{ "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": 6.192782117885149, "learning_rate": 3.2520325203252037e-07, "loss": 0.8042, "step": 1 }, { "epoch": 0.00810126582278481, "grad_norm": 6.347907497106777, "learning_rate": 6.504065040650407e-07, "loss": 0.8181, "step": 2 }, { "epoch": 0.012151898734177215, "grad_norm": 6.533564649730392, "learning_rate": 9.75609756097561e-07, "loss": 0.8405, "step": 3 }, { "epoch": 0.01620253164556962, "grad_norm": 6.119362441352054, "learning_rate": 1.3008130081300815e-06, "loss": 0.8101, "step": 4 }, { "epoch": 0.020253164556962026, "grad_norm": 6.061087450466809, "learning_rate": 1.6260162601626018e-06, "loss": 0.8309, "step": 5 }, { "epoch": 0.02430379746835443, "grad_norm": 5.775222421415922, "learning_rate": 1.951219512195122e-06, "loss": 0.8138, "step": 6 }, { "epoch": 0.028354430379746835, "grad_norm": 4.220801509188668, "learning_rate": 2.2764227642276426e-06, "loss": 0.7701, "step": 7 }, { "epoch": 0.03240506329113924, "grad_norm": 3.9754160889749235, "learning_rate": 2.601626016260163e-06, "loss": 0.7594, "step": 8 }, { "epoch": 0.03645569620253165, "grad_norm": 3.058322266433838, "learning_rate": 2.926829268292683e-06, "loss": 0.793, "step": 9 }, { "epoch": 0.04050632911392405, "grad_norm": 2.08741374332377, "learning_rate": 3.2520325203252037e-06, "loss": 0.7417, "step": 10 }, { "epoch": 0.044556962025316456, "grad_norm": 2.0259558647644624, "learning_rate": 3.577235772357724e-06, "loss": 0.741, "step": 11 }, { "epoch": 0.04860759493670886, "grad_norm": 3.6264054077627046, "learning_rate": 3.902439024390244e-06, "loss": 0.7251, "step": 12 }, { "epoch": 0.052658227848101265, "grad_norm": 3.9943233566244385, "learning_rate": 4.227642276422765e-06, "loss": 0.7284, "step": 13 }, { "epoch": 0.05670886075949367, "grad_norm": 3.900179189132747, "learning_rate": 4.552845528455285e-06, "loss": 0.7221, "step": 14 }, { "epoch": 0.060759493670886074, "grad_norm": 3.8240512390501227, "learning_rate": 4.8780487804878055e-06, "loss": 0.7099, "step": 15 }, { "epoch": 0.06481012658227848, "grad_norm": 3.2417891518253086, "learning_rate": 5.203252032520326e-06, "loss": 0.6751, "step": 16 }, { "epoch": 0.06886075949367089, "grad_norm": 2.7544258489404156, "learning_rate": 5.528455284552846e-06, "loss": 0.6627, "step": 17 }, { "epoch": 0.0729113924050633, "grad_norm": 2.1770581170670016, "learning_rate": 5.853658536585366e-06, "loss": 0.6583, "step": 18 }, { "epoch": 0.0769620253164557, "grad_norm": 1.4588693322856523, "learning_rate": 6.178861788617887e-06, "loss": 0.6474, "step": 19 }, { "epoch": 0.0810126582278481, "grad_norm": 1.3285896213258146, "learning_rate": 6.504065040650407e-06, "loss": 0.6458, "step": 20 }, { "epoch": 0.08506329113924051, "grad_norm": 1.3535172282697856, "learning_rate": 6.829268292682928e-06, "loss": 0.6204, "step": 21 }, { "epoch": 0.08911392405063291, "grad_norm": 1.3726846570407525, "learning_rate": 7.154471544715448e-06, "loss": 0.6126, "step": 22 }, { "epoch": 0.09316455696202532, "grad_norm": 1.18383588817754, "learning_rate": 7.4796747967479676e-06, "loss": 0.6144, "step": 23 }, { "epoch": 0.09721518987341772, "grad_norm": 0.8232197629198006, "learning_rate": 7.804878048780489e-06, "loss": 0.6009, "step": 24 }, { "epoch": 0.10126582278481013, "grad_norm": 0.8906906974084577, "learning_rate": 8.130081300813009e-06, "loss": 0.5957, "step": 25 }, { "epoch": 0.10531645569620253, "grad_norm": 0.9809372627231678, "learning_rate": 8.45528455284553e-06, "loss": 0.5933, "step": 26 }, { "epoch": 0.10936708860759493, "grad_norm": 0.7842148985891311, "learning_rate": 8.78048780487805e-06, "loss": 0.5638, "step": 27 }, { "epoch": 0.11341772151898734, "grad_norm": 0.819909058260966, "learning_rate": 9.10569105691057e-06, "loss": 0.5713, "step": 28 }, { "epoch": 0.11746835443037974, "grad_norm": 0.8159187171036182, "learning_rate": 9.43089430894309e-06, "loss": 0.5678, "step": 29 }, { "epoch": 0.12151898734177215, "grad_norm": 0.6847400819768004, "learning_rate": 9.756097560975611e-06, "loss": 0.5729, "step": 30 }, { "epoch": 0.12556962025316457, "grad_norm": 0.6424080201196167, "learning_rate": 1.008130081300813e-05, "loss": 0.5649, "step": 31 }, { "epoch": 0.12962025316455697, "grad_norm": 0.7983465014978809, "learning_rate": 1.0406504065040652e-05, "loss": 0.5662, "step": 32 }, { "epoch": 0.13367088607594937, "grad_norm": 0.6501865000222062, "learning_rate": 1.0731707317073172e-05, "loss": 0.5529, "step": 33 }, { "epoch": 0.13772151898734178, "grad_norm": 0.47406328540159753, "learning_rate": 1.1056910569105692e-05, "loss": 0.5448, "step": 34 }, { "epoch": 0.14177215189873418, "grad_norm": 0.641162934494188, "learning_rate": 1.1382113821138213e-05, "loss": 0.5439, "step": 35 }, { "epoch": 0.1458227848101266, "grad_norm": 0.6179263454321454, "learning_rate": 1.1707317073170731e-05, "loss": 0.5504, "step": 36 }, { "epoch": 0.149873417721519, "grad_norm": 0.5470618473635996, "learning_rate": 1.2032520325203254e-05, "loss": 0.5419, "step": 37 }, { "epoch": 0.1539240506329114, "grad_norm": 0.5966863785061962, "learning_rate": 1.2357723577235774e-05, "loss": 0.541, "step": 38 }, { "epoch": 0.1579746835443038, "grad_norm": 0.5280832983478004, "learning_rate": 1.2682926829268294e-05, "loss": 0.5183, "step": 39 }, { "epoch": 0.1620253164556962, "grad_norm": 0.5576117122974271, "learning_rate": 1.3008130081300815e-05, "loss": 0.5241, "step": 40 }, { "epoch": 0.1660759493670886, "grad_norm": 0.5226159145916782, "learning_rate": 1.3333333333333333e-05, "loss": 0.5153, "step": 41 }, { "epoch": 0.17012658227848101, "grad_norm": 0.5383423809294313, "learning_rate": 1.3658536585365855e-05, "loss": 0.5199, "step": 42 }, { "epoch": 0.17417721518987342, "grad_norm": 0.449042183384951, "learning_rate": 1.3983739837398376e-05, "loss": 0.5163, "step": 43 }, { "epoch": 0.17822784810126582, "grad_norm": 0.5285446895818416, "learning_rate": 1.4308943089430896e-05, "loss": 0.5263, "step": 44 }, { "epoch": 0.18227848101265823, "grad_norm": 0.36991723113142183, "learning_rate": 1.4634146341463415e-05, "loss": 0.5053, "step": 45 }, { "epoch": 0.18632911392405063, "grad_norm": 0.4552192792748823, "learning_rate": 1.4959349593495935e-05, "loss": 0.5058, "step": 46 }, { "epoch": 0.19037974683544304, "grad_norm": 0.4766562902001539, "learning_rate": 1.528455284552846e-05, "loss": 0.5333, "step": 47 }, { "epoch": 0.19443037974683544, "grad_norm": 0.45585588749729683, "learning_rate": 1.5609756097560978e-05, "loss": 0.5041, "step": 48 }, { "epoch": 0.19848101265822785, "grad_norm": 0.4989967910288126, "learning_rate": 1.5934959349593496e-05, "loss": 0.5286, "step": 49 }, { "epoch": 0.20253164556962025, "grad_norm": 0.5370209008297756, "learning_rate": 1.6260162601626018e-05, "loss": 0.5111, "step": 50 }, { "epoch": 0.20658227848101265, "grad_norm": 0.44291916696059497, "learning_rate": 1.6585365853658537e-05, "loss": 0.5065, "step": 51 }, { "epoch": 0.21063291139240506, "grad_norm": 0.6665167282847996, "learning_rate": 1.691056910569106e-05, "loss": 0.4967, "step": 52 }, { "epoch": 0.21468354430379746, "grad_norm": 0.4309997390825627, "learning_rate": 1.7235772357723578e-05, "loss": 0.5124, "step": 53 }, { "epoch": 0.21873417721518987, "grad_norm": 0.5443492504225955, "learning_rate": 1.75609756097561e-05, "loss": 0.5048, "step": 54 }, { "epoch": 0.22278481012658227, "grad_norm": 0.4486197235118565, "learning_rate": 1.788617886178862e-05, "loss": 0.5128, "step": 55 }, { "epoch": 0.22683544303797468, "grad_norm": 0.461503699485267, "learning_rate": 1.821138211382114e-05, "loss": 0.4966, "step": 56 }, { "epoch": 0.23088607594936708, "grad_norm": 0.43589542196156145, "learning_rate": 1.8536585365853663e-05, "loss": 0.5034, "step": 57 }, { "epoch": 0.23493670886075949, "grad_norm": 0.4508484435861481, "learning_rate": 1.886178861788618e-05, "loss": 0.4892, "step": 58 }, { "epoch": 0.2389873417721519, "grad_norm": 0.4394130948650658, "learning_rate": 1.91869918699187e-05, "loss": 0.4959, "step": 59 }, { "epoch": 0.2430379746835443, "grad_norm": 0.5070163298723913, "learning_rate": 1.9512195121951222e-05, "loss": 0.4968, "step": 60 }, { "epoch": 0.2470886075949367, "grad_norm": 0.4456616119583461, "learning_rate": 1.983739837398374e-05, "loss": 0.4889, "step": 61 }, { "epoch": 0.25113924050632913, "grad_norm": 0.41856040542638784, "learning_rate": 2.016260162601626e-05, "loss": 0.4869, "step": 62 }, { "epoch": 0.25518987341772154, "grad_norm": 0.4278193536462553, "learning_rate": 2.048780487804878e-05, "loss": 0.4797, "step": 63 }, { "epoch": 0.25924050632911394, "grad_norm": 0.49569198461155906, "learning_rate": 2.0813008130081303e-05, "loss": 0.491, "step": 64 }, { "epoch": 0.26329113924050634, "grad_norm": 0.5018840931470369, "learning_rate": 2.1138211382113822e-05, "loss": 0.5054, "step": 65 }, { "epoch": 0.26734177215189875, "grad_norm": 0.5012074013266263, "learning_rate": 2.1463414634146344e-05, "loss": 0.4837, "step": 66 }, { "epoch": 0.27139240506329115, "grad_norm": 0.5387825376602455, "learning_rate": 2.1788617886178863e-05, "loss": 0.4943, "step": 67 }, { "epoch": 0.27544303797468356, "grad_norm": 0.6360097654275052, "learning_rate": 2.2113821138211385e-05, "loss": 0.4818, "step": 68 }, { "epoch": 0.27949367088607596, "grad_norm": 0.6462750768544492, "learning_rate": 2.2439024390243907e-05, "loss": 0.4849, "step": 69 }, { "epoch": 0.28354430379746837, "grad_norm": 0.8549273866495698, "learning_rate": 2.2764227642276426e-05, "loss": 0.4859, "step": 70 }, { "epoch": 0.28759493670886077, "grad_norm": 0.8674167763944011, "learning_rate": 2.3089430894308948e-05, "loss": 0.4943, "step": 71 }, { "epoch": 0.2916455696202532, "grad_norm": 0.7976340307667927, "learning_rate": 2.3414634146341463e-05, "loss": 0.4959, "step": 72 }, { "epoch": 0.2956962025316456, "grad_norm": 0.7115736909997912, "learning_rate": 2.3739837398373985e-05, "loss": 0.4719, "step": 73 }, { "epoch": 0.299746835443038, "grad_norm": 0.8816925423452006, "learning_rate": 2.4065040650406507e-05, "loss": 0.4777, "step": 74 }, { "epoch": 0.3037974683544304, "grad_norm": 1.0151138298789963, "learning_rate": 2.4390243902439026e-05, "loss": 0.4791, "step": 75 }, { "epoch": 0.3078481012658228, "grad_norm": 0.7247020594591468, "learning_rate": 2.4715447154471548e-05, "loss": 0.4849, "step": 76 }, { "epoch": 0.3118987341772152, "grad_norm": 0.6743863704382536, "learning_rate": 2.5040650406504066e-05, "loss": 0.4826, "step": 77 }, { "epoch": 0.3159493670886076, "grad_norm": 0.7886484050838153, "learning_rate": 2.536585365853659e-05, "loss": 0.4796, "step": 78 }, { "epoch": 0.32, "grad_norm": 1.0943869386501957, "learning_rate": 2.569105691056911e-05, "loss": 0.4666, "step": 79 }, { "epoch": 0.3240506329113924, "grad_norm": 0.5512069308494992, "learning_rate": 2.601626016260163e-05, "loss": 0.466, "step": 80 }, { "epoch": 0.3281012658227848, "grad_norm": 1.009819733794329, "learning_rate": 2.634146341463415e-05, "loss": 0.4939, "step": 81 }, { "epoch": 0.3321518987341772, "grad_norm": 1.1598071717563698, "learning_rate": 2.6666666666666667e-05, "loss": 0.4776, "step": 82 }, { "epoch": 0.3362025316455696, "grad_norm": 0.6463183766052328, "learning_rate": 2.699186991869919e-05, "loss": 0.4737, "step": 83 }, { "epoch": 0.34025316455696203, "grad_norm": 1.0940378271567066, "learning_rate": 2.731707317073171e-05, "loss": 0.4683, "step": 84 }, { "epoch": 0.34430379746835443, "grad_norm": 1.0408373983593244, "learning_rate": 2.764227642276423e-05, "loss": 0.4837, "step": 85 }, { "epoch": 0.34835443037974684, "grad_norm": 0.7292092124822765, "learning_rate": 2.796747967479675e-05, "loss": 0.4953, "step": 86 }, { "epoch": 0.35240506329113924, "grad_norm": 1.0262080465886434, "learning_rate": 2.829268292682927e-05, "loss": 0.476, "step": 87 }, { "epoch": 0.35645569620253165, "grad_norm": 0.7680474619206683, "learning_rate": 2.8617886178861792e-05, "loss": 0.4709, "step": 88 }, { "epoch": 0.36050632911392405, "grad_norm": 0.6776477307309131, "learning_rate": 2.8943089430894314e-05, "loss": 0.4669, "step": 89 }, { "epoch": 0.36455696202531646, "grad_norm": 0.815251682057846, "learning_rate": 2.926829268292683e-05, "loss": 0.4767, "step": 90 }, { "epoch": 0.36860759493670886, "grad_norm": 1.1053325576605457, "learning_rate": 2.959349593495935e-05, "loss": 0.47, "step": 91 }, { "epoch": 0.37265822784810126, "grad_norm": 0.8184813074432724, "learning_rate": 2.991869918699187e-05, "loss": 0.4702, "step": 92 }, { "epoch": 0.37670886075949367, "grad_norm": 0.9547155771990864, "learning_rate": 3.0243902439024392e-05, "loss": 0.4867, "step": 93 }, { "epoch": 0.3807594936708861, "grad_norm": 0.9804864370209758, "learning_rate": 3.056910569105692e-05, "loss": 0.4964, "step": 94 }, { "epoch": 0.3848101265822785, "grad_norm": 0.6902135897736645, "learning_rate": 3.089430894308943e-05, "loss": 0.4667, "step": 95 }, { "epoch": 0.3888607594936709, "grad_norm": 0.8250453347499305, "learning_rate": 3.1219512195121955e-05, "loss": 0.4653, "step": 96 }, { "epoch": 0.3929113924050633, "grad_norm": 0.8436526995564569, "learning_rate": 3.154471544715447e-05, "loss": 0.4663, "step": 97 }, { "epoch": 0.3969620253164557, "grad_norm": 0.8629640953087353, "learning_rate": 3.186991869918699e-05, "loss": 0.4626, "step": 98 }, { "epoch": 0.4010126582278481, "grad_norm": 0.7111377112849689, "learning_rate": 3.2195121951219514e-05, "loss": 0.4705, "step": 99 }, { "epoch": 0.4050632911392405, "grad_norm": 0.5864197048024865, "learning_rate": 3.2520325203252037e-05, "loss": 0.4839, "step": 100 }, { "epoch": 0.4091139240506329, "grad_norm": 0.8707661552502973, "learning_rate": 3.284552845528456e-05, "loss": 0.4603, "step": 101 }, { "epoch": 0.4131645569620253, "grad_norm": 0.9971842639729975, "learning_rate": 3.3170731707317074e-05, "loss": 0.4624, "step": 102 }, { "epoch": 0.4172151898734177, "grad_norm": 0.9736985410398703, "learning_rate": 3.3495934959349596e-05, "loss": 0.4609, "step": 103 }, { "epoch": 0.4212658227848101, "grad_norm": 0.808385698894197, "learning_rate": 3.382113821138212e-05, "loss": 0.4632, "step": 104 }, { "epoch": 0.4253164556962025, "grad_norm": 0.8174069617357106, "learning_rate": 3.414634146341463e-05, "loss": 0.4613, "step": 105 }, { "epoch": 0.4293670886075949, "grad_norm": 0.91562644110876, "learning_rate": 3.4471544715447155e-05, "loss": 0.4617, "step": 106 }, { "epoch": 0.43341772151898733, "grad_norm": 0.5943037599672973, "learning_rate": 3.479674796747968e-05, "loss": 0.4459, "step": 107 }, { "epoch": 0.43746835443037974, "grad_norm": 0.7651511189464997, "learning_rate": 3.51219512195122e-05, "loss": 0.477, "step": 108 }, { "epoch": 0.44151898734177214, "grad_norm": 0.6785835271707269, "learning_rate": 3.544715447154472e-05, "loss": 0.4569, "step": 109 }, { "epoch": 0.44556962025316454, "grad_norm": 0.8666114901026053, "learning_rate": 3.577235772357724e-05, "loss": 0.476, "step": 110 }, { "epoch": 0.44962025316455695, "grad_norm": 1.0968916108920448, "learning_rate": 3.609756097560976e-05, "loss": 0.4547, "step": 111 }, { "epoch": 0.45367088607594935, "grad_norm": 0.9416491308162978, "learning_rate": 3.642276422764228e-05, "loss": 0.4713, "step": 112 }, { "epoch": 0.45772151898734176, "grad_norm": 0.8212966640952902, "learning_rate": 3.67479674796748e-05, "loss": 0.466, "step": 113 }, { "epoch": 0.46177215189873416, "grad_norm": 0.6229801526578622, "learning_rate": 3.7073170731707325e-05, "loss": 0.4639, "step": 114 }, { "epoch": 0.46582278481012657, "grad_norm": 0.6446804976091918, "learning_rate": 3.739837398373984e-05, "loss": 0.4562, "step": 115 }, { "epoch": 0.46987341772151897, "grad_norm": 0.5217422486015, "learning_rate": 3.772357723577236e-05, "loss": 0.4676, "step": 116 }, { "epoch": 0.4739240506329114, "grad_norm": 0.7984579191914271, "learning_rate": 3.804878048780488e-05, "loss": 0.4698, "step": 117 }, { "epoch": 0.4779746835443038, "grad_norm": 0.6600995294289894, "learning_rate": 3.83739837398374e-05, "loss": 0.4462, "step": 118 }, { "epoch": 0.4820253164556962, "grad_norm": 0.5947175998495745, "learning_rate": 3.869918699186992e-05, "loss": 0.467, "step": 119 }, { "epoch": 0.4860759493670886, "grad_norm": 0.6805904291844809, "learning_rate": 3.9024390243902444e-05, "loss": 0.4743, "step": 120 }, { "epoch": 0.490126582278481, "grad_norm": 0.7134193041796234, "learning_rate": 3.9349593495934966e-05, "loss": 0.4588, "step": 121 }, { "epoch": 0.4941772151898734, "grad_norm": 0.7264532987980241, "learning_rate": 3.967479674796748e-05, "loss": 0.4556, "step": 122 }, { "epoch": 0.4982278481012658, "grad_norm": 0.6550418891705375, "learning_rate": 4e-05, "loss": 0.4652, "step": 123 }, { "epoch": 0.5022784810126583, "grad_norm": 0.5734473126854817, "learning_rate": 3.999991946137476e-05, "loss": 0.4599, "step": 124 }, { "epoch": 0.5063291139240507, "grad_norm": 0.8725277109465279, "learning_rate": 3.999967784614766e-05, "loss": 0.4703, "step": 125 }, { "epoch": 0.5103797468354431, "grad_norm": 0.9576288719211717, "learning_rate": 3.9999275156264656e-05, "loss": 0.4637, "step": 126 }, { "epoch": 0.5144303797468355, "grad_norm": 0.8054720039569715, "learning_rate": 3.999871139496895e-05, "loss": 0.4733, "step": 127 }, { "epoch": 0.5184810126582279, "grad_norm": 0.8096616782479703, "learning_rate": 3.9997986566800995e-05, "loss": 0.4638, "step": 128 }, { "epoch": 0.5225316455696203, "grad_norm": 0.6762703667735523, "learning_rate": 3.999710067759846e-05, "loss": 0.4636, "step": 129 }, { "epoch": 0.5265822784810127, "grad_norm": 0.8501367674156919, "learning_rate": 3.999605373449617e-05, "loss": 0.465, "step": 130 }, { "epoch": 0.5306329113924051, "grad_norm": 0.8938063043236246, "learning_rate": 3.9994845745926075e-05, "loss": 0.4586, "step": 131 }, { "epoch": 0.5346835443037975, "grad_norm": 1.0025002119845077, "learning_rate": 3.999347672161713e-05, "loss": 0.4463, "step": 132 }, { "epoch": 0.5387341772151899, "grad_norm": 0.9056045935189706, "learning_rate": 3.999194667259528e-05, "loss": 0.4453, "step": 133 }, { "epoch": 0.5427848101265823, "grad_norm": 0.7023302355345264, "learning_rate": 3.999025561118334e-05, "loss": 0.4516, "step": 134 }, { "epoch": 0.5468354430379747, "grad_norm": 0.9388653292278941, "learning_rate": 3.998840355100086e-05, "loss": 0.4569, "step": 135 }, { "epoch": 0.5508860759493671, "grad_norm": 0.8833546170458844, "learning_rate": 3.998639050696409e-05, "loss": 0.4602, "step": 136 }, { "epoch": 0.5549367088607595, "grad_norm": 0.979523608551023, "learning_rate": 3.998421649528582e-05, "loss": 0.4676, "step": 137 }, { "epoch": 0.5589873417721519, "grad_norm": 1.0476010724088443, "learning_rate": 3.9981881533475234e-05, "loss": 0.4594, "step": 138 }, { "epoch": 0.5630379746835443, "grad_norm": 0.6541736594162805, "learning_rate": 3.997938564033779e-05, "loss": 0.4534, "step": 139 }, { "epoch": 0.5670886075949367, "grad_norm": 1.0242214801689224, "learning_rate": 3.9976728835975064e-05, "loss": 0.447, "step": 140 }, { "epoch": 0.5711392405063291, "grad_norm": 0.5607147370656428, "learning_rate": 3.9973911141784605e-05, "loss": 0.455, "step": 141 }, { "epoch": 0.5751898734177215, "grad_norm": 1.0171791805574744, "learning_rate": 3.997093258045973e-05, "loss": 0.4553, "step": 142 }, { "epoch": 0.579240506329114, "grad_norm": 0.6511023975109874, "learning_rate": 3.996779317598936e-05, "loss": 0.4687, "step": 143 }, { "epoch": 0.5832911392405064, "grad_norm": 0.7032238762383006, "learning_rate": 3.996449295365782e-05, "loss": 0.4523, "step": 144 }, { "epoch": 0.5873417721518988, "grad_norm": 0.714074237272412, "learning_rate": 3.996103194004467e-05, "loss": 0.4431, "step": 145 }, { "epoch": 0.5913924050632912, "grad_norm": 0.6055413061582606, "learning_rate": 3.995741016302441e-05, "loss": 0.4479, "step": 146 }, { "epoch": 0.5954430379746836, "grad_norm": 0.7707953995790497, "learning_rate": 3.9953627651766364e-05, "loss": 0.4496, "step": 147 }, { "epoch": 0.599493670886076, "grad_norm": 0.5722176526022051, "learning_rate": 3.9949684436734325e-05, "loss": 0.4511, "step": 148 }, { "epoch": 0.6035443037974684, "grad_norm": 0.5712628062164959, "learning_rate": 3.994558054968643e-05, "loss": 0.4475, "step": 149 }, { "epoch": 0.6075949367088608, "grad_norm": 0.5420778104554757, "learning_rate": 3.994131602367481e-05, "loss": 0.4579, "step": 150 }, { "epoch": 0.6116455696202532, "grad_norm": 0.5022767697724007, "learning_rate": 3.9936890893045376e-05, "loss": 0.4519, "step": 151 }, { "epoch": 0.6156962025316456, "grad_norm": 0.6203083321533992, "learning_rate": 3.993230519343752e-05, "loss": 0.4623, "step": 152 }, { "epoch": 0.619746835443038, "grad_norm": 0.42713911368886365, "learning_rate": 3.992755896178383e-05, "loss": 0.4506, "step": 153 }, { "epoch": 0.6237974683544304, "grad_norm": 0.5683907510567702, "learning_rate": 3.992265223630981e-05, "loss": 0.4367, "step": 154 }, { "epoch": 0.6278481012658228, "grad_norm": 0.5306728181449657, "learning_rate": 3.991758505653355e-05, "loss": 0.4497, "step": 155 }, { "epoch": 0.6318987341772152, "grad_norm": 0.4935624590752313, "learning_rate": 3.991235746326543e-05, "loss": 0.4528, "step": 156 }, { "epoch": 0.6359493670886076, "grad_norm": 0.5727582988538343, "learning_rate": 3.9906969498607745e-05, "loss": 0.4537, "step": 157 }, { "epoch": 0.64, "grad_norm": 0.6287553151037129, "learning_rate": 3.990142120595444e-05, "loss": 0.4479, "step": 158 }, { "epoch": 0.6440506329113924, "grad_norm": 0.4844881829612033, "learning_rate": 3.98957126299907e-05, "loss": 0.4475, "step": 159 }, { "epoch": 0.6481012658227848, "grad_norm": 0.6957328845254983, "learning_rate": 3.9889843816692596e-05, "loss": 0.4486, "step": 160 }, { "epoch": 0.6521518987341772, "grad_norm": 0.48392327368684485, "learning_rate": 3.9883814813326766e-05, "loss": 0.4409, "step": 161 }, { "epoch": 0.6562025316455696, "grad_norm": 0.6064489104114884, "learning_rate": 3.9877625668449956e-05, "loss": 0.445, "step": 162 }, { "epoch": 0.660253164556962, "grad_norm": 0.6031291277523604, "learning_rate": 3.98712764319087e-05, "loss": 0.4372, "step": 163 }, { "epoch": 0.6643037974683544, "grad_norm": 0.4684652104607554, "learning_rate": 3.9864767154838864e-05, "loss": 0.4432, "step": 164 }, { "epoch": 0.6683544303797468, "grad_norm": 0.7307241628326727, "learning_rate": 3.9858097889665277e-05, "loss": 0.4572, "step": 165 }, { "epoch": 0.6724050632911392, "grad_norm": 0.49429843584180416, "learning_rate": 3.985126869010129e-05, "loss": 0.4535, "step": 166 }, { "epoch": 0.6764556962025317, "grad_norm": 0.5994480688772259, "learning_rate": 3.984427961114833e-05, "loss": 0.4637, "step": 167 }, { "epoch": 0.6805063291139241, "grad_norm": 0.6365419179350111, "learning_rate": 3.9837130709095475e-05, "loss": 0.4462, "step": 168 }, { "epoch": 0.6845569620253165, "grad_norm": 0.5788629116395598, "learning_rate": 3.982982204151901e-05, "loss": 0.4415, "step": 169 }, { "epoch": 0.6886075949367089, "grad_norm": 0.5054208476363627, "learning_rate": 3.982235366728193e-05, "loss": 0.4419, "step": 170 }, { "epoch": 0.6926582278481013, "grad_norm": 0.4956974441881692, "learning_rate": 3.9814725646533505e-05, "loss": 0.4343, "step": 171 }, { "epoch": 0.6967088607594937, "grad_norm": 0.4395109899445885, "learning_rate": 3.9806938040708746e-05, "loss": 0.4386, "step": 172 }, { "epoch": 0.7007594936708861, "grad_norm": 0.4326073917405354, "learning_rate": 3.9798990912527976e-05, "loss": 0.4459, "step": 173 }, { "epoch": 0.7048101265822785, "grad_norm": 0.414464866864531, "learning_rate": 3.979088432599627e-05, "loss": 0.4255, "step": 174 }, { "epoch": 0.7088607594936709, "grad_norm": 0.4312900990588482, "learning_rate": 3.9782618346402964e-05, "loss": 0.4307, "step": 175 }, { "epoch": 0.7129113924050633, "grad_norm": 0.49605724896980813, "learning_rate": 3.977419304032111e-05, "loss": 0.446, "step": 176 }, { "epoch": 0.7169620253164557, "grad_norm": 0.5099258526069576, "learning_rate": 3.976560847560697e-05, "loss": 0.4512, "step": 177 }, { "epoch": 0.7210126582278481, "grad_norm": 0.48661939473122184, "learning_rate": 3.9756864721399456e-05, "loss": 0.4355, "step": 178 }, { "epoch": 0.7250632911392405, "grad_norm": 0.3952935591626611, "learning_rate": 3.974796184811956e-05, "loss": 0.4318, "step": 179 }, { "epoch": 0.7291139240506329, "grad_norm": 0.42979125370965, "learning_rate": 3.973889992746979e-05, "loss": 0.4349, "step": 180 }, { "epoch": 0.7331645569620253, "grad_norm": 0.4724870191565255, "learning_rate": 3.972967903243361e-05, "loss": 0.427, "step": 181 }, { "epoch": 0.7372151898734177, "grad_norm": 0.46543120887123457, "learning_rate": 3.972029923727486e-05, "loss": 0.4328, "step": 182 }, { "epoch": 0.7412658227848101, "grad_norm": 0.37700441617007396, "learning_rate": 3.971076061753709e-05, "loss": 0.431, "step": 183 }, { "epoch": 0.7453164556962025, "grad_norm": 0.5858561369992502, "learning_rate": 3.9701063250043066e-05, "loss": 0.4354, "step": 184 }, { "epoch": 0.7493670886075949, "grad_norm": 0.5047085533700139, "learning_rate": 3.969120721289402e-05, "loss": 0.4378, "step": 185 }, { "epoch": 0.7534177215189873, "grad_norm": 0.45609650193064566, "learning_rate": 3.9681192585469146e-05, "loss": 0.4367, "step": 186 }, { "epoch": 0.7574683544303797, "grad_norm": 0.6732437807284691, "learning_rate": 3.9671019448424865e-05, "loss": 0.4287, "step": 187 }, { "epoch": 0.7615189873417721, "grad_norm": 0.4847693553521699, "learning_rate": 3.966068788369422e-05, "loss": 0.4341, "step": 188 }, { "epoch": 0.7655696202531646, "grad_norm": 0.4579930148591227, "learning_rate": 3.965019797448622e-05, "loss": 0.4471, "step": 189 }, { "epoch": 0.769620253164557, "grad_norm": 0.49024467923797777, "learning_rate": 3.963954980528515e-05, "loss": 0.4367, "step": 190 }, { "epoch": 0.7736708860759494, "grad_norm": 0.4850725266981783, "learning_rate": 3.9628743461849905e-05, "loss": 0.4269, "step": 191 }, { "epoch": 0.7777215189873418, "grad_norm": 0.5331838432015377, "learning_rate": 3.961777903121329e-05, "loss": 0.4379, "step": 192 }, { "epoch": 0.7817721518987342, "grad_norm": 0.47228331445968147, "learning_rate": 3.960665660168131e-05, "loss": 0.4366, "step": 193 }, { "epoch": 0.7858227848101266, "grad_norm": 0.5086341444568176, "learning_rate": 3.9595376262832485e-05, "loss": 0.4372, "step": 194 }, { "epoch": 0.789873417721519, "grad_norm": 0.7187148070313548, "learning_rate": 3.9583938105517127e-05, "loss": 0.445, "step": 195 }, { "epoch": 0.7939240506329114, "grad_norm": 0.563246522537201, "learning_rate": 3.957234222185657e-05, "loss": 0.4464, "step": 196 }, { "epoch": 0.7979746835443038, "grad_norm": 0.512191969890331, "learning_rate": 3.9560588705242474e-05, "loss": 0.4404, "step": 197 }, { "epoch": 0.8020253164556962, "grad_norm": 0.5126735366424823, "learning_rate": 3.954867765033605e-05, "loss": 0.4411, "step": 198 }, { "epoch": 0.8060759493670886, "grad_norm": 0.43726695949078676, "learning_rate": 3.953660915306728e-05, "loss": 0.4329, "step": 199 }, { "epoch": 0.810126582278481, "grad_norm": 0.5009019282893528, "learning_rate": 3.952438331063419e-05, "loss": 0.4351, "step": 200 }, { "epoch": 0.8141772151898734, "grad_norm": 0.48096981879883305, "learning_rate": 3.951200022150205e-05, "loss": 0.4375, "step": 201 }, { "epoch": 0.8182278481012658, "grad_norm": 0.4512410521780731, "learning_rate": 3.949945998540253e-05, "loss": 0.438, "step": 202 }, { "epoch": 0.8222784810126582, "grad_norm": 0.5921148771843654, "learning_rate": 3.9486762703332993e-05, "loss": 0.4368, "step": 203 }, { "epoch": 0.8263291139240506, "grad_norm": 0.60000580388586, "learning_rate": 3.947390847755559e-05, "loss": 0.4402, "step": 204 }, { "epoch": 0.830379746835443, "grad_norm": 0.42658571030430853, "learning_rate": 3.946089741159648e-05, "loss": 0.4282, "step": 205 }, { "epoch": 0.8344303797468354, "grad_norm": 0.6284288574981501, "learning_rate": 3.944772961024501e-05, "loss": 0.4374, "step": 206 }, { "epoch": 0.8384810126582278, "grad_norm": 0.6225685085770342, "learning_rate": 3.943440517955285e-05, "loss": 0.4484, "step": 207 }, { "epoch": 0.8425316455696202, "grad_norm": 0.5689414946354177, "learning_rate": 3.9420924226833126e-05, "loss": 0.4382, "step": 208 }, { "epoch": 0.8465822784810126, "grad_norm": 0.5664565465953145, "learning_rate": 3.9407286860659566e-05, "loss": 0.4264, "step": 209 }, { "epoch": 0.850632911392405, "grad_norm": 0.4984082505168923, "learning_rate": 3.9393493190865657e-05, "loss": 0.4365, "step": 210 }, { "epoch": 0.8546835443037974, "grad_norm": 0.5377327619795564, "learning_rate": 3.937954332854371e-05, "loss": 0.4401, "step": 211 }, { "epoch": 0.8587341772151899, "grad_norm": 0.5060745433122842, "learning_rate": 3.9365437386044016e-05, "loss": 0.4447, "step": 212 }, { "epoch": 0.8627848101265823, "grad_norm": 0.46871667629426045, "learning_rate": 3.935117547697387e-05, "loss": 0.4479, "step": 213 }, { "epoch": 0.8668354430379747, "grad_norm": 0.4339712435858941, "learning_rate": 3.933675771619675e-05, "loss": 0.4355, "step": 214 }, { "epoch": 0.8708860759493671, "grad_norm": 0.47828292157275426, "learning_rate": 3.932218421983131e-05, "loss": 0.4234, "step": 215 }, { "epoch": 0.8749367088607595, "grad_norm": 0.5168772367783878, "learning_rate": 3.9307455105250484e-05, "loss": 0.4316, "step": 216 }, { "epoch": 0.8789873417721519, "grad_norm": 0.5058209615190657, "learning_rate": 3.929257049108054e-05, "loss": 0.4273, "step": 217 }, { "epoch": 0.8830379746835443, "grad_norm": 0.5318364149463346, "learning_rate": 3.927753049720011e-05, "loss": 0.4304, "step": 218 }, { "epoch": 0.8870886075949367, "grad_norm": 0.5490621108110387, "learning_rate": 3.9262335244739234e-05, "loss": 0.4366, "step": 219 }, { "epoch": 0.8911392405063291, "grad_norm": 0.5562866534257679, "learning_rate": 3.92469848560784e-05, "loss": 0.4202, "step": 220 }, { "epoch": 0.8951898734177215, "grad_norm": 0.45414041346832484, "learning_rate": 3.923147945484751e-05, "loss": 0.4349, "step": 221 }, { "epoch": 0.8992405063291139, "grad_norm": 0.5475510193939906, "learning_rate": 3.9215819165924956e-05, "loss": 0.4291, "step": 222 }, { "epoch": 0.9032911392405063, "grad_norm": 0.5186033891089277, "learning_rate": 3.920000411543654e-05, "loss": 0.4369, "step": 223 }, { "epoch": 0.9073417721518987, "grad_norm": 0.5127676210230074, "learning_rate": 3.9184034430754495e-05, "loss": 0.4239, "step": 224 }, { "epoch": 0.9113924050632911, "grad_norm": 0.522778598865623, "learning_rate": 3.916791024049648e-05, "loss": 0.4329, "step": 225 }, { "epoch": 0.9154430379746835, "grad_norm": 0.3775981397912477, "learning_rate": 3.91516316745245e-05, "loss": 0.4292, "step": 226 }, { "epoch": 0.9194936708860759, "grad_norm": 0.45759979482975444, "learning_rate": 3.913519886394389e-05, "loss": 0.4315, "step": 227 }, { "epoch": 0.9235443037974683, "grad_norm": 0.43655910120895725, "learning_rate": 3.911861194110225e-05, "loss": 0.442, "step": 228 }, { "epoch": 0.9275949367088607, "grad_norm": 0.43107471209021536, "learning_rate": 3.910187103958837e-05, "loss": 0.4301, "step": 229 }, { "epoch": 0.9316455696202531, "grad_norm": 0.623792378078441, "learning_rate": 3.908497629423117e-05, "loss": 0.4317, "step": 230 }, { "epoch": 0.9356962025316455, "grad_norm": 0.7004675700654163, "learning_rate": 3.9067927841098614e-05, "loss": 0.4281, "step": 231 }, { "epoch": 0.9397468354430379, "grad_norm": 0.463801671526994, "learning_rate": 3.9050725817496594e-05, "loss": 0.4413, "step": 232 }, { "epoch": 0.9437974683544303, "grad_norm": 0.4749701455851151, "learning_rate": 3.9033370361967844e-05, "loss": 0.4325, "step": 233 }, { "epoch": 0.9478481012658228, "grad_norm": 0.4477281376310566, "learning_rate": 3.901586161429081e-05, "loss": 0.4445, "step": 234 }, { "epoch": 0.9518987341772152, "grad_norm": 0.44344804589117187, "learning_rate": 3.8998199715478545e-05, "loss": 0.4149, "step": 235 }, { "epoch": 0.9559493670886076, "grad_norm": 0.3867476129368342, "learning_rate": 3.8980384807777564e-05, "loss": 0.432, "step": 236 }, { "epoch": 0.96, "grad_norm": 0.589039454629225, "learning_rate": 3.896241703466667e-05, "loss": 0.4433, "step": 237 }, { "epoch": 0.9640506329113924, "grad_norm": 0.5719898396786502, "learning_rate": 3.894429654085585e-05, "loss": 0.4397, "step": 238 }, { "epoch": 0.9681012658227848, "grad_norm": 0.37511213847591884, "learning_rate": 3.892602347228505e-05, "loss": 0.4313, "step": 239 }, { "epoch": 0.9721518987341772, "grad_norm": 0.5039074501955708, "learning_rate": 3.890759797612307e-05, "loss": 0.419, "step": 240 }, { "epoch": 0.9762025316455696, "grad_norm": 0.5215692244318336, "learning_rate": 3.888902020076632e-05, "loss": 0.4215, "step": 241 }, { "epoch": 0.980253164556962, "grad_norm": 0.5431174987749691, "learning_rate": 3.887029029583764e-05, "loss": 0.4312, "step": 242 }, { "epoch": 0.9843037974683544, "grad_norm": 0.5462461056429732, "learning_rate": 3.8851408412185125e-05, "loss": 0.4163, "step": 243 }, { "epoch": 0.9883544303797468, "grad_norm": 0.37412780870393403, "learning_rate": 3.8832374701880855e-05, "loss": 0.4179, "step": 244 }, { "epoch": 0.9924050632911392, "grad_norm": 0.44891381067086145, "learning_rate": 3.881318931821972e-05, "loss": 0.4303, "step": 245 }, { "epoch": 0.9964556962025316, "grad_norm": 0.49167898487216166, "learning_rate": 3.879385241571817e-05, "loss": 0.4221, "step": 246 }, { "epoch": 1.000506329113924, "grad_norm": 0.4713315021013112, "learning_rate": 3.8774364150112955e-05, "loss": 0.4284, "step": 247 }, { "epoch": 1.0045569620253165, "grad_norm": 0.47659116537263085, "learning_rate": 3.8754724678359884e-05, "loss": 0.3939, "step": 248 }, { "epoch": 1.0086075949367088, "grad_norm": 0.5731334880273113, "learning_rate": 3.873493415863256e-05, "loss": 0.3967, "step": 249 }, { "epoch": 1.0126582278481013, "grad_norm": 0.6695696143177428, "learning_rate": 3.871499275032111e-05, "loss": 0.394, "step": 250 }, { "epoch": 1.0167088607594936, "grad_norm": 0.6750551622409886, "learning_rate": 3.869490061403091e-05, "loss": 0.3978, "step": 251 }, { "epoch": 1.0207594936708861, "grad_norm": 0.5956354234005682, "learning_rate": 3.867465791158124e-05, "loss": 0.3819, "step": 252 }, { "epoch": 1.0248101265822784, "grad_norm": 0.42960027513614296, "learning_rate": 3.865426480600407e-05, "loss": 0.4008, "step": 253 }, { "epoch": 1.028860759493671, "grad_norm": 0.590894196252442, "learning_rate": 3.863372146154264e-05, "loss": 0.3966, "step": 254 }, { "epoch": 1.0329113924050632, "grad_norm": 0.6311317411938507, "learning_rate": 3.861302804365024e-05, "loss": 0.4016, "step": 255 }, { "epoch": 1.0369620253164558, "grad_norm": 0.5071875905390709, "learning_rate": 3.85921847189888e-05, "loss": 0.3928, "step": 256 }, { "epoch": 1.041012658227848, "grad_norm": 0.47635780085218166, "learning_rate": 3.85711916554276e-05, "loss": 0.3969, "step": 257 }, { "epoch": 1.0450632911392406, "grad_norm": 0.5880022226972057, "learning_rate": 3.85500490220419e-05, "loss": 0.3931, "step": 258 }, { "epoch": 1.0491139240506329, "grad_norm": 0.5314413779058397, "learning_rate": 3.852875698911154e-05, "loss": 0.4052, "step": 259 }, { "epoch": 1.0531645569620254, "grad_norm": 0.4607791429689732, "learning_rate": 3.850731572811963e-05, "loss": 0.3964, "step": 260 }, { "epoch": 1.0572151898734177, "grad_norm": 0.41501177741157375, "learning_rate": 3.848572541175116e-05, "loss": 0.3981, "step": 261 }, { "epoch": 1.0612658227848102, "grad_norm": 0.4229362709952775, "learning_rate": 3.846398621389154e-05, "loss": 0.3876, "step": 262 }, { "epoch": 1.0653164556962025, "grad_norm": 0.530867850446378, "learning_rate": 3.84420983096253e-05, "loss": 0.3845, "step": 263 }, { "epoch": 1.069367088607595, "grad_norm": 0.4156118154094799, "learning_rate": 3.8420061875234606e-05, "loss": 0.3771, "step": 264 }, { "epoch": 1.0734177215189873, "grad_norm": 0.4637619400712209, "learning_rate": 3.839787708819787e-05, "loss": 0.3903, "step": 265 }, { "epoch": 1.0774683544303798, "grad_norm": 0.4632659545437359, "learning_rate": 3.8375544127188325e-05, "loss": 0.3853, "step": 266 }, { "epoch": 1.081518987341772, "grad_norm": 0.40885480616835373, "learning_rate": 3.8353063172072564e-05, "loss": 0.3851, "step": 267 }, { "epoch": 1.0855696202531646, "grad_norm": 0.47199151063389894, "learning_rate": 3.8330434403909105e-05, "loss": 0.3866, "step": 268 }, { "epoch": 1.089620253164557, "grad_norm": 0.3978303666376786, "learning_rate": 3.8307658004946934e-05, "loss": 0.4018, "step": 269 }, { "epoch": 1.0936708860759494, "grad_norm": 0.49731021695801936, "learning_rate": 3.8284734158624046e-05, "loss": 0.3961, "step": 270 }, { "epoch": 1.0977215189873417, "grad_norm": 0.5068254279064742, "learning_rate": 3.826166304956594e-05, "loss": 0.3801, "step": 271 }, { "epoch": 1.1017721518987342, "grad_norm": 0.4232494422201747, "learning_rate": 3.8238444863584164e-05, "loss": 0.3966, "step": 272 }, { "epoch": 1.1058227848101265, "grad_norm": 0.4861357218203612, "learning_rate": 3.821507978767479e-05, "loss": 0.401, "step": 273 }, { "epoch": 1.109873417721519, "grad_norm": 0.4708272605524651, "learning_rate": 3.819156801001693e-05, "loss": 0.3883, "step": 274 }, { "epoch": 1.1139240506329113, "grad_norm": 0.38067456553843, "learning_rate": 3.816790971997121e-05, "loss": 0.3891, "step": 275 }, { "epoch": 1.1179746835443038, "grad_norm": 0.4860023114772295, "learning_rate": 3.8144105108078246e-05, "loss": 0.3836, "step": 276 }, { "epoch": 1.1220253164556961, "grad_norm": 0.4956058378905689, "learning_rate": 3.81201543660571e-05, "loss": 0.382, "step": 277 }, { "epoch": 1.1260759493670887, "grad_norm": 0.4386785450186426, "learning_rate": 3.809605768680377e-05, "loss": 0.3967, "step": 278 }, { "epoch": 1.130126582278481, "grad_norm": 0.4667516995319242, "learning_rate": 3.807181526438958e-05, "loss": 0.3845, "step": 279 }, { "epoch": 1.1341772151898735, "grad_norm": 0.36837912492807057, "learning_rate": 3.8047427294059697e-05, "loss": 0.3878, "step": 280 }, { "epoch": 1.1382278481012658, "grad_norm": 0.42619322052698216, "learning_rate": 3.802289397223145e-05, "loss": 0.3926, "step": 281 }, { "epoch": 1.1422784810126583, "grad_norm": 0.4487448315407799, "learning_rate": 3.7998215496492854e-05, "loss": 0.401, "step": 282 }, { "epoch": 1.1463291139240506, "grad_norm": 0.443451499416285, "learning_rate": 3.797339206560096e-05, "loss": 0.3841, "step": 283 }, { "epoch": 1.150379746835443, "grad_norm": 0.41170343592239467, "learning_rate": 3.794842387948027e-05, "loss": 0.394, "step": 284 }, { "epoch": 1.1544303797468354, "grad_norm": 0.4843180749606831, "learning_rate": 3.7923311139221114e-05, "loss": 0.3904, "step": 285 }, { "epoch": 1.158481012658228, "grad_norm": 0.41722582857813634, "learning_rate": 3.7898054047078054e-05, "loss": 0.4057, "step": 286 }, { "epoch": 1.1625316455696202, "grad_norm": 0.38004994736709635, "learning_rate": 3.787265280646825e-05, "loss": 0.3871, "step": 287 }, { "epoch": 1.1665822784810127, "grad_norm": 0.42848593618753666, "learning_rate": 3.7847107621969786e-05, "loss": 0.3964, "step": 288 }, { "epoch": 1.170632911392405, "grad_norm": 0.46566090563767365, "learning_rate": 3.7821418699320064e-05, "loss": 0.3869, "step": 289 }, { "epoch": 1.1746835443037975, "grad_norm": 0.45510602900956615, "learning_rate": 3.7795586245414145e-05, "loss": 0.3796, "step": 290 }, { "epoch": 1.1787341772151898, "grad_norm": 0.38493966612230357, "learning_rate": 3.776961046830306e-05, "loss": 0.3735, "step": 291 }, { "epoch": 1.1827848101265823, "grad_norm": 0.5764696608589822, "learning_rate": 3.774349157719215e-05, "loss": 0.3867, "step": 292 }, { "epoch": 1.1868354430379746, "grad_norm": 0.40698154499223577, "learning_rate": 3.7717229782439365e-05, "loss": 0.3999, "step": 293 }, { "epoch": 1.1908860759493671, "grad_norm": 0.4476754372677214, "learning_rate": 3.769082529555359e-05, "loss": 0.3881, "step": 294 }, { "epoch": 1.1949367088607594, "grad_norm": 0.37396895720482226, "learning_rate": 3.766427832919294e-05, "loss": 0.3857, "step": 295 }, { "epoch": 1.198987341772152, "grad_norm": 0.4591866778004681, "learning_rate": 3.7637589097163024e-05, "loss": 0.3893, "step": 296 }, { "epoch": 1.2030379746835442, "grad_norm": 0.43920921423011444, "learning_rate": 3.761075781441526e-05, "loss": 0.3964, "step": 297 }, { "epoch": 1.2070886075949367, "grad_norm": 0.3806616445698244, "learning_rate": 3.75837846970451e-05, "loss": 0.3809, "step": 298 }, { "epoch": 1.211139240506329, "grad_norm": 0.49778614240990804, "learning_rate": 3.755666996229032e-05, "loss": 0.3839, "step": 299 }, { "epoch": 1.2151898734177216, "grad_norm": 0.37755222719819215, "learning_rate": 3.752941382852927e-05, "loss": 0.3944, "step": 300 }, { "epoch": 1.2192405063291138, "grad_norm": 0.4658175472939277, "learning_rate": 3.7502016515279115e-05, "loss": 0.4026, "step": 301 }, { "epoch": 1.2232911392405064, "grad_norm": 0.4261661542282853, "learning_rate": 3.7474478243194043e-05, "loss": 0.3905, "step": 302 }, { "epoch": 1.2273417721518987, "grad_norm": 0.38310188563564906, "learning_rate": 3.744679923406351e-05, "loss": 0.3839, "step": 303 }, { "epoch": 1.2313924050632912, "grad_norm": 0.4876950902380557, "learning_rate": 3.741897971081043e-05, "loss": 0.3965, "step": 304 }, { "epoch": 1.2354430379746835, "grad_norm": 0.42767900126834996, "learning_rate": 3.739101989748946e-05, "loss": 0.3875, "step": 305 }, { "epoch": 1.239493670886076, "grad_norm": 0.3751868978075541, "learning_rate": 3.7362920019285066e-05, "loss": 0.3893, "step": 306 }, { "epoch": 1.2435443037974683, "grad_norm": 0.4087831538551082, "learning_rate": 3.73346803025098e-05, "loss": 0.3961, "step": 307 }, { "epoch": 1.2475949367088608, "grad_norm": 0.42942127619136033, "learning_rate": 3.730630097460247e-05, "loss": 0.3905, "step": 308 }, { "epoch": 1.251645569620253, "grad_norm": 0.4836977779780299, "learning_rate": 3.727778226412628e-05, "loss": 0.3852, "step": 309 }, { "epoch": 1.2556962025316456, "grad_norm": 0.4208646455964783, "learning_rate": 3.7249124400767006e-05, "loss": 0.3884, "step": 310 }, { "epoch": 1.259746835443038, "grad_norm": 0.5055257372612614, "learning_rate": 3.722032761533114e-05, "loss": 0.3953, "step": 311 }, { "epoch": 1.2637974683544304, "grad_norm": 0.5017255724984082, "learning_rate": 3.719139213974403e-05, "loss": 0.3938, "step": 312 }, { "epoch": 1.2678481012658227, "grad_norm": 0.3974655726630842, "learning_rate": 3.7162318207048006e-05, "loss": 0.3908, "step": 313 }, { "epoch": 1.2718987341772152, "grad_norm": 0.4269055213540897, "learning_rate": 3.713310605140055e-05, "loss": 0.392, "step": 314 }, { "epoch": 1.2759493670886077, "grad_norm": 0.35546120983535684, "learning_rate": 3.710375590807233e-05, "loss": 0.3886, "step": 315 }, { "epoch": 1.28, "grad_norm": 0.46667779302939016, "learning_rate": 3.7074268013445365e-05, "loss": 0.3889, "step": 316 }, { "epoch": 1.2840506329113923, "grad_norm": 0.5333939110595945, "learning_rate": 3.7044642605011114e-05, "loss": 0.3949, "step": 317 }, { "epoch": 1.2881012658227848, "grad_norm": 0.4844418084266881, "learning_rate": 3.701487992136854e-05, "loss": 0.3925, "step": 318 }, { "epoch": 1.2921518987341774, "grad_norm": 0.36213942336121513, "learning_rate": 3.69849802022222e-05, "loss": 0.3871, "step": 319 }, { "epoch": 1.2962025316455696, "grad_norm": 0.44803501051308864, "learning_rate": 3.6954943688380334e-05, "loss": 0.3896, "step": 320 }, { "epoch": 1.300253164556962, "grad_norm": 0.5280135830095172, "learning_rate": 3.692477062175289e-05, "loss": 0.3833, "step": 321 }, { "epoch": 1.3043037974683545, "grad_norm": 0.4041362671262719, "learning_rate": 3.689446124534958e-05, "loss": 0.389, "step": 322 }, { "epoch": 1.308354430379747, "grad_norm": 0.4228343734760428, "learning_rate": 3.686401580327799e-05, "loss": 0.3911, "step": 323 }, { "epoch": 1.3124050632911393, "grad_norm": 0.4580353212591961, "learning_rate": 3.683343454074149e-05, "loss": 0.4025, "step": 324 }, { "epoch": 1.3164556962025316, "grad_norm": 0.38603628141331153, "learning_rate": 3.6802717704037386e-05, "loss": 0.3937, "step": 325 }, { "epoch": 1.320506329113924, "grad_norm": 0.412759236854437, "learning_rate": 3.6771865540554855e-05, "loss": 0.3879, "step": 326 }, { "epoch": 1.3245569620253166, "grad_norm": 0.5090827448013643, "learning_rate": 3.674087829877297e-05, "loss": 0.3892, "step": 327 }, { "epoch": 1.3286075949367089, "grad_norm": 0.42083076334362945, "learning_rate": 3.6709756228258735e-05, "loss": 0.38, "step": 328 }, { "epoch": 1.3326582278481012, "grad_norm": 0.3556940339429273, "learning_rate": 3.667849957966501e-05, "loss": 0.3868, "step": 329 }, { "epoch": 1.3367088607594937, "grad_norm": 0.5186859198827286, "learning_rate": 3.6647108604728546e-05, "loss": 0.3949, "step": 330 }, { "epoch": 1.3407594936708862, "grad_norm": 0.5675289692280935, "learning_rate": 3.661558355626795e-05, "loss": 0.4003, "step": 331 }, { "epoch": 1.3448101265822785, "grad_norm": 0.39546171616127956, "learning_rate": 3.658392468818163e-05, "loss": 0.3799, "step": 332 }, { "epoch": 1.3488607594936708, "grad_norm": 0.4700850518563118, "learning_rate": 3.655213225544574e-05, "loss": 0.3863, "step": 333 }, { "epoch": 1.3529113924050633, "grad_norm": 0.4242085641101108, "learning_rate": 3.652020651411218e-05, "loss": 0.3795, "step": 334 }, { "epoch": 1.3569620253164558, "grad_norm": 0.47584594840975536, "learning_rate": 3.6488147721306474e-05, "loss": 0.3789, "step": 335 }, { "epoch": 1.3610126582278481, "grad_norm": 0.4642874410343589, "learning_rate": 3.645595613522574e-05, "loss": 0.3991, "step": 336 }, { "epoch": 1.3650632911392404, "grad_norm": 0.4039508826467368, "learning_rate": 3.642363201513657e-05, "loss": 0.3923, "step": 337 }, { "epoch": 1.369113924050633, "grad_norm": 0.4477524262377764, "learning_rate": 3.6391175621373006e-05, "loss": 0.3902, "step": 338 }, { "epoch": 1.3731645569620254, "grad_norm": 0.4807613764703749, "learning_rate": 3.6358587215334355e-05, "loss": 0.3847, "step": 339 }, { "epoch": 1.3772151898734177, "grad_norm": 0.4306008069674042, "learning_rate": 3.632586705948318e-05, "loss": 0.3857, "step": 340 }, { "epoch": 1.38126582278481, "grad_norm": 0.43694590729574123, "learning_rate": 3.629301541734311e-05, "loss": 0.3858, "step": 341 }, { "epoch": 1.3853164556962025, "grad_norm": 0.35361060959472673, "learning_rate": 3.626003255349676e-05, "loss": 0.4002, "step": 342 }, { "epoch": 1.389367088607595, "grad_norm": 0.46991252831573954, "learning_rate": 3.622691873358357e-05, "loss": 0.3989, "step": 343 }, { "epoch": 1.3934177215189874, "grad_norm": 0.40076094976699655, "learning_rate": 3.61936742242977e-05, "loss": 0.3881, "step": 344 }, { "epoch": 1.3974683544303796, "grad_norm": 0.4128148657331585, "learning_rate": 3.6160299293385864e-05, "loss": 0.39, "step": 345 }, { "epoch": 1.4015189873417722, "grad_norm": 0.43180714476694426, "learning_rate": 3.612679420964516e-05, "loss": 0.3814, "step": 346 }, { "epoch": 1.4055696202531647, "grad_norm": 0.368507714709271, "learning_rate": 3.609315924292092e-05, "loss": 0.4037, "step": 347 }, { "epoch": 1.409620253164557, "grad_norm": 0.43076118438444816, "learning_rate": 3.6059394664104554e-05, "loss": 0.3724, "step": 348 }, { "epoch": 1.4136708860759493, "grad_norm": 0.3044189735474016, "learning_rate": 3.602550074513133e-05, "loss": 0.3832, "step": 349 }, { "epoch": 1.4177215189873418, "grad_norm": 0.40368486397069203, "learning_rate": 3.599147775897822e-05, "loss": 0.3795, "step": 350 }, { "epoch": 1.4217721518987343, "grad_norm": 0.3431129512773974, "learning_rate": 3.595732597966167e-05, "loss": 0.3939, "step": 351 }, { "epoch": 1.4258227848101266, "grad_norm": 0.464525971579453, "learning_rate": 3.592304568223542e-05, "loss": 0.3969, "step": 352 }, { "epoch": 1.4298734177215189, "grad_norm": 0.5156121107550087, "learning_rate": 3.588863714278826e-05, "loss": 0.3926, "step": 353 }, { "epoch": 1.4339240506329114, "grad_norm": 0.4039797749290497, "learning_rate": 3.585410063844186e-05, "loss": 0.3937, "step": 354 }, { "epoch": 1.437974683544304, "grad_norm": 0.37854085760424805, "learning_rate": 3.581943644734846e-05, "loss": 0.3912, "step": 355 }, { "epoch": 1.4420253164556962, "grad_norm": 0.4607163364641137, "learning_rate": 3.578464484868869e-05, "loss": 0.3934, "step": 356 }, { "epoch": 1.4460759493670885, "grad_norm": 0.514835036528387, "learning_rate": 3.5749726122669316e-05, "loss": 0.3909, "step": 357 }, { "epoch": 1.450126582278481, "grad_norm": 0.38048268185403256, "learning_rate": 3.5714680550520943e-05, "loss": 0.3924, "step": 358 }, { "epoch": 1.4541772151898735, "grad_norm": 0.3398724155446108, "learning_rate": 3.5679508414495794e-05, "loss": 0.3924, "step": 359 }, { "epoch": 1.4582278481012658, "grad_norm": 0.42837050083372996, "learning_rate": 3.564420999786543e-05, "loss": 0.3838, "step": 360 }, { "epoch": 1.4622784810126581, "grad_norm": 0.39488371119564286, "learning_rate": 3.560878558491842e-05, "loss": 0.3807, "step": 361 }, { "epoch": 1.4663291139240506, "grad_norm": 0.33963476749846483, "learning_rate": 3.5573235460958145e-05, "loss": 0.3809, "step": 362 }, { "epoch": 1.4703797468354431, "grad_norm": 0.47739376022886754, "learning_rate": 3.553755991230039e-05, "loss": 0.3868, "step": 363 }, { "epoch": 1.4744303797468354, "grad_norm": 0.3525788705794152, "learning_rate": 3.5501759226271144e-05, "loss": 0.3812, "step": 364 }, { "epoch": 1.4784810126582277, "grad_norm": 0.42333753597398216, "learning_rate": 3.546583369120419e-05, "loss": 0.3964, "step": 365 }, { "epoch": 1.4825316455696202, "grad_norm": 0.41577773387495476, "learning_rate": 3.5429783596438864e-05, "loss": 0.3893, "step": 366 }, { "epoch": 1.4865822784810128, "grad_norm": 0.42225426664806087, "learning_rate": 3.539360923231766e-05, "loss": 0.3879, "step": 367 }, { "epoch": 1.490632911392405, "grad_norm": 0.42871945107719955, "learning_rate": 3.535731089018394e-05, "loss": 0.3809, "step": 368 }, { "epoch": 1.4946835443037974, "grad_norm": 0.4060931170409786, "learning_rate": 3.532088886237956e-05, "loss": 0.3823, "step": 369 }, { "epoch": 1.4987341772151899, "grad_norm": 0.39664720016132193, "learning_rate": 3.528434344224253e-05, "loss": 0.3863, "step": 370 }, { "epoch": 1.5027848101265824, "grad_norm": 0.43570954098322034, "learning_rate": 3.524767492410464e-05, "loss": 0.3908, "step": 371 }, { "epoch": 1.5068354430379747, "grad_norm": 0.40327938696344773, "learning_rate": 3.521088360328908e-05, "loss": 0.3876, "step": 372 }, { "epoch": 1.510886075949367, "grad_norm": 0.5615512351212479, "learning_rate": 3.517396977610811e-05, "loss": 0.3853, "step": 373 }, { "epoch": 1.5149367088607595, "grad_norm": 0.3756956802198135, "learning_rate": 3.5136933739860595e-05, "loss": 0.3908, "step": 374 }, { "epoch": 1.518987341772152, "grad_norm": 0.4169735778527404, "learning_rate": 3.509977579282971e-05, "loss": 0.3848, "step": 375 }, { "epoch": 1.5230379746835443, "grad_norm": 0.47894257434249604, "learning_rate": 3.5062496234280424e-05, "loss": 0.3883, "step": 376 }, { "epoch": 1.5270886075949366, "grad_norm": 0.39852838848542554, "learning_rate": 3.502509536445719e-05, "loss": 0.3918, "step": 377 }, { "epoch": 1.531139240506329, "grad_norm": 0.46050778673504633, "learning_rate": 3.498757348458147e-05, "loss": 0.3865, "step": 378 }, { "epoch": 1.5351898734177216, "grad_norm": 0.4229637014725358, "learning_rate": 3.4949930896849324e-05, "loss": 0.3967, "step": 379 }, { "epoch": 1.539240506329114, "grad_norm": 0.3809729391283922, "learning_rate": 3.491216790442899e-05, "loss": 0.3905, "step": 380 }, { "epoch": 1.5432911392405062, "grad_norm": 0.473359970112973, "learning_rate": 3.487428481145839e-05, "loss": 0.389, "step": 381 }, { "epoch": 1.5473417721518987, "grad_norm": 0.34492119088597145, "learning_rate": 3.483628192304278e-05, "loss": 0.387, "step": 382 }, { "epoch": 1.5513924050632912, "grad_norm": 0.3910415371971755, "learning_rate": 3.479815954525219e-05, "loss": 0.3913, "step": 383 }, { "epoch": 1.5554430379746835, "grad_norm": 0.353607496501162, "learning_rate": 3.475991798511899e-05, "loss": 0.3825, "step": 384 }, { "epoch": 1.5594936708860758, "grad_norm": 0.39662399333639325, "learning_rate": 3.4721557550635464e-05, "loss": 0.388, "step": 385 }, { "epoch": 1.5635443037974683, "grad_norm": 0.35819857328644394, "learning_rate": 3.468307855075128e-05, "loss": 0.3895, "step": 386 }, { "epoch": 1.5675949367088609, "grad_norm": 0.35273845677134286, "learning_rate": 3.4644481295371005e-05, "loss": 0.3743, "step": 387 }, { "epoch": 1.5716455696202531, "grad_norm": 0.30770276358525805, "learning_rate": 3.460576609535163e-05, "loss": 0.3901, "step": 388 }, { "epoch": 1.5756962025316454, "grad_norm": 0.3889883527040115, "learning_rate": 3.456693326250006e-05, "loss": 0.3876, "step": 389 }, { "epoch": 1.579746835443038, "grad_norm": 0.35201487291302624, "learning_rate": 3.452798310957058e-05, "loss": 0.3809, "step": 390 }, { "epoch": 1.5837974683544305, "grad_norm": 0.32230371388237095, "learning_rate": 3.4488915950262386e-05, "loss": 0.3803, "step": 391 }, { "epoch": 1.5878481012658228, "grad_norm": 0.34566972204865665, "learning_rate": 3.4449732099216985e-05, "loss": 0.3863, "step": 392 }, { "epoch": 1.591898734177215, "grad_norm": 0.33450425003280965, "learning_rate": 3.441043187201574e-05, "loss": 0.4004, "step": 393 }, { "epoch": 1.5959493670886076, "grad_norm": 0.3695283702426974, "learning_rate": 3.437101558517728e-05, "loss": 0.3923, "step": 394 }, { "epoch": 1.6, "grad_norm": 0.38815145903900733, "learning_rate": 3.433148355615496e-05, "loss": 0.3821, "step": 395 }, { "epoch": 1.6040506329113924, "grad_norm": 0.35899799477104305, "learning_rate": 3.4291836103334294e-05, "loss": 0.3857, "step": 396 }, { "epoch": 1.6081012658227847, "grad_norm": 0.32473608612637256, "learning_rate": 3.425207354603043e-05, "loss": 0.39, "step": 397 }, { "epoch": 1.6121518987341772, "grad_norm": 0.36349410415429884, "learning_rate": 3.421219620448553e-05, "loss": 0.38, "step": 398 }, { "epoch": 1.6162025316455697, "grad_norm": 0.3333921989410631, "learning_rate": 3.417220439986623e-05, "loss": 0.3861, "step": 399 }, { "epoch": 1.620253164556962, "grad_norm": 0.3581371891181588, "learning_rate": 3.4132098454261024e-05, "loss": 0.3676, "step": 400 }, { "epoch": 1.6243037974683543, "grad_norm": 0.30452507672989665, "learning_rate": 3.4091878690677676e-05, "loss": 0.3902, "step": 401 }, { "epoch": 1.6283544303797468, "grad_norm": 0.34558821054502803, "learning_rate": 3.405154543304065e-05, "loss": 0.3954, "step": 402 }, { "epoch": 1.6324050632911393, "grad_norm": 0.3464711054171687, "learning_rate": 3.401109900618843e-05, "loss": 0.3826, "step": 403 }, { "epoch": 1.6364556962025316, "grad_norm": 0.31767900380686787, "learning_rate": 3.3970539735870996e-05, "loss": 0.3912, "step": 404 }, { "epoch": 1.640506329113924, "grad_norm": 0.38765880769499694, "learning_rate": 3.392986794874714e-05, "loss": 0.3877, "step": 405 }, { "epoch": 1.6445569620253164, "grad_norm": 0.3606495283572469, "learning_rate": 3.388908397238184e-05, "loss": 0.3776, "step": 406 }, { "epoch": 1.648607594936709, "grad_norm": 0.3525919958937264, "learning_rate": 3.384818813524362e-05, "loss": 0.3778, "step": 407 }, { "epoch": 1.6526582278481012, "grad_norm": 0.3346455311264116, "learning_rate": 3.380718076670195e-05, "loss": 0.3811, "step": 408 }, { "epoch": 1.6567088607594935, "grad_norm": 0.43507180971356213, "learning_rate": 3.376606219702454e-05, "loss": 0.3841, "step": 409 }, { "epoch": 1.660759493670886, "grad_norm": 0.39917535137278953, "learning_rate": 3.372483275737468e-05, "loss": 0.3877, "step": 410 }, { "epoch": 1.6648101265822786, "grad_norm": 0.37812847526460414, "learning_rate": 3.368349277980861e-05, "loss": 0.3847, "step": 411 }, { "epoch": 1.6688607594936709, "grad_norm": 0.46803102890052095, "learning_rate": 3.3642042597272844e-05, "loss": 0.3791, "step": 412 }, { "epoch": 1.6729113924050631, "grad_norm": 0.4159098403441607, "learning_rate": 3.360048254360144e-05, "loss": 0.3779, "step": 413 }, { "epoch": 1.6769620253164557, "grad_norm": 0.37618737346913345, "learning_rate": 3.355881295351336e-05, "loss": 0.3777, "step": 414 }, { "epoch": 1.6810126582278482, "grad_norm": 0.40986540298401186, "learning_rate": 3.351703416260975e-05, "loss": 0.3933, "step": 415 }, { "epoch": 1.6850632911392405, "grad_norm": 0.40811981694655974, "learning_rate": 3.347514650737126e-05, "loss": 0.3813, "step": 416 }, { "epoch": 1.6891139240506328, "grad_norm": 0.33413580249410263, "learning_rate": 3.3433150325155295e-05, "loss": 0.3855, "step": 417 }, { "epoch": 1.6931645569620253, "grad_norm": 0.3695594521824038, "learning_rate": 3.339104595419334e-05, "loss": 0.3838, "step": 418 }, { "epoch": 1.6972151898734178, "grad_norm": 0.30092115862269025, "learning_rate": 3.3348833733588204e-05, "loss": 0.3846, "step": 419 }, { "epoch": 1.70126582278481, "grad_norm": 0.36978636830810824, "learning_rate": 3.3306514003311305e-05, "loss": 0.3866, "step": 420 }, { "epoch": 1.7053164556962024, "grad_norm": 0.29967527880152117, "learning_rate": 3.326408710419996e-05, "loss": 0.3927, "step": 421 }, { "epoch": 1.709367088607595, "grad_norm": 0.3735249104348313, "learning_rate": 3.322155337795454e-05, "loss": 0.3908, "step": 422 }, { "epoch": 1.7134177215189874, "grad_norm": 0.2997659783872088, "learning_rate": 3.317891316713587e-05, "loss": 0.3911, "step": 423 }, { "epoch": 1.7174683544303797, "grad_norm": 0.3444852493860245, "learning_rate": 3.313616681516231e-05, "loss": 0.3753, "step": 424 }, { "epoch": 1.721518987341772, "grad_norm": 0.3928648898525009, "learning_rate": 3.309331466630713e-05, "loss": 0.3867, "step": 425 }, { "epoch": 1.7255696202531645, "grad_norm": 0.3015450508549416, "learning_rate": 3.305035706569563e-05, "loss": 0.3712, "step": 426 }, { "epoch": 1.729620253164557, "grad_norm": 0.4073756766132042, "learning_rate": 3.3007294359302433e-05, "loss": 0.3917, "step": 427 }, { "epoch": 1.7336708860759493, "grad_norm": 0.39780615752060333, "learning_rate": 3.296412689394864e-05, "loss": 0.382, "step": 428 }, { "epoch": 1.7377215189873416, "grad_norm": 0.3030453448452509, "learning_rate": 3.292085501729909e-05, "loss": 0.3875, "step": 429 }, { "epoch": 1.7417721518987341, "grad_norm": 0.3576191290973827, "learning_rate": 3.2877479077859534e-05, "loss": 0.3708, "step": 430 }, { "epoch": 1.7458227848101266, "grad_norm": 0.28280715036255755, "learning_rate": 3.283399942497381e-05, "loss": 0.3697, "step": 431 }, { "epoch": 1.749873417721519, "grad_norm": 0.34253193878702376, "learning_rate": 3.279041640882108e-05, "loss": 0.3839, "step": 432 }, { "epoch": 1.7539240506329112, "grad_norm": 0.31153840183730425, "learning_rate": 3.2746730380412964e-05, "loss": 0.3744, "step": 433 }, { "epoch": 1.7579746835443038, "grad_norm": 0.34122604350268804, "learning_rate": 3.2702941691590726e-05, "loss": 0.3857, "step": 434 }, { "epoch": 1.7620253164556963, "grad_norm": 0.31254284288157813, "learning_rate": 3.265905069502244e-05, "loss": 0.3823, "step": 435 }, { "epoch": 1.7660759493670886, "grad_norm": 0.32674856827078036, "learning_rate": 3.261505774420016e-05, "loss": 0.3916, "step": 436 }, { "epoch": 1.7701265822784809, "grad_norm": 0.305059646747832, "learning_rate": 3.257096319343707e-05, "loss": 0.3834, "step": 437 }, { "epoch": 1.7741772151898734, "grad_norm": 0.35147729832664426, "learning_rate": 3.2526767397864614e-05, "loss": 0.3871, "step": 438 }, { "epoch": 1.7782278481012659, "grad_norm": 0.34978977121852856, "learning_rate": 3.248247071342966e-05, "loss": 0.3903, "step": 439 }, { "epoch": 1.7822784810126582, "grad_norm": 0.32516057797244624, "learning_rate": 3.243807349689161e-05, "loss": 0.3805, "step": 440 }, { "epoch": 1.7863291139240505, "grad_norm": 0.3654172209254254, "learning_rate": 3.2393576105819544e-05, "loss": 0.3926, "step": 441 }, { "epoch": 1.790379746835443, "grad_norm": 1.3307029924476705, "learning_rate": 3.2348978898589333e-05, "loss": 0.3905, "step": 442 }, { "epoch": 1.7944303797468355, "grad_norm": 0.3475163994214563, "learning_rate": 3.230428223438075e-05, "loss": 0.3768, "step": 443 }, { "epoch": 1.7984810126582278, "grad_norm": 0.3232129639076688, "learning_rate": 3.225948647317459e-05, "loss": 0.3679, "step": 444 }, { "epoch": 1.80253164556962, "grad_norm": 0.29852045659413223, "learning_rate": 3.2214591975749745e-05, "loss": 0.3912, "step": 445 }, { "epoch": 1.8065822784810126, "grad_norm": 0.39660444943453227, "learning_rate": 3.216959910368034e-05, "loss": 0.3892, "step": 446 }, { "epoch": 1.8106329113924051, "grad_norm": 0.3391499894741644, "learning_rate": 3.212450821933277e-05, "loss": 0.3754, "step": 447 }, { "epoch": 1.8146835443037974, "grad_norm": 0.3389301650532031, "learning_rate": 3.207931968586281e-05, "loss": 0.3887, "step": 448 }, { "epoch": 1.81873417721519, "grad_norm": 0.31912335623423826, "learning_rate": 3.203403386721272e-05, "loss": 0.3667, "step": 449 }, { "epoch": 1.8227848101265822, "grad_norm": 0.32900006378785873, "learning_rate": 3.1988651128108245e-05, "loss": 0.3874, "step": 450 }, { "epoch": 1.8268354430379747, "grad_norm": 0.3376347031161654, "learning_rate": 3.194317183405573e-05, "loss": 0.3836, "step": 451 }, { "epoch": 1.8308860759493673, "grad_norm": 0.29406768317763216, "learning_rate": 3.189759635133914e-05, "loss": 0.3841, "step": 452 }, { "epoch": 1.8349367088607595, "grad_norm": 0.3155543885684301, "learning_rate": 3.185192504701718e-05, "loss": 0.3872, "step": 453 }, { "epoch": 1.8389873417721518, "grad_norm": 0.3362273304174418, "learning_rate": 3.1806158288920234e-05, "loss": 0.3968, "step": 454 }, { "epoch": 1.8430379746835444, "grad_norm": 0.2810220523190306, "learning_rate": 3.1760296445647477e-05, "loss": 0.3807, "step": 455 }, { "epoch": 1.8470886075949369, "grad_norm": 0.34140029164900015, "learning_rate": 3.1714339886563896e-05, "loss": 0.3891, "step": 456 }, { "epoch": 1.8511392405063292, "grad_norm": 1.0683645230839462, "learning_rate": 3.166828898179731e-05, "loss": 0.3894, "step": 457 }, { "epoch": 1.8551898734177215, "grad_norm": 0.5189686280710587, "learning_rate": 3.162214410223536e-05, "loss": 0.3917, "step": 458 }, { "epoch": 1.859240506329114, "grad_norm": 0.567149929515341, "learning_rate": 3.157590561952257e-05, "loss": 0.3892, "step": 459 }, { "epoch": 1.8632911392405065, "grad_norm": 0.40453141078935995, "learning_rate": 3.152957390605732e-05, "loss": 0.3875, "step": 460 }, { "epoch": 1.8673417721518988, "grad_norm": 0.46090076951258385, "learning_rate": 3.148314933498886e-05, "loss": 0.3859, "step": 461 }, { "epoch": 1.871392405063291, "grad_norm": 0.5938487699087618, "learning_rate": 3.143663228021431e-05, "loss": 0.3833, "step": 462 }, { "epoch": 1.8754430379746836, "grad_norm": 0.4107615772819101, "learning_rate": 3.1390023116375624e-05, "loss": 0.3801, "step": 463 }, { "epoch": 1.879493670886076, "grad_norm": 0.45606925196994963, "learning_rate": 3.134332221885661e-05, "loss": 0.3888, "step": 464 }, { "epoch": 1.8835443037974684, "grad_norm": 0.5456040082408068, "learning_rate": 3.129652996377987e-05, "loss": 0.3793, "step": 465 }, { "epoch": 1.8875949367088607, "grad_norm": 0.3581636599108726, "learning_rate": 3.12496467280038e-05, "loss": 0.3784, "step": 466 }, { "epoch": 1.8916455696202532, "grad_norm": 0.5310314513651788, "learning_rate": 3.120267288911952e-05, "loss": 0.3924, "step": 467 }, { "epoch": 1.8956962025316457, "grad_norm": 0.4971155062345163, "learning_rate": 3.11556088254479e-05, "loss": 0.389, "step": 468 }, { "epoch": 1.899746835443038, "grad_norm": 0.3743724437396115, "learning_rate": 3.11084549160364e-05, "loss": 0.3953, "step": 469 }, { "epoch": 1.9037974683544303, "grad_norm": 0.4450846753787939, "learning_rate": 3.106121154065615e-05, "loss": 0.3935, "step": 470 }, { "epoch": 1.9078481012658228, "grad_norm": 0.37402921090583197, "learning_rate": 3.1013879079798805e-05, "loss": 0.3823, "step": 471 }, { "epoch": 1.9118987341772153, "grad_norm": 0.3777811943732949, "learning_rate": 3.096645791467348e-05, "loss": 0.3711, "step": 472 }, { "epoch": 1.9159493670886076, "grad_norm": 0.37621584177175005, "learning_rate": 3.091894842720373e-05, "loss": 0.3723, "step": 473 }, { "epoch": 1.92, "grad_norm": 0.3310341236819141, "learning_rate": 3.0871351000024425e-05, "loss": 0.3834, "step": 474 }, { "epoch": 1.9240506329113924, "grad_norm": 0.3991348584670799, "learning_rate": 3.0823666016478716e-05, "loss": 0.3835, "step": 475 }, { "epoch": 1.928101265822785, "grad_norm": 0.31840258831321283, "learning_rate": 3.0775893860614896e-05, "loss": 0.3772, "step": 476 }, { "epoch": 1.9321518987341773, "grad_norm": 0.35986714913107387, "learning_rate": 3.0728034917183336e-05, "loss": 0.3876, "step": 477 }, { "epoch": 1.9362025316455695, "grad_norm": 0.3956592373790224, "learning_rate": 3.06800895716334e-05, "loss": 0.3729, "step": 478 }, { "epoch": 1.940253164556962, "grad_norm": 0.40596445574181234, "learning_rate": 3.063205821011029e-05, "loss": 0.3881, "step": 479 }, { "epoch": 1.9443037974683546, "grad_norm": 0.409722976724895, "learning_rate": 3.0583941219452016e-05, "loss": 0.3864, "step": 480 }, { "epoch": 1.9483544303797469, "grad_norm": 0.3752759575007561, "learning_rate": 3.053573898718618e-05, "loss": 0.3801, "step": 481 }, { "epoch": 1.9524050632911392, "grad_norm": 0.3949397989272809, "learning_rate": 3.0487451901526956e-05, "loss": 0.3695, "step": 482 }, { "epoch": 1.9564556962025317, "grad_norm": 0.36749314369213065, "learning_rate": 3.0439080351371875e-05, "loss": 0.3809, "step": 483 }, { "epoch": 1.9605063291139242, "grad_norm": 0.4276454841973511, "learning_rate": 3.0390624726298764e-05, "loss": 0.3849, "step": 484 }, { "epoch": 1.9645569620253165, "grad_norm": 0.39413500597492424, "learning_rate": 3.034208541656255e-05, "loss": 0.3784, "step": 485 }, { "epoch": 1.9686075949367088, "grad_norm": 0.3497496164688692, "learning_rate": 3.029346281309218e-05, "loss": 0.3833, "step": 486 }, { "epoch": 1.9726582278481013, "grad_norm": 0.4137906417865161, "learning_rate": 3.0244757307487415e-05, "loss": 0.3729, "step": 487 }, { "epoch": 1.9767088607594938, "grad_norm": 0.2939506515404968, "learning_rate": 3.019596929201569e-05, "loss": 0.3713, "step": 488 }, { "epoch": 1.980759493670886, "grad_norm": 0.40171141653136094, "learning_rate": 3.0147099159608985e-05, "loss": 0.3894, "step": 489 }, { "epoch": 1.9848101265822784, "grad_norm": 0.40105093602337655, "learning_rate": 3.0098147303860616e-05, "loss": 0.3808, "step": 490 }, { "epoch": 1.988860759493671, "grad_norm": 0.33576058256354135, "learning_rate": 3.0049114119022117e-05, "loss": 0.3838, "step": 491 }, { "epoch": 1.9929113924050634, "grad_norm": 0.38849886465218314, "learning_rate": 3.0000000000000004e-05, "loss": 0.39, "step": 492 }, { "epoch": 1.9969620253164557, "grad_norm": 0.33222136164053806, "learning_rate": 2.995080534235264e-05, "loss": 0.3845, "step": 493 }, { "epoch": 2.001012658227848, "grad_norm": 0.41629156384505756, "learning_rate": 2.9901530542287044e-05, "loss": 0.3559, "step": 494 }, { "epoch": 2.0050632911392405, "grad_norm": 0.38025438478456136, "learning_rate": 2.9852175996655676e-05, "loss": 0.3482, "step": 495 }, { "epoch": 2.009113924050633, "grad_norm": 0.541573300037102, "learning_rate": 2.980274210295326e-05, "loss": 0.3296, "step": 496 }, { "epoch": 2.013164556962025, "grad_norm": 0.38591195740287476, "learning_rate": 2.9753229259313578e-05, "loss": 0.3234, "step": 497 }, { "epoch": 2.0172151898734176, "grad_norm": 0.3825662660738237, "learning_rate": 2.9703637864506274e-05, "loss": 0.3383, "step": 498 }, { "epoch": 2.02126582278481, "grad_norm": 0.32642104656964915, "learning_rate": 2.965396831793362e-05, "loss": 0.3265, "step": 499 }, { "epoch": 2.0253164556962027, "grad_norm": 0.41433567777167407, "learning_rate": 2.9604221019627316e-05, "loss": 0.3275, "step": 500 }, { "epoch": 2.0293670886075947, "grad_norm": 0.47372325690117684, "learning_rate": 2.955439637024526e-05, "loss": 0.3237, "step": 501 }, { "epoch": 2.0334177215189873, "grad_norm": 0.4076965393957157, "learning_rate": 2.9504494771068334e-05, "loss": 0.3243, "step": 502 }, { "epoch": 2.0374683544303798, "grad_norm": 0.44446813020918474, "learning_rate": 2.9454516623997156e-05, "loss": 0.3422, "step": 503 }, { "epoch": 2.0415189873417723, "grad_norm": 0.457091974794531, "learning_rate": 2.9404462331548847e-05, "loss": 0.3222, "step": 504 }, { "epoch": 2.0455696202531644, "grad_norm": 0.32211043764276964, "learning_rate": 2.93543322968538e-05, "loss": 0.3247, "step": 505 }, { "epoch": 2.049620253164557, "grad_norm": 0.38341531993107136, "learning_rate": 2.9304126923652428e-05, "loss": 0.3345, "step": 506 }, { "epoch": 2.0536708860759494, "grad_norm": 0.4518065253505309, "learning_rate": 2.9253846616291896e-05, "loss": 0.3225, "step": 507 }, { "epoch": 2.057721518987342, "grad_norm": 0.33361156663448027, "learning_rate": 2.9203491779722896e-05, "loss": 0.3277, "step": 508 }, { "epoch": 2.061772151898734, "grad_norm": 0.37427847193327857, "learning_rate": 2.9153062819496357e-05, "loss": 0.3264, "step": 509 }, { "epoch": 2.0658227848101265, "grad_norm": 0.44141128036605687, "learning_rate": 2.9102560141760178e-05, "loss": 0.3426, "step": 510 }, { "epoch": 2.069873417721519, "grad_norm": 0.3316857848797948, "learning_rate": 2.9051984153256004e-05, "loss": 0.319, "step": 511 }, { "epoch": 2.0739240506329115, "grad_norm": 0.3383375427731726, "learning_rate": 2.900133526131588e-05, "loss": 0.3296, "step": 512 }, { "epoch": 2.0779746835443036, "grad_norm": 0.3554268882435945, "learning_rate": 2.8950613873859025e-05, "loss": 0.3365, "step": 513 }, { "epoch": 2.082025316455696, "grad_norm": 0.32003096447209695, "learning_rate": 2.8899820399388515e-05, "loss": 0.3198, "step": 514 }, { "epoch": 2.0860759493670886, "grad_norm": 0.3180433293188836, "learning_rate": 2.8848955246988012e-05, "loss": 0.339, "step": 515 }, { "epoch": 2.090126582278481, "grad_norm": 0.3730637798348488, "learning_rate": 2.879801882631847e-05, "loss": 0.3396, "step": 516 }, { "epoch": 2.094177215189873, "grad_norm": 0.3173002086681488, "learning_rate": 2.8747011547614808e-05, "loss": 0.3433, "step": 517 }, { "epoch": 2.0982278481012657, "grad_norm": 0.3441413027607466, "learning_rate": 2.8695933821682635e-05, "loss": 0.3361, "step": 518 }, { "epoch": 2.1022784810126582, "grad_norm": 0.37921180140063276, "learning_rate": 2.864478605989494e-05, "loss": 0.3232, "step": 519 }, { "epoch": 2.1063291139240508, "grad_norm": 0.3575336456309297, "learning_rate": 2.8593568674188765e-05, "loss": 0.3261, "step": 520 }, { "epoch": 2.110379746835443, "grad_norm": 0.3776868029749526, "learning_rate": 2.8542282077061892e-05, "loss": 0.3383, "step": 521 }, { "epoch": 2.1144303797468353, "grad_norm": 0.42004302879389693, "learning_rate": 2.8490926681569523e-05, "loss": 0.3267, "step": 522 }, { "epoch": 2.118481012658228, "grad_norm": 0.3417821098691685, "learning_rate": 2.8439502901320956e-05, "loss": 0.3333, "step": 523 }, { "epoch": 2.1225316455696204, "grad_norm": 0.3585492535731972, "learning_rate": 2.8388011150476237e-05, "loss": 0.3172, "step": 524 }, { "epoch": 2.1265822784810124, "grad_norm": 0.3800696698637577, "learning_rate": 2.8336451843742866e-05, "loss": 0.3301, "step": 525 }, { "epoch": 2.130632911392405, "grad_norm": 0.3372503028037264, "learning_rate": 2.8284825396372387e-05, "loss": 0.3331, "step": 526 }, { "epoch": 2.1346835443037975, "grad_norm": 0.3847271482160567, "learning_rate": 2.8233132224157132e-05, "loss": 0.3339, "step": 527 }, { "epoch": 2.13873417721519, "grad_norm": 0.29965184736196293, "learning_rate": 2.8181372743426805e-05, "loss": 0.3313, "step": 528 }, { "epoch": 2.1427848101265825, "grad_norm": 0.3350896588071411, "learning_rate": 2.8129547371045128e-05, "loss": 0.3281, "step": 529 }, { "epoch": 2.1468354430379746, "grad_norm": 0.36049485320022845, "learning_rate": 2.8077656524406534e-05, "loss": 0.343, "step": 530 }, { "epoch": 2.150886075949367, "grad_norm": 0.324607660582093, "learning_rate": 2.802570062143278e-05, "loss": 0.3185, "step": 531 }, { "epoch": 2.1549367088607596, "grad_norm": 0.3164251842980858, "learning_rate": 2.7973680080569555e-05, "loss": 0.3516, "step": 532 }, { "epoch": 2.1589873417721517, "grad_norm": 0.35899975778427606, "learning_rate": 2.792159532078314e-05, "loss": 0.3298, "step": 533 }, { "epoch": 2.163037974683544, "grad_norm": 0.28632767943850473, "learning_rate": 2.7869446761557033e-05, "loss": 0.3325, "step": 534 }, { "epoch": 2.1670886075949367, "grad_norm": 0.354724708521616, "learning_rate": 2.781723482288857e-05, "loss": 0.3305, "step": 535 }, { "epoch": 2.1711392405063292, "grad_norm": 0.34295543993968425, "learning_rate": 2.7764959925285517e-05, "loss": 0.329, "step": 536 }, { "epoch": 2.1751898734177217, "grad_norm": 0.3910360414404185, "learning_rate": 2.771262248976272e-05, "loss": 0.3346, "step": 537 }, { "epoch": 2.179240506329114, "grad_norm": 0.3079273722566993, "learning_rate": 2.7660222937838677e-05, "loss": 0.3307, "step": 538 }, { "epoch": 2.1832911392405063, "grad_norm": 0.44053506574176415, "learning_rate": 2.7607761691532186e-05, "loss": 0.3319, "step": 539 }, { "epoch": 2.187341772151899, "grad_norm": 0.3080867662367879, "learning_rate": 2.7555239173358916e-05, "loss": 0.3383, "step": 540 }, { "epoch": 2.191392405063291, "grad_norm": 0.44610446453804803, "learning_rate": 2.7502655806328e-05, "loss": 0.337, "step": 541 }, { "epoch": 2.1954430379746834, "grad_norm": 0.3185161211940699, "learning_rate": 2.7450012013938648e-05, "loss": 0.3141, "step": 542 }, { "epoch": 2.199493670886076, "grad_norm": 0.43438550069690557, "learning_rate": 2.739730822017673e-05, "loss": 0.3342, "step": 543 }, { "epoch": 2.2035443037974685, "grad_norm": 0.35743576825041395, "learning_rate": 2.7344544849511355e-05, "loss": 0.331, "step": 544 }, { "epoch": 2.207594936708861, "grad_norm": 0.3497944724145401, "learning_rate": 2.7291722326891456e-05, "loss": 0.3372, "step": 545 }, { "epoch": 2.211645569620253, "grad_norm": 0.3077850153695275, "learning_rate": 2.723884107774236e-05, "loss": 0.3459, "step": 546 }, { "epoch": 2.2156962025316456, "grad_norm": 0.2709359298650794, "learning_rate": 2.718590152796239e-05, "loss": 0.3384, "step": 547 }, { "epoch": 2.219746835443038, "grad_norm": 0.2987850824290351, "learning_rate": 2.71329041039194e-05, "loss": 0.329, "step": 548 }, { "epoch": 2.22379746835443, "grad_norm": 0.2861686702699415, "learning_rate": 2.7079849232447357e-05, "loss": 0.3477, "step": 549 }, { "epoch": 2.2278481012658227, "grad_norm": 0.2774295699857127, "learning_rate": 2.7026737340842895e-05, "loss": 0.3399, "step": 550 }, { "epoch": 2.231898734177215, "grad_norm": 0.266677330307668, "learning_rate": 2.697356885686189e-05, "loss": 0.3287, "step": 551 }, { "epoch": 2.2359493670886077, "grad_norm": 0.2549505537540859, "learning_rate": 2.6920344208716014e-05, "loss": 0.3278, "step": 552 }, { "epoch": 2.24, "grad_norm": 0.26023917295857896, "learning_rate": 2.6867063825069252e-05, "loss": 0.3304, "step": 553 }, { "epoch": 2.2440506329113923, "grad_norm": 0.2844968565551243, "learning_rate": 2.6813728135034494e-05, "loss": 0.3447, "step": 554 }, { "epoch": 2.248101265822785, "grad_norm": 0.2627715704613999, "learning_rate": 2.6760337568170056e-05, "loss": 0.3451, "step": 555 }, { "epoch": 2.2521518987341773, "grad_norm": 0.261265812293219, "learning_rate": 2.6706892554476226e-05, "loss": 0.3347, "step": 556 }, { "epoch": 2.2562025316455694, "grad_norm": 0.27871436073958905, "learning_rate": 2.6653393524391795e-05, "loss": 0.3248, "step": 557 }, { "epoch": 2.260253164556962, "grad_norm": 0.25977687504097835, "learning_rate": 2.6599840908790592e-05, "loss": 0.3344, "step": 558 }, { "epoch": 2.2643037974683544, "grad_norm": 0.2693212424297404, "learning_rate": 2.6546235138978028e-05, "loss": 0.3415, "step": 559 }, { "epoch": 2.268354430379747, "grad_norm": 0.32939374590768755, "learning_rate": 2.6492576646687597e-05, "loss": 0.3246, "step": 560 }, { "epoch": 2.2724050632911394, "grad_norm": 0.22642815309351072, "learning_rate": 2.6438865864077425e-05, "loss": 0.3256, "step": 561 }, { "epoch": 2.2764556962025315, "grad_norm": 0.3010417159459777, "learning_rate": 2.6385103223726766e-05, "loss": 0.3367, "step": 562 }, { "epoch": 2.280506329113924, "grad_norm": 0.2558317767105212, "learning_rate": 2.6331289158632537e-05, "loss": 0.3376, "step": 563 }, { "epoch": 2.2845569620253166, "grad_norm": 0.31569222512968137, "learning_rate": 2.6277424102205817e-05, "loss": 0.3421, "step": 564 }, { "epoch": 2.2886075949367086, "grad_norm": 0.32754828446525236, "learning_rate": 2.6223508488268374e-05, "loss": 0.3374, "step": 565 }, { "epoch": 2.292658227848101, "grad_norm": 0.29116671480336503, "learning_rate": 2.6169542751049148e-05, "loss": 0.3321, "step": 566 }, { "epoch": 2.2967088607594937, "grad_norm": 0.31825435840921307, "learning_rate": 2.6115527325180754e-05, "loss": 0.3212, "step": 567 }, { "epoch": 2.300759493670886, "grad_norm": 0.31527799950542046, "learning_rate": 2.606146264569603e-05, "loss": 0.3305, "step": 568 }, { "epoch": 2.3048101265822787, "grad_norm": 0.2689527779082951, "learning_rate": 2.6007349148024447e-05, "loss": 0.3296, "step": 569 }, { "epoch": 2.3088607594936708, "grad_norm": 0.3099266415219233, "learning_rate": 2.5953187267988694e-05, "loss": 0.3336, "step": 570 }, { "epoch": 2.3129113924050633, "grad_norm": 0.27418065004865944, "learning_rate": 2.5898977441801097e-05, "loss": 0.3244, "step": 571 }, { "epoch": 2.316962025316456, "grad_norm": 0.3414994111161154, "learning_rate": 2.584472010606015e-05, "loss": 0.3345, "step": 572 }, { "epoch": 2.321012658227848, "grad_norm": 0.3021916546967295, "learning_rate": 2.5790415697746976e-05, "loss": 0.3272, "step": 573 }, { "epoch": 2.3250632911392404, "grad_norm": 0.30457626500192314, "learning_rate": 2.5736064654221808e-05, "loss": 0.3357, "step": 574 }, { "epoch": 2.329113924050633, "grad_norm": 0.32718096943269304, "learning_rate": 2.568166741322048e-05, "loss": 0.3389, "step": 575 }, { "epoch": 2.3331645569620254, "grad_norm": 0.2934768798389796, "learning_rate": 2.56272244128509e-05, "loss": 0.3333, "step": 576 }, { "epoch": 2.337215189873418, "grad_norm": 0.2831837288942364, "learning_rate": 2.55727360915895e-05, "loss": 0.334, "step": 577 }, { "epoch": 2.34126582278481, "grad_norm": 0.27877953605828737, "learning_rate": 2.5518202888277734e-05, "loss": 0.347, "step": 578 }, { "epoch": 2.3453164556962025, "grad_norm": 0.29994938420918715, "learning_rate": 2.5463625242118523e-05, "loss": 0.3379, "step": 579 }, { "epoch": 2.349367088607595, "grad_norm": 0.26856001158961623, "learning_rate": 2.5409003592672723e-05, "loss": 0.3293, "step": 580 }, { "epoch": 2.353417721518987, "grad_norm": 0.27276845598963273, "learning_rate": 2.535433837985559e-05, "loss": 0.3391, "step": 581 }, { "epoch": 2.3574683544303796, "grad_norm": 0.25865561357221284, "learning_rate": 2.529963004393324e-05, "loss": 0.3159, "step": 582 }, { "epoch": 2.361518987341772, "grad_norm": 0.2869484492156443, "learning_rate": 2.524487902551908e-05, "loss": 0.3283, "step": 583 }, { "epoch": 2.3655696202531646, "grad_norm": 0.24161609560009176, "learning_rate": 2.519008576557029e-05, "loss": 0.3295, "step": 584 }, { "epoch": 2.369620253164557, "grad_norm": 0.320905315330286, "learning_rate": 2.5135250705384254e-05, "loss": 0.3337, "step": 585 }, { "epoch": 2.3736708860759492, "grad_norm": 0.2628548864578926, "learning_rate": 2.5080374286595007e-05, "loss": 0.34, "step": 586 }, { "epoch": 2.3777215189873417, "grad_norm": 0.3300258646678102, "learning_rate": 2.5025456951169677e-05, "loss": 0.3396, "step": 587 }, { "epoch": 2.3817721518987343, "grad_norm": 0.2819326416086143, "learning_rate": 2.4970499141404942e-05, "loss": 0.3301, "step": 588 }, { "epoch": 2.3858227848101268, "grad_norm": 0.2451635349951327, "learning_rate": 2.491550129992345e-05, "loss": 0.3272, "step": 589 }, { "epoch": 2.389873417721519, "grad_norm": 0.2908252292019938, "learning_rate": 2.486046386967024e-05, "loss": 0.3362, "step": 590 }, { "epoch": 2.3939240506329114, "grad_norm": 0.2709610528244221, "learning_rate": 2.4805387293909214e-05, "loss": 0.3288, "step": 591 }, { "epoch": 2.397974683544304, "grad_norm": 0.29200689729028656, "learning_rate": 2.4750272016219552e-05, "loss": 0.3288, "step": 592 }, { "epoch": 2.4020253164556964, "grad_norm": 0.2873295178435606, "learning_rate": 2.4695118480492114e-05, "loss": 0.3457, "step": 593 }, { "epoch": 2.4060759493670885, "grad_norm": 0.31309493386214726, "learning_rate": 2.4639927130925898e-05, "loss": 0.343, "step": 594 }, { "epoch": 2.410126582278481, "grad_norm": 0.26621860563850186, "learning_rate": 2.458469841202444e-05, "loss": 0.3335, "step": 595 }, { "epoch": 2.4141772151898735, "grad_norm": 0.29554928546588355, "learning_rate": 2.452943276859226e-05, "loss": 0.3317, "step": 596 }, { "epoch": 2.418227848101266, "grad_norm": 0.2586624927770081, "learning_rate": 2.447413064573125e-05, "loss": 0.3326, "step": 597 }, { "epoch": 2.422278481012658, "grad_norm": 0.293736492727049, "learning_rate": 2.4418792488837095e-05, "loss": 0.3319, "step": 598 }, { "epoch": 2.4263291139240506, "grad_norm": 0.31462932976943686, "learning_rate": 2.4363418743595713e-05, "loss": 0.3334, "step": 599 }, { "epoch": 2.430379746835443, "grad_norm": 0.27417325901186174, "learning_rate": 2.430800985597963e-05, "loss": 0.3353, "step": 600 }, { "epoch": 2.4344303797468356, "grad_norm": 0.28229738518425695, "learning_rate": 2.4252566272244415e-05, "loss": 0.3324, "step": 601 }, { "epoch": 2.4384810126582277, "grad_norm": 0.30445127586242343, "learning_rate": 2.4197088438925063e-05, "loss": 0.3349, "step": 602 }, { "epoch": 2.44253164556962, "grad_norm": 0.29033280228969155, "learning_rate": 2.4141576802832417e-05, "loss": 0.3348, "step": 603 }, { "epoch": 2.4465822784810127, "grad_norm": 0.2983461162722682, "learning_rate": 2.408603181104957e-05, "loss": 0.3311, "step": 604 }, { "epoch": 2.4506329113924052, "grad_norm": 0.2920791173642606, "learning_rate": 2.4030453910928245e-05, "loss": 0.3395, "step": 605 }, { "epoch": 2.4546835443037973, "grad_norm": 0.2658746750869072, "learning_rate": 2.397484355008521e-05, "loss": 0.3351, "step": 606 }, { "epoch": 2.45873417721519, "grad_norm": 0.3025199578940178, "learning_rate": 2.3919201176398662e-05, "loss": 0.3365, "step": 607 }, { "epoch": 2.4627848101265823, "grad_norm": 0.3319611656550088, "learning_rate": 2.3863527238004633e-05, "loss": 0.335, "step": 608 }, { "epoch": 2.466835443037975, "grad_norm": 0.2769174837113213, "learning_rate": 2.380782218329337e-05, "loss": 0.337, "step": 609 }, { "epoch": 2.470886075949367, "grad_norm": 0.2908678130793002, "learning_rate": 2.3752086460905725e-05, "loss": 0.3331, "step": 610 }, { "epoch": 2.4749367088607594, "grad_norm": 0.2688601596608133, "learning_rate": 2.3696320519729544e-05, "loss": 0.3382, "step": 611 }, { "epoch": 2.478987341772152, "grad_norm": 0.2853957314347417, "learning_rate": 2.3640524808896045e-05, "loss": 0.3278, "step": 612 }, { "epoch": 2.4830379746835445, "grad_norm": 0.2688323662567755, "learning_rate": 2.3584699777776222e-05, "loss": 0.3329, "step": 613 }, { "epoch": 2.4870886075949366, "grad_norm": 0.3063645146243304, "learning_rate": 2.3528845875977195e-05, "loss": 0.322, "step": 614 }, { "epoch": 2.491139240506329, "grad_norm": 0.2801162374405138, "learning_rate": 2.3472963553338614e-05, "loss": 0.33, "step": 615 }, { "epoch": 2.4951898734177216, "grad_norm": 0.25919446780370475, "learning_rate": 2.341705325992901e-05, "loss": 0.3272, "step": 616 }, { "epoch": 2.499240506329114, "grad_norm": 0.25558229911392233, "learning_rate": 2.336111544604222e-05, "loss": 0.3321, "step": 617 }, { "epoch": 2.503291139240506, "grad_norm": 0.3081171628250543, "learning_rate": 2.33051505621937e-05, "loss": 0.3382, "step": 618 }, { "epoch": 2.5073417721518987, "grad_norm": 0.26153510571717575, "learning_rate": 2.324915905911693e-05, "loss": 0.3244, "step": 619 }, { "epoch": 2.511392405063291, "grad_norm": 0.3461211388187404, "learning_rate": 2.319314138775977e-05, "loss": 0.3403, "step": 620 }, { "epoch": 2.5154430379746833, "grad_norm": 0.2850385977147204, "learning_rate": 2.3137097999280856e-05, "loss": 0.3337, "step": 621 }, { "epoch": 2.519493670886076, "grad_norm": 0.3457330295053786, "learning_rate": 2.308102934504593e-05, "loss": 0.3257, "step": 622 }, { "epoch": 2.5235443037974683, "grad_norm": 0.3326562963693331, "learning_rate": 2.3024935876624222e-05, "loss": 0.3349, "step": 623 }, { "epoch": 2.527594936708861, "grad_norm": 0.3354157812199446, "learning_rate": 2.2968818045784813e-05, "loss": 0.3303, "step": 624 }, { "epoch": 2.5316455696202533, "grad_norm": 0.40792622642529847, "learning_rate": 2.2912676304493006e-05, "loss": 0.3397, "step": 625 }, { "epoch": 2.5356962025316454, "grad_norm": 0.3096765157948457, "learning_rate": 2.2856511104906668e-05, "loss": 0.333, "step": 626 }, { "epoch": 2.539746835443038, "grad_norm": 0.3817477339447169, "learning_rate": 2.2800322899372586e-05, "loss": 0.3333, "step": 627 }, { "epoch": 2.5437974683544304, "grad_norm": 0.3163803141618468, "learning_rate": 2.2744112140422844e-05, "loss": 0.3355, "step": 628 }, { "epoch": 2.547848101265823, "grad_norm": 0.2758564871108341, "learning_rate": 2.2687879280771177e-05, "loss": 0.3253, "step": 629 }, { "epoch": 2.5518987341772155, "grad_norm": 0.3419959094947528, "learning_rate": 2.26316247733093e-05, "loss": 0.3335, "step": 630 }, { "epoch": 2.5559493670886075, "grad_norm": 0.24403374760715887, "learning_rate": 2.257534907110328e-05, "loss": 0.3231, "step": 631 }, { "epoch": 2.56, "grad_norm": 0.3198471949699964, "learning_rate": 2.2519052627389882e-05, "loss": 0.3288, "step": 632 }, { "epoch": 2.5640506329113926, "grad_norm": 0.27168628236720044, "learning_rate": 2.246273589557294e-05, "loss": 0.3363, "step": 633 }, { "epoch": 2.5681012658227846, "grad_norm": 0.30115145865015674, "learning_rate": 2.240639932921966e-05, "loss": 0.33, "step": 634 }, { "epoch": 2.572151898734177, "grad_norm": 0.2978624679110213, "learning_rate": 2.2350043382056995e-05, "loss": 0.3433, "step": 635 }, { "epoch": 2.5762025316455697, "grad_norm": 0.27698986717716745, "learning_rate": 2.2293668507968015e-05, "loss": 0.3349, "step": 636 }, { "epoch": 2.580253164556962, "grad_norm": 0.3037837862538224, "learning_rate": 2.2237275160988186e-05, "loss": 0.3304, "step": 637 }, { "epoch": 2.5843037974683547, "grad_norm": 0.2833597143620634, "learning_rate": 2.2180863795301787e-05, "loss": 0.3354, "step": 638 }, { "epoch": 2.5883544303797468, "grad_norm": 0.30394841980083087, "learning_rate": 2.212443486523819e-05, "loss": 0.3185, "step": 639 }, { "epoch": 2.5924050632911393, "grad_norm": 0.2599319312221832, "learning_rate": 2.2067988825268243e-05, "loss": 0.3415, "step": 640 }, { "epoch": 2.596455696202532, "grad_norm": 0.30804079086124725, "learning_rate": 2.2011526130000596e-05, "loss": 0.3343, "step": 641 }, { "epoch": 2.600506329113924, "grad_norm": 0.2625665106209559, "learning_rate": 2.1955047234178038e-05, "loss": 0.337, "step": 642 }, { "epoch": 2.6045569620253164, "grad_norm": 0.29000187824978596, "learning_rate": 2.1898552592673825e-05, "loss": 0.332, "step": 643 }, { "epoch": 2.608607594936709, "grad_norm": 0.2690473017370044, "learning_rate": 2.184204266048803e-05, "loss": 0.3365, "step": 644 }, { "epoch": 2.6126582278481014, "grad_norm": 0.27548478829414363, "learning_rate": 2.1785517892743887e-05, "loss": 0.3279, "step": 645 }, { "epoch": 2.616708860759494, "grad_norm": 0.2839254918541328, "learning_rate": 2.17289787446841e-05, "loss": 0.3384, "step": 646 }, { "epoch": 2.620759493670886, "grad_norm": 0.25796768504846423, "learning_rate": 2.1672425671667198e-05, "loss": 0.3312, "step": 647 }, { "epoch": 2.6248101265822785, "grad_norm": 0.2519525633078452, "learning_rate": 2.161585912916385e-05, "loss": 0.3389, "step": 648 }, { "epoch": 2.628860759493671, "grad_norm": 0.2481995728959832, "learning_rate": 2.1559279572753214e-05, "loss": 0.3228, "step": 649 }, { "epoch": 2.632911392405063, "grad_norm": 0.2649176420253923, "learning_rate": 2.1502687458119268e-05, "loss": 0.3288, "step": 650 }, { "epoch": 2.6369620253164556, "grad_norm": 0.2690439696216254, "learning_rate": 2.1446083241047116e-05, "loss": 0.3353, "step": 651 }, { "epoch": 2.641012658227848, "grad_norm": 0.2392592361628268, "learning_rate": 2.1389467377419333e-05, "loss": 0.3354, "step": 652 }, { "epoch": 2.6450632911392407, "grad_norm": 0.24720854811100185, "learning_rate": 2.133284032321232e-05, "loss": 0.334, "step": 653 }, { "epoch": 2.649113924050633, "grad_norm": 0.2294459851378275, "learning_rate": 2.1276202534492566e-05, "loss": 0.3134, "step": 654 }, { "epoch": 2.6531645569620252, "grad_norm": 0.2672399109143056, "learning_rate": 2.121955446741306e-05, "loss": 0.3398, "step": 655 }, { "epoch": 2.6572151898734178, "grad_norm": 0.2623366155830041, "learning_rate": 2.1162896578209517e-05, "loss": 0.3341, "step": 656 }, { "epoch": 2.6612658227848103, "grad_norm": 0.25510331782722495, "learning_rate": 2.1106229323196813e-05, "loss": 0.3287, "step": 657 }, { "epoch": 2.6653164556962023, "grad_norm": 0.2629033226580914, "learning_rate": 2.1049553158765214e-05, "loss": 0.3359, "step": 658 }, { "epoch": 2.669367088607595, "grad_norm": 0.24572233369949525, "learning_rate": 2.0992868541376764e-05, "loss": 0.3302, "step": 659 }, { "epoch": 2.6734177215189874, "grad_norm": 0.2585095578668617, "learning_rate": 2.093617592756158e-05, "loss": 0.3323, "step": 660 }, { "epoch": 2.67746835443038, "grad_norm": 0.2509353699162798, "learning_rate": 2.0879475773914167e-05, "loss": 0.3289, "step": 661 }, { "epoch": 2.6815189873417724, "grad_norm": 0.2428140373457367, "learning_rate": 2.082276853708978e-05, "loss": 0.3314, "step": 662 }, { "epoch": 2.6855696202531645, "grad_norm": 0.2768422605179291, "learning_rate": 2.076605467380071e-05, "loss": 0.3274, "step": 663 }, { "epoch": 2.689620253164557, "grad_norm": 0.2467516613992883, "learning_rate": 2.0709334640812613e-05, "loss": 0.3301, "step": 664 }, { "epoch": 2.6936708860759495, "grad_norm": 0.26457317192936713, "learning_rate": 2.0652608894940824e-05, "loss": 0.3338, "step": 665 }, { "epoch": 2.6977215189873416, "grad_norm": 0.26201635162347015, "learning_rate": 2.0595877893046722e-05, "loss": 0.331, "step": 666 }, { "epoch": 2.701772151898734, "grad_norm": 0.24911193969712625, "learning_rate": 2.0539142092033985e-05, "loss": 0.3343, "step": 667 }, { "epoch": 2.7058227848101266, "grad_norm": 1.5314500537003932, "learning_rate": 2.048240194884496e-05, "loss": 0.3519, "step": 668 }, { "epoch": 2.709873417721519, "grad_norm": 0.28887066728774385, "learning_rate": 2.042565792045695e-05, "loss": 0.3287, "step": 669 }, { "epoch": 2.7139240506329116, "grad_norm": 0.2845677622554474, "learning_rate": 2.036891046387857e-05, "loss": 0.3303, "step": 670 }, { "epoch": 2.7179746835443037, "grad_norm": 0.2768831379026178, "learning_rate": 2.0312160036146036e-05, "loss": 0.3352, "step": 671 }, { "epoch": 2.7220253164556962, "grad_norm": 0.3003225470277515, "learning_rate": 2.025540709431948e-05, "loss": 0.3334, "step": 672 }, { "epoch": 2.7260759493670887, "grad_norm": 0.3053033001822151, "learning_rate": 2.0198652095479298e-05, "loss": 0.3471, "step": 673 }, { "epoch": 2.730126582278481, "grad_norm": 0.27631343601483727, "learning_rate": 2.014189549672245e-05, "loss": 0.34, "step": 674 }, { "epoch": 2.7341772151898733, "grad_norm": 0.3478982205068707, "learning_rate": 2.0085137755158776e-05, "loss": 0.3269, "step": 675 }, { "epoch": 2.738227848101266, "grad_norm": 0.2820457643337349, "learning_rate": 2.0028379327907327e-05, "loss": 0.3347, "step": 676 }, { "epoch": 2.7422784810126584, "grad_norm": 0.3191429054319394, "learning_rate": 1.9971620672092676e-05, "loss": 0.3362, "step": 677 }, { "epoch": 2.746329113924051, "grad_norm": 0.2538845180955586, "learning_rate": 1.991486224484123e-05, "loss": 0.3184, "step": 678 }, { "epoch": 2.750379746835443, "grad_norm": 0.2614505542494955, "learning_rate": 1.985810450327756e-05, "loss": 0.3281, "step": 679 }, { "epoch": 2.7544303797468355, "grad_norm": 0.2743839240313915, "learning_rate": 1.9801347904520706e-05, "loss": 0.3313, "step": 680 }, { "epoch": 2.758481012658228, "grad_norm": 0.22509018001127654, "learning_rate": 1.974459290568053e-05, "loss": 0.323, "step": 681 }, { "epoch": 2.76253164556962, "grad_norm": 0.2627866951835147, "learning_rate": 1.968783996385397e-05, "loss": 0.3312, "step": 682 }, { "epoch": 2.7665822784810126, "grad_norm": 0.27243222217071, "learning_rate": 1.963108953612143e-05, "loss": 0.3244, "step": 683 }, { "epoch": 2.770632911392405, "grad_norm": 0.28037167309095634, "learning_rate": 1.9574342079543056e-05, "loss": 0.3262, "step": 684 }, { "epoch": 2.7746835443037976, "grad_norm": 0.27449730905152886, "learning_rate": 1.9517598051155046e-05, "loss": 0.3269, "step": 685 }, { "epoch": 2.77873417721519, "grad_norm": 0.29697350924524524, "learning_rate": 1.9460857907966025e-05, "loss": 0.3398, "step": 686 }, { "epoch": 2.782784810126582, "grad_norm": 0.27309733886991083, "learning_rate": 1.9404122106953285e-05, "loss": 0.3307, "step": 687 }, { "epoch": 2.7868354430379747, "grad_norm": 0.2922849155217476, "learning_rate": 1.9347391105059176e-05, "loss": 0.3356, "step": 688 }, { "epoch": 2.790886075949367, "grad_norm": 0.2576566313894675, "learning_rate": 1.92906653591874e-05, "loss": 0.3362, "step": 689 }, { "epoch": 2.7949367088607593, "grad_norm": 0.2952308155440196, "learning_rate": 1.9233945326199295e-05, "loss": 0.3297, "step": 690 }, { "epoch": 2.798987341772152, "grad_norm": 0.2805111077804522, "learning_rate": 1.917723146291022e-05, "loss": 0.3359, "step": 691 }, { "epoch": 2.8030379746835443, "grad_norm": 0.2727756697349241, "learning_rate": 1.912052422608584e-05, "loss": 0.3344, "step": 692 }, { "epoch": 2.807088607594937, "grad_norm": 0.2961352391073362, "learning_rate": 1.9063824072438428e-05, "loss": 0.3264, "step": 693 }, { "epoch": 2.8111392405063294, "grad_norm": 0.26617064616409736, "learning_rate": 1.9007131458623246e-05, "loss": 0.337, "step": 694 }, { "epoch": 2.8151898734177214, "grad_norm": 0.28970315418366277, "learning_rate": 1.895044684123479e-05, "loss": 0.3325, "step": 695 }, { "epoch": 2.819240506329114, "grad_norm": 0.2949986113360529, "learning_rate": 1.8893770676803194e-05, "loss": 0.3464, "step": 696 }, { "epoch": 2.8232911392405065, "grad_norm": 0.2527930697760292, "learning_rate": 1.8837103421790486e-05, "loss": 0.3305, "step": 697 }, { "epoch": 2.8273417721518985, "grad_norm": 0.26407140674478596, "learning_rate": 1.8780445532586952e-05, "loss": 0.3225, "step": 698 }, { "epoch": 2.831392405063291, "grad_norm": 0.22176088511941514, "learning_rate": 1.872379746550743e-05, "loss": 0.3224, "step": 699 }, { "epoch": 2.8354430379746836, "grad_norm": 0.25093859010654157, "learning_rate": 1.866715967678769e-05, "loss": 0.3223, "step": 700 }, { "epoch": 2.839493670886076, "grad_norm": 0.24289550136085106, "learning_rate": 1.861053262258067e-05, "loss": 0.3166, "step": 701 }, { "epoch": 2.8435443037974686, "grad_norm": 0.27664531357038424, "learning_rate": 1.8553916758952897e-05, "loss": 0.332, "step": 702 }, { "epoch": 2.8475949367088607, "grad_norm": 0.26528806263435123, "learning_rate": 1.8497312541880735e-05, "loss": 0.3265, "step": 703 }, { "epoch": 2.851645569620253, "grad_norm": 0.26461953154774864, "learning_rate": 1.8440720427246786e-05, "loss": 0.3296, "step": 704 }, { "epoch": 2.8556962025316457, "grad_norm": 0.28396827001020813, "learning_rate": 1.8384140870836157e-05, "loss": 0.3212, "step": 705 }, { "epoch": 2.8597468354430378, "grad_norm": 0.26432824303336994, "learning_rate": 1.8327574328332806e-05, "loss": 0.3371, "step": 706 }, { "epoch": 2.8637974683544303, "grad_norm": 0.27072175576884533, "learning_rate": 1.8271021255315906e-05, "loss": 0.3297, "step": 707 }, { "epoch": 2.867848101265823, "grad_norm": 0.26611478332806593, "learning_rate": 1.8214482107256117e-05, "loss": 0.3354, "step": 708 }, { "epoch": 2.8718987341772153, "grad_norm": 0.28982869660882415, "learning_rate": 1.8157957339511968e-05, "loss": 0.3256, "step": 709 }, { "epoch": 2.875949367088608, "grad_norm": 0.2574930866817214, "learning_rate": 1.8101447407326182e-05, "loss": 0.3351, "step": 710 }, { "epoch": 2.88, "grad_norm": 0.28835688848901975, "learning_rate": 1.8044952765821966e-05, "loss": 0.3314, "step": 711 }, { "epoch": 2.8840506329113924, "grad_norm": 0.2941232237718961, "learning_rate": 1.7988473869999407e-05, "loss": 0.3346, "step": 712 }, { "epoch": 2.888101265822785, "grad_norm": 0.32687755910089256, "learning_rate": 1.7932011174731764e-05, "loss": 0.3301, "step": 713 }, { "epoch": 2.892151898734177, "grad_norm": 0.23954160073597977, "learning_rate": 1.7875565134761817e-05, "loss": 0.3271, "step": 714 }, { "epoch": 2.8962025316455695, "grad_norm": 0.28774552738724635, "learning_rate": 1.7819136204698226e-05, "loss": 0.3304, "step": 715 }, { "epoch": 2.900253164556962, "grad_norm": 0.25781415295838983, "learning_rate": 1.776272483901182e-05, "loss": 0.3414, "step": 716 }, { "epoch": 2.9043037974683545, "grad_norm": 0.29066776576411635, "learning_rate": 1.7706331492031995e-05, "loss": 0.3388, "step": 717 }, { "epoch": 2.908354430379747, "grad_norm": 0.24838446211529275, "learning_rate": 1.764995661794301e-05, "loss": 0.3307, "step": 718 }, { "epoch": 2.912405063291139, "grad_norm": 0.269009950931881, "learning_rate": 1.759360067078035e-05, "loss": 0.3304, "step": 719 }, { "epoch": 2.9164556962025316, "grad_norm": 0.2548276898691161, "learning_rate": 1.7537264104427064e-05, "loss": 0.3352, "step": 720 }, { "epoch": 2.920506329113924, "grad_norm": 0.27349555596642483, "learning_rate": 1.748094737261012e-05, "loss": 0.3293, "step": 721 }, { "epoch": 2.9245569620253162, "grad_norm": 0.24258008465113154, "learning_rate": 1.7424650928896726e-05, "loss": 0.3239, "step": 722 }, { "epoch": 2.9286075949367087, "grad_norm": 0.25480114665489634, "learning_rate": 1.7368375226690712e-05, "loss": 0.3405, "step": 723 }, { "epoch": 2.9326582278481013, "grad_norm": 0.24545567294203835, "learning_rate": 1.731212071922883e-05, "loss": 0.3296, "step": 724 }, { "epoch": 2.9367088607594938, "grad_norm": 0.28048376831334987, "learning_rate": 1.7255887859577156e-05, "loss": 0.3341, "step": 725 }, { "epoch": 2.9407594936708863, "grad_norm": 0.2677164548594137, "learning_rate": 1.7199677100627427e-05, "loss": 0.334, "step": 726 }, { "epoch": 2.9448101265822784, "grad_norm": 0.2640127965274114, "learning_rate": 1.7143488895093343e-05, "loss": 0.3206, "step": 727 }, { "epoch": 2.948860759493671, "grad_norm": 0.2637444524629287, "learning_rate": 1.7087323695506994e-05, "loss": 0.334, "step": 728 }, { "epoch": 2.9529113924050634, "grad_norm": 0.24648675686461977, "learning_rate": 1.7031181954215194e-05, "loss": 0.3362, "step": 729 }, { "epoch": 2.9569620253164555, "grad_norm": 0.3066319663883438, "learning_rate": 1.6975064123375788e-05, "loss": 0.3265, "step": 730 }, { "epoch": 2.961012658227848, "grad_norm": 0.35313747866374917, "learning_rate": 1.6918970654954084e-05, "loss": 0.3201, "step": 731 }, { "epoch": 2.9650632911392405, "grad_norm": 0.2706542516455608, "learning_rate": 1.686290200071915e-05, "loss": 0.3345, "step": 732 }, { "epoch": 2.969113924050633, "grad_norm": 0.25803405146940117, "learning_rate": 1.6806858612240234e-05, "loss": 0.3331, "step": 733 }, { "epoch": 2.9731645569620255, "grad_norm": 0.236049515284004, "learning_rate": 1.6750840940883078e-05, "loss": 0.3341, "step": 734 }, { "epoch": 2.9772151898734176, "grad_norm": 0.2572224781494753, "learning_rate": 1.6694849437806305e-05, "loss": 0.3184, "step": 735 }, { "epoch": 2.98126582278481, "grad_norm": 0.2579781990450531, "learning_rate": 1.663888455395778e-05, "loss": 0.3381, "step": 736 }, { "epoch": 2.9853164556962026, "grad_norm": 0.23518591135691394, "learning_rate": 1.6582946740070995e-05, "loss": 0.3375, "step": 737 }, { "epoch": 2.9893670886075947, "grad_norm": 0.25394059940545194, "learning_rate": 1.6527036446661396e-05, "loss": 0.3339, "step": 738 }, { "epoch": 2.993417721518987, "grad_norm": 0.26170130103502903, "learning_rate": 1.6471154124022818e-05, "loss": 0.3345, "step": 739 }, { "epoch": 2.9974683544303797, "grad_norm": 0.2540434268961394, "learning_rate": 1.6415300222223788e-05, "loss": 0.3273, "step": 740 }, { "epoch": 3.0015189873417722, "grad_norm": 0.23623324467239015, "learning_rate": 1.6359475191103958e-05, "loss": 0.3181, "step": 741 }, { "epoch": 3.0055696202531648, "grad_norm": 0.29751637196294883, "learning_rate": 1.6303679480270466e-05, "loss": 0.2843, "step": 742 }, { "epoch": 3.009620253164557, "grad_norm": 0.48265334601075494, "learning_rate": 1.624791353909428e-05, "loss": 0.2824, "step": 743 }, { "epoch": 3.0136708860759494, "grad_norm": 0.27852725092892167, "learning_rate": 1.619217781670663e-05, "loss": 0.2778, "step": 744 }, { "epoch": 3.017721518987342, "grad_norm": 0.3964969620299199, "learning_rate": 1.6136472761995373e-05, "loss": 0.2944, "step": 745 }, { "epoch": 3.0217721518987344, "grad_norm": 0.27999821108964834, "learning_rate": 1.608079882360134e-05, "loss": 0.2752, "step": 746 }, { "epoch": 3.0258227848101265, "grad_norm": 0.3482854648776222, "learning_rate": 1.60251564499148e-05, "loss": 0.2868, "step": 747 }, { "epoch": 3.029873417721519, "grad_norm": 0.3396164827596434, "learning_rate": 1.596954608907176e-05, "loss": 0.2996, "step": 748 }, { "epoch": 3.0339240506329115, "grad_norm": 0.3121295603785226, "learning_rate": 1.591396818895043e-05, "loss": 0.2856, "step": 749 }, { "epoch": 3.037974683544304, "grad_norm": 0.36241389638956484, "learning_rate": 1.585842319716759e-05, "loss": 0.2888, "step": 750 }, { "epoch": 3.042025316455696, "grad_norm": 0.2736825122125203, "learning_rate": 1.5802911561074944e-05, "loss": 0.2871, "step": 751 }, { "epoch": 3.0460759493670886, "grad_norm": 0.29085289179691376, "learning_rate": 1.5747433727755595e-05, "loss": 0.2947, "step": 752 }, { "epoch": 3.050126582278481, "grad_norm": 0.2725057335542469, "learning_rate": 1.5691990144020376e-05, "loss": 0.2895, "step": 753 }, { "epoch": 3.0541772151898736, "grad_norm": 0.2639287589569249, "learning_rate": 1.5636581256404297e-05, "loss": 0.2797, "step": 754 }, { "epoch": 3.0582278481012657, "grad_norm": 0.2541998073195875, "learning_rate": 1.558120751116291e-05, "loss": 0.2818, "step": 755 }, { "epoch": 3.062278481012658, "grad_norm": 0.27233274106319955, "learning_rate": 1.552586935426876e-05, "loss": 0.2829, "step": 756 }, { "epoch": 3.0663291139240507, "grad_norm": 0.29109983481060003, "learning_rate": 1.547056723140774e-05, "loss": 0.2945, "step": 757 }, { "epoch": 3.0703797468354432, "grad_norm": 0.28279981877728055, "learning_rate": 1.5415301587975565e-05, "loss": 0.2802, "step": 758 }, { "epoch": 3.0744303797468353, "grad_norm": 0.26920576357917964, "learning_rate": 1.536007286907411e-05, "loss": 0.2841, "step": 759 }, { "epoch": 3.078481012658228, "grad_norm": 0.290603437283236, "learning_rate": 1.5304881519507896e-05, "loss": 0.2747, "step": 760 }, { "epoch": 3.0825316455696203, "grad_norm": 0.2557796151742281, "learning_rate": 1.5249727983780453e-05, "loss": 0.2733, "step": 761 }, { "epoch": 3.086582278481013, "grad_norm": 0.2438501263109006, "learning_rate": 1.5194612706090786e-05, "loss": 0.2802, "step": 762 }, { "epoch": 3.090632911392405, "grad_norm": 0.2754023025387584, "learning_rate": 1.5139536130329771e-05, "loss": 0.2795, "step": 763 }, { "epoch": 3.0946835443037974, "grad_norm": 0.27981821345113345, "learning_rate": 1.508449870007656e-05, "loss": 0.2816, "step": 764 }, { "epoch": 3.09873417721519, "grad_norm": 0.24716443879172523, "learning_rate": 1.5029500858595056e-05, "loss": 0.2708, "step": 765 }, { "epoch": 3.1027848101265825, "grad_norm": 0.24800504302979992, "learning_rate": 1.4974543048830328e-05, "loss": 0.2804, "step": 766 }, { "epoch": 3.1068354430379745, "grad_norm": 0.26165944981892686, "learning_rate": 1.4919625713405e-05, "loss": 0.2828, "step": 767 }, { "epoch": 3.110886075949367, "grad_norm": 0.23826577494823586, "learning_rate": 1.4864749294615756e-05, "loss": 0.2879, "step": 768 }, { "epoch": 3.1149367088607596, "grad_norm": 0.22641356239067778, "learning_rate": 1.4809914234429716e-05, "loss": 0.2832, "step": 769 }, { "epoch": 3.118987341772152, "grad_norm": 0.247272845796454, "learning_rate": 1.4755120974480923e-05, "loss": 0.2829, "step": 770 }, { "epoch": 3.123037974683544, "grad_norm": 0.23363816360826745, "learning_rate": 1.4700369956066771e-05, "loss": 0.2797, "step": 771 }, { "epoch": 3.1270886075949367, "grad_norm": 0.2438582110211572, "learning_rate": 1.4645661620144413e-05, "loss": 0.282, "step": 772 }, { "epoch": 3.131139240506329, "grad_norm": 0.23537788033645582, "learning_rate": 1.4590996407327284e-05, "loss": 0.2799, "step": 773 }, { "epoch": 3.1351898734177217, "grad_norm": 0.23265030145688825, "learning_rate": 1.4536374757881487e-05, "loss": 0.2897, "step": 774 }, { "epoch": 3.1392405063291138, "grad_norm": 0.22795195386008643, "learning_rate": 1.4481797111722271e-05, "loss": 0.2854, "step": 775 }, { "epoch": 3.1432911392405063, "grad_norm": 0.2471683030567116, "learning_rate": 1.4427263908410507e-05, "loss": 0.2834, "step": 776 }, { "epoch": 3.147341772151899, "grad_norm": 0.2133857889781099, "learning_rate": 1.4372775587149108e-05, "loss": 0.2816, "step": 777 }, { "epoch": 3.1513924050632913, "grad_norm": 0.2293725997752909, "learning_rate": 1.4318332586779522e-05, "loss": 0.282, "step": 778 }, { "epoch": 3.1554430379746834, "grad_norm": 0.23023667472420348, "learning_rate": 1.4263935345778202e-05, "loss": 0.2925, "step": 779 }, { "epoch": 3.159493670886076, "grad_norm": 0.24703094736634804, "learning_rate": 1.420958430225303e-05, "loss": 0.2826, "step": 780 }, { "epoch": 3.1635443037974684, "grad_norm": 0.23075382149293194, "learning_rate": 1.415527989393985e-05, "loss": 0.2856, "step": 781 }, { "epoch": 3.167594936708861, "grad_norm": 0.23880836313834883, "learning_rate": 1.410102255819891e-05, "loss": 0.2863, "step": 782 }, { "epoch": 3.171645569620253, "grad_norm": 0.2489934978258691, "learning_rate": 1.404681273201131e-05, "loss": 0.2848, "step": 783 }, { "epoch": 3.1756962025316455, "grad_norm": 0.2401326964647999, "learning_rate": 1.399265085197556e-05, "loss": 0.2907, "step": 784 }, { "epoch": 3.179746835443038, "grad_norm": 0.2294285345957783, "learning_rate": 1.393853735430398e-05, "loss": 0.2846, "step": 785 }, { "epoch": 3.1837974683544306, "grad_norm": 0.2292111058440387, "learning_rate": 1.3884472674819246e-05, "loss": 0.2886, "step": 786 }, { "epoch": 3.1878481012658226, "grad_norm": 0.2233619832639575, "learning_rate": 1.3830457248950864e-05, "loss": 0.2917, "step": 787 }, { "epoch": 3.191898734177215, "grad_norm": 0.2365867844367519, "learning_rate": 1.377649151173163e-05, "loss": 0.277, "step": 788 }, { "epoch": 3.1959493670886077, "grad_norm": 0.24046628193162733, "learning_rate": 1.3722575897794181e-05, "loss": 0.2769, "step": 789 }, { "epoch": 3.2, "grad_norm": 0.2525297474159182, "learning_rate": 1.3668710841367472e-05, "loss": 0.2854, "step": 790 }, { "epoch": 3.2040506329113922, "grad_norm": 0.232659525727612, "learning_rate": 1.361489677627324e-05, "loss": 0.2802, "step": 791 }, { "epoch": 3.2081012658227848, "grad_norm": 0.26380920043140665, "learning_rate": 1.3561134135922585e-05, "loss": 0.276, "step": 792 }, { "epoch": 3.2121518987341773, "grad_norm": 0.22095609857717674, "learning_rate": 1.350742335331241e-05, "loss": 0.2892, "step": 793 }, { "epoch": 3.21620253164557, "grad_norm": 0.23962162034259968, "learning_rate": 1.345376486102198e-05, "loss": 0.2765, "step": 794 }, { "epoch": 3.220253164556962, "grad_norm": 0.2140512738951565, "learning_rate": 1.3400159091209414e-05, "loss": 0.2841, "step": 795 }, { "epoch": 3.2243037974683544, "grad_norm": 0.23247943924882938, "learning_rate": 1.3346606475608216e-05, "loss": 0.2824, "step": 796 }, { "epoch": 3.228354430379747, "grad_norm": 0.24514189608532264, "learning_rate": 1.3293107445523781e-05, "loss": 0.2968, "step": 797 }, { "epoch": 3.2324050632911394, "grad_norm": 0.23797557900526128, "learning_rate": 1.3239662431829949e-05, "loss": 0.2873, "step": 798 }, { "epoch": 3.2364556962025315, "grad_norm": 0.2324925131495259, "learning_rate": 1.3186271864965509e-05, "loss": 0.2895, "step": 799 }, { "epoch": 3.240506329113924, "grad_norm": 0.20250142273077626, "learning_rate": 1.3132936174930756e-05, "loss": 0.2812, "step": 800 }, { "epoch": 3.2445569620253165, "grad_norm": 0.2394074650234095, "learning_rate": 1.3079655791283995e-05, "loss": 0.2706, "step": 801 }, { "epoch": 3.248607594936709, "grad_norm": 0.2228580314937344, "learning_rate": 1.3026431143138108e-05, "loss": 0.2785, "step": 802 }, { "epoch": 3.252658227848101, "grad_norm": 0.22041982142548047, "learning_rate": 1.2973262659157114e-05, "loss": 0.2879, "step": 803 }, { "epoch": 3.2567088607594936, "grad_norm": 0.22560005570776184, "learning_rate": 1.2920150767552651e-05, "loss": 0.2867, "step": 804 }, { "epoch": 3.260759493670886, "grad_norm": 0.2121120625175986, "learning_rate": 1.2867095896080607e-05, "loss": 0.2865, "step": 805 }, { "epoch": 3.2648101265822786, "grad_norm": 0.20962344720783885, "learning_rate": 1.2814098472037612e-05, "loss": 0.2867, "step": 806 }, { "epoch": 3.2688607594936707, "grad_norm": 0.2116946822237789, "learning_rate": 1.276115892225764e-05, "loss": 0.2721, "step": 807 }, { "epoch": 3.2729113924050632, "grad_norm": 0.20164929706071877, "learning_rate": 1.2708277673108555e-05, "loss": 0.2737, "step": 808 }, { "epoch": 3.2769620253164558, "grad_norm": 0.24067188798858116, "learning_rate": 1.2655455150488649e-05, "loss": 0.287, "step": 809 }, { "epoch": 3.2810126582278483, "grad_norm": 0.24559396518870674, "learning_rate": 1.2602691779823272e-05, "loss": 0.283, "step": 810 }, { "epoch": 3.2850632911392403, "grad_norm": 0.22387071699427114, "learning_rate": 1.2549987986061355e-05, "loss": 0.2857, "step": 811 }, { "epoch": 3.289113924050633, "grad_norm": 0.2477308651443567, "learning_rate": 1.2497344193672005e-05, "loss": 0.2928, "step": 812 }, { "epoch": 3.2931645569620254, "grad_norm": 0.21125612308380837, "learning_rate": 1.2444760826641092e-05, "loss": 0.2856, "step": 813 }, { "epoch": 3.297215189873418, "grad_norm": 0.20203486074761315, "learning_rate": 1.2392238308467817e-05, "loss": 0.2838, "step": 814 }, { "epoch": 3.30126582278481, "grad_norm": 0.2140403881581592, "learning_rate": 1.2339777062161326e-05, "loss": 0.275, "step": 815 }, { "epoch": 3.3053164556962025, "grad_norm": 0.22699994953226146, "learning_rate": 1.2287377510237293e-05, "loss": 0.2893, "step": 816 }, { "epoch": 3.309367088607595, "grad_norm": 0.22265135538391825, "learning_rate": 1.2235040074714488e-05, "loss": 0.2854, "step": 817 }, { "epoch": 3.3134177215189875, "grad_norm": 0.23195804045412532, "learning_rate": 1.2182765177111434e-05, "loss": 0.2799, "step": 818 }, { "epoch": 3.3174683544303796, "grad_norm": 0.2205003049049808, "learning_rate": 1.213055323844297e-05, "loss": 0.2868, "step": 819 }, { "epoch": 3.321518987341772, "grad_norm": 0.22219862597853787, "learning_rate": 1.2078404679216864e-05, "loss": 0.2793, "step": 820 }, { "epoch": 3.3255696202531646, "grad_norm": 0.23806436185805088, "learning_rate": 1.2026319919430458e-05, "loss": 0.2904, "step": 821 }, { "epoch": 3.329620253164557, "grad_norm": 0.2137997298253505, "learning_rate": 1.1974299378567227e-05, "loss": 0.2887, "step": 822 }, { "epoch": 3.333670886075949, "grad_norm": 0.21335624060985392, "learning_rate": 1.1922343475593462e-05, "loss": 0.2804, "step": 823 }, { "epoch": 3.3377215189873417, "grad_norm": 0.23681021808180122, "learning_rate": 1.187045262895488e-05, "loss": 0.2833, "step": 824 }, { "epoch": 3.3417721518987342, "grad_norm": 0.20898533989053297, "learning_rate": 1.1818627256573203e-05, "loss": 0.2829, "step": 825 }, { "epoch": 3.3458227848101267, "grad_norm": 0.20880887215657615, "learning_rate": 1.1766867775842864e-05, "loss": 0.2856, "step": 826 }, { "epoch": 3.349873417721519, "grad_norm": 0.22407222384726097, "learning_rate": 1.1715174603627615e-05, "loss": 0.2759, "step": 827 }, { "epoch": 3.3539240506329113, "grad_norm": 0.20298677581905333, "learning_rate": 1.1663548156257147e-05, "loss": 0.2825, "step": 828 }, { "epoch": 3.357974683544304, "grad_norm": 0.22727079113480184, "learning_rate": 1.161198884952377e-05, "loss": 0.2725, "step": 829 }, { "epoch": 3.3620253164556964, "grad_norm": 0.21414132285796564, "learning_rate": 1.1560497098679056e-05, "loss": 0.2887, "step": 830 }, { "epoch": 3.3660759493670884, "grad_norm": 0.2148552512154992, "learning_rate": 1.1509073318430479e-05, "loss": 0.2697, "step": 831 }, { "epoch": 3.370126582278481, "grad_norm": 0.230094636024686, "learning_rate": 1.1457717922938116e-05, "loss": 0.2887, "step": 832 }, { "epoch": 3.3741772151898735, "grad_norm": 0.8010196488669155, "learning_rate": 1.1406431325811233e-05, "loss": 0.2938, "step": 833 }, { "epoch": 3.378227848101266, "grad_norm": 0.22529378107360798, "learning_rate": 1.135521394010506e-05, "loss": 0.2867, "step": 834 }, { "epoch": 3.382278481012658, "grad_norm": 0.23005625134606905, "learning_rate": 1.1304066178317367e-05, "loss": 0.2722, "step": 835 }, { "epoch": 3.3863291139240506, "grad_norm": 0.21846122592746728, "learning_rate": 1.1252988452385199e-05, "loss": 0.2921, "step": 836 }, { "epoch": 3.390379746835443, "grad_norm": 0.2310486645668538, "learning_rate": 1.1201981173681536e-05, "loss": 0.272, "step": 837 }, { "epoch": 3.3944303797468356, "grad_norm": 0.22113580483661013, "learning_rate": 1.1151044753011991e-05, "loss": 0.2846, "step": 838 }, { "epoch": 3.3984810126582277, "grad_norm": 0.2057894524558694, "learning_rate": 1.1100179600611491e-05, "loss": 0.2817, "step": 839 }, { "epoch": 3.40253164556962, "grad_norm": 0.22995236149075454, "learning_rate": 1.1049386126140985e-05, "loss": 0.2833, "step": 840 }, { "epoch": 3.4065822784810127, "grad_norm": 0.25404776358669695, "learning_rate": 1.0998664738684128e-05, "loss": 0.2838, "step": 841 }, { "epoch": 3.410632911392405, "grad_norm": 0.21720618686259427, "learning_rate": 1.0948015846744e-05, "loss": 0.2806, "step": 842 }, { "epoch": 3.4146835443037973, "grad_norm": 0.22855874484122393, "learning_rate": 1.0897439858239832e-05, "loss": 0.283, "step": 843 }, { "epoch": 3.41873417721519, "grad_norm": 0.22075104274586976, "learning_rate": 1.0846937180503652e-05, "loss": 0.2857, "step": 844 }, { "epoch": 3.4227848101265823, "grad_norm": 0.20093622711984815, "learning_rate": 1.0796508220277117e-05, "loss": 0.2708, "step": 845 }, { "epoch": 3.426835443037975, "grad_norm": 0.21337284912786056, "learning_rate": 1.0746153383708107e-05, "loss": 0.2786, "step": 846 }, { "epoch": 3.430886075949367, "grad_norm": 0.19629129266937392, "learning_rate": 1.0695873076347579e-05, "loss": 0.2804, "step": 847 }, { "epoch": 3.4349367088607594, "grad_norm": 0.230654187726251, "learning_rate": 1.0645667703146205e-05, "loss": 0.2894, "step": 848 }, { "epoch": 3.438987341772152, "grad_norm": 0.21177589629631802, "learning_rate": 1.0595537668451161e-05, "loss": 0.2689, "step": 849 }, { "epoch": 3.4430379746835444, "grad_norm": 0.22497511835976686, "learning_rate": 1.0545483376002854e-05, "loss": 0.2792, "step": 850 }, { "epoch": 3.4470886075949365, "grad_norm": 0.20697200729182794, "learning_rate": 1.0495505228931676e-05, "loss": 0.2782, "step": 851 }, { "epoch": 3.451139240506329, "grad_norm": 0.21326541240934602, "learning_rate": 1.044560362975474e-05, "loss": 0.2742, "step": 852 }, { "epoch": 3.4551898734177215, "grad_norm": 0.22128882723443577, "learning_rate": 1.0395778980372695e-05, "loss": 0.2721, "step": 853 }, { "epoch": 3.459240506329114, "grad_norm": 0.1962764383409489, "learning_rate": 1.0346031682066381e-05, "loss": 0.2746, "step": 854 }, { "epoch": 3.463291139240506, "grad_norm": 0.2282900206962145, "learning_rate": 1.0296362135493724e-05, "loss": 0.2913, "step": 855 }, { "epoch": 3.4673417721518986, "grad_norm": 0.21557651281739967, "learning_rate": 1.0246770740686422e-05, "loss": 0.2789, "step": 856 }, { "epoch": 3.471392405063291, "grad_norm": 0.20838391443177645, "learning_rate": 1.0197257897046743e-05, "loss": 0.2759, "step": 857 }, { "epoch": 3.4754430379746837, "grad_norm": 0.21544120445134857, "learning_rate": 1.014782400334433e-05, "loss": 0.2901, "step": 858 }, { "epoch": 3.479493670886076, "grad_norm": 0.22236049981281752, "learning_rate": 1.009846945771296e-05, "loss": 0.2802, "step": 859 }, { "epoch": 3.4835443037974683, "grad_norm": 0.21384023755238088, "learning_rate": 1.0049194657647363e-05, "loss": 0.2803, "step": 860 }, { "epoch": 3.487594936708861, "grad_norm": 0.2157118350399454, "learning_rate": 1.0000000000000006e-05, "loss": 0.2775, "step": 861 }, { "epoch": 3.4916455696202533, "grad_norm": 0.20904257742036159, "learning_rate": 9.950885880977891e-06, "loss": 0.2852, "step": 862 }, { "epoch": 3.4956962025316454, "grad_norm": 0.20438578768624863, "learning_rate": 9.901852696139382e-06, "loss": 0.2777, "step": 863 }, { "epoch": 3.499746835443038, "grad_norm": 0.19176349154077982, "learning_rate": 9.852900840391027e-06, "loss": 0.276, "step": 864 }, { "epoch": 3.5037974683544304, "grad_norm": 0.20599991774284707, "learning_rate": 9.804030707984313e-06, "loss": 0.2893, "step": 865 }, { "epoch": 3.507848101265823, "grad_norm": 0.20109127572657337, "learning_rate": 9.755242692512599e-06, "loss": 0.2762, "step": 866 }, { "epoch": 3.5118987341772154, "grad_norm": 0.20844447533322005, "learning_rate": 9.70653718690782e-06, "loss": 0.28, "step": 867 }, { "epoch": 3.5159493670886075, "grad_norm": 0.20804791950841225, "learning_rate": 9.657914583437454e-06, "loss": 0.2863, "step": 868 }, { "epoch": 3.52, "grad_norm": 0.204116211796302, "learning_rate": 9.609375273701246e-06, "loss": 0.277, "step": 869 }, { "epoch": 3.5240506329113925, "grad_norm": 0.1896900380082347, "learning_rate": 9.560919648628133e-06, "loss": 0.2767, "step": 870 }, { "epoch": 3.5281012658227846, "grad_norm": 0.1942634160799906, "learning_rate": 9.512548098473047e-06, "loss": 0.285, "step": 871 }, { "epoch": 3.532151898734177, "grad_norm": 0.20958816598488644, "learning_rate": 9.464261012813825e-06, "loss": 0.274, "step": 872 }, { "epoch": 3.5362025316455696, "grad_norm": 0.20037673795689973, "learning_rate": 9.416058780547987e-06, "loss": 0.2699, "step": 873 }, { "epoch": 3.540253164556962, "grad_norm": 0.22811327221022626, "learning_rate": 9.367941789889714e-06, "loss": 0.2762, "step": 874 }, { "epoch": 3.5443037974683547, "grad_norm": 0.21163619212592, "learning_rate": 9.319910428366607e-06, "loss": 0.2753, "step": 875 }, { "epoch": 3.5483544303797467, "grad_norm": 0.20911901484700018, "learning_rate": 9.271965082816667e-06, "loss": 0.2859, "step": 876 }, { "epoch": 3.5524050632911393, "grad_norm": 0.21919770238137012, "learning_rate": 9.224106139385111e-06, "loss": 0.2809, "step": 877 }, { "epoch": 3.5564556962025318, "grad_norm": 0.21833459608239464, "learning_rate": 9.176333983521291e-06, "loss": 0.2831, "step": 878 }, { "epoch": 3.560506329113924, "grad_norm": 0.19582260356380854, "learning_rate": 9.12864899997558e-06, "loss": 0.2805, "step": 879 }, { "epoch": 3.5645569620253164, "grad_norm": 0.2030980224713768, "learning_rate": 9.08105157279628e-06, "loss": 0.2834, "step": 880 }, { "epoch": 3.568607594936709, "grad_norm": 0.20711957086040564, "learning_rate": 9.03354208532653e-06, "loss": 0.2754, "step": 881 }, { "epoch": 3.5726582278481014, "grad_norm": 0.20650945149053604, "learning_rate": 8.986120920201205e-06, "loss": 0.2946, "step": 882 }, { "epoch": 3.576708860759494, "grad_norm": 0.2012911436838596, "learning_rate": 8.938788459343852e-06, "loss": 0.2759, "step": 883 }, { "epoch": 3.580759493670886, "grad_norm": 0.1974063400768925, "learning_rate": 8.8915450839636e-06, "loss": 0.2742, "step": 884 }, { "epoch": 3.5848101265822785, "grad_norm": 0.22095284132608264, "learning_rate": 8.844391174552116e-06, "loss": 0.2767, "step": 885 }, { "epoch": 3.588860759493671, "grad_norm": 0.22089955012379675, "learning_rate": 8.797327110880479e-06, "loss": 0.2873, "step": 886 }, { "epoch": 3.592911392405063, "grad_norm": 0.20937618064878133, "learning_rate": 8.750353271996206e-06, "loss": 0.2763, "step": 887 }, { "epoch": 3.5969620253164556, "grad_norm": 0.20047321110668553, "learning_rate": 8.703470036220132e-06, "loss": 0.2871, "step": 888 }, { "epoch": 3.601012658227848, "grad_norm": 0.21369393098080447, "learning_rate": 8.656677781143394e-06, "loss": 0.2847, "step": 889 }, { "epoch": 3.6050632911392406, "grad_norm": 0.20852903643585743, "learning_rate": 8.609976883624377e-06, "loss": 0.2931, "step": 890 }, { "epoch": 3.609113924050633, "grad_norm": 0.2039230924137743, "learning_rate": 8.563367719785698e-06, "loss": 0.2929, "step": 891 }, { "epoch": 3.613164556962025, "grad_norm": 0.21706652274490915, "learning_rate": 8.516850665011138e-06, "loss": 0.2791, "step": 892 }, { "epoch": 3.6172151898734177, "grad_norm": 0.21341001623272912, "learning_rate": 8.47042609394269e-06, "loss": 0.2803, "step": 893 }, { "epoch": 3.6212658227848102, "grad_norm": 0.21815236012078035, "learning_rate": 8.424094380477432e-06, "loss": 0.2767, "step": 894 }, { "epoch": 3.6253164556962023, "grad_norm": 0.22392275859306673, "learning_rate": 8.37785589776465e-06, "loss": 0.2821, "step": 895 }, { "epoch": 3.629367088607595, "grad_norm": 0.20857757754133222, "learning_rate": 8.331711018202694e-06, "loss": 0.2845, "step": 896 }, { "epoch": 3.6334177215189873, "grad_norm": 0.2358191298054322, "learning_rate": 8.285660113436104e-06, "loss": 0.279, "step": 897 }, { "epoch": 3.63746835443038, "grad_norm": 0.2040329510952304, "learning_rate": 8.239703554352527e-06, "loss": 0.2876, "step": 898 }, { "epoch": 3.6415189873417724, "grad_norm": 0.20638345602194458, "learning_rate": 8.193841711079775e-06, "loss": 0.2788, "step": 899 }, { "epoch": 3.6455696202531644, "grad_norm": 0.23513442524856884, "learning_rate": 8.148074952982828e-06, "loss": 0.2753, "step": 900 }, { "epoch": 3.649620253164557, "grad_norm": 0.21056760105545083, "learning_rate": 8.102403648660859e-06, "loss": 0.2879, "step": 901 }, { "epoch": 3.6536708860759495, "grad_norm": 0.21741655578879437, "learning_rate": 8.056828165944282e-06, "loss": 0.2719, "step": 902 }, { "epoch": 3.6577215189873415, "grad_norm": 0.23591163209837945, "learning_rate": 8.011348871891762e-06, "loss": 0.2848, "step": 903 }, { "epoch": 3.661772151898734, "grad_norm": 0.19762670768377702, "learning_rate": 7.965966132787287e-06, "loss": 0.2824, "step": 904 }, { "epoch": 3.6658227848101266, "grad_norm": 0.21402720004153764, "learning_rate": 7.920680314137189e-06, "loss": 0.2794, "step": 905 }, { "epoch": 3.669873417721519, "grad_norm": 0.21996611835946897, "learning_rate": 7.875491780667246e-06, "loss": 0.2781, "step": 906 }, { "epoch": 3.6739240506329116, "grad_norm": 0.1946038367418936, "learning_rate": 7.830400896319667e-06, "loss": 0.278, "step": 907 }, { "epoch": 3.6779746835443037, "grad_norm": 0.21542537827940705, "learning_rate": 7.785408024250259e-06, "loss": 0.2807, "step": 908 }, { "epoch": 3.682025316455696, "grad_norm": 0.24583102226676354, "learning_rate": 7.74051352682542e-06, "loss": 0.2802, "step": 909 }, { "epoch": 3.6860759493670887, "grad_norm": 0.1922002241288014, "learning_rate": 7.695717765619257e-06, "loss": 0.286, "step": 910 }, { "epoch": 3.690126582278481, "grad_norm": 0.19681625122224194, "learning_rate": 7.651021101410673e-06, "loss": 0.2771, "step": 911 }, { "epoch": 3.6941772151898733, "grad_norm": 0.2451987670990835, "learning_rate": 7.606423894180464e-06, "loss": 0.2814, "step": 912 }, { "epoch": 3.698227848101266, "grad_norm": 0.21492441372245916, "learning_rate": 7.56192650310839e-06, "loss": 0.2758, "step": 913 }, { "epoch": 3.7022784810126583, "grad_norm": 0.19246424485085398, "learning_rate": 7.517529286570349e-06, "loss": 0.2874, "step": 914 }, { "epoch": 3.706329113924051, "grad_norm": 0.22179981554509232, "learning_rate": 7.473232602135387e-06, "loss": 0.2927, "step": 915 }, { "epoch": 3.710379746835443, "grad_norm": 0.20651255675483768, "learning_rate": 7.429036806562935e-06, "loss": 0.2851, "step": 916 }, { "epoch": 3.7144303797468354, "grad_norm": 0.19798916930719354, "learning_rate": 7.3849422557998455e-06, "loss": 0.2834, "step": 917 }, { "epoch": 3.718481012658228, "grad_norm": 0.19966261738984548, "learning_rate": 7.340949304977567e-06, "loss": 0.2758, "step": 918 }, { "epoch": 3.72253164556962, "grad_norm": 0.21201478366178997, "learning_rate": 7.297058308409282e-06, "loss": 0.2899, "step": 919 }, { "epoch": 3.7265822784810125, "grad_norm": 0.19917600317408218, "learning_rate": 7.25326961958704e-06, "loss": 0.2887, "step": 920 }, { "epoch": 3.730632911392405, "grad_norm": 0.19174145583271374, "learning_rate": 7.209583591178921e-06, "loss": 0.2806, "step": 921 }, { "epoch": 3.7346835443037976, "grad_norm": 0.20212939284838913, "learning_rate": 7.1660005750261925e-06, "loss": 0.2787, "step": 922 }, { "epoch": 3.73873417721519, "grad_norm": 0.1948371922056933, "learning_rate": 7.1225209221404765e-06, "loss": 0.285, "step": 923 }, { "epoch": 3.742784810126582, "grad_norm": 0.18862280615595856, "learning_rate": 7.079144982700909e-06, "loss": 0.288, "step": 924 }, { "epoch": 3.7468354430379747, "grad_norm": 0.20184085359768927, "learning_rate": 7.0358731060513695e-06, "loss": 0.2819, "step": 925 }, { "epoch": 3.750886075949367, "grad_norm": 0.201164106020583, "learning_rate": 6.99270564069757e-06, "loss": 0.293, "step": 926 }, { "epoch": 3.7549367088607593, "grad_norm": 0.21251409980874192, "learning_rate": 6.949642934304375e-06, "loss": 0.284, "step": 927 }, { "epoch": 3.7589873417721518, "grad_norm": 0.20796248655362898, "learning_rate": 6.906685333692871e-06, "loss": 0.2736, "step": 928 }, { "epoch": 3.7630379746835443, "grad_norm": 0.1988327581660035, "learning_rate": 6.86383318483769e-06, "loss": 0.2932, "step": 929 }, { "epoch": 3.767088607594937, "grad_norm": 0.2067569314382297, "learning_rate": 6.821086832864139e-06, "loss": 0.2774, "step": 930 }, { "epoch": 3.7711392405063293, "grad_norm": 0.1883012566752189, "learning_rate": 6.77844662204546e-06, "loss": 0.2793, "step": 931 }, { "epoch": 3.7751898734177214, "grad_norm": 0.1954908955127146, "learning_rate": 6.7359128958000455e-06, "loss": 0.2757, "step": 932 }, { "epoch": 3.779240506329114, "grad_norm": 0.19560119744477766, "learning_rate": 6.693485996688695e-06, "loss": 0.2852, "step": 933 }, { "epoch": 3.7832911392405064, "grad_norm": 0.1867682157424592, "learning_rate": 6.651166266411801e-06, "loss": 0.2873, "step": 934 }, { "epoch": 3.7873417721518985, "grad_norm": 0.18540865161759726, "learning_rate": 6.6089540458066725e-06, "loss": 0.2846, "step": 935 }, { "epoch": 3.791392405063291, "grad_norm": 0.19575016705068823, "learning_rate": 6.566849674844711e-06, "loss": 0.2695, "step": 936 }, { "epoch": 3.7954430379746835, "grad_norm": 0.19102562967772097, "learning_rate": 6.524853492628747e-06, "loss": 0.2739, "step": 937 }, { "epoch": 3.799493670886076, "grad_norm": 0.19155547942966447, "learning_rate": 6.4829658373902536e-06, "loss": 0.2797, "step": 938 }, { "epoch": 3.8035443037974686, "grad_norm": 0.19287987942568458, "learning_rate": 6.441187046486648e-06, "loss": 0.2883, "step": 939 }, { "epoch": 3.8075949367088606, "grad_norm": 0.20002771816325274, "learning_rate": 6.399517456398567e-06, "loss": 0.2718, "step": 940 }, { "epoch": 3.811645569620253, "grad_norm": 0.195879261515232, "learning_rate": 6.357957402727164e-06, "loss": 0.2761, "step": 941 }, { "epoch": 3.8156962025316457, "grad_norm": 0.18574223069120124, "learning_rate": 6.316507220191395e-06, "loss": 0.2878, "step": 942 }, { "epoch": 3.8197468354430377, "grad_norm": 0.19479614783193672, "learning_rate": 6.275167242625331e-06, "loss": 0.2837, "step": 943 }, { "epoch": 3.8237974683544302, "grad_norm": 0.1979466226919014, "learning_rate": 6.233937802975471e-06, "loss": 0.2756, "step": 944 }, { "epoch": 3.8278481012658228, "grad_norm": 0.19293427379334183, "learning_rate": 6.192819233298046e-06, "loss": 0.2827, "step": 945 }, { "epoch": 3.8318987341772153, "grad_norm": 0.19595109469166264, "learning_rate": 6.151811864756383e-06, "loss": 0.2777, "step": 946 }, { "epoch": 3.835949367088608, "grad_norm": 0.18819270391841758, "learning_rate": 6.1109160276181655e-06, "loss": 0.2816, "step": 947 }, { "epoch": 3.84, "grad_norm": 0.18040963747191643, "learning_rate": 6.070132051252868e-06, "loss": 0.2861, "step": 948 }, { "epoch": 3.8440506329113924, "grad_norm": 0.19173368888371134, "learning_rate": 6.0294602641290034e-06, "loss": 0.2853, "step": 949 }, { "epoch": 3.848101265822785, "grad_norm": 0.18184226609342913, "learning_rate": 5.988900993811575e-06, "loss": 0.272, "step": 950 }, { "epoch": 3.852151898734177, "grad_norm": 0.19234221621117176, "learning_rate": 5.948454566959363e-06, "loss": 0.2778, "step": 951 }, { "epoch": 3.8562025316455695, "grad_norm": 0.1915672004640378, "learning_rate": 5.908121309322328e-06, "loss": 0.2763, "step": 952 }, { "epoch": 3.860253164556962, "grad_norm": 0.20227741693879245, "learning_rate": 5.867901545738976e-06, "loss": 0.2809, "step": 953 }, { "epoch": 3.8643037974683545, "grad_norm": 0.19942807233563473, "learning_rate": 5.827795600133774e-06, "loss": 0.2745, "step": 954 }, { "epoch": 3.868354430379747, "grad_norm": 0.2031426580818639, "learning_rate": 5.787803795514466e-06, "loss": 0.2848, "step": 955 }, { "epoch": 3.872405063291139, "grad_norm": 0.18735705838602545, "learning_rate": 5.747926453969576e-06, "loss": 0.2789, "step": 956 }, { "epoch": 3.8764556962025316, "grad_norm": 0.19303992732383507, "learning_rate": 5.708163896665708e-06, "loss": 0.2751, "step": 957 }, { "epoch": 3.880506329113924, "grad_norm": 0.19868910681407714, "learning_rate": 5.668516443845047e-06, "loss": 0.2857, "step": 958 }, { "epoch": 3.884556962025316, "grad_norm": 0.18137408871370375, "learning_rate": 5.6289844148227225e-06, "loss": 0.2784, "step": 959 }, { "epoch": 3.8886075949367087, "grad_norm": 0.18569040745122978, "learning_rate": 5.5895681279842615e-06, "loss": 0.279, "step": 960 }, { "epoch": 3.8926582278481012, "grad_norm": 0.18368026147107644, "learning_rate": 5.550267900783019e-06, "loss": 0.2794, "step": 961 }, { "epoch": 3.8967088607594937, "grad_norm": 0.191480585335417, "learning_rate": 5.511084049737623e-06, "loss": 0.2915, "step": 962 }, { "epoch": 3.9007594936708863, "grad_norm": 0.1755900283354759, "learning_rate": 5.4720168904294215e-06, "loss": 0.2796, "step": 963 }, { "epoch": 3.9048101265822783, "grad_norm": 0.19524683217153566, "learning_rate": 5.433066737499948e-06, "loss": 0.2809, "step": 964 }, { "epoch": 3.908860759493671, "grad_norm": 0.19049923005810115, "learning_rate": 5.394233904648376e-06, "loss": 0.2747, "step": 965 }, { "epoch": 3.9129113924050634, "grad_norm": 0.18959482364883654, "learning_rate": 5.355518704628997e-06, "loss": 0.2806, "step": 966 }, { "epoch": 3.9169620253164554, "grad_norm": 0.1981691257159052, "learning_rate": 5.316921449248731e-06, "loss": 0.278, "step": 967 }, { "epoch": 3.921012658227848, "grad_norm": 0.185609411573403, "learning_rate": 5.278442449364538e-06, "loss": 0.2781, "step": 968 }, { "epoch": 3.9250632911392405, "grad_norm": 0.20256933157428475, "learning_rate": 5.240082014881016e-06, "loss": 0.2759, "step": 969 }, { "epoch": 3.929113924050633, "grad_norm": 0.20152838138338688, "learning_rate": 5.201840454747822e-06, "loss": 0.285, "step": 970 }, { "epoch": 3.9331645569620255, "grad_norm": 0.21941474360437788, "learning_rate": 5.163718076957223e-06, "loss": 0.2824, "step": 971 }, { "epoch": 3.9372151898734176, "grad_norm": 0.17376717188295046, "learning_rate": 5.125715188541609e-06, "loss": 0.2726, "step": 972 }, { "epoch": 3.94126582278481, "grad_norm": 0.1930825604541352, "learning_rate": 5.087832095571021e-06, "loss": 0.2724, "step": 973 }, { "epoch": 3.9453164556962026, "grad_norm": 0.19212385576477078, "learning_rate": 5.0500691031506766e-06, "loss": 0.2758, "step": 974 }, { "epoch": 3.9493670886075947, "grad_norm": 0.1888786072701489, "learning_rate": 5.01242651541854e-06, "loss": 0.2728, "step": 975 }, { "epoch": 3.953417721518987, "grad_norm": 0.1847786146134642, "learning_rate": 4.974904635542815e-06, "loss": 0.2785, "step": 976 }, { "epoch": 3.9574683544303797, "grad_norm": 0.18391129460753433, "learning_rate": 4.937503765719582e-06, "loss": 0.2811, "step": 977 }, { "epoch": 3.961518987341772, "grad_norm": 0.18546523816815774, "learning_rate": 4.900224207170299e-06, "loss": 0.2796, "step": 978 }, { "epoch": 3.9655696202531647, "grad_norm": 0.19376541514832704, "learning_rate": 4.8630662601394065e-06, "loss": 0.2926, "step": 979 }, { "epoch": 3.969620253164557, "grad_norm": 0.18023115946395382, "learning_rate": 4.8260302238918995e-06, "loss": 0.2747, "step": 980 }, { "epoch": 3.9736708860759493, "grad_norm": 0.18606242474820409, "learning_rate": 4.789116396710924e-06, "loss": 0.285, "step": 981 }, { "epoch": 3.977721518987342, "grad_norm": 0.1824375548755175, "learning_rate": 4.752325075895368e-06, "loss": 0.2817, "step": 982 }, { "epoch": 3.981772151898734, "grad_norm": 0.20144808478307677, "learning_rate": 4.715656557757473e-06, "loss": 0.2807, "step": 983 }, { "epoch": 3.9858227848101264, "grad_norm": 0.1865428637543025, "learning_rate": 4.679111137620442e-06, "loss": 0.2846, "step": 984 }, { "epoch": 3.989873417721519, "grad_norm": 0.18817010538235107, "learning_rate": 4.6426891098160585e-06, "loss": 0.2837, "step": 985 }, { "epoch": 3.9939240506329114, "grad_norm": 0.18777432018151843, "learning_rate": 4.6063907676823474e-06, "loss": 0.2818, "step": 986 }, { "epoch": 3.997974683544304, "grad_norm": 0.17725120977636702, "learning_rate": 4.570216403561141e-06, "loss": 0.2756, "step": 987 }, { "epoch": 4.002025316455696, "grad_norm": 0.2204914044171772, "learning_rate": 4.534166308795815e-06, "loss": 0.2624, "step": 988 }, { "epoch": 4.006075949367089, "grad_norm": 0.29660645579729744, "learning_rate": 4.498240773728859e-06, "loss": 0.2524, "step": 989 }, { "epoch": 4.010126582278481, "grad_norm": 0.2190385579212289, "learning_rate": 4.462440087699609e-06, "loss": 0.2409, "step": 990 }, { "epoch": 4.014177215189873, "grad_norm": 0.37078942084526106, "learning_rate": 4.426764539041861e-06, "loss": 0.2517, "step": 991 }, { "epoch": 4.018227848101266, "grad_norm": 0.30384513044586176, "learning_rate": 4.391214415081582e-06, "loss": 0.2441, "step": 992 }, { "epoch": 4.022278481012658, "grad_norm": 0.231940193810648, "learning_rate": 4.355790002134579e-06, "loss": 0.2555, "step": 993 }, { "epoch": 4.02632911392405, "grad_norm": 0.3007736740016241, "learning_rate": 4.320491585504207e-06, "loss": 0.2472, "step": 994 }, { "epoch": 4.030379746835443, "grad_norm": 0.3098785415015643, "learning_rate": 4.2853194494790615e-06, "loss": 0.2426, "step": 995 }, { "epoch": 4.034430379746835, "grad_norm": 0.21784896983393756, "learning_rate": 4.250273877330691e-06, "loss": 0.2535, "step": 996 }, { "epoch": 4.038481012658228, "grad_norm": 0.2287065187472983, "learning_rate": 4.215355151311313e-06, "loss": 0.2488, "step": 997 }, { "epoch": 4.04253164556962, "grad_norm": 0.2510150164555489, "learning_rate": 4.180563552651542e-06, "loss": 0.2409, "step": 998 }, { "epoch": 4.046582278481012, "grad_norm": 0.2319614615481396, "learning_rate": 4.145899361558147e-06, "loss": 0.2412, "step": 999 }, { "epoch": 4.050632911392405, "grad_norm": 0.20360725940466115, "learning_rate": 4.111362857211738e-06, "loss": 0.2531, "step": 1000 }, { "epoch": 4.054683544303797, "grad_norm": 0.20017295174282518, "learning_rate": 4.076954317764592e-06, "loss": 0.2473, "step": 1001 }, { "epoch": 4.0587341772151895, "grad_norm": 0.21489961457106888, "learning_rate": 4.042674020338335e-06, "loss": 0.2384, "step": 1002 }, { "epoch": 4.062784810126582, "grad_norm": 0.21828829575898484, "learning_rate": 4.0085222410217835e-06, "loss": 0.25, "step": 1003 }, { "epoch": 4.0668354430379745, "grad_norm": 0.20493373136599755, "learning_rate": 3.974499254868674e-06, "loss": 0.2457, "step": 1004 }, { "epoch": 4.0708860759493675, "grad_norm": 0.21139990243309395, "learning_rate": 3.940605335895451e-06, "loss": 0.2456, "step": 1005 }, { "epoch": 4.0749367088607595, "grad_norm": 0.2349728297774634, "learning_rate": 3.90684075707908e-06, "loss": 0.2518, "step": 1006 }, { "epoch": 4.078987341772152, "grad_norm": 0.19119517216491175, "learning_rate": 3.8732057903548505e-06, "loss": 0.2435, "step": 1007 }, { "epoch": 4.083037974683545, "grad_norm": 0.19426625865648528, "learning_rate": 3.8397007066141375e-06, "loss": 0.245, "step": 1008 }, { "epoch": 4.087088607594937, "grad_norm": 0.1988176944702149, "learning_rate": 3.806325775702304e-06, "loss": 0.2536, "step": 1009 }, { "epoch": 4.091139240506329, "grad_norm": 0.1935026414657581, "learning_rate": 3.773081266416434e-06, "loss": 0.2456, "step": 1010 }, { "epoch": 4.095189873417722, "grad_norm": 0.19401659178542485, "learning_rate": 3.739967446503245e-06, "loss": 0.2452, "step": 1011 }, { "epoch": 4.099240506329114, "grad_norm": 0.18428783341502633, "learning_rate": 3.706984582656894e-06, "loss": 0.2458, "step": 1012 }, { "epoch": 4.103291139240507, "grad_norm": 0.1991882431147228, "learning_rate": 3.6741329405168237e-06, "loss": 0.2428, "step": 1013 }, { "epoch": 4.107341772151899, "grad_norm": 0.1942398257017, "learning_rate": 3.641412784665648e-06, "loss": 0.2456, "step": 1014 }, { "epoch": 4.111392405063291, "grad_norm": 0.1808166346180385, "learning_rate": 3.608824378627005e-06, "loss": 0.2426, "step": 1015 }, { "epoch": 4.115443037974684, "grad_norm": 0.18502888923208158, "learning_rate": 3.5763679848634337e-06, "loss": 0.2481, "step": 1016 }, { "epoch": 4.119493670886076, "grad_norm": 0.1822662663075149, "learning_rate": 3.544043864774269e-06, "loss": 0.2511, "step": 1017 }, { "epoch": 4.123544303797468, "grad_norm": 0.1888929885252409, "learning_rate": 3.5118522786935282e-06, "loss": 0.2473, "step": 1018 }, { "epoch": 4.127594936708861, "grad_norm": 0.1830373083177208, "learning_rate": 3.479793485887819e-06, "loss": 0.2513, "step": 1019 }, { "epoch": 4.131645569620253, "grad_norm": 0.1821666910296491, "learning_rate": 3.4478677445542653e-06, "loss": 0.2364, "step": 1020 }, { "epoch": 4.135696202531646, "grad_norm": 0.19381735392947683, "learning_rate": 3.4160753118183767e-06, "loss": 0.2561, "step": 1021 }, { "epoch": 4.139746835443038, "grad_norm": 0.19002840051547723, "learning_rate": 3.3844164437320527e-06, "loss": 0.2477, "step": 1022 }, { "epoch": 4.14379746835443, "grad_norm": 0.1898320796684689, "learning_rate": 3.3528913952714558e-06, "loss": 0.2491, "step": 1023 }, { "epoch": 4.147848101265823, "grad_norm": 0.1844132620059918, "learning_rate": 3.321500420335e-06, "loss": 0.2409, "step": 1024 }, { "epoch": 4.151898734177215, "grad_norm": 0.18422667994157113, "learning_rate": 3.290243771741275e-06, "loss": 0.2482, "step": 1025 }, { "epoch": 4.155949367088607, "grad_norm": 0.19041620758780128, "learning_rate": 3.2591217012270325e-06, "loss": 0.2526, "step": 1026 }, { "epoch": 4.16, "grad_norm": 0.7081909370286524, "learning_rate": 3.228134459445149e-06, "loss": 0.255, "step": 1027 }, { "epoch": 4.164050632911392, "grad_norm": 0.19995685244662134, "learning_rate": 3.1972822959626205e-06, "loss": 0.2519, "step": 1028 }, { "epoch": 4.168101265822785, "grad_norm": 0.17525722163284857, "learning_rate": 3.166565459258513e-06, "loss": 0.2385, "step": 1029 }, { "epoch": 4.172151898734177, "grad_norm": 0.17920265049726528, "learning_rate": 3.1359841967220193e-06, "loss": 0.2476, "step": 1030 }, { "epoch": 4.176202531645569, "grad_norm": 0.1800688552530942, "learning_rate": 3.105538754650419e-06, "loss": 0.2528, "step": 1031 }, { "epoch": 4.180253164556962, "grad_norm": 0.1919177174890085, "learning_rate": 3.07522937824712e-06, "loss": 0.2459, "step": 1032 }, { "epoch": 4.184303797468354, "grad_norm": 0.18083805900612043, "learning_rate": 3.0450563116196697e-06, "loss": 0.2554, "step": 1033 }, { "epoch": 4.188354430379746, "grad_norm": 0.18927735542341184, "learning_rate": 3.0150197977778008e-06, "loss": 0.2516, "step": 1034 }, { "epoch": 4.192405063291139, "grad_norm": 0.18243006602946552, "learning_rate": 2.985120078631465e-06, "loss": 0.2351, "step": 1035 }, { "epoch": 4.1964556962025314, "grad_norm": 0.1742562945804944, "learning_rate": 2.9553573949888893e-06, "loss": 0.2516, "step": 1036 }, { "epoch": 4.200506329113924, "grad_norm": 0.17718084085553873, "learning_rate": 2.9257319865546384e-06, "loss": 0.2389, "step": 1037 }, { "epoch": 4.2045569620253165, "grad_norm": 0.19696892465871935, "learning_rate": 2.896244091927678e-06, "loss": 0.2399, "step": 1038 }, { "epoch": 4.2086075949367086, "grad_norm": 0.1850069284547718, "learning_rate": 2.8668939485994584e-06, "loss": 0.2506, "step": 1039 }, { "epoch": 4.2126582278481015, "grad_norm": 0.17557679148761457, "learning_rate": 2.837681792951994e-06, "loss": 0.2477, "step": 1040 }, { "epoch": 4.216708860759494, "grad_norm": 0.1790258789475921, "learning_rate": 2.808607860255981e-06, "loss": 0.2503, "step": 1041 }, { "epoch": 4.220759493670886, "grad_norm": 0.18355261410417584, "learning_rate": 2.7796723846688634e-06, "loss": 0.2402, "step": 1042 }, { "epoch": 4.224810126582279, "grad_norm": 0.1764125433995528, "learning_rate": 2.7508755992329937e-06, "loss": 0.2458, "step": 1043 }, { "epoch": 4.228860759493671, "grad_norm": 0.1847733314503205, "learning_rate": 2.722217735873718e-06, "loss": 0.2627, "step": 1044 }, { "epoch": 4.232911392405064, "grad_norm": 0.18106332994675636, "learning_rate": 2.6936990253975315e-06, "loss": 0.2475, "step": 1045 }, { "epoch": 4.236962025316456, "grad_norm": 0.17477595290220974, "learning_rate": 2.665319697490205e-06, "loss": 0.2462, "step": 1046 }, { "epoch": 4.241012658227848, "grad_norm": 0.17272752457213525, "learning_rate": 2.637079980714945e-06, "loss": 0.2414, "step": 1047 }, { "epoch": 4.245063291139241, "grad_norm": 0.1868683226873294, "learning_rate": 2.6089801025105453e-06, "loss": 0.2469, "step": 1048 }, { "epoch": 4.249113924050633, "grad_norm": 0.17755627820625172, "learning_rate": 2.581020289189571e-06, "loss": 0.2433, "step": 1049 }, { "epoch": 4.253164556962025, "grad_norm": 0.1697134963115736, "learning_rate": 2.553200765936501e-06, "loss": 0.2405, "step": 1050 }, { "epoch": 4.257215189873418, "grad_norm": 0.1714126039533855, "learning_rate": 2.525521756805962e-06, "loss": 0.2524, "step": 1051 }, { "epoch": 4.26126582278481, "grad_norm": 0.17310577922811415, "learning_rate": 2.497983484720885e-06, "loss": 0.2501, "step": 1052 }, { "epoch": 4.265316455696203, "grad_norm": 0.19506881783662433, "learning_rate": 2.470586171470728e-06, "loss": 0.2415, "step": 1053 }, { "epoch": 4.269367088607595, "grad_norm": 0.175642876814744, "learning_rate": 2.4433300377096836e-06, "loss": 0.2457, "step": 1054 }, { "epoch": 4.273417721518987, "grad_norm": 0.18192123271568236, "learning_rate": 2.4162153029549073e-06, "loss": 0.2586, "step": 1055 }, { "epoch": 4.27746835443038, "grad_norm": 0.17677813037136395, "learning_rate": 2.3892421855847458e-06, "loss": 0.2419, "step": 1056 }, { "epoch": 4.281518987341772, "grad_norm": 0.17341502007717502, "learning_rate": 2.362410902836978e-06, "loss": 0.2442, "step": 1057 }, { "epoch": 4.285569620253165, "grad_norm": 0.17610042571828438, "learning_rate": 2.3357216708070653e-06, "loss": 0.2477, "step": 1058 }, { "epoch": 4.289620253164557, "grad_norm": 0.18050575883914888, "learning_rate": 2.309174704446411e-06, "loss": 0.2454, "step": 1059 }, { "epoch": 4.293670886075949, "grad_norm": 0.17874900981677297, "learning_rate": 2.2827702175606437e-06, "loss": 0.2414, "step": 1060 }, { "epoch": 4.297721518987342, "grad_norm": 0.1670223704345936, "learning_rate": 2.256508422807855e-06, "loss": 0.2523, "step": 1061 }, { "epoch": 4.301772151898734, "grad_norm": 0.17564542901478944, "learning_rate": 2.230389531696946e-06, "loss": 0.2431, "step": 1062 }, { "epoch": 4.305822784810126, "grad_norm": 0.16739364406207577, "learning_rate": 2.204413754585857e-06, "loss": 0.244, "step": 1063 }, { "epoch": 4.309873417721519, "grad_norm": 0.17906216456041874, "learning_rate": 2.1785813006799406e-06, "loss": 0.249, "step": 1064 }, { "epoch": 4.313924050632911, "grad_norm": 0.1796931435408572, "learning_rate": 2.1528923780302224e-06, "loss": 0.2388, "step": 1065 }, { "epoch": 4.317974683544303, "grad_norm": 0.18025157233376246, "learning_rate": 2.127347193531757e-06, "loss": 0.2525, "step": 1066 }, { "epoch": 4.322025316455696, "grad_norm": 0.18004616100108492, "learning_rate": 2.101945952921942e-06, "loss": 0.2456, "step": 1067 }, { "epoch": 4.326075949367088, "grad_norm": 0.17457789155692202, "learning_rate": 2.0766888607788906e-06, "loss": 0.2473, "step": 1068 }, { "epoch": 4.330126582278481, "grad_norm": 0.17651593249327854, "learning_rate": 2.0515761205197337e-06, "loss": 0.2462, "step": 1069 }, { "epoch": 4.334177215189873, "grad_norm": 0.16900096735771775, "learning_rate": 2.0266079343990453e-06, "loss": 0.2473, "step": 1070 }, { "epoch": 4.3382278481012655, "grad_norm": 0.19415775165752028, "learning_rate": 2.0017845035071494e-06, "loss": 0.2354, "step": 1071 }, { "epoch": 4.3422784810126585, "grad_norm": 0.17723589454819574, "learning_rate": 1.9771060277685537e-06, "loss": 0.2367, "step": 1072 }, { "epoch": 4.3463291139240505, "grad_norm": 0.16940358654944634, "learning_rate": 1.95257270594031e-06, "loss": 0.2461, "step": 1073 }, { "epoch": 4.3503797468354435, "grad_norm": 0.17703964423131124, "learning_rate": 1.9281847356104188e-06, "loss": 0.2516, "step": 1074 }, { "epoch": 4.3544303797468356, "grad_norm": 0.19029918248091982, "learning_rate": 1.9039423131962365e-06, "loss": 0.2504, "step": 1075 }, { "epoch": 4.358481012658228, "grad_norm": 0.18218465814490936, "learning_rate": 1.8798456339429027e-06, "loss": 0.2369, "step": 1076 }, { "epoch": 4.362531645569621, "grad_norm": 0.17772350802882483, "learning_rate": 1.8558948919217612e-06, "loss": 0.2501, "step": 1077 }, { "epoch": 4.366582278481013, "grad_norm": 0.17998460391262466, "learning_rate": 1.8320902800287954e-06, "loss": 0.2365, "step": 1078 }, { "epoch": 4.370632911392405, "grad_norm": 0.1753640078079894, "learning_rate": 1.8084319899830726e-06, "loss": 0.2466, "step": 1079 }, { "epoch": 4.374683544303798, "grad_norm": 0.1728907324590177, "learning_rate": 1.7849202123252097e-06, "loss": 0.246, "step": 1080 }, { "epoch": 4.37873417721519, "grad_norm": 0.17022176236828584, "learning_rate": 1.7615551364158401e-06, "loss": 0.2537, "step": 1081 }, { "epoch": 4.382784810126582, "grad_norm": 0.1727296857733399, "learning_rate": 1.738336950434061e-06, "loss": 0.2501, "step": 1082 }, { "epoch": 4.386835443037975, "grad_norm": 0.17908129917386517, "learning_rate": 1.715265841375957e-06, "loss": 0.2441, "step": 1083 }, { "epoch": 4.390886075949367, "grad_norm": 0.1711450100743856, "learning_rate": 1.6923419950530684e-06, "loss": 0.2538, "step": 1084 }, { "epoch": 4.39493670886076, "grad_norm": 0.16950951734232741, "learning_rate": 1.6695655960909008e-06, "loss": 0.2411, "step": 1085 }, { "epoch": 4.398987341772152, "grad_norm": 0.1710888858006677, "learning_rate": 1.646936827927441e-06, "loss": 0.2473, "step": 1086 }, { "epoch": 4.403037974683544, "grad_norm": 0.17131393544638618, "learning_rate": 1.6244558728116766e-06, "loss": 0.2606, "step": 1087 }, { "epoch": 4.407088607594937, "grad_norm": 0.18644743567963024, "learning_rate": 1.6021229118021265e-06, "loss": 0.2437, "step": 1088 }, { "epoch": 4.411139240506329, "grad_norm": 0.1723284684905226, "learning_rate": 1.5799381247653967e-06, "loss": 0.2388, "step": 1089 }, { "epoch": 4.415189873417722, "grad_norm": 0.1694890798111992, "learning_rate": 1.5579016903747013e-06, "loss": 0.253, "step": 1090 }, { "epoch": 4.419240506329114, "grad_norm": 0.16676885362874036, "learning_rate": 1.5360137861084656e-06, "loss": 0.2545, "step": 1091 }, { "epoch": 4.423291139240506, "grad_norm": 0.1691757231838893, "learning_rate": 1.5142745882488475e-06, "loss": 0.2561, "step": 1092 }, { "epoch": 4.427341772151899, "grad_norm": 0.16768293731664682, "learning_rate": 1.4926842718803691e-06, "loss": 0.2431, "step": 1093 }, { "epoch": 4.431392405063291, "grad_norm": 0.17136019505340339, "learning_rate": 1.4712430108884657e-06, "loss": 0.2463, "step": 1094 }, { "epoch": 4.435443037974683, "grad_norm": 0.17424245523013263, "learning_rate": 1.4499509779581078e-06, "loss": 0.2546, "step": 1095 }, { "epoch": 4.439493670886076, "grad_norm": 0.1799224134270283, "learning_rate": 1.4288083445723988e-06, "loss": 0.2417, "step": 1096 }, { "epoch": 4.443544303797468, "grad_norm": 0.16377767436345256, "learning_rate": 1.4078152810112045e-06, "loss": 0.2497, "step": 1097 }, { "epoch": 4.44759493670886, "grad_norm": 0.1716775425081038, "learning_rate": 1.3869719563497697e-06, "loss": 0.2383, "step": 1098 }, { "epoch": 4.451645569620253, "grad_norm": 0.1676198735796929, "learning_rate": 1.3662785384573663e-06, "loss": 0.2448, "step": 1099 }, { "epoch": 4.455696202531645, "grad_norm": 0.16978035666456937, "learning_rate": 1.3457351939959383e-06, "loss": 0.2437, "step": 1100 }, { "epoch": 4.459746835443038, "grad_norm": 0.1671011567386778, "learning_rate": 1.3253420884187551e-06, "loss": 0.2471, "step": 1101 }, { "epoch": 4.46379746835443, "grad_norm": 0.1687322885722124, "learning_rate": 1.3050993859690953e-06, "loss": 0.2369, "step": 1102 }, { "epoch": 4.467848101265822, "grad_norm": 0.16960958617715044, "learning_rate": 1.2850072496788869e-06, "loss": 0.2454, "step": 1103 }, { "epoch": 4.471898734177215, "grad_norm": 0.16750354736234957, "learning_rate": 1.2650658413674434e-06, "loss": 0.2405, "step": 1104 }, { "epoch": 4.4759493670886075, "grad_norm": 0.17029931128418002, "learning_rate": 1.2452753216401226e-06, "loss": 0.2458, "step": 1105 }, { "epoch": 4.48, "grad_norm": 0.17371840265729602, "learning_rate": 1.2256358498870503e-06, "loss": 0.2412, "step": 1106 }, { "epoch": 4.4840506329113925, "grad_norm": 0.1746324979478279, "learning_rate": 1.2061475842818337e-06, "loss": 0.2487, "step": 1107 }, { "epoch": 4.488101265822785, "grad_norm": 0.17901973823907347, "learning_rate": 1.1868106817802816e-06, "loss": 0.2531, "step": 1108 }, { "epoch": 4.4921518987341775, "grad_norm": 0.1618501379283033, "learning_rate": 1.1676252981191482e-06, "loss": 0.2433, "step": 1109 }, { "epoch": 4.49620253164557, "grad_norm": 0.17473592562561763, "learning_rate": 1.1485915878148823e-06, "loss": 0.253, "step": 1110 }, { "epoch": 4.500253164556962, "grad_norm": 0.16800674217770226, "learning_rate": 1.1297097041623584e-06, "loss": 0.2446, "step": 1111 }, { "epoch": 4.504303797468355, "grad_norm": 0.16737789078367854, "learning_rate": 1.1109797992336847e-06, "loss": 0.2473, "step": 1112 }, { "epoch": 4.508354430379747, "grad_norm": 0.16722208719654444, "learning_rate": 1.092402023876933e-06, "loss": 0.2462, "step": 1113 }, { "epoch": 4.512405063291139, "grad_norm": 0.1760804290961061, "learning_rate": 1.0739765277149527e-06, "loss": 0.2424, "step": 1114 }, { "epoch": 4.516455696202532, "grad_norm": 0.17242224920955404, "learning_rate": 1.0557034591441596e-06, "loss": 0.2512, "step": 1115 }, { "epoch": 4.520506329113924, "grad_norm": 0.16588871623295917, "learning_rate": 1.0375829653333324e-06, "loss": 0.2471, "step": 1116 }, { "epoch": 4.524556962025317, "grad_norm": 0.17444941466562755, "learning_rate": 1.0196151922224385e-06, "loss": 0.2372, "step": 1117 }, { "epoch": 4.528607594936709, "grad_norm": 0.1734653445837689, "learning_rate": 1.0018002845214526e-06, "loss": 0.2461, "step": 1118 }, { "epoch": 4.532658227848101, "grad_norm": 0.16901225239672604, "learning_rate": 9.841383857091947e-07, "loss": 0.2482, "step": 1119 }, { "epoch": 4.536708860759494, "grad_norm": 0.16889687342553752, "learning_rate": 9.666296380321616e-07, "loss": 0.2385, "step": 1120 }, { "epoch": 4.540759493670886, "grad_norm": 0.16554748594827676, "learning_rate": 9.492741825034124e-07, "loss": 0.2482, "step": 1121 }, { "epoch": 4.544810126582279, "grad_norm": 0.17049397566524319, "learning_rate": 9.320721589013892e-07, "loss": 0.2438, "step": 1122 }, { "epoch": 4.548860759493671, "grad_norm": 0.17339611570845942, "learning_rate": 9.150237057688339e-07, "loss": 0.2505, "step": 1123 }, { "epoch": 4.552911392405063, "grad_norm": 0.17204607545515396, "learning_rate": 8.981289604116328e-07, "loss": 0.2453, "step": 1124 }, { "epoch": 4.556962025316456, "grad_norm": 0.16562563072215467, "learning_rate": 8.813880588977542e-07, "loss": 0.2531, "step": 1125 }, { "epoch": 4.561012658227848, "grad_norm": 0.16893941874226334, "learning_rate": 8.648011360561126e-07, "loss": 0.2442, "step": 1126 }, { "epoch": 4.56506329113924, "grad_norm": 0.1674687517648003, "learning_rate": 8.483683254755037e-07, "loss": 0.2583, "step": 1127 }, { "epoch": 4.569113924050633, "grad_norm": 0.16928584048605783, "learning_rate": 8.320897595035227e-07, "loss": 0.2527, "step": 1128 }, { "epoch": 4.573164556962025, "grad_norm": 0.1803852201439178, "learning_rate": 8.159655692455093e-07, "loss": 0.2493, "step": 1129 }, { "epoch": 4.577215189873417, "grad_norm": 0.16986558420915815, "learning_rate": 7.999958845634648e-07, "loss": 0.2462, "step": 1130 }, { "epoch": 4.58126582278481, "grad_norm": 0.17331401045080716, "learning_rate": 7.841808340750478e-07, "loss": 0.2541, "step": 1131 }, { "epoch": 4.585316455696202, "grad_norm": 0.16789948604984578, "learning_rate": 7.685205451524869e-07, "loss": 0.2425, "step": 1132 }, { "epoch": 4.589367088607595, "grad_norm": 0.16643904150166494, "learning_rate": 7.530151439216027e-07, "loss": 0.241, "step": 1133 }, { "epoch": 4.593417721518987, "grad_norm": 0.1714910852613664, "learning_rate": 7.376647552607675e-07, "loss": 0.2448, "step": 1134 }, { "epoch": 4.597468354430379, "grad_norm": 0.16815798202068205, "learning_rate": 7.224695027998963e-07, "loss": 0.2547, "step": 1135 }, { "epoch": 4.601518987341772, "grad_norm": 0.16929175757806578, "learning_rate": 7.07429508919466e-07, "loss": 0.2431, "step": 1136 }, { "epoch": 4.605569620253164, "grad_norm": 0.1627477756518389, "learning_rate": 6.925448947495206e-07, "loss": 0.2487, "step": 1137 }, { "epoch": 4.609620253164557, "grad_norm": 0.1708449621515848, "learning_rate": 6.778157801686936e-07, "loss": 0.2475, "step": 1138 }, { "epoch": 4.613670886075949, "grad_norm": 0.17610510759326134, "learning_rate": 6.632422838032515e-07, "loss": 0.237, "step": 1139 }, { "epoch": 4.6177215189873415, "grad_norm": 0.16679897917383513, "learning_rate": 6.488245230261281e-07, "loss": 0.2406, "step": 1140 }, { "epoch": 4.6217721518987345, "grad_norm": 0.17020205722695558, "learning_rate": 6.345626139559868e-07, "loss": 0.2404, "step": 1141 }, { "epoch": 4.6258227848101265, "grad_norm": 0.17057023340953834, "learning_rate": 6.204566714562866e-07, "loss": 0.2436, "step": 1142 }, { "epoch": 4.629873417721519, "grad_norm": 0.17198491861034212, "learning_rate": 6.06506809134344e-07, "loss": 0.2508, "step": 1143 }, { "epoch": 4.633924050632912, "grad_norm": 0.18022796133914917, "learning_rate": 5.927131393404373e-07, "loss": 0.2501, "step": 1144 }, { "epoch": 4.637974683544304, "grad_norm": 0.16154010963952925, "learning_rate": 5.790757731668817e-07, "loss": 0.243, "step": 1145 }, { "epoch": 4.642025316455696, "grad_norm": 0.164468276379417, "learning_rate": 5.655948204471507e-07, "loss": 0.2562, "step": 1146 }, { "epoch": 4.646075949367089, "grad_norm": 0.16546584261369685, "learning_rate": 5.522703897549875e-07, "loss": 0.248, "step": 1147 }, { "epoch": 4.650126582278481, "grad_norm": 0.17147685824376038, "learning_rate": 5.391025884035239e-07, "loss": 0.2421, "step": 1148 }, { "epoch": 4.654177215189874, "grad_norm": 0.16492295215598482, "learning_rate": 5.260915224444207e-07, "loss": 0.2437, "step": 1149 }, { "epoch": 4.658227848101266, "grad_norm": 0.16070396053302377, "learning_rate": 5.132372966670129e-07, "loss": 0.2424, "step": 1150 }, { "epoch": 4.662278481012658, "grad_norm": 0.17091298836143076, "learning_rate": 5.005400145974704e-07, "loss": 0.2554, "step": 1151 }, { "epoch": 4.666329113924051, "grad_norm": 0.1692664892974822, "learning_rate": 4.879997784979562e-07, "loss": 0.2429, "step": 1152 }, { "epoch": 4.670379746835443, "grad_norm": 0.16654841772727863, "learning_rate": 4.7561668936580984e-07, "loss": 0.2478, "step": 1153 }, { "epoch": 4.674430379746836, "grad_norm": 0.16835942871581316, "learning_rate": 4.6339084693272306e-07, "loss": 0.2531, "step": 1154 }, { "epoch": 4.678481012658228, "grad_norm": 0.17105832134523832, "learning_rate": 4.5132234966395847e-07, "loss": 0.2395, "step": 1155 }, { "epoch": 4.68253164556962, "grad_norm": 0.16687753626682492, "learning_rate": 4.3941129475752795e-07, "loss": 0.2477, "step": 1156 }, { "epoch": 4.686582278481013, "grad_norm": 0.1664339686852176, "learning_rate": 4.27657778143431e-07, "loss": 0.2481, "step": 1157 }, { "epoch": 4.690632911392405, "grad_norm": 0.16586718527246042, "learning_rate": 4.1606189448287757e-07, "loss": 0.2364, "step": 1158 }, { "epoch": 4.694683544303797, "grad_norm": 0.1669457624976133, "learning_rate": 4.046237371675177e-07, "loss": 0.2572, "step": 1159 }, { "epoch": 4.69873417721519, "grad_norm": 0.16768933441229794, "learning_rate": 3.9334339831869963e-07, "loss": 0.2494, "step": 1160 }, { "epoch": 4.702784810126582, "grad_norm": 0.1580096770042282, "learning_rate": 3.8222096878671955e-07, "loss": 0.2342, "step": 1161 }, { "epoch": 4.706835443037974, "grad_norm": 0.16745206732274256, "learning_rate": 3.7125653815009545e-07, "loss": 0.2396, "step": 1162 }, { "epoch": 4.710886075949367, "grad_norm": 0.16682280589005735, "learning_rate": 3.6045019471484974e-07, "loss": 0.2424, "step": 1163 }, { "epoch": 4.714936708860759, "grad_norm": 0.16778374087104078, "learning_rate": 3.498020255137813e-07, "loss": 0.2453, "step": 1164 }, { "epoch": 4.718987341772152, "grad_norm": 0.16635524931605195, "learning_rate": 3.393121163057811e-07, "loss": 0.2407, "step": 1165 }, { "epoch": 4.723037974683544, "grad_norm": 0.16856684305529007, "learning_rate": 3.289805515751399e-07, "loss": 0.2461, "step": 1166 }, { "epoch": 4.727088607594936, "grad_norm": 0.16602911405857856, "learning_rate": 3.188074145308573e-07, "loss": 0.2484, "step": 1167 }, { "epoch": 4.731139240506329, "grad_norm": 0.16645644516589295, "learning_rate": 3.087927871059804e-07, "loss": 0.2478, "step": 1168 }, { "epoch": 4.735189873417721, "grad_norm": 0.1708964939252288, "learning_rate": 2.989367499569418e-07, "loss": 0.2481, "step": 1169 }, { "epoch": 4.739240506329114, "grad_norm": 0.17063122252684704, "learning_rate": 2.8923938246290917e-07, "loss": 0.2489, "step": 1170 }, { "epoch": 4.743291139240506, "grad_norm": 0.166408797937444, "learning_rate": 2.7970076272514804e-07, "loss": 0.2423, "step": 1171 }, { "epoch": 4.7473417721518985, "grad_norm": 0.17153303479628662, "learning_rate": 2.703209675663887e-07, "loss": 0.245, "step": 1172 }, { "epoch": 4.751392405063291, "grad_norm": 0.16051191536121973, "learning_rate": 2.6110007253021374e-07, "loss": 0.2579, "step": 1173 }, { "epoch": 4.7554430379746835, "grad_norm": 0.1643120155730496, "learning_rate": 2.520381518804471e-07, "loss": 0.2505, "step": 1174 }, { "epoch": 4.759493670886076, "grad_norm": 0.17688883601145128, "learning_rate": 2.4313527860054585e-07, "loss": 0.2407, "step": 1175 }, { "epoch": 4.7635443037974685, "grad_norm": 0.1703952649136099, "learning_rate": 2.343915243930317e-07, "loss": 0.2532, "step": 1176 }, { "epoch": 4.767594936708861, "grad_norm": 0.1670148083285226, "learning_rate": 2.2580695967889367e-07, "loss": 0.2459, "step": 1177 }, { "epoch": 4.7716455696202535, "grad_norm": 0.17089941192026767, "learning_rate": 2.1738165359704189e-07, "loss": 0.2452, "step": 1178 }, { "epoch": 4.775696202531646, "grad_norm": 0.1684652910191662, "learning_rate": 2.0911567400373257e-07, "loss": 0.2522, "step": 1179 }, { "epoch": 4.779746835443038, "grad_norm": 0.16746289712196172, "learning_rate": 2.0100908747202607e-07, "loss": 0.2395, "step": 1180 }, { "epoch": 4.783797468354431, "grad_norm": 0.1700070218336565, "learning_rate": 1.9306195929125638e-07, "loss": 0.243, "step": 1181 }, { "epoch": 4.787848101265823, "grad_norm": 0.17219281542246928, "learning_rate": 1.8527435346650247e-07, "loss": 0.2589, "step": 1182 }, { "epoch": 4.791898734177215, "grad_norm": 0.1709540979138623, "learning_rate": 1.7764633271807108e-07, "loss": 0.2465, "step": 1183 }, { "epoch": 4.795949367088608, "grad_norm": 0.16258681964888014, "learning_rate": 1.7017795848099262e-07, "loss": 0.2501, "step": 1184 }, { "epoch": 4.8, "grad_norm": 0.16652645680692588, "learning_rate": 1.6286929090452596e-07, "loss": 0.2458, "step": 1185 }, { "epoch": 4.804050632911393, "grad_norm": 0.16045426376922586, "learning_rate": 1.557203888516745e-07, "loss": 0.2443, "step": 1186 }, { "epoch": 4.808101265822785, "grad_norm": 0.16262535107749604, "learning_rate": 1.487313098987131e-07, "loss": 0.2426, "step": 1187 }, { "epoch": 4.812151898734177, "grad_norm": 0.1639933757107104, "learning_rate": 1.4190211033472402e-07, "loss": 0.2579, "step": 1188 }, { "epoch": 4.81620253164557, "grad_norm": 0.15877715286894536, "learning_rate": 1.3523284516113955e-07, "loss": 0.2524, "step": 1189 }, { "epoch": 4.820253164556962, "grad_norm": 0.16951219678174687, "learning_rate": 1.2872356809130682e-07, "loss": 0.2543, "step": 1190 }, { "epoch": 4.824303797468355, "grad_norm": 0.1632815665980184, "learning_rate": 1.2237433155004807e-07, "loss": 0.2446, "step": 1191 }, { "epoch": 4.828354430379747, "grad_norm": 0.16500853425995987, "learning_rate": 1.1618518667323886e-07, "loss": 0.2389, "step": 1192 }, { "epoch": 4.832405063291139, "grad_norm": 0.17076616684883306, "learning_rate": 1.1015618330740385e-07, "loss": 0.2474, "step": 1193 }, { "epoch": 4.836455696202532, "grad_norm": 0.17025898991426422, "learning_rate": 1.042873700093061e-07, "loss": 0.2473, "step": 1194 }, { "epoch": 4.840506329113924, "grad_norm": 0.16999653064243864, "learning_rate": 9.857879404556291e-08, "loss": 0.2453, "step": 1195 }, { "epoch": 4.844556962025316, "grad_norm": 0.16728776035833415, "learning_rate": 9.303050139225722e-08, "loss": 0.2462, "step": 1196 }, { "epoch": 4.848607594936709, "grad_norm": 0.1742292298742044, "learning_rate": 8.76425367345779e-08, "loss": 0.2404, "step": 1197 }, { "epoch": 4.852658227848101, "grad_norm": 0.15992140658012902, "learning_rate": 8.241494346644897e-08, "loss": 0.2439, "step": 1198 }, { "epoch": 4.856708860759493, "grad_norm": 0.17293659347037366, "learning_rate": 7.734776369019204e-08, "loss": 0.2527, "step": 1199 }, { "epoch": 4.860759493670886, "grad_norm": 0.16967998530471357, "learning_rate": 7.244103821617332e-08, "loss": 0.2429, "step": 1200 }, { "epoch": 4.864810126582278, "grad_norm": 0.16589515382038383, "learning_rate": 6.769480656248606e-08, "loss": 0.2444, "step": 1201 }, { "epoch": 4.868860759493671, "grad_norm": 0.16537468774017502, "learning_rate": 6.310910695462635e-08, "loss": 0.2397, "step": 1202 }, { "epoch": 4.872911392405063, "grad_norm": 0.1675859495067197, "learning_rate": 5.8683976325191185e-08, "loss": 0.2499, "step": 1203 }, { "epoch": 4.876962025316455, "grad_norm": 0.17241702246557714, "learning_rate": 5.4419450313571984e-08, "loss": 0.2432, "step": 1204 }, { "epoch": 4.881012658227848, "grad_norm": 0.1613836879155604, "learning_rate": 5.031556326567488e-08, "loss": 0.2435, "step": 1205 }, { "epoch": 4.88506329113924, "grad_norm": 0.19174382527834763, "learning_rate": 4.637234823364312e-08, "loss": 0.2488, "step": 1206 }, { "epoch": 4.889113924050633, "grad_norm": 0.1637953710313765, "learning_rate": 4.258983697558838e-08, "loss": 0.2465, "step": 1207 }, { "epoch": 4.8931645569620255, "grad_norm": 0.17088673247760278, "learning_rate": 3.896805995533548e-08, "loss": 0.2372, "step": 1208 }, { "epoch": 4.8972151898734175, "grad_norm": 0.1684619271983402, "learning_rate": 3.550704634218028e-08, "loss": 0.2499, "step": 1209 }, { "epoch": 4.9012658227848105, "grad_norm": 0.17268683396192347, "learning_rate": 3.2206824010647676e-08, "loss": 0.2494, "step": 1210 }, { "epoch": 4.905316455696203, "grad_norm": 0.16280655453290246, "learning_rate": 2.9067419540278476e-08, "loss": 0.2416, "step": 1211 }, { "epoch": 4.909367088607595, "grad_norm": 0.16403929444374352, "learning_rate": 2.6088858215400638e-08, "loss": 0.2357, "step": 1212 }, { "epoch": 4.913417721518988, "grad_norm": 0.16543802993149753, "learning_rate": 2.3271164024940564e-08, "loss": 0.2424, "step": 1213 }, { "epoch": 4.91746835443038, "grad_norm": 0.16677741401885968, "learning_rate": 2.061435966221881e-08, "loss": 0.2519, "step": 1214 }, { "epoch": 4.921518987341772, "grad_norm": 0.1674699435036471, "learning_rate": 1.811846652477245e-08, "loss": 0.2506, "step": 1215 }, { "epoch": 4.925569620253165, "grad_norm": 0.16854605066370185, "learning_rate": 1.5783504714184106e-08, "loss": 0.2506, "step": 1216 }, { "epoch": 4.929620253164557, "grad_norm": 0.16793835024635131, "learning_rate": 1.360949303591097e-08, "loss": 0.2513, "step": 1217 }, { "epoch": 4.93367088607595, "grad_norm": 0.16239960629776692, "learning_rate": 1.1596448999144916e-08, "loss": 0.2396, "step": 1218 }, { "epoch": 4.937721518987342, "grad_norm": 0.17070244847658625, "learning_rate": 9.744388816668172e-09, "loss": 0.2532, "step": 1219 }, { "epoch": 4.941772151898734, "grad_norm": 0.16406989316108303, "learning_rate": 8.05332740472009e-09, "loss": 0.2386, "step": 1220 }, { "epoch": 4.945822784810127, "grad_norm": 0.16478596587634686, "learning_rate": 6.523278382872811e-09, "loss": 0.246, "step": 1221 }, { "epoch": 4.949873417721519, "grad_norm": 0.16482728100964505, "learning_rate": 5.15425407393133e-09, "loss": 0.2465, "step": 1222 }, { "epoch": 4.953924050632912, "grad_norm": 0.1723826368790951, "learning_rate": 3.94626550383137e-09, "loss": 0.2477, "step": 1223 }, { "epoch": 4.957974683544304, "grad_norm": 0.16794362434646928, "learning_rate": 2.899322401546112e-09, "loss": 0.2429, "step": 1224 }, { "epoch": 4.962025316455696, "grad_norm": 0.17449500109707422, "learning_rate": 2.013433199010706e-09, "loss": 0.2416, "step": 1225 }, { "epoch": 4.966075949367089, "grad_norm": 0.16937015189698543, "learning_rate": 1.2886050310556563e-09, "loss": 0.2454, "step": 1226 }, { "epoch": 4.970126582278481, "grad_norm": 0.1622560060615877, "learning_rate": 7.248437353468695e-10, "loss": 0.2447, "step": 1227 }, { "epoch": 4.974177215189873, "grad_norm": 0.16359626137021813, "learning_rate": 3.221538523412449e-10, "loss": 0.2457, "step": 1228 }, { "epoch": 4.978227848101266, "grad_norm": 0.16626981626611104, "learning_rate": 8.053862524670663e-11, "loss": 0.2387, "step": 1229 }, { "epoch": 4.982278481012658, "grad_norm": 0.16832459564008495, "learning_rate": 0.0, "loss": 0.2467, "step": 1230 }, { "epoch": 4.982278481012658, "step": 1230, "total_flos": 5.926379603753468e+18, "train_loss": 0.3479239087884988, "train_runtime": 54743.201, "train_samples_per_second": 2.886, "train_steps_per_second": 0.022 } ], "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": 5.926379603753468e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }