1745, "step": 1093 }, { "epoch": 4.431392405063291, "grad_norm": 0.25321675520277187, "learning_rate": 1.4712430108884657e-06, "loss": 0.1703, "step": 1094 }, { "epoch": 4.435443037974683, "grad_norm": 0.24994779193949543, "learning_rate": 1.4499509779581078e-06, "loss": 0.1737, "step": 1095 }, { "epoch": 4.439493670886076, "grad_norm": 0.24338456462466554, "learning_rate": 1.4288083445723988e-06, "loss": 0.1918, "step": 1096 }, { "epoch": 4.443544303797468, "grad_norm": 0.25411003809312604, "learning_rate": 1.4078152810112045e-06, "loss": 0.1692, "step": 1097 }, { "epoch": 4.44759493670886, "grad_norm": 0.24490186093727423, "learning_rate": 1.3869719563497697e-06, "loss": 0.2009, "step": 1098 }, { "epoch": 4.451645569620253, "grad_norm": 0.25604937181706483, "learning_rate": 1.3662785384573663e-06, "loss": 0.1857, "step": 1099 }, { "epoch": 4.455696202531645, "grad_norm": 0.26049344828097803, "learning_rate": 1.3457351939959383e-06, "loss": 0.1743, "step": 1100 }, { "epoch": 4.459746835443038, "grad_norm": 0.24848612879210916, "learning_rate": 1.3253420884187551e-06, "loss": 0.182, "step": 1101 }, { "epoch": 4.46379746835443, "grad_norm": 0.24952662161617298, "learning_rate": 1.3050993859690953e-06, "loss": 0.1767, "step": 1102 }, { "epoch": 4.467848101265822, "grad_norm": 0.253375529896674, "learning_rate": 1.2850072496788869e-06, "loss": 0.1904, "step": 1103 }, { "epoch": 4.471898734177215, "grad_norm": 0.24239635299329707, "learning_rate": 1.2650658413674434e-06, "loss": 0.1821, "step": 1104 }, { "epoch": 4.4759493670886075, "grad_norm": 0.2495691975146163, "learning_rate": 1.2452753216401226e-06, "loss": 0.1779, "step": 1105 }, { "epoch": 4.48, "grad_norm": 0.2565801017096709, "learning_rate": 1.2256358498870503e-06, "loss": 0.1874, "step": 1106 }, { "epoch": 4.4840506329113925, "grad_norm": 0.25129095544510177, "learning_rate": 1.2061475842818337e-06, "loss": 0.1786, "step": 1107 }, { "epoch": 4.488101265822785, "grad_norm": 0.24910834672696622, "learning_rate": 1.1868106817802816e-06, "loss": 0.1782, "step": 1108 }, { "epoch": 4.4921518987341775, "grad_norm": 0.25859295576946184, "learning_rate": 1.1676252981191482e-06, "loss": 0.1883, "step": 1109 }, { "epoch": 4.49620253164557, "grad_norm": 0.24726082823089982, "learning_rate": 1.1485915878148823e-06, "loss": 0.1685, "step": 1110 }, { "epoch": 4.500253164556962, "grad_norm": 0.2520430041829727, "learning_rate": 1.1297097041623584e-06, "loss": 0.2023, "step": 1111 }, { "epoch": 4.504303797468355, "grad_norm": 0.2557075988197277, "learning_rate": 1.1109797992336847e-06, "loss": 0.1693, "step": 1112 }, { "epoch": 4.508354430379747, "grad_norm": 0.24756323318117132, "learning_rate": 1.092402023876933e-06, "loss": 0.159, "step": 1113 }, { "epoch": 4.512405063291139, "grad_norm": 0.2497051383384519, "learning_rate": 1.0739765277149527e-06, "loss": 0.1886, "step": 1114 }, { "epoch": 4.516455696202532, "grad_norm": 0.25301704563875094, "learning_rate": 1.0557034591441596e-06, "loss": 0.1884, "step": 1115 }, { "epoch": 4.520506329113924, "grad_norm": 0.25447898538252883, "learning_rate": 1.0375829653333324e-06, "loss": 0.1894, "step": 1116 }, { "epoch": 4.524556962025317, "grad_norm": 0.2380468941095484, "learning_rate": 1.0196151922224385e-06, "loss": 0.1632, "step": 1117 }, { "epoch": 4.528607594936709, "grad_norm": 0.2441256257644526, "learning_rate": 1.0018002845214526e-06, "loss": 0.1903, "step": 1118 }, { "epoch": 4.532658227848101, "grad_norm": 0.24667195721359036, "learning_rate": 9.841383857091947e-07, "loss": 0.1867, "step": 1119 }, { "epoch": 4.536708860759494, "grad_norm": 0.2481290137442997, "learning_rate": 9.666296380321616e-07, "loss": 0.2026, "step": 1120 }, { "epoch": 4.540759493670886, "grad_norm": 0.25522807451525337, "learning_rate": 9.492741825034124e-07, "loss": 0.1613, "step": 1121 }, { "epoch": 4.544810126582279, "grad_norm": 0.2442602944076241, "learning_rate": 9.320721589013892e-07, "loss": 0.1686, "step": 1122 }, { "epoch": 4.548860759493671, "grad_norm": 0.2573016343466042, "learning_rate": 9.150237057688339e-07, "loss": 0.1809, "step": 1123 }, { "epoch": 4.552911392405063, "grad_norm": 0.26568435634962384, "learning_rate": 8.981289604116328e-07, "loss": 0.1962, "step": 1124 }, { "epoch": 4.556962025316456, "grad_norm": 0.244923925190853, "learning_rate": 8.813880588977542e-07, "loss": 0.1815, "step": 1125 }, { "epoch": 4.561012658227848, "grad_norm": 0.24555089560028623, "learning_rate": 8.648011360561126e-07, "loss": 0.1685, "step": 1126 }, { "epoch": 4.56506329113924, "grad_norm": 0.24808366434887053, "learning_rate": 8.483683254755037e-07, "loss": 0.1811, "step": 1127 }, { "epoch": 4.569113924050633, "grad_norm": 0.25996979668143017, "learning_rate": 8.320897595035227e-07, "loss": 0.1966, "step": 1128 }, { "epoch": 4.573164556962025, "grad_norm": 0.2466294071180623, "learning_rate": 8.159655692455093e-07, "loss": 0.1824, "step": 1129 }, { "epoch": 4.577215189873417, "grad_norm": 0.25240428641326274, "learning_rate": 7.999958845634648e-07, "loss": 0.1765, "step": 1130 }, { "epoch": 4.58126582278481, "grad_norm": 0.2513714965018812, "learning_rate": 7.841808340750478e-07, "loss": 0.1929, "step": 1131 }, { "epoch": 4.585316455696202, "grad_norm": 0.2431837819946938, "learning_rate": 7.685205451524869e-07, "loss": 0.1611, "step": 1132 }, { "epoch": 4.589367088607595, "grad_norm": 0.24831230833293577, "learning_rate": 7.530151439216027e-07, "loss": 0.1946, "step": 1133 }, { "epoch": 4.593417721518987, "grad_norm": 0.25105436854004554, "learning_rate": 7.376647552607675e-07, "loss": 0.1761, "step": 1134 }, { "epoch": 4.597468354430379, "grad_norm": 0.23908764812517685, "learning_rate": 7.224695027998963e-07, "loss": 0.182, "step": 1135 }, { "epoch": 4.601518987341772, "grad_norm": 0.26907298201288554, "learning_rate": 7.07429508919466e-07, "loss": 0.1683, "step": 1136 }, { "epoch": 4.605569620253164, "grad_norm": 0.2590951363261018, "learning_rate": 6.925448947495206e-07, "loss": 0.1644, "step": 1137 }, { "epoch": 4.609620253164557, "grad_norm": 0.2628981930657257, "learning_rate": 6.778157801686936e-07, "loss": 0.1778, "step": 1138 }, { "epoch": 4.613670886075949, "grad_norm": 0.2496620549471387, "learning_rate": 6.632422838032515e-07, "loss": 0.186, "step": 1139 }, { "epoch": 4.6177215189873415, "grad_norm": 0.25755608113787987, "learning_rate": 6.488245230261281e-07, "loss": 0.1788, "step": 1140 }, { "epoch": 4.6217721518987345, "grad_norm": 0.25250231661340267, "learning_rate": 6.345626139559868e-07, "loss": 0.2008, "step": 1141 }, { "epoch": 4.6258227848101265, "grad_norm": 0.2505273842696049, "learning_rate": 6.204566714562866e-07, "loss": 0.1736, "step": 1142 }, { "epoch": 4.629873417721519, "grad_norm": 0.25546260205352883, "learning_rate": 6.06506809134344e-07, "loss": 0.1669, "step": 1143 }, { "epoch": 4.633924050632912, "grad_norm": 0.2516054751880713, "learning_rate": 5.927131393404373e-07, "loss": 0.1937, "step": 1144 }, { "epoch": 4.637974683544304, "grad_norm": 0.24742822886143057, "learning_rate": 5.790757731668817e-07, "loss": 0.2092, "step": 1145 }, { "epoch": 4.642025316455696, "grad_norm": 0.25123607066652376, "learning_rate": 5.655948204471507e-07, "loss": 0.1951, "step": 1146 }, { "epoch": 4.646075949367089, "grad_norm": 0.24011772360356945, "learning_rate": 5.522703897549875e-07, "loss": 0.2053, "step": 1147 }, { "epoch": 4.650126582278481, "grad_norm": 0.2617765637269628, "learning_rate": 5.391025884035239e-07, "loss": 0.1815, "step": 1148 }, { "epoch": 4.654177215189874, "grad_norm": 0.2560220225471958, "learning_rate": 5.260915224444207e-07, "loss": 0.1844, "step": 1149 }, { "epoch": 4.658227848101266, "grad_norm": 0.2491612016383771, "learning_rate": 5.132372966670129e-07, "loss": 0.1708, "step": 1150 }, { "epoch": 4.662278481012658, "grad_norm": 0.26848217948921627, "learning_rate": 5.005400145974704e-07, "loss": 0.193, "step": 1151 }, { "epoch": 4.666329113924051, "grad_norm": 0.26404817085972293, "learning_rate": 4.879997784979562e-07, "loss": 0.1902, "step": 1152 }, { "epoch": 4.670379746835443, "grad_norm": 0.2561165648025565, "learning_rate": 4.7561668936580984e-07, "loss": 0.1942, "step": 1153 }, { "epoch": 4.674430379746836, "grad_norm": 0.2485886945885765, "learning_rate": 4.6339084693272306e-07, "loss": 0.1823, "step": 1154 }, { "epoch": 4.678481012658228, "grad_norm": 0.2492330788446468, "learning_rate": 4.5132234966395847e-07, "loss": 0.1727, "step": 1155 }, { "epoch": 4.68253164556962, "grad_norm": 0.24503003309912993, "learning_rate": 4.3941129475752795e-07, "loss": 0.1748, "step": 1156 }, { "epoch": 4.686582278481013, "grad_norm": 0.2669732678878237, "learning_rate": 4.27657778143431e-07, "loss": 0.1751, "step": 1157 }, { "epoch": 4.690632911392405, "grad_norm": 0.25699041247734117, "learning_rate": 4.1606189448287757e-07, "loss": 0.1695, "step": 1158 }, { "epoch": 4.694683544303797, "grad_norm": 0.2549833468495404, "learning_rate": 4.046237371675177e-07, "loss": 0.2, "step": 1159 }, { "epoch": 4.69873417721519, "grad_norm": 0.2553172063531275, "learning_rate": 3.9334339831869963e-07, "loss": 0.181, "step": 1160 }, { "epoch": 4.702784810126582, "grad_norm": 0.258282713600918, "learning_rate": 3.8222096878671955e-07, "loss": 0.1852, "step": 1161 }, { "epoch": 4.706835443037974, "grad_norm": 0.25570156466279725, "learning_rate": 3.7125653815009545e-07, "loss": 0.1636, "step": 1162 }, { "epoch": 4.710886075949367, "grad_norm": 0.2562536474125051, "learning_rate": 3.6045019471484974e-07, "loss": 0.172, "step": 1163 }, { "epoch": 4.714936708860759, "grad_norm": 0.2533072941260365, "learning_rate": 3.498020255137813e-07, "loss": 0.1883, "step": 1164 }, { "epoch": 4.718987341772152, "grad_norm": 0.2615866515842902, "learning_rate": 3.393121163057811e-07, "loss": 0.1566, "step": 1165 }, { "epoch": 4.723037974683544, "grad_norm": 0.2504837792055102, "learning_rate": 3.289805515751399e-07, "loss": 0.1966, "step": 1166 }, { "epoch": 4.727088607594936, "grad_norm": 0.24370044362879323, "learning_rate": 3.188074145308573e-07, "loss": 0.1922, "step": 1167 }, { "epoch": 4.731139240506329, "grad_norm": 0.2526903151385949, "learning_rate": 3.087927871059804e-07, "loss": 0.1813, "step": 1168 }, { "epoch": 4.735189873417721, "grad_norm": 0.2598744007102339, "learning_rate": 2.989367499569418e-07, "loss": 0.188, "step": 1169 }, { "epoch": 4.739240506329114, "grad_norm": 0.245481195311086, "learning_rate": 2.8923938246290917e-07, "loss": 0.1712, "step": 1170 }, { "epoch": 4.743291139240506, "grad_norm": 0.24645528419190518, "learning_rate": 2.7970076272514804e-07, "loss": 0.1823, "step": 1171 }, { "epoch": 4.7473417721518985, "grad_norm": 0.24806603252510342, "learning_rate": 2.703209675663887e-07, "loss": 0.1992, "step": 1172 }, { "epoch": 4.751392405063291, "grad_norm": 0.24963432744373645, "learning_rate": 2.6110007253021374e-07, "loss": 0.2083, "step": 1173 }, { "epoch": 4.7554430379746835, "grad_norm": 0.24568373701618554, "learning_rate": 2.520381518804471e-07, "loss": 0.1845, "step": 1174 }, { "epoch": 4.759493670886076, "grad_norm": 0.25097786044149684, "learning_rate": 2.4313527860054585e-07, "loss": 0.1666, "step": 1175 }, { "epoch": 4.7635443037974685, "grad_norm": 0.2489386760686691, "learning_rate": 2.343915243930317e-07, "loss": 0.1861, "step": 1176 }, { "epoch": 4.767594936708861, "grad_norm": 0.2745161444109072, "learning_rate": 2.2580695967889367e-07, "loss": 0.1855, "step": 1177 }, { "epoch": 4.7716455696202535, "grad_norm": 0.25216248897456106, "learning_rate": 2.1738165359704189e-07, "loss": 0.1792, "step": 1178 }, { "epoch": 4.775696202531646, "grad_norm": 0.25249730189068326, "learning_rate": 2.0911567400373257e-07, "loss": 0.1789, "step": 1179 }, { "epoch": 4.779746835443038, "grad_norm": 0.2651312219679918, "learning_rate": 2.0100908747202607e-07, "loss": 0.183, "step": 1180 }, { "epoch": 4.783797468354431, "grad_norm": 0.24987817494671993, "learning_rate": 1.9306195929125638e-07, "loss": 0.1933, "step": 1181 }, { "epoch": 4.787848101265823, "grad_norm": 0.24723165436901193, "learning_rate": 1.8527435346650247e-07, "loss": 0.1677, "step": 1182 }, { "epoch": 4.791898734177215, "grad_norm": 0.24712965831313222, "learning_rate": 1.7764633271807108e-07, "loss": 0.1975, "step": 1183 }, { "epoch": 4.795949367088608, "grad_norm": 0.24408027142689778, "learning_rate": 1.7017795848099262e-07, "loss": 0.1838, "step": 1184 }, { "epoch": 4.8, "grad_norm": 0.2566112267507943, "learning_rate": 1.6286929090452596e-07, "loss": 0.1775, "step": 1185 }, { "epoch": 4.804050632911393, "grad_norm": 0.260036069454411, "learning_rate": 1.557203888516745e-07, "loss": 0.1777, "step": 1186 }, { "epoch": 4.808101265822785, "grad_norm": 0.23841175514469176, "learning_rate": 1.487313098987131e-07, "loss": 0.2036, "step": 1187 }, { "epoch": 4.812151898734177, "grad_norm": 0.24830641366729206, "learning_rate": 1.4190211033472402e-07, "loss": 0.1762, "step": 1188 }, { "epoch": 4.81620253164557, "grad_norm": 0.2547840384560194, "learning_rate": 1.3523284516113955e-07, "loss": 0.172, "step": 1189 }, { "epoch": 4.820253164556962, "grad_norm": 0.25531738976388596, "learning_rate": 1.2872356809130682e-07, "loss": 0.1817, "step": 1190 }, { "epoch": 4.824303797468355, "grad_norm": 0.2549021536945061, "learning_rate": 1.2237433155004807e-07, "loss": 0.1882, "step": 1191 }, { "epoch": 4.828354430379747, "grad_norm": 0.2517018646626047, "learning_rate": 1.1618518667323886e-07, "loss": 0.189, "step": 1192 }, { "epoch": 4.832405063291139, "grad_norm": 0.2515608327662169, "learning_rate": 1.1015618330740385e-07, "loss": 0.2109, "step": 1193 }, { "epoch": 4.836455696202532, "grad_norm": 0.25402582070564456, "learning_rate": 1.042873700093061e-07, "loss": 0.1947, "step": 1194 }, { "epoch": 4.840506329113924, "grad_norm": 0.2503215917462116, "learning_rate": 9.857879404556291e-08, "loss": 0.1679, "step": 1195 }, { "epoch": 4.844556962025316, "grad_norm": 0.2499763128220732, "learning_rate": 9.303050139225722e-08, "loss": 0.1792, "step": 1196 }, { "epoch": 4.848607594936709, "grad_norm": 0.24893035687323817, "learning_rate": 8.76425367345779e-08, "loss": 0.181, "step": 1197 }, { "epoch": 4.852658227848101, "grad_norm": 1.2999263734368414, "learning_rate": 8.241494346644897e-08, "loss": 0.2048, "step": 1198 }, { "epoch": 4.856708860759493, "grad_norm": 0.2530455541860734, "learning_rate": 7.734776369019204e-08, "loss": 0.1691, "step": 1199 }, { "epoch": 4.860759493670886, "grad_norm": 0.2519155050215826, "learning_rate": 7.244103821617332e-08, "loss": 0.1559, "step": 1200 }, { "epoch": 4.864810126582278, "grad_norm": 0.2590595371165821, "learning_rate": 6.769480656248606e-08, "loss": 0.1667, "step": 1201 }, { "epoch": 4.868860759493671, "grad_norm": 0.2580936189230853, "learning_rate": 6.310910695462635e-08, "loss": 0.1689, "step": 1202 }, { "epoch": 4.872911392405063, "grad_norm": 0.25420846813305864, "learning_rate": 5.8683976325191185e-08, "loss": 0.1953, "step": 1203 }, { "epoch": 4.876962025316455, "grad_norm": 0.24998106290536498, "learning_rate": 5.4419450313571984e-08, "loss": 0.1871, "step": 1204 }, { "epoch": 4.881012658227848, "grad_norm": 0.2528710004003964, "learning_rate": 5.031556326567488e-08, "loss": 0.188, "step": 1205 }, { "epoch": 4.88506329113924, "grad_norm": 0.2596720007499516, "learning_rate": 4.637234823364312e-08, "loss": 0.2096, "step": 1206 }, { "epoch": 4.889113924050633, "grad_norm": 0.23200166579847806, "learning_rate": 4.258983697558838e-08, "loss": 0.165, "step": 1207 }, { "epoch": 4.8931645569620255, "grad_norm": 0.2610468301734908, "learning_rate": 3.896805995533548e-08, "loss": 0.1822, "step": 1208 }, { "epoch": 4.8972151898734175, "grad_norm": 0.25289180669687567, "learning_rate": 3.550704634218028e-08, "loss": 0.1776, "step": 1209 }, { "epoch": 4.9012658227848105, "grad_norm": 0.4840332701020245, "learning_rate": 3.2206824010647676e-08, "loss": 0.1988, "step": 1210 }, { "epoch": 4.905316455696203, "grad_norm": 0.24866283277776838, "learning_rate": 2.9067419540278476e-08, "loss": 0.1793, "step": 1211 }, { "epoch": 4.909367088607595, "grad_norm": 0.2506315726206063, "learning_rate": 2.6088858215400638e-08, "loss": 0.1672, "step": 1212 }, { "epoch": 4.913417721518988, "grad_norm": 0.24491159365527382, "learning_rate": 2.3271164024940564e-08, "loss": 0.1771, "step": 1213 }, { "epoch": 4.91746835443038, "grad_norm": 0.24932565023039382, "learning_rate": 2.061435966221881e-08, "loss": 0.1984, "step": 1214 }, { "epoch": 4.921518987341772, "grad_norm": 0.2472604439438776, "learning_rate": 1.811846652477245e-08, "loss": 0.1592, "step": 1215 }, { "epoch": 4.925569620253165, "grad_norm": 0.25370136894930084, "learning_rate": 1.5783504714184106e-08, "loss": 0.1717, "step": 1216 }, { "epoch": 4.929620253164557, "grad_norm": 0.24829701569790338, "learning_rate": 1.360949303591097e-08, "loss": 0.1918, "step": 1217 }, { "epoch": 4.93367088607595, "grad_norm": 0.2418827140509262, "learning_rate": 1.1596448999144916e-08, "loss": 0.1806, "step": 1218 }, { "epoch": 4.937721518987342, "grad_norm": 0.2538199475032668, "learning_rate": 9.744388816668172e-09, "loss": 0.1777, "step": 1219 }, { "epoch": 4.941772151898734, "grad_norm": 0.2524910523696915, "learning_rate": 8.05332740472009e-09, "loss": 0.1701, "step": 1220 }, { "epoch": 4.945822784810127, "grad_norm": 0.2445988843597678, "learning_rate": 6.523278382872811e-09, "loss": 0.2047, "step": 1221 }, { "epoch": 4.949873417721519, "grad_norm": 0.24411378532316233, "learning_rate": 5.15425407393133e-09, "loss": 0.1861, "step": 1222 }, { "epoch": 4.953924050632912, "grad_norm": 0.24991737815943288, "learning_rate": 3.94626550383137e-09, "loss": 0.1843, "step": 1223 }, { "epoch": 4.957974683544304, "grad_norm": 0.24623081746341668, "learning_rate": 2.899322401546112e-09, "loss": 0.1906, "step": 1224 }, { "epoch": 4.962025316455696, "grad_norm": 0.26074647605605644, "learning_rate": 2.013433199010706e-09, "loss": 0.1866, "step": 1225 }, { "epoch": 4.966075949367089, "grad_norm": 0.2542237383304025, "learning_rate": 1.2886050310556563e-09, "loss": 0.1838, "step": 1226 }, { "epoch": 4.970126582278481, "grad_norm": 0.2557020517677089, "learning_rate": 7.248437353468695e-10, "loss": 0.1651, "step": 1227 }, { "epoch": 4.974177215189873, "grad_norm": 0.24713808036547366, "learning_rate": 3.221538523412449e-10, "loss": 0.1782, "step": 1228 }, { "epoch": 4.978227848101266, "grad_norm": 0.2500085562699426, "learning_rate": 8.053862524670663e-11, "loss": 0.1824, "step": 1229 }, { "epoch": 4.982278481012658, "grad_norm": 0.254262088216227, "learning_rate": 0.0, "loss": 0.2005, "step": 1230 }, { "epoch": 4.982278481012658, "step": 1230, "total_flos": 2.6727219362579743e+18, "train_loss": 0.3913675991500296, "train_runtime": 41403.3428, "train_samples_per_second": 3.816, "train_steps_per_second": 0.03 } ], "logging_steps": 1, "max_steps": 1230, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.6727219362579743e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }