{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.982278481012658, "eval_steps": 500, "global_step": 1230, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004050632911392405, "grad_norm": 7.69970267018566, "learning_rate": 3.2520325203252037e-07, "loss": 1.124, "step": 1 }, { "epoch": 0.00810126582278481, "grad_norm": 7.923894647000294, "learning_rate": 6.504065040650407e-07, "loss": 1.1721, "step": 2 }, { "epoch": 0.012151898734177215, "grad_norm": 7.939199067603654, "learning_rate": 9.75609756097561e-07, "loss": 1.1682, "step": 3 }, { "epoch": 0.01620253164556962, "grad_norm": 8.092069863001534, "learning_rate": 1.3008130081300815e-06, "loss": 1.1525, "step": 4 }, { "epoch": 0.020253164556962026, "grad_norm": 7.160724228484259, "learning_rate": 1.6260162601626018e-06, "loss": 1.1067, "step": 5 }, { "epoch": 0.02430379746835443, "grad_norm": 7.23210083341947, "learning_rate": 1.951219512195122e-06, "loss": 1.098, "step": 6 }, { "epoch": 0.028354430379746835, "grad_norm": 6.186295812872652, "learning_rate": 2.2764227642276426e-06, "loss": 1.0688, "step": 7 }, { "epoch": 0.03240506329113924, "grad_norm": 5.67711851783084, "learning_rate": 2.601626016260163e-06, "loss": 1.0768, "step": 8 }, { "epoch": 0.03645569620253165, "grad_norm": 3.1659399106434383, "learning_rate": 2.926829268292683e-06, "loss": 1.0181, "step": 9 }, { "epoch": 0.04050632911392405, "grad_norm": 2.853027318554926, "learning_rate": 3.2520325203252037e-06, "loss": 1.0114, "step": 10 }, { "epoch": 0.044556962025316456, "grad_norm": 2.7225440119989344, "learning_rate": 3.577235772357724e-06, "loss": 1.0259, "step": 11 }, { "epoch": 0.04860759493670886, "grad_norm": 4.3985687366946635, "learning_rate": 3.902439024390244e-06, "loss": 0.9992, "step": 12 }, { "epoch": 0.052658227848101265, "grad_norm": 4.772946877116913, "learning_rate": 4.227642276422765e-06, "loss": 0.972, "step": 13 }, { "epoch": 0.05670886075949367, "grad_norm": 4.839995642284366, "learning_rate": 4.552845528455285e-06, "loss": 0.9829, "step": 14 }, { "epoch": 0.060759493670886074, "grad_norm": 4.333364395500183, "learning_rate": 4.8780487804878055e-06, "loss": 0.9311, "step": 15 }, { "epoch": 0.06481012658227848, "grad_norm": 3.2756135936128907, "learning_rate": 5.203252032520326e-06, "loss": 0.9186, "step": 16 }, { "epoch": 0.06886075949367089, "grad_norm": 3.261960034278652, "learning_rate": 5.528455284552846e-06, "loss": 0.9508, "step": 17 }, { "epoch": 0.0729113924050633, "grad_norm": 2.783387183280708, "learning_rate": 5.853658536585366e-06, "loss": 0.8996, "step": 18 }, { "epoch": 0.0769620253164557, "grad_norm": 2.38365863900912, "learning_rate": 6.178861788617887e-06, "loss": 0.8732, "step": 19 }, { "epoch": 0.0810126582278481, "grad_norm": 2.2912461685658636, "learning_rate": 6.504065040650407e-06, "loss": 0.8591, "step": 20 }, { "epoch": 0.08506329113924051, "grad_norm": 1.971044394160563, "learning_rate": 6.829268292682928e-06, "loss": 0.8357, "step": 21 }, { "epoch": 0.08911392405063291, "grad_norm": 1.8959363093748194, "learning_rate": 7.154471544715448e-06, "loss": 0.8312, "step": 22 }, { "epoch": 0.09316455696202532, "grad_norm": 1.830571535938326, "learning_rate": 7.4796747967479676e-06, "loss": 0.7844, "step": 23 }, { "epoch": 0.09721518987341772, "grad_norm": 1.6444138143435825, "learning_rate": 7.804878048780489e-06, "loss": 0.8332, "step": 24 }, { "epoch": 0.10126582278481013, "grad_norm": 1.6423079403007097, "learning_rate": 8.130081300813009e-06, "loss": 0.8204, "step": 25 }, { "epoch": 0.10531645569620253, "grad_norm": 1.2998756382854308, "learning_rate": 8.45528455284553e-06, "loss": 0.7822, "step": 26 }, { "epoch": 0.10936708860759493, "grad_norm": 1.2096951462245302, "learning_rate": 8.78048780487805e-06, "loss": 0.7886, "step": 27 }, { "epoch": 0.11341772151898734, "grad_norm": 1.1483822124969336, "learning_rate": 9.10569105691057e-06, "loss": 0.795, "step": 28 }, { "epoch": 0.11746835443037974, "grad_norm": 1.1029006047306231, "learning_rate": 9.43089430894309e-06, "loss": 0.7667, "step": 29 }, { "epoch": 0.12151898734177215, "grad_norm": 1.0385940585518625, "learning_rate": 9.756097560975611e-06, "loss": 0.7659, "step": 30 }, { "epoch": 0.12556962025316457, "grad_norm": 0.9851409422475386, "learning_rate": 1.008130081300813e-05, "loss": 0.7726, "step": 31 }, { "epoch": 0.12962025316455697, "grad_norm": 1.0029706478557208, "learning_rate": 1.0406504065040652e-05, "loss": 0.7888, "step": 32 }, { "epoch": 0.13367088607594937, "grad_norm": 0.8540079375375064, "learning_rate": 1.0731707317073172e-05, "loss": 0.8102, "step": 33 }, { "epoch": 0.13772151898734178, "grad_norm": 0.889117783840132, "learning_rate": 1.1056910569105692e-05, "loss": 0.759, "step": 34 }, { "epoch": 0.14177215189873418, "grad_norm": 0.9058085707135138, "learning_rate": 1.1382113821138213e-05, "loss": 0.7401, "step": 35 }, { "epoch": 0.1458227848101266, "grad_norm": 0.8709622155937737, "learning_rate": 1.1707317073170731e-05, "loss": 0.7247, "step": 36 }, { "epoch": 0.149873417721519, "grad_norm": 0.7752432605854113, "learning_rate": 1.2032520325203254e-05, "loss": 0.7273, "step": 37 }, { "epoch": 0.1539240506329114, "grad_norm": 0.8503947340296998, "learning_rate": 1.2357723577235774e-05, "loss": 0.7121, "step": 38 }, { "epoch": 0.1579746835443038, "grad_norm": 0.8451477573948325, "learning_rate": 1.2682926829268294e-05, "loss": 0.7562, "step": 39 }, { "epoch": 0.1620253164556962, "grad_norm": 0.8731511949108206, "learning_rate": 1.3008130081300815e-05, "loss": 0.7398, "step": 40 }, { "epoch": 0.1660759493670886, "grad_norm": 0.8492398264315745, "learning_rate": 1.3333333333333333e-05, "loss": 0.7727, "step": 41 }, { "epoch": 0.17012658227848101, "grad_norm": 0.7836917702777504, "learning_rate": 1.3658536585365855e-05, "loss": 0.7393, "step": 42 }, { "epoch": 0.17417721518987342, "grad_norm": 0.7452459301354036, "learning_rate": 1.3983739837398376e-05, "loss": 0.7486, "step": 43 }, { "epoch": 0.17822784810126582, "grad_norm": 0.8316896536142998, "learning_rate": 1.4308943089430896e-05, "loss": 0.7328, "step": 44 }, { "epoch": 0.18227848101265823, "grad_norm": 0.7022621899031778, "learning_rate": 1.4634146341463415e-05, "loss": 0.7311, "step": 45 }, { "epoch": 0.18632911392405063, "grad_norm": 0.8196543126374348, "learning_rate": 1.4959349593495935e-05, "loss": 0.7299, "step": 46 }, { "epoch": 0.19037974683544304, "grad_norm": 0.7100100197100301, "learning_rate": 1.528455284552846e-05, "loss": 0.7252, "step": 47 }, { "epoch": 0.19443037974683544, "grad_norm": 0.8274149440761387, "learning_rate": 1.5609756097560978e-05, "loss": 0.7405, "step": 48 }, { "epoch": 0.19848101265822785, "grad_norm": 0.8176946570703757, "learning_rate": 1.5934959349593496e-05, "loss": 0.7457, "step": 49 }, { "epoch": 0.20253164556962025, "grad_norm": 0.7975493835168115, "learning_rate": 1.6260162601626018e-05, "loss": 0.7292, "step": 50 }, { "epoch": 0.20658227848101265, "grad_norm": 0.7861203856072139, "learning_rate": 1.6585365853658537e-05, "loss": 0.7264, "step": 51 }, { "epoch": 0.21063291139240506, "grad_norm": 1.0136219881309623, "learning_rate": 1.691056910569106e-05, "loss": 0.7394, "step": 52 }, { "epoch": 0.21468354430379746, "grad_norm": 0.7433204348031978, "learning_rate": 1.7235772357723578e-05, "loss": 0.7204, "step": 53 }, { "epoch": 0.21873417721518987, "grad_norm": 1.0870626149154587, "learning_rate": 1.75609756097561e-05, "loss": 0.7224, "step": 54 }, { "epoch": 0.22278481012658227, "grad_norm": 0.773250959430038, "learning_rate": 1.788617886178862e-05, "loss": 0.703, "step": 55 }, { "epoch": 0.22683544303797468, "grad_norm": 0.8712382403666326, "learning_rate": 1.821138211382114e-05, "loss": 0.7114, "step": 56 }, { "epoch": 0.23088607594936708, "grad_norm": 0.7872817576017482, "learning_rate": 1.8536585365853663e-05, "loss": 0.7009, "step": 57 }, { "epoch": 0.23493670886075949, "grad_norm": 0.7569643176037177, "learning_rate": 1.886178861788618e-05, "loss": 0.7368, "step": 58 }, { "epoch": 0.2389873417721519, "grad_norm": 0.8935711590311504, "learning_rate": 1.91869918699187e-05, "loss": 0.708, "step": 59 }, { "epoch": 0.2430379746835443, "grad_norm": 0.8852657363743471, "learning_rate": 1.9512195121951222e-05, "loss": 0.7524, "step": 60 }, { "epoch": 0.2470886075949367, "grad_norm": 0.7752914644582227, "learning_rate": 1.983739837398374e-05, "loss": 0.7144, "step": 61 }, { "epoch": 0.25113924050632913, "grad_norm": 0.8669892834088836, "learning_rate": 2.016260162601626e-05, "loss": 0.7051, "step": 62 }, { "epoch": 0.25518987341772154, "grad_norm": 0.7516034133773357, "learning_rate": 2.048780487804878e-05, "loss": 0.7096, "step": 63 }, { "epoch": 0.25924050632911394, "grad_norm": 0.9046834918192725, "learning_rate": 2.0813008130081303e-05, "loss": 0.7111, "step": 64 }, { "epoch": 0.26329113924050634, "grad_norm": 0.8395935542639781, "learning_rate": 2.1138211382113822e-05, "loss": 0.7132, "step": 65 }, { "epoch": 0.26734177215189875, "grad_norm": 0.8781046902132453, "learning_rate": 2.1463414634146344e-05, "loss": 0.7315, "step": 66 }, { "epoch": 0.27139240506329115, "grad_norm": 0.7884432299258433, "learning_rate": 2.1788617886178863e-05, "loss": 0.7226, "step": 67 }, { "epoch": 0.27544303797468356, "grad_norm": 1.0253644506715593, "learning_rate": 2.2113821138211385e-05, "loss": 0.7174, "step": 68 }, { "epoch": 0.27949367088607596, "grad_norm": 0.7200215862288353, "learning_rate": 2.2439024390243907e-05, "loss": 0.7072, "step": 69 }, { "epoch": 0.28354430379746837, "grad_norm": 0.8915721866639248, "learning_rate": 2.2764227642276426e-05, "loss": 0.6801, "step": 70 }, { "epoch": 0.28759493670886077, "grad_norm": 0.8634773941729773, "learning_rate": 2.3089430894308948e-05, "loss": 0.674, "step": 71 }, { "epoch": 0.2916455696202532, "grad_norm": 0.8687218486871734, "learning_rate": 2.3414634146341463e-05, "loss": 0.6988, "step": 72 }, { "epoch": 0.2956962025316456, "grad_norm": 0.9318527934880888, "learning_rate": 2.3739837398373985e-05, "loss": 0.7018, "step": 73 }, { "epoch": 0.299746835443038, "grad_norm": 0.8389550067996822, "learning_rate": 2.4065040650406507e-05, "loss": 0.7125, "step": 74 }, { "epoch": 0.3037974683544304, "grad_norm": 0.8131569614610321, "learning_rate": 2.4390243902439026e-05, "loss": 0.6923, "step": 75 }, { "epoch": 0.3078481012658228, "grad_norm": 0.9100667965993641, "learning_rate": 2.4715447154471548e-05, "loss": 0.7116, "step": 76 }, { "epoch": 0.3118987341772152, "grad_norm": 0.8624990837670086, "learning_rate": 2.5040650406504066e-05, "loss": 0.7292, "step": 77 }, { "epoch": 0.3159493670886076, "grad_norm": 0.8958195762498758, "learning_rate": 2.536585365853659e-05, "loss": 0.6927, "step": 78 }, { "epoch": 0.32, "grad_norm": 0.8516962180275229, "learning_rate": 2.569105691056911e-05, "loss": 0.7058, "step": 79 }, { "epoch": 0.3240506329113924, "grad_norm": 1.0175071493819792, "learning_rate": 2.601626016260163e-05, "loss": 0.6823, "step": 80 }, { "epoch": 0.3281012658227848, "grad_norm": 1.040067247156228, "learning_rate": 2.634146341463415e-05, "loss": 0.7011, "step": 81 }, { "epoch": 0.3321518987341772, "grad_norm": 1.0754818827602592, "learning_rate": 2.6666666666666667e-05, "loss": 0.7019, "step": 82 }, { "epoch": 0.3362025316455696, "grad_norm": 1.1709792677590944, "learning_rate": 2.699186991869919e-05, "loss": 0.7064, "step": 83 }, { "epoch": 0.34025316455696203, "grad_norm": 1.0524206378070742, "learning_rate": 2.731707317073171e-05, "loss": 0.6816, "step": 84 }, { "epoch": 0.34430379746835443, "grad_norm": 0.8967050280625507, "learning_rate": 2.764227642276423e-05, "loss": 0.7102, "step": 85 }, { "epoch": 0.34835443037974684, "grad_norm": 1.0423590095663546, "learning_rate": 2.796747967479675e-05, "loss": 0.6822, "step": 86 }, { "epoch": 0.35240506329113924, "grad_norm": 0.8222932896168589, "learning_rate": 2.829268292682927e-05, "loss": 0.6864, "step": 87 }, { "epoch": 0.35645569620253165, "grad_norm": 1.1579322529295424, "learning_rate": 2.8617886178861792e-05, "loss": 0.7191, "step": 88 }, { "epoch": 0.36050632911392405, "grad_norm": 0.8136567617929038, "learning_rate": 2.8943089430894314e-05, "loss": 0.6976, "step": 89 }, { "epoch": 0.36455696202531646, "grad_norm": 1.15321223818772, "learning_rate": 2.926829268292683e-05, "loss": 0.7124, "step": 90 }, { "epoch": 0.36860759493670886, "grad_norm": 0.7598378186502093, "learning_rate": 2.959349593495935e-05, "loss": 0.6996, "step": 91 }, { "epoch": 0.37265822784810126, "grad_norm": 0.9952949754635837, "learning_rate": 2.991869918699187e-05, "loss": 0.7212, "step": 92 }, { "epoch": 0.37670886075949367, "grad_norm": 0.8009176770814644, "learning_rate": 3.0243902439024392e-05, "loss": 0.676, "step": 93 }, { "epoch": 0.3807594936708861, "grad_norm": 0.8884089040708147, "learning_rate": 3.056910569105692e-05, "loss": 0.7118, "step": 94 }, { "epoch": 0.3848101265822785, "grad_norm": 0.988501853811144, "learning_rate": 3.089430894308943e-05, "loss": 0.7103, "step": 95 }, { "epoch": 0.3888607594936709, "grad_norm": 0.8166136096987501, "learning_rate": 3.1219512195121955e-05, "loss": 0.7068, "step": 96 }, { "epoch": 0.3929113924050633, "grad_norm": 1.0422130162472574, "learning_rate": 3.154471544715447e-05, "loss": 0.6854, "step": 97 }, { "epoch": 0.3969620253164557, "grad_norm": 0.9485090361568005, "learning_rate": 3.186991869918699e-05, "loss": 0.7216, "step": 98 }, { "epoch": 0.4010126582278481, "grad_norm": 0.8032564872121868, "learning_rate": 3.2195121951219514e-05, "loss": 0.7145, "step": 99 }, { "epoch": 0.4050632911392405, "grad_norm": 0.7213209204719553, "learning_rate": 3.2520325203252037e-05, "loss": 0.7002, "step": 100 }, { "epoch": 0.4091139240506329, "grad_norm": 0.9306879471901583, "learning_rate": 3.284552845528456e-05, "loss": 0.7293, "step": 101 }, { "epoch": 0.4131645569620253, "grad_norm": 0.8888694269939893, "learning_rate": 3.3170731707317074e-05, "loss": 0.7187, "step": 102 }, { "epoch": 0.4172151898734177, "grad_norm": 0.9460651023469309, "learning_rate": 3.3495934959349596e-05, "loss": 0.7213, "step": 103 }, { "epoch": 0.4212658227848101, "grad_norm": 1.1211842915684742, "learning_rate": 3.382113821138212e-05, "loss": 0.6931, "step": 104 }, { "epoch": 0.4253164556962025, "grad_norm": 0.999446936273417, "learning_rate": 3.414634146341463e-05, "loss": 0.7385, "step": 105 }, { "epoch": 0.4293670886075949, "grad_norm": 1.073497310055349, "learning_rate": 3.4471544715447155e-05, "loss": 0.7153, "step": 106 }, { "epoch": 0.43341772151898733, "grad_norm": 0.8361071868561997, "learning_rate": 3.479674796747968e-05, "loss": 0.6836, "step": 107 }, { "epoch": 0.43746835443037974, "grad_norm": 0.8553001722124145, "learning_rate": 3.51219512195122e-05, "loss": 0.7022, "step": 108 }, { "epoch": 0.44151898734177214, "grad_norm": 0.8855020659644245, "learning_rate": 3.544715447154472e-05, "loss": 0.7183, "step": 109 }, { "epoch": 0.44556962025316454, "grad_norm": 0.735613785112289, "learning_rate": 3.577235772357724e-05, "loss": 0.6869, "step": 110 }, { "epoch": 0.44962025316455695, "grad_norm": 0.7880594745810434, "learning_rate": 3.609756097560976e-05, "loss": 0.7008, "step": 111 }, { "epoch": 0.45367088607594935, "grad_norm": 0.8955936285734886, "learning_rate": 3.642276422764228e-05, "loss": 0.6992, "step": 112 }, { "epoch": 0.45772151898734176, "grad_norm": 0.8645354201135064, "learning_rate": 3.67479674796748e-05, "loss": 0.686, "step": 113 }, { "epoch": 0.46177215189873416, "grad_norm": 0.6738838498336114, "learning_rate": 3.7073170731707325e-05, "loss": 0.6591, "step": 114 }, { "epoch": 0.46582278481012657, "grad_norm": 0.8900918656911843, "learning_rate": 3.739837398373984e-05, "loss": 0.729, "step": 115 }, { "epoch": 0.46987341772151897, "grad_norm": 0.8807954819638936, "learning_rate": 3.772357723577236e-05, "loss": 0.7161, "step": 116 }, { "epoch": 0.4739240506329114, "grad_norm": 0.7589738906610285, "learning_rate": 3.804878048780488e-05, "loss": 0.6928, "step": 117 }, { "epoch": 0.4779746835443038, "grad_norm": 0.8744259604718262, "learning_rate": 3.83739837398374e-05, "loss": 0.6971, "step": 118 }, { "epoch": 0.4820253164556962, "grad_norm": 0.7167322340395043, "learning_rate": 3.869918699186992e-05, "loss": 0.7069, "step": 119 }, { "epoch": 0.4860759493670886, "grad_norm": 0.8553047106329071, "learning_rate": 3.9024390243902444e-05, "loss": 0.7152, "step": 120 }, { "epoch": 0.490126582278481, "grad_norm": 0.8422917580059801, "learning_rate": 3.9349593495934966e-05, "loss": 0.7329, "step": 121 }, { "epoch": 0.4941772151898734, "grad_norm": 0.8581564021502041, "learning_rate": 3.967479674796748e-05, "loss": 0.6817, "step": 122 }, { "epoch": 0.4982278481012658, "grad_norm": 0.9928284066279608, "learning_rate": 4e-05, "loss": 0.7188, "step": 123 }, { "epoch": 0.5022784810126583, "grad_norm": 0.8579985224755804, "learning_rate": 3.999991946137476e-05, "loss": 0.6844, "step": 124 }, { "epoch": 0.5063291139240507, "grad_norm": 0.7719881574757794, "learning_rate": 3.999967784614766e-05, "loss": 0.7034, "step": 125 }, { "epoch": 0.5103797468354431, "grad_norm": 0.9692469414935728, "learning_rate": 3.9999275156264656e-05, "loss": 0.6767, "step": 126 }, { "epoch": 0.5144303797468355, "grad_norm": 0.7870513705900746, "learning_rate": 3.999871139496895e-05, "loss": 0.7142, "step": 127 }, { "epoch": 0.5184810126582279, "grad_norm": 0.9904120576601553, "learning_rate": 3.9997986566800995e-05, "loss": 0.6747, "step": 128 }, { "epoch": 0.5225316455696203, "grad_norm": 1.176168117201554, "learning_rate": 3.999710067759846e-05, "loss": 0.7109, "step": 129 }, { "epoch": 0.5265822784810127, "grad_norm": 0.8987308264664385, "learning_rate": 3.999605373449617e-05, "loss": 0.6892, "step": 130 }, { "epoch": 0.5306329113924051, "grad_norm": 1.2115065199295487, "learning_rate": 3.9994845745926075e-05, "loss": 0.708, "step": 131 }, { "epoch": 0.5346835443037975, "grad_norm": 1.1000674917634397, "learning_rate": 3.999347672161713e-05, "loss": 0.7154, "step": 132 }, { "epoch": 0.5387341772151899, "grad_norm": 1.120034667267797, "learning_rate": 3.999194667259528e-05, "loss": 0.7041, "step": 133 }, { "epoch": 0.5427848101265823, "grad_norm": 0.828867127422357, "learning_rate": 3.999025561118334e-05, "loss": 0.67, "step": 134 }, { "epoch": 0.5468354430379747, "grad_norm": 0.9954359207256646, "learning_rate": 3.998840355100086e-05, "loss": 0.6992, "step": 135 }, { "epoch": 0.5508860759493671, "grad_norm": 0.8407020728249802, "learning_rate": 3.998639050696409e-05, "loss": 0.7091, "step": 136 }, { "epoch": 0.5549367088607595, "grad_norm": 0.8989947636802232, "learning_rate": 3.998421649528582e-05, "loss": 0.7283, "step": 137 }, { "epoch": 0.5589873417721519, "grad_norm": 0.8170351850726857, "learning_rate": 3.9981881533475234e-05, "loss": 0.6991, "step": 138 }, { "epoch": 0.5630379746835443, "grad_norm": 0.7998390949088188, "learning_rate": 3.997938564033779e-05, "loss": 0.6965, "step": 139 }, { "epoch": 0.5670886075949367, "grad_norm": 0.8774468377973084, "learning_rate": 3.9976728835975064e-05, "loss": 0.7248, "step": 140 }, { "epoch": 0.5711392405063291, "grad_norm": 0.7886957381044866, "learning_rate": 3.9973911141784605e-05, "loss": 0.7023, "step": 141 }, { "epoch": 0.5751898734177215, "grad_norm": 0.7507084676378678, "learning_rate": 3.997093258045973e-05, "loss": 0.6885, "step": 142 }, { "epoch": 0.579240506329114, "grad_norm": 0.6908921920444779, "learning_rate": 3.996779317598936e-05, "loss": 0.6996, "step": 143 }, { "epoch": 0.5832911392405064, "grad_norm": 0.7737881437814217, "learning_rate": 3.996449295365782e-05, "loss": 0.6666, "step": 144 }, { "epoch": 0.5873417721518988, "grad_norm": 0.7382266737274427, "learning_rate": 3.996103194004467e-05, "loss": 0.6816, "step": 145 }, { "epoch": 0.5913924050632912, "grad_norm": 0.799047072015188, "learning_rate": 3.995741016302441e-05, "loss": 0.6776, "step": 146 }, { "epoch": 0.5954430379746836, "grad_norm": 0.6676249304239134, "learning_rate": 3.9953627651766364e-05, "loss": 0.6982, "step": 147 }, { "epoch": 0.599493670886076, "grad_norm": 0.7252446086588544, "learning_rate": 3.9949684436734325e-05, "loss": 0.6883, "step": 148 }, { "epoch": 0.6035443037974684, "grad_norm": 0.6523278250633938, "learning_rate": 3.994558054968643e-05, "loss": 0.6927, "step": 149 }, { "epoch": 0.6075949367088608, "grad_norm": 0.7228044012629431, "learning_rate": 3.994131602367481e-05, "loss": 0.7011, "step": 150 }, { "epoch": 0.6116455696202532, "grad_norm": 0.8216926008544966, "learning_rate": 3.9936890893045376e-05, "loss": 0.6942, "step": 151 }, { "epoch": 0.6156962025316456, "grad_norm": 0.6636888361038242, "learning_rate": 3.993230519343752e-05, "loss": 0.6983, "step": 152 }, { "epoch": 0.619746835443038, "grad_norm": 0.8803435748646617, "learning_rate": 3.992755896178383e-05, "loss": 0.6721, "step": 153 }, { "epoch": 0.6237974683544304, "grad_norm": 0.7613641751292672, "learning_rate": 3.992265223630981e-05, "loss": 0.7035, "step": 154 }, { "epoch": 0.6278481012658228, "grad_norm": 0.708057407771589, "learning_rate": 3.991758505653355e-05, "loss": 0.696, "step": 155 }, { "epoch": 0.6318987341772152, "grad_norm": 0.6982703689718862, "learning_rate": 3.991235746326543e-05, "loss": 0.6798, "step": 156 }, { "epoch": 0.6359493670886076, "grad_norm": 0.8424202888598292, "learning_rate": 3.9906969498607745e-05, "loss": 0.731, "step": 157 }, { "epoch": 0.64, "grad_norm": 0.6905333974319268, "learning_rate": 3.990142120595444e-05, "loss": 0.6768, "step": 158 }, { "epoch": 0.6440506329113924, "grad_norm": 0.7288897193728336, "learning_rate": 3.98957126299907e-05, "loss": 0.6481, "step": 159 }, { "epoch": 0.6481012658227848, "grad_norm": 0.7704156771773795, "learning_rate": 3.9889843816692596e-05, "loss": 0.6766, "step": 160 }, { "epoch": 0.6521518987341772, "grad_norm": 0.8846036268104028, "learning_rate": 3.9883814813326766e-05, "loss": 0.6864, "step": 161 }, { "epoch": 0.6562025316455696, "grad_norm": 0.7659253703198216, "learning_rate": 3.9877625668449956e-05, "loss": 0.6908, "step": 162 }, { "epoch": 0.660253164556962, "grad_norm": 0.9873019187433328, "learning_rate": 3.98712764319087e-05, "loss": 0.7032, "step": 163 }, { "epoch": 0.6643037974683544, "grad_norm": 0.8163680567513515, "learning_rate": 3.9864767154838864e-05, "loss": 0.6909, "step": 164 }, { "epoch": 0.6683544303797468, "grad_norm": 0.7649789276287174, "learning_rate": 3.9858097889665277e-05, "loss": 0.7053, "step": 165 }, { "epoch": 0.6724050632911392, "grad_norm": 0.6946187366403074, "learning_rate": 3.985126869010129e-05, "loss": 0.7208, "step": 166 }, { "epoch": 0.6764556962025317, "grad_norm": 0.8183565906776837, "learning_rate": 3.984427961114833e-05, "loss": 0.6969, "step": 167 }, { "epoch": 0.6805063291139241, "grad_norm": 0.707756449236673, "learning_rate": 3.9837130709095475e-05, "loss": 0.7039, "step": 168 }, { "epoch": 0.6845569620253165, "grad_norm": 0.7426295065112539, "learning_rate": 3.982982204151901e-05, "loss": 0.6877, "step": 169 }, { "epoch": 0.6886075949367089, "grad_norm": 0.7466700763432536, "learning_rate": 3.982235366728193e-05, "loss": 0.6944, "step": 170 }, { "epoch": 0.6926582278481013, "grad_norm": 0.6793640149005772, "learning_rate": 3.9814725646533505e-05, "loss": 0.7022, "step": 171 }, { "epoch": 0.6967088607594937, "grad_norm": 0.7310230530619827, "learning_rate": 3.9806938040708746e-05, "loss": 0.6862, "step": 172 }, { "epoch": 0.7007594936708861, "grad_norm": 0.7224263992329728, "learning_rate": 3.9798990912527976e-05, "loss": 0.6798, "step": 173 }, { "epoch": 0.7048101265822785, "grad_norm": 0.7379055513532224, "learning_rate": 3.979088432599627e-05, "loss": 0.685, "step": 174 }, { "epoch": 0.7088607594936709, "grad_norm": 0.7631681917176983, "learning_rate": 3.9782618346402964e-05, "loss": 0.6961, "step": 175 }, { "epoch": 0.7129113924050633, "grad_norm": 0.7735576815119202, "learning_rate": 3.977419304032111e-05, "loss": 0.6909, "step": 176 }, { "epoch": 0.7169620253164557, "grad_norm": 0.7596804532583568, "learning_rate": 3.976560847560697e-05, "loss": 0.7067, "step": 177 }, { "epoch": 0.7210126582278481, "grad_norm": 0.8504549647869627, "learning_rate": 3.9756864721399456e-05, "loss": 0.698, "step": 178 }, { "epoch": 0.7250632911392405, "grad_norm": 0.5821743754612839, "learning_rate": 3.974796184811956e-05, "loss": 0.6458, "step": 179 }, { "epoch": 0.7291139240506329, "grad_norm": 0.786800388746853, "learning_rate": 3.973889992746979e-05, "loss": 0.677, "step": 180 }, { "epoch": 0.7331645569620253, "grad_norm": 0.6750627588874698, "learning_rate": 3.972967903243361e-05, "loss": 0.6769, "step": 181 }, { "epoch": 0.7372151898734177, "grad_norm": 0.6065453387032979, "learning_rate": 3.972029923727486e-05, "loss": 0.6684, "step": 182 }, { "epoch": 0.7412658227848101, "grad_norm": 0.6822190784918477, "learning_rate": 3.971076061753709e-05, "loss": 0.6579, "step": 183 }, { "epoch": 0.7453164556962025, "grad_norm": 0.5861060853667038, "learning_rate": 3.9701063250043066e-05, "loss": 0.6909, "step": 184 }, { "epoch": 0.7493670886075949, "grad_norm": 0.6510516964306973, "learning_rate": 3.969120721289402e-05, "loss": 0.6841, "step": 185 }, { "epoch": 0.7534177215189873, "grad_norm": 0.6323955219484405, "learning_rate": 3.9681192585469146e-05, "loss": 0.7091, "step": 186 }, { "epoch": 0.7574683544303797, "grad_norm": 0.6433255714813336, "learning_rate": 3.9671019448424865e-05, "loss": 0.6617, "step": 187 }, { "epoch": 0.7615189873417721, "grad_norm": 0.6447047200007159, "learning_rate": 3.966068788369422e-05, "loss": 0.6826, "step": 188 }, { "epoch": 0.7655696202531646, "grad_norm": 0.7355254328818408, "learning_rate": 3.965019797448622e-05, "loss": 0.684, "step": 189 }, { "epoch": 0.769620253164557, "grad_norm": 0.6100718091055728, "learning_rate": 3.963954980528515e-05, "loss": 0.6624, "step": 190 }, { "epoch": 0.7736708860759494, "grad_norm": 0.7578945505815394, "learning_rate": 3.9628743461849905e-05, "loss": 0.6824, "step": 191 }, { "epoch": 0.7777215189873418, "grad_norm": 0.5883591265182702, "learning_rate": 3.961777903121329e-05, "loss": 0.6774, "step": 192 }, { "epoch": 0.7817721518987342, "grad_norm": 0.6134268396763725, "learning_rate": 3.960665660168131e-05, "loss": 0.6863, "step": 193 }, { "epoch": 0.7858227848101266, "grad_norm": 0.6196652370514212, "learning_rate": 3.9595376262832485e-05, "loss": 0.6687, "step": 194 }, { "epoch": 0.789873417721519, "grad_norm": 0.6184953335390576, "learning_rate": 3.9583938105517127e-05, "loss": 0.6835, "step": 195 }, { "epoch": 0.7939240506329114, "grad_norm": 0.6386414199464258, "learning_rate": 3.957234222185657e-05, "loss": 0.6782, "step": 196 }, { "epoch": 0.7979746835443038, "grad_norm": 0.6557787701978459, "learning_rate": 3.9560588705242474e-05, "loss": 0.6727, "step": 197 }, { "epoch": 0.8020253164556962, "grad_norm": 0.6469702048106363, "learning_rate": 3.954867765033605e-05, "loss": 0.6815, "step": 198 }, { "epoch": 0.8060759493670886, "grad_norm": 0.7557888809014296, "learning_rate": 3.953660915306728e-05, "loss": 0.6982, "step": 199 }, { "epoch": 0.810126582278481, "grad_norm": 0.6418220088512095, "learning_rate": 3.952438331063419e-05, "loss": 0.6718, "step": 200 }, { "epoch": 0.8141772151898734, "grad_norm": 0.6442298006657676, "learning_rate": 3.951200022150205e-05, "loss": 0.6703, "step": 201 }, { "epoch": 0.8182278481012658, "grad_norm": 0.6491992687499857, "learning_rate": 3.949945998540253e-05, "loss": 0.6701, "step": 202 }, { "epoch": 0.8222784810126582, "grad_norm": 0.6513877467437416, "learning_rate": 3.9486762703332993e-05, "loss": 0.6973, "step": 203 }, { "epoch": 0.8263291139240506, "grad_norm": 0.6022565029100964, "learning_rate": 3.947390847755559e-05, "loss": 0.6801, "step": 204 }, { "epoch": 0.830379746835443, "grad_norm": 0.6602019754227716, "learning_rate": 3.946089741159648e-05, "loss": 0.7009, "step": 205 }, { "epoch": 0.8344303797468354, "grad_norm": 0.5890198895743078, "learning_rate": 3.944772961024501e-05, "loss": 0.6562, "step": 206 }, { "epoch": 0.8384810126582278, "grad_norm": 0.5901681210376836, "learning_rate": 3.943440517955285e-05, "loss": 0.6683, "step": 207 }, { "epoch": 0.8425316455696202, "grad_norm": 0.6095997426229873, "learning_rate": 3.9420924226833126e-05, "loss": 0.6606, "step": 208 }, { "epoch": 0.8465822784810126, "grad_norm": 0.6380155761000842, "learning_rate": 3.9407286860659566e-05, "loss": 0.6924, "step": 209 }, { "epoch": 0.850632911392405, "grad_norm": 0.6301627361566847, "learning_rate": 3.9393493190865657e-05, "loss": 0.669, "step": 210 }, { "epoch": 0.8546835443037974, "grad_norm": 0.6478619482143823, "learning_rate": 3.937954332854371e-05, "loss": 0.6981, "step": 211 }, { "epoch": 0.8587341772151899, "grad_norm": 0.7457882267838598, "learning_rate": 3.9365437386044016e-05, "loss": 0.689, "step": 212 }, { "epoch": 0.8627848101265823, "grad_norm": 0.6339981096254158, "learning_rate": 3.935117547697387e-05, "loss": 0.667, "step": 213 }, { "epoch": 0.8668354430379747, "grad_norm": 0.7212193488087695, "learning_rate": 3.933675771619675e-05, "loss": 0.6711, "step": 214 }, { "epoch": 0.8708860759493671, "grad_norm": 0.663084788299034, "learning_rate": 3.932218421983131e-05, "loss": 0.6805, "step": 215 }, { "epoch": 0.8749367088607595, "grad_norm": 0.5961165039670391, "learning_rate": 3.9307455105250484e-05, "loss": 0.6384, "step": 216 }, { "epoch": 0.8789873417721519, "grad_norm": 0.7021773755479036, "learning_rate": 3.929257049108054e-05, "loss": 0.6798, "step": 217 }, { "epoch": 0.8830379746835443, "grad_norm": 0.6481709833916661, "learning_rate": 3.927753049720011e-05, "loss": 0.675, "step": 218 }, { "epoch": 0.8870886075949367, "grad_norm": 0.7243917955225546, "learning_rate": 3.9262335244739234e-05, "loss": 0.6799, "step": 219 }, { "epoch": 0.8911392405063291, "grad_norm": 0.5698873316938579, "learning_rate": 3.92469848560784e-05, "loss": 0.6732, "step": 220 }, { "epoch": 0.8951898734177215, "grad_norm": 0.7037826791791024, "learning_rate": 3.923147945484751e-05, "loss": 0.6983, "step": 221 }, { "epoch": 0.8992405063291139, "grad_norm": 0.692802144928321, "learning_rate": 3.9215819165924956e-05, "loss": 0.6954, "step": 222 }, { "epoch": 0.9032911392405063, "grad_norm": 0.5811666129659256, "learning_rate": 3.920000411543654e-05, "loss": 0.657, "step": 223 }, { "epoch": 0.9073417721518987, "grad_norm": 0.6273584160997444, "learning_rate": 3.9184034430754495e-05, "loss": 0.6984, "step": 224 }, { "epoch": 0.9113924050632911, "grad_norm": 0.5810748886770299, "learning_rate": 3.916791024049648e-05, "loss": 0.6571, "step": 225 }, { "epoch": 0.9154430379746835, "grad_norm": 0.5840492983324392, "learning_rate": 3.91516316745245e-05, "loss": 0.6582, "step": 226 }, { "epoch": 0.9194936708860759, "grad_norm": 0.612219168201689, "learning_rate": 3.913519886394389e-05, "loss": 0.6834, "step": 227 }, { "epoch": 0.9235443037974683, "grad_norm": 0.5558444327450094, "learning_rate": 3.911861194110225e-05, "loss": 0.6689, "step": 228 }, { "epoch": 0.9275949367088607, "grad_norm": 0.5471778491201101, "learning_rate": 3.910187103958837e-05, "loss": 0.6778, "step": 229 }, { "epoch": 0.9316455696202531, "grad_norm": 0.5766096864837146, "learning_rate": 3.908497629423117e-05, "loss": 0.6716, "step": 230 }, { "epoch": 0.9356962025316455, "grad_norm": 0.6719354372327575, "learning_rate": 3.9067927841098614e-05, "loss": 0.6722, "step": 231 }, { "epoch": 0.9397468354430379, "grad_norm": 0.6562921063466274, "learning_rate": 3.9050725817496594e-05, "loss": 0.6841, "step": 232 }, { "epoch": 0.9437974683544303, "grad_norm": 0.6396478059900162, "learning_rate": 3.9033370361967844e-05, "loss": 0.6622, "step": 233 }, { "epoch": 0.9478481012658228, "grad_norm": 0.5999543566819449, "learning_rate": 3.901586161429081e-05, "loss": 0.6538, "step": 234 }, { "epoch": 0.9518987341772152, "grad_norm": 0.632471583124651, "learning_rate": 3.8998199715478545e-05, "loss": 0.6567, "step": 235 }, { "epoch": 0.9559493670886076, "grad_norm": 0.6436071047724086, "learning_rate": 3.8980384807777564e-05, "loss": 0.6734, "step": 236 }, { "epoch": 0.96, "grad_norm": 0.6375100005984208, "learning_rate": 3.896241703466667e-05, "loss": 0.7013, "step": 237 }, { "epoch": 0.9640506329113924, "grad_norm": 0.6082502191769378, "learning_rate": 3.894429654085585e-05, "loss": 0.6797, "step": 238 }, { "epoch": 0.9681012658227848, "grad_norm": 0.5677818531141545, "learning_rate": 3.892602347228505e-05, "loss": 0.6705, "step": 239 }, { "epoch": 0.9721518987341772, "grad_norm": 0.5846919012858934, "learning_rate": 3.890759797612307e-05, "loss": 0.6376, "step": 240 }, { "epoch": 0.9762025316455696, "grad_norm": 0.6027731206221959, "learning_rate": 3.888902020076632e-05, "loss": 0.6585, "step": 241 }, { "epoch": 0.980253164556962, "grad_norm": 0.6001348158434846, "learning_rate": 3.887029029583764e-05, "loss": 0.6634, "step": 242 }, { "epoch": 0.9843037974683544, "grad_norm": 0.6151983586934091, "learning_rate": 3.8851408412185125e-05, "loss": 0.6639, "step": 243 }, { "epoch": 0.9883544303797468, "grad_norm": 0.538021595267008, "learning_rate": 3.8832374701880855e-05, "loss": 0.6844, "step": 244 }, { "epoch": 0.9924050632911392, "grad_norm": 0.6147362108943362, "learning_rate": 3.881318931821972e-05, "loss": 0.6586, "step": 245 }, { "epoch": 0.9964556962025316, "grad_norm": 0.5673753243144825, "learning_rate": 3.879385241571817e-05, "loss": 0.6914, "step": 246 }, { "epoch": 1.000506329113924, "grad_norm": 0.565092900900514, "learning_rate": 3.8774364150112955e-05, "loss": 0.6327, "step": 247 }, { "epoch": 1.0045569620253165, "grad_norm": 0.7149145534102889, "learning_rate": 3.8754724678359884e-05, "loss": 0.5215, "step": 248 }, { "epoch": 1.0086075949367088, "grad_norm": 0.5956060828722487, "learning_rate": 3.873493415863256e-05, "loss": 0.5331, "step": 249 }, { "epoch": 1.0126582278481013, "grad_norm": 0.7671835460705372, "learning_rate": 3.871499275032111e-05, "loss": 0.5357, "step": 250 }, { "epoch": 1.0167088607594936, "grad_norm": 0.6477002218684673, "learning_rate": 3.869490061403091e-05, "loss": 0.5055, "step": 251 }, { "epoch": 1.0207594936708861, "grad_norm": 0.682072460598869, "learning_rate": 3.867465791158124e-05, "loss": 0.525, "step": 252 }, { "epoch": 1.0248101265822784, "grad_norm": 0.77163778132628, "learning_rate": 3.865426480600407e-05, "loss": 0.5025, "step": 253 }, { "epoch": 1.028860759493671, "grad_norm": 0.6355623466702569, "learning_rate": 3.863372146154264e-05, "loss": 0.5348, "step": 254 }, { "epoch": 1.0329113924050632, "grad_norm": 0.7062650617435692, "learning_rate": 3.861302804365024e-05, "loss": 0.5232, "step": 255 }, { "epoch": 1.0369620253164558, "grad_norm": 0.67561205621561, "learning_rate": 3.85921847189888e-05, "loss": 0.5189, "step": 256 }, { "epoch": 1.041012658227848, "grad_norm": 0.6865037557303143, "learning_rate": 3.85711916554276e-05, "loss": 0.533, "step": 257 }, { "epoch": 1.0450632911392406, "grad_norm": 0.6629255729812946, "learning_rate": 3.85500490220419e-05, "loss": 0.5138, "step": 258 }, { "epoch": 1.0491139240506329, "grad_norm": 0.726465596730934, "learning_rate": 3.852875698911154e-05, "loss": 0.5247, "step": 259 }, { "epoch": 1.0531645569620254, "grad_norm": 0.7260798720974461, "learning_rate": 3.850731572811963e-05, "loss": 0.5209, "step": 260 }, { "epoch": 1.0572151898734177, "grad_norm": 0.7241249449609841, "learning_rate": 3.848572541175116e-05, "loss": 0.5296, "step": 261 }, { "epoch": 1.0612658227848102, "grad_norm": 0.7971849325510647, "learning_rate": 3.846398621389154e-05, "loss": 0.5018, "step": 262 }, { "epoch": 1.0653164556962025, "grad_norm": 0.6952660605542195, "learning_rate": 3.84420983096253e-05, "loss": 0.522, "step": 263 }, { "epoch": 1.069367088607595, "grad_norm": 0.654017997581266, "learning_rate": 3.8420061875234606e-05, "loss": 0.5088, "step": 264 }, { "epoch": 1.0734177215189873, "grad_norm": 0.7386585067452415, "learning_rate": 3.839787708819787e-05, "loss": 0.4987, "step": 265 }, { "epoch": 1.0774683544303798, "grad_norm": 0.6515932210590282, "learning_rate": 3.8375544127188325e-05, "loss": 0.5252, "step": 266 }, { "epoch": 1.081518987341772, "grad_norm": 0.6972698456234939, "learning_rate": 3.8353063172072564e-05, "loss": 0.5132, "step": 267 }, { "epoch": 1.0855696202531646, "grad_norm": 0.6726190797780659, "learning_rate": 3.8330434403909105e-05, "loss": 0.5378, "step": 268 }, { "epoch": 1.089620253164557, "grad_norm": 0.703300197520636, "learning_rate": 3.8307658004946934e-05, "loss": 0.5061, "step": 269 }, { "epoch": 1.0936708860759494, "grad_norm": 0.704726896890891, "learning_rate": 3.8284734158624046e-05, "loss": 0.5071, "step": 270 }, { "epoch": 1.0977215189873417, "grad_norm": 0.7610803526202733, "learning_rate": 3.826166304956594e-05, "loss": 0.5176, "step": 271 }, { "epoch": 1.1017721518987342, "grad_norm": 0.7019462637784173, "learning_rate": 3.8238444863584164e-05, "loss": 0.5059, "step": 272 }, { "epoch": 1.1058227848101265, "grad_norm": 0.7072150769917406, "learning_rate": 3.821507978767479e-05, "loss": 0.4961, "step": 273 }, { "epoch": 1.109873417721519, "grad_norm": 0.7474052307702118, "learning_rate": 3.819156801001693e-05, "loss": 0.4967, "step": 274 }, { "epoch": 1.1139240506329113, "grad_norm": 0.7726460897980836, "learning_rate": 3.816790971997121e-05, "loss": 0.5178, "step": 275 }, { "epoch": 1.1179746835443038, "grad_norm": 0.7899400800454776, "learning_rate": 3.8144105108078246e-05, "loss": 0.5094, "step": 276 }, { "epoch": 1.1220253164556961, "grad_norm": 0.6183683249405572, "learning_rate": 3.81201543660571e-05, "loss": 0.4876, "step": 277 }, { "epoch": 1.1260759493670887, "grad_norm": 0.7215966706124739, "learning_rate": 3.809605768680377e-05, "loss": 0.5289, "step": 278 }, { "epoch": 1.130126582278481, "grad_norm": 0.6136332011005695, "learning_rate": 3.807181526438958e-05, "loss": 0.483, "step": 279 }, { "epoch": 1.1341772151898735, "grad_norm": 0.6741635384997543, "learning_rate": 3.8047427294059697e-05, "loss": 0.506, "step": 280 }, { "epoch": 1.1382278481012658, "grad_norm": 0.6324580021585452, "learning_rate": 3.802289397223145e-05, "loss": 0.5092, "step": 281 }, { "epoch": 1.1422784810126583, "grad_norm": 0.5998654134107996, "learning_rate": 3.7998215496492854e-05, "loss": 0.5327, "step": 282 }, { "epoch": 1.1463291139240506, "grad_norm": 0.6290807148748295, "learning_rate": 3.797339206560096e-05, "loss": 0.5218, "step": 283 }, { "epoch": 1.150379746835443, "grad_norm": 0.6472623289781784, "learning_rate": 3.794842387948027e-05, "loss": 0.5033, "step": 284 }, { "epoch": 1.1544303797468354, "grad_norm": 0.6041988023401208, "learning_rate": 3.7923311139221114e-05, "loss": 0.5025, "step": 285 }, { "epoch": 1.158481012658228, "grad_norm": 0.6431450271885055, "learning_rate": 3.7898054047078054e-05, "loss": 0.4989, "step": 286 }, { "epoch": 1.1625316455696202, "grad_norm": 0.6140305376605314, "learning_rate": 3.787265280646825e-05, "loss": 0.5423, "step": 287 }, { "epoch": 1.1665822784810127, "grad_norm": 0.6134308122885841, "learning_rate": 3.7847107621969786e-05, "loss": 0.5158, "step": 288 }, { "epoch": 1.170632911392405, "grad_norm": 0.6910055641408112, "learning_rate": 3.7821418699320064e-05, "loss": 0.5299, "step": 289 }, { "epoch": 1.1746835443037975, "grad_norm": 0.5358889530896341, "learning_rate": 3.7795586245414145e-05, "loss": 0.5298, "step": 290 }, { "epoch": 1.1787341772151898, "grad_norm": 0.6687401600086532, "learning_rate": 3.776961046830306e-05, "loss": 0.4903, "step": 291 }, { "epoch": 1.1827848101265823, "grad_norm": 0.6368275703077801, "learning_rate": 3.774349157719215e-05, "loss": 0.5229, "step": 292 }, { "epoch": 1.1868354430379746, "grad_norm": 0.6811408024331037, "learning_rate": 3.7717229782439365e-05, "loss": 0.4994, "step": 293 }, { "epoch": 1.1908860759493671, "grad_norm": 0.5791781363260831, "learning_rate": 3.769082529555359e-05, "loss": 0.5197, "step": 294 }, { "epoch": 1.1949367088607594, "grad_norm": 0.6587233601455758, "learning_rate": 3.766427832919294e-05, "loss": 0.5102, "step": 295 }, { "epoch": 1.198987341772152, "grad_norm": 0.5741819135208843, "learning_rate": 3.7637589097163024e-05, "loss": 0.5154, "step": 296 }, { "epoch": 1.2030379746835442, "grad_norm": 0.7240546406880323, "learning_rate": 3.761075781441526e-05, "loss": 0.5089, "step": 297 }, { "epoch": 1.2070886075949367, "grad_norm": 0.6185603631908825, "learning_rate": 3.75837846970451e-05, "loss": 0.4953, "step": 298 }, { "epoch": 1.211139240506329, "grad_norm": 0.6769135929617891, "learning_rate": 3.755666996229032e-05, "loss": 0.5353, "step": 299 }, { "epoch": 1.2151898734177216, "grad_norm": 0.6595818537919265, "learning_rate": 3.752941382852927e-05, "loss": 0.5218, "step": 300 }, { "epoch": 1.2192405063291138, "grad_norm": 0.6423987464090137, "learning_rate": 3.7502016515279115e-05, "loss": 0.5323, "step": 301 }, { "epoch": 1.2232911392405064, "grad_norm": 0.597095192054157, "learning_rate": 3.7474478243194043e-05, "loss": 0.516, "step": 302 }, { "epoch": 1.2273417721518987, "grad_norm": 0.6578071149850448, "learning_rate": 3.744679923406351e-05, "loss": 0.5159, "step": 303 }, { "epoch": 1.2313924050632912, "grad_norm": 0.5525997624124608, "learning_rate": 3.741897971081043e-05, "loss": 0.5175, "step": 304 }, { "epoch": 1.2354430379746835, "grad_norm": 0.691995221547308, "learning_rate": 3.739101989748946e-05, "loss": 0.5304, "step": 305 }, { "epoch": 1.239493670886076, "grad_norm": 0.5372863871759954, "learning_rate": 3.7362920019285066e-05, "loss": 0.514, "step": 306 }, { "epoch": 1.2435443037974683, "grad_norm": 0.6019297176932275, "learning_rate": 3.73346803025098e-05, "loss": 0.4957, "step": 307 }, { "epoch": 1.2475949367088608, "grad_norm": 0.5332222403999906, "learning_rate": 3.730630097460247e-05, "loss": 0.4911, "step": 308 }, { "epoch": 1.251645569620253, "grad_norm": 0.570488096304111, "learning_rate": 3.727778226412628e-05, "loss": 0.5255, "step": 309 }, { "epoch": 1.2556962025316456, "grad_norm": 0.663253681152295, "learning_rate": 3.7249124400767006e-05, "loss": 0.5126, "step": 310 }, { "epoch": 1.259746835443038, "grad_norm": 0.5741522203129932, "learning_rate": 3.722032761533114e-05, "loss": 0.5279, "step": 311 }, { "epoch": 1.2637974683544304, "grad_norm": 0.6926689885319844, "learning_rate": 3.719139213974403e-05, "loss": 0.5234, "step": 312 }, { "epoch": 1.2678481012658227, "grad_norm": 0.5910970003856061, "learning_rate": 3.7162318207048006e-05, "loss": 0.4929, "step": 313 }, { "epoch": 1.2718987341772152, "grad_norm": 0.6907257551963087, "learning_rate": 3.713310605140055e-05, "loss": 0.5085, "step": 314 }, { "epoch": 1.2759493670886077, "grad_norm": 0.5650540467946072, "learning_rate": 3.710375590807233e-05, "loss": 0.5206, "step": 315 }, { "epoch": 1.28, "grad_norm": 0.634371231704033, "learning_rate": 3.7074268013445365e-05, "loss": 0.5275, "step": 316 }, { "epoch": 1.2840506329113923, "grad_norm": 0.5522632172099259, "learning_rate": 3.7044642605011114e-05, "loss": 0.4913, "step": 317 }, { "epoch": 1.2881012658227848, "grad_norm": 0.679675361792392, "learning_rate": 3.701487992136854e-05, "loss": 0.4946, "step": 318 }, { "epoch": 1.2921518987341774, "grad_norm": 0.6545115191896037, "learning_rate": 3.69849802022222e-05, "loss": 0.5197, "step": 319 }, { "epoch": 1.2962025316455696, "grad_norm": 0.6448526015042921, "learning_rate": 3.6954943688380334e-05, "loss": 0.5125, "step": 320 }, { "epoch": 1.300253164556962, "grad_norm": 0.6769815967417045, "learning_rate": 3.692477062175289e-05, "loss": 0.5224, "step": 321 }, { "epoch": 1.3043037974683545, "grad_norm": 0.602769801085819, "learning_rate": 3.689446124534958e-05, "loss": 0.5185, "step": 322 }, { "epoch": 1.308354430379747, "grad_norm": 0.6676650281217779, "learning_rate": 3.686401580327799e-05, "loss": 0.5255, "step": 323 }, { "epoch": 1.3124050632911393, "grad_norm": 0.5876717948394674, "learning_rate": 3.683343454074149e-05, "loss": 0.5113, "step": 324 }, { "epoch": 1.3164556962025316, "grad_norm": 0.6140209807915856, "learning_rate": 3.6802717704037386e-05, "loss": 0.4878, "step": 325 }, { "epoch": 1.320506329113924, "grad_norm": 0.6041819007285766, "learning_rate": 3.6771865540554855e-05, "loss": 0.5072, "step": 326 }, { "epoch": 1.3245569620253166, "grad_norm": 0.6228340110248093, "learning_rate": 3.674087829877297e-05, "loss": 0.5111, "step": 327 }, { "epoch": 1.3286075949367089, "grad_norm": 0.5710907426573741, "learning_rate": 3.6709756228258735e-05, "loss": 0.5264, "step": 328 }, { "epoch": 1.3326582278481012, "grad_norm": 0.6387406322627028, "learning_rate": 3.667849957966501e-05, "loss": 0.4826, "step": 329 }, { "epoch": 1.3367088607594937, "grad_norm": 0.5879392305300852, "learning_rate": 3.6647108604728546e-05, "loss": 0.5142, "step": 330 }, { "epoch": 1.3407594936708862, "grad_norm": 0.7188643377727777, "learning_rate": 3.661558355626795e-05, "loss": 0.5339, "step": 331 }, { "epoch": 1.3448101265822785, "grad_norm": 0.6322735224509821, "learning_rate": 3.658392468818163e-05, "loss": 0.4968, "step": 332 }, { "epoch": 1.3488607594936708, "grad_norm": 0.5957240898854566, "learning_rate": 3.655213225544574e-05, "loss": 0.5152, "step": 333 }, { "epoch": 1.3529113924050633, "grad_norm": 0.6640216253669787, "learning_rate": 3.652020651411218e-05, "loss": 0.5172, "step": 334 }, { "epoch": 1.3569620253164558, "grad_norm": 0.5994920653336939, "learning_rate": 3.6488147721306474e-05, "loss": 0.5305, "step": 335 }, { "epoch": 1.3610126582278481, "grad_norm": 0.619268895867421, "learning_rate": 3.645595613522574e-05, "loss": 0.5044, "step": 336 }, { "epoch": 1.3650632911392404, "grad_norm": 0.5579458230292926, "learning_rate": 3.642363201513657e-05, "loss": 0.5349, "step": 337 }, { "epoch": 1.369113924050633, "grad_norm": 0.6460202454681361, "learning_rate": 3.6391175621373006e-05, "loss": 0.5324, "step": 338 }, { "epoch": 1.3731645569620254, "grad_norm": 0.6090116672775598, "learning_rate": 3.6358587215334355e-05, "loss": 0.5055, "step": 339 }, { "epoch": 1.3772151898734177, "grad_norm": 0.6194360510153931, "learning_rate": 3.632586705948318e-05, "loss": 0.4974, "step": 340 }, { "epoch": 1.38126582278481, "grad_norm": 0.6733192041282758, "learning_rate": 3.629301541734311e-05, "loss": 0.519, "step": 341 }, { "epoch": 1.3853164556962025, "grad_norm": 0.5435956864406987, "learning_rate": 3.626003255349676e-05, "loss": 0.5105, "step": 342 }, { "epoch": 1.389367088607595, "grad_norm": 0.573633510260476, "learning_rate": 3.622691873358357e-05, "loss": 0.5056, "step": 343 }, { "epoch": 1.3934177215189874, "grad_norm": 0.6399327055072811, "learning_rate": 3.61936742242977e-05, "loss": 0.5117, "step": 344 }, { "epoch": 1.3974683544303796, "grad_norm": 0.5893360137737447, "learning_rate": 3.6160299293385864e-05, "loss": 0.5083, "step": 345 }, { "epoch": 1.4015189873417722, "grad_norm": 0.5649424286838332, "learning_rate": 3.612679420964516e-05, "loss": 0.519, "step": 346 }, { "epoch": 1.4055696202531647, "grad_norm": 0.5862136356363693, "learning_rate": 3.609315924292092e-05, "loss": 0.5092, "step": 347 }, { "epoch": 1.409620253164557, "grad_norm": 0.6081814280745935, "learning_rate": 3.6059394664104554e-05, "loss": 0.5433, "step": 348 }, { "epoch": 1.4136708860759493, "grad_norm": 0.7127061949889311, "learning_rate": 3.602550074513133e-05, "loss": 0.5127, "step": 349 }, { "epoch": 1.4177215189873418, "grad_norm": 0.6114107279292057, "learning_rate": 3.599147775897822e-05, "loss": 0.506, "step": 350 }, { "epoch": 1.4217721518987343, "grad_norm": 0.7065161411639823, "learning_rate": 3.595732597966167e-05, "loss": 0.5224, "step": 351 }, { "epoch": 1.4258227848101266, "grad_norm": 0.502765543182647, "learning_rate": 3.592304568223542e-05, "loss": 0.5032, "step": 352 }, { "epoch": 1.4298734177215189, "grad_norm": 0.6468724558106146, "learning_rate": 3.588863714278826e-05, "loss": 0.5047, "step": 353 }, { "epoch": 1.4339240506329114, "grad_norm": 0.5860792460144295, "learning_rate": 3.585410063844186e-05, "loss": 0.5293, "step": 354 }, { "epoch": 1.437974683544304, "grad_norm": 0.5920779068170806, "learning_rate": 3.581943644734846e-05, "loss": 0.5008, "step": 355 }, { "epoch": 1.4420253164556962, "grad_norm": 0.5971308376027806, "learning_rate": 3.578464484868869e-05, "loss": 0.5217, "step": 356 }, { "epoch": 1.4460759493670885, "grad_norm": 0.5454059186391053, "learning_rate": 3.5749726122669316e-05, "loss": 0.5094, "step": 357 }, { "epoch": 1.450126582278481, "grad_norm": 0.6055752503167148, "learning_rate": 3.5714680550520943e-05, "loss": 0.5159, "step": 358 }, { "epoch": 1.4541772151898735, "grad_norm": 0.6611261578173644, "learning_rate": 3.5679508414495794e-05, "loss": 0.5095, "step": 359 }, { "epoch": 1.4582278481012658, "grad_norm": 0.6583962334735947, "learning_rate": 3.564420999786543e-05, "loss": 0.5164, "step": 360 }, { "epoch": 1.4622784810126581, "grad_norm": 0.5875883057112671, "learning_rate": 3.560878558491842e-05, "loss": 0.4963, "step": 361 }, { "epoch": 1.4663291139240506, "grad_norm": 0.6464978256734796, "learning_rate": 3.5573235460958145e-05, "loss": 0.5253, "step": 362 }, { "epoch": 1.4703797468354431, "grad_norm": 0.7548833014320926, "learning_rate": 3.553755991230039e-05, "loss": 0.5439, "step": 363 }, { "epoch": 1.4744303797468354, "grad_norm": 0.6384261880131867, "learning_rate": 3.5501759226271144e-05, "loss": 0.5333, "step": 364 }, { "epoch": 1.4784810126582277, "grad_norm": 0.674574755918693, "learning_rate": 3.546583369120419e-05, "loss": 0.5234, "step": 365 }, { "epoch": 1.4825316455696202, "grad_norm": 0.6498068222470607, "learning_rate": 3.5429783596438864e-05, "loss": 0.5293, "step": 366 }, { "epoch": 1.4865822784810128, "grad_norm": 0.7221737148549313, "learning_rate": 3.539360923231766e-05, "loss": 0.5159, "step": 367 }, { "epoch": 1.490632911392405, "grad_norm": 0.6453067283433305, "learning_rate": 3.535731089018394e-05, "loss": 0.5216, "step": 368 }, { "epoch": 1.4946835443037974, "grad_norm": 0.6111341405130095, "learning_rate": 3.532088886237956e-05, "loss": 0.5248, "step": 369 }, { "epoch": 1.4987341772151899, "grad_norm": 0.6162799065473474, "learning_rate": 3.528434344224253e-05, "loss": 0.5291, "step": 370 }, { "epoch": 1.5027848101265824, "grad_norm": 0.6106026150057743, "learning_rate": 3.524767492410464e-05, "loss": 0.5279, "step": 371 }, { "epoch": 1.5068354430379747, "grad_norm": 0.6925018042074355, "learning_rate": 3.521088360328908e-05, "loss": 0.5315, "step": 372 }, { "epoch": 1.510886075949367, "grad_norm": 0.541420942944414, "learning_rate": 3.517396977610811e-05, "loss": 0.5011, "step": 373 }, { "epoch": 1.5149367088607595, "grad_norm": 0.6031579645094614, "learning_rate": 3.5136933739860595e-05, "loss": 0.5129, "step": 374 }, { "epoch": 1.518987341772152, "grad_norm": 0.5611488555215367, "learning_rate": 3.509977579282971e-05, "loss": 0.5137, "step": 375 }, { "epoch": 1.5230379746835443, "grad_norm": 0.5730485646486152, "learning_rate": 3.5062496234280424e-05, "loss": 0.4728, "step": 376 }, { "epoch": 1.5270886075949366, "grad_norm": 0.6154755676780835, "learning_rate": 3.502509536445719e-05, "loss": 0.5417, "step": 377 }, { "epoch": 1.531139240506329, "grad_norm": 0.578548675108124, "learning_rate": 3.498757348458147e-05, "loss": 0.5227, "step": 378 }, { "epoch": 1.5351898734177216, "grad_norm": 0.5532189206840623, "learning_rate": 3.4949930896849324e-05, "loss": 0.5213, "step": 379 }, { "epoch": 1.539240506329114, "grad_norm": 0.5657258614547871, "learning_rate": 3.491216790442899e-05, "loss": 0.5128, "step": 380 }, { "epoch": 1.5432911392405062, "grad_norm": 0.5468556605122009, "learning_rate": 3.487428481145839e-05, "loss": 0.514, "step": 381 }, { "epoch": 1.5473417721518987, "grad_norm": 0.6283564695063891, "learning_rate": 3.483628192304278e-05, "loss": 0.5195, "step": 382 }, { "epoch": 1.5513924050632912, "grad_norm": 0.5492694181094562, "learning_rate": 3.479815954525219e-05, "loss": 0.5505, "step": 383 }, { "epoch": 1.5554430379746835, "grad_norm": 0.6738176580007299, "learning_rate": 3.475991798511899e-05, "loss": 0.5369, "step": 384 }, { "epoch": 1.5594936708860758, "grad_norm": 0.5491812695538183, "learning_rate": 3.4721557550635464e-05, "loss": 0.5378, "step": 385 }, { "epoch": 1.5635443037974683, "grad_norm": 0.614351897119312, "learning_rate": 3.468307855075128e-05, "loss": 0.5047, "step": 386 }, { "epoch": 1.5675949367088609, "grad_norm": 0.5043070152513672, "learning_rate": 3.4644481295371005e-05, "loss": 0.5009, "step": 387 }, { "epoch": 1.5716455696202531, "grad_norm": 0.6470870086053772, "learning_rate": 3.460576609535163e-05, "loss": 0.5079, "step": 388 }, { "epoch": 1.5756962025316454, "grad_norm": 0.5877636807630627, "learning_rate": 3.456693326250006e-05, "loss": 0.5061, "step": 389 }, { "epoch": 1.579746835443038, "grad_norm": 0.5996132265636813, "learning_rate": 3.452798310957058e-05, "loss": 0.5223, "step": 390 }, { "epoch": 1.5837974683544305, "grad_norm": 0.6554278431503997, "learning_rate": 3.4488915950262386e-05, "loss": 0.5153, "step": 391 }, { "epoch": 1.5878481012658228, "grad_norm": 0.4768592429644678, "learning_rate": 3.4449732099216985e-05, "loss": 0.5337, "step": 392 }, { "epoch": 1.591898734177215, "grad_norm": 0.5855012681360289, "learning_rate": 3.441043187201574e-05, "loss": 0.5198, "step": 393 }, { "epoch": 1.5959493670886076, "grad_norm": 0.5479950280796649, "learning_rate": 3.437101558517728e-05, "loss": 0.5228, "step": 394 }, { "epoch": 1.6, "grad_norm": 0.5706116850965532, "learning_rate": 3.433148355615496e-05, "loss": 0.5315, "step": 395 }, { "epoch": 1.6040506329113924, "grad_norm": 0.6128173827148442, "learning_rate": 3.4291836103334294e-05, "loss": 0.5343, "step": 396 }, { "epoch": 1.6081012658227847, "grad_norm": 0.6539582500749781, "learning_rate": 3.425207354603043e-05, "loss": 0.5547, "step": 397 }, { "epoch": 1.6121518987341772, "grad_norm": 0.6158091146139023, "learning_rate": 3.421219620448553e-05, "loss": 0.5195, "step": 398 }, { "epoch": 1.6162025316455697, "grad_norm": 0.6517748071636363, "learning_rate": 3.417220439986623e-05, "loss": 0.5176, "step": 399 }, { "epoch": 1.620253164556962, "grad_norm": 0.6842259034317076, "learning_rate": 3.4132098454261024e-05, "loss": 0.4953, "step": 400 }, { "epoch": 1.6243037974683543, "grad_norm": 0.5853237387541361, "learning_rate": 3.4091878690677676e-05, "loss": 0.5137, "step": 401 }, { "epoch": 1.6283544303797468, "grad_norm": 0.6542702335592273, "learning_rate": 3.405154543304065e-05, "loss": 0.5026, "step": 402 }, { "epoch": 1.6324050632911393, "grad_norm": 0.6558464588079318, "learning_rate": 3.401109900618843e-05, "loss": 0.5319, "step": 403 }, { "epoch": 1.6364556962025316, "grad_norm": 0.634593553749296, "learning_rate": 3.3970539735870996e-05, "loss": 0.5159, "step": 404 }, { "epoch": 1.640506329113924, "grad_norm": 0.6357089251176189, "learning_rate": 3.392986794874714e-05, "loss": 0.5264, "step": 405 }, { "epoch": 1.6445569620253164, "grad_norm": 0.5640226584735847, "learning_rate": 3.388908397238184e-05, "loss": 0.5128, "step": 406 }, { "epoch": 1.648607594936709, "grad_norm": 0.5888146660941902, "learning_rate": 3.384818813524362e-05, "loss": 0.506, "step": 407 }, { "epoch": 1.6526582278481012, "grad_norm": 0.6323840046427059, "learning_rate": 3.380718076670195e-05, "loss": 0.4973, "step": 408 }, { "epoch": 1.6567088607594935, "grad_norm": 0.5036633910097746, "learning_rate": 3.376606219702454e-05, "loss": 0.5139, "step": 409 }, { "epoch": 1.660759493670886, "grad_norm": 0.5909569467395188, "learning_rate": 3.372483275737468e-05, "loss": 0.5144, "step": 410 }, { "epoch": 1.6648101265822786, "grad_norm": 0.5526469880321783, "learning_rate": 3.368349277980861e-05, "loss": 0.521, "step": 411 }, { "epoch": 1.6688607594936709, "grad_norm": 0.5722440716556195, "learning_rate": 3.3642042597272844e-05, "loss": 0.5382, "step": 412 }, { "epoch": 1.6729113924050631, "grad_norm": 0.5388994822925325, "learning_rate": 3.360048254360144e-05, "loss": 0.5107, "step": 413 }, { "epoch": 1.6769620253164557, "grad_norm": 0.544192745860697, "learning_rate": 3.355881295351336e-05, "loss": 0.4982, "step": 414 }, { "epoch": 1.6810126582278482, "grad_norm": 0.5577687145942031, "learning_rate": 3.351703416260975e-05, "loss": 0.5492, "step": 415 }, { "epoch": 1.6850632911392405, "grad_norm": 0.5531319826451607, "learning_rate": 3.347514650737126e-05, "loss": 0.5269, "step": 416 }, { "epoch": 1.6891139240506328, "grad_norm": 0.514058973908768, "learning_rate": 3.3433150325155295e-05, "loss": 0.5204, "step": 417 }, { "epoch": 1.6931645569620253, "grad_norm": 0.5457150022304883, "learning_rate": 3.339104595419334e-05, "loss": 0.5528, "step": 418 }, { "epoch": 1.6972151898734178, "grad_norm": 0.5105236103125679, "learning_rate": 3.3348833733588204e-05, "loss": 0.5075, "step": 419 }, { "epoch": 1.70126582278481, "grad_norm": 0.582934830647459, "learning_rate": 3.3306514003311305e-05, "loss": 0.5196, "step": 420 }, { "epoch": 1.7053164556962024, "grad_norm": 0.4993242161702117, "learning_rate": 3.326408710419996e-05, "loss": 0.5063, "step": 421 }, { "epoch": 1.709367088607595, "grad_norm": 0.49271453486142774, "learning_rate": 3.322155337795454e-05, "loss": 0.4987, "step": 422 }, { "epoch": 1.7134177215189874, "grad_norm": 0.5683104122504594, "learning_rate": 3.317891316713587e-05, "loss": 0.5089, "step": 423 }, { "epoch": 1.7174683544303797, "grad_norm": 0.5672830663816271, "learning_rate": 3.313616681516231e-05, "loss": 0.5227, "step": 424 }, { "epoch": 1.721518987341772, "grad_norm": 0.5595890532095826, "learning_rate": 3.309331466630713e-05, "loss": 0.5301, "step": 425 }, { "epoch": 1.7255696202531645, "grad_norm": 0.5471883948232213, "learning_rate": 3.305035706569563e-05, "loss": 0.5142, "step": 426 }, { "epoch": 1.729620253164557, "grad_norm": 0.5253542013776216, "learning_rate": 3.3007294359302433e-05, "loss": 0.5397, "step": 427 }, { "epoch": 1.7336708860759493, "grad_norm": 0.5386124506712162, "learning_rate": 3.296412689394864e-05, "loss": 0.5287, "step": 428 }, { "epoch": 1.7377215189873416, "grad_norm": 0.4946299150459146, "learning_rate": 3.292085501729909e-05, "loss": 0.5129, "step": 429 }, { "epoch": 1.7417721518987341, "grad_norm": 0.5170738444357365, "learning_rate": 3.2877479077859534e-05, "loss": 0.5203, "step": 430 }, { "epoch": 1.7458227848101266, "grad_norm": 0.5246230006647054, "learning_rate": 3.283399942497381e-05, "loss": 0.5352, "step": 431 }, { "epoch": 1.749873417721519, "grad_norm": 0.49104576426004715, "learning_rate": 3.279041640882108e-05, "loss": 0.5143, "step": 432 }, { "epoch": 1.7539240506329112, "grad_norm": 0.6087764391608405, "learning_rate": 3.2746730380412964e-05, "loss": 0.5184, "step": 433 }, { "epoch": 1.7579746835443038, "grad_norm": 0.5554997185910301, "learning_rate": 3.2702941691590726e-05, "loss": 0.5076, "step": 434 }, { "epoch": 1.7620253164556963, "grad_norm": 0.5490528439616986, "learning_rate": 3.265905069502244e-05, "loss": 0.5156, "step": 435 }, { "epoch": 1.7660759493670886, "grad_norm": 0.5316807441357029, "learning_rate": 3.261505774420016e-05, "loss": 0.5181, "step": 436 }, { "epoch": 1.7701265822784809, "grad_norm": 0.5402266909633093, "learning_rate": 3.257096319343707e-05, "loss": 0.5219, "step": 437 }, { "epoch": 1.7741772151898734, "grad_norm": 0.5116760073977115, "learning_rate": 3.2526767397864614e-05, "loss": 0.4818, "step": 438 }, { "epoch": 1.7782278481012659, "grad_norm": 0.5634931962186337, "learning_rate": 3.248247071342966e-05, "loss": 0.5112, "step": 439 }, { "epoch": 1.7822784810126582, "grad_norm": 0.5970704961077711, "learning_rate": 3.243807349689161e-05, "loss": 0.5157, "step": 440 }, { "epoch": 1.7863291139240505, "grad_norm": 0.6442321139865645, "learning_rate": 3.2393576105819544e-05, "loss": 0.5271, "step": 441 }, { "epoch": 1.790379746835443, "grad_norm": 0.4936732994421937, "learning_rate": 3.2348978898589333e-05, "loss": 0.4937, "step": 442 }, { "epoch": 1.7944303797468355, "grad_norm": 0.6102035267058128, "learning_rate": 3.230428223438075e-05, "loss": 0.475, "step": 443 }, { "epoch": 1.7984810126582278, "grad_norm": 0.7114627124847664, "learning_rate": 3.225948647317459e-05, "loss": 0.5316, "step": 444 }, { "epoch": 1.80253164556962, "grad_norm": 0.5206768460568496, "learning_rate": 3.2214591975749745e-05, "loss": 0.5013, "step": 445 }, { "epoch": 1.8065822784810126, "grad_norm": 0.6425095983914398, "learning_rate": 3.216959910368034e-05, "loss": 0.5251, "step": 446 }, { "epoch": 1.8106329113924051, "grad_norm": 0.6154386373277289, "learning_rate": 3.212450821933277e-05, "loss": 0.5352, "step": 447 }, { "epoch": 1.8146835443037974, "grad_norm": 0.5452118837092892, "learning_rate": 3.207931968586281e-05, "loss": 0.5322, "step": 448 }, { "epoch": 1.81873417721519, "grad_norm": 0.577246470667571, "learning_rate": 3.203403386721272e-05, "loss": 0.492, "step": 449 }, { "epoch": 1.8227848101265822, "grad_norm": 0.5934531079456339, "learning_rate": 3.1988651128108245e-05, "loss": 0.5065, "step": 450 }, { "epoch": 1.8268354430379747, "grad_norm": 0.5662759134834118, "learning_rate": 3.194317183405573e-05, "loss": 0.5197, "step": 451 }, { "epoch": 1.8308860759493673, "grad_norm": 0.6440254077626, "learning_rate": 3.189759635133914e-05, "loss": 0.5245, "step": 452 }, { "epoch": 1.8349367088607595, "grad_norm": 0.5639874308878924, "learning_rate": 3.185192504701718e-05, "loss": 0.4943, "step": 453 }, { "epoch": 1.8389873417721518, "grad_norm": 0.5367118727465823, "learning_rate": 3.1806158288920234e-05, "loss": 0.5279, "step": 454 }, { "epoch": 1.8430379746835444, "grad_norm": 0.5491204611204745, "learning_rate": 3.1760296445647477e-05, "loss": 0.5069, "step": 455 }, { "epoch": 1.8470886075949369, "grad_norm": 0.5772288620276705, "learning_rate": 3.1714339886563896e-05, "loss": 0.5468, "step": 456 }, { "epoch": 1.8511392405063292, "grad_norm": 0.5741235393143295, "learning_rate": 3.166828898179731e-05, "loss": 0.5306, "step": 457 }, { "epoch": 1.8551898734177215, "grad_norm": 0.5578614186487695, "learning_rate": 3.162214410223536e-05, "loss": 0.5198, "step": 458 }, { "epoch": 1.859240506329114, "grad_norm": 0.5555130324186835, "learning_rate": 3.157590561952257e-05, "loss": 0.5364, "step": 459 }, { "epoch": 1.8632911392405065, "grad_norm": 0.5257496026705194, "learning_rate": 3.152957390605732e-05, "loss": 0.5212, "step": 460 }, { "epoch": 1.8673417721518988, "grad_norm": 0.5842453595641119, "learning_rate": 3.148314933498886e-05, "loss": 0.513, "step": 461 }, { "epoch": 1.871392405063291, "grad_norm": 0.5282505119178627, "learning_rate": 3.143663228021431e-05, "loss": 0.5353, "step": 462 }, { "epoch": 1.8754430379746836, "grad_norm": 0.5814407950536546, "learning_rate": 3.1390023116375624e-05, "loss": 0.5016, "step": 463 }, { "epoch": 1.879493670886076, "grad_norm": 0.6126760756099765, "learning_rate": 3.134332221885661e-05, "loss": 0.5132, "step": 464 }, { "epoch": 1.8835443037974684, "grad_norm": 0.5410496649616249, "learning_rate": 3.129652996377987e-05, "loss": 0.5075, "step": 465 }, { "epoch": 1.8875949367088607, "grad_norm": 0.6727068259364852, "learning_rate": 3.12496467280038e-05, "loss": 0.4934, "step": 466 }, { "epoch": 1.8916455696202532, "grad_norm": 0.5473841481500688, "learning_rate": 3.120267288911952e-05, "loss": 0.5357, "step": 467 }, { "epoch": 1.8956962025316457, "grad_norm": 0.572849002532361, "learning_rate": 3.11556088254479e-05, "loss": 0.5272, "step": 468 }, { "epoch": 1.899746835443038, "grad_norm": 0.5831273116099095, "learning_rate": 3.11084549160364e-05, "loss": 0.52, "step": 469 }, { "epoch": 1.9037974683544303, "grad_norm": 0.5851340439633145, "learning_rate": 3.106121154065615e-05, "loss": 0.5103, "step": 470 }, { "epoch": 1.9078481012658228, "grad_norm": 0.5783040127270516, "learning_rate": 3.1013879079798805e-05, "loss": 0.5401, "step": 471 }, { "epoch": 1.9118987341772153, "grad_norm": 0.5669145462406621, "learning_rate": 3.096645791467348e-05, "loss": 0.5085, "step": 472 }, { "epoch": 1.9159493670886076, "grad_norm": 0.5314421881685373, "learning_rate": 3.091894842720373e-05, "loss": 0.5123, "step": 473 }, { "epoch": 1.92, "grad_norm": 0.6417203724505194, "learning_rate": 3.0871351000024425e-05, "loss": 0.5097, "step": 474 }, { "epoch": 1.9240506329113924, "grad_norm": 0.601415846103956, "learning_rate": 3.0823666016478716e-05, "loss": 0.5152, "step": 475 }, { "epoch": 1.928101265822785, "grad_norm": 0.5520895080068675, "learning_rate": 3.0775893860614896e-05, "loss": 0.5064, "step": 476 }, { "epoch": 1.9321518987341773, "grad_norm": 0.6202045092237413, "learning_rate": 3.0728034917183336e-05, "loss": 0.5341, "step": 477 }, { "epoch": 1.9362025316455695, "grad_norm": 0.5324118250396703, "learning_rate": 3.06800895716334e-05, "loss": 0.5119, "step": 478 }, { "epoch": 1.940253164556962, "grad_norm": 0.5023600292676446, "learning_rate": 3.063205821011029e-05, "loss": 0.4908, "step": 479 }, { "epoch": 1.9443037974683546, "grad_norm": 0.550666329488633, "learning_rate": 3.0583941219452016e-05, "loss": 0.5153, "step": 480 }, { "epoch": 1.9483544303797469, "grad_norm": 0.5876127914811788, "learning_rate": 3.053573898718618e-05, "loss": 0.5198, "step": 481 }, { "epoch": 1.9524050632911392, "grad_norm": 0.5552681431739963, "learning_rate": 3.0487451901526956e-05, "loss": 0.5039, "step": 482 }, { "epoch": 1.9564556962025317, "grad_norm": 0.5607652018710032, "learning_rate": 3.0439080351371875e-05, "loss": 0.5198, "step": 483 }, { "epoch": 1.9605063291139242, "grad_norm": 0.5274573537215281, "learning_rate": 3.0390624726298764e-05, "loss": 0.5166, "step": 484 }, { "epoch": 1.9645569620253165, "grad_norm": 0.47956031982281166, "learning_rate": 3.034208541656255e-05, "loss": 0.5227, "step": 485 }, { "epoch": 1.9686075949367088, "grad_norm": 0.5828910833013619, "learning_rate": 3.029346281309218e-05, "loss": 0.512, "step": 486 }, { "epoch": 1.9726582278481013, "grad_norm": 0.47763738623108715, "learning_rate": 3.0244757307487415e-05, "loss": 0.4874, "step": 487 }, { "epoch": 1.9767088607594938, "grad_norm": 0.6479605688864913, "learning_rate": 3.019596929201569e-05, "loss": 0.4891, "step": 488 }, { "epoch": 1.980759493670886, "grad_norm": 0.552080432842177, "learning_rate": 3.0147099159608985e-05, "loss": 0.5238, "step": 489 }, { "epoch": 1.9848101265822784, "grad_norm": 0.6083232615429964, "learning_rate": 3.0098147303860616e-05, "loss": 0.4898, "step": 490 }, { "epoch": 1.988860759493671, "grad_norm": 0.6049434341297012, "learning_rate": 3.0049114119022117e-05, "loss": 0.5114, "step": 491 }, { "epoch": 1.9929113924050634, "grad_norm": 0.5488738912554425, "learning_rate": 3.0000000000000004e-05, "loss": 0.52, "step": 492 }, { "epoch": 1.9969620253164557, "grad_norm": 0.5409797429061671, "learning_rate": 2.995080534235264e-05, "loss": 0.5058, "step": 493 }, { "epoch": 2.001012658227848, "grad_norm": 0.5936053580554401, "learning_rate": 2.9901530542287044e-05, "loss": 0.4743, "step": 494 }, { "epoch": 2.0050632911392405, "grad_norm": 0.7083448688478303, "learning_rate": 2.9852175996655676e-05, "loss": 0.3457, "step": 495 }, { "epoch": 2.009113924050633, "grad_norm": 0.6443912173361386, "learning_rate": 2.980274210295326e-05, "loss": 0.3292, "step": 496 }, { "epoch": 2.013164556962025, "grad_norm": 0.9760569193328126, "learning_rate": 2.9753229259313578e-05, "loss": 0.3424, "step": 497 }, { "epoch": 2.0172151898734176, "grad_norm": 0.610471004877181, "learning_rate": 2.9703637864506274e-05, "loss": 0.339, "step": 498 }, { "epoch": 2.02126582278481, "grad_norm": 0.6363806791491352, "learning_rate": 2.965396831793362e-05, "loss": 0.3408, "step": 499 }, { "epoch": 2.0253164556962027, "grad_norm": 0.6605796897403498, "learning_rate": 2.9604221019627316e-05, "loss": 0.3643, "step": 500 }, { "epoch": 2.0293670886075947, "grad_norm": 0.5209952416875553, "learning_rate": 2.955439637024526e-05, "loss": 0.333, "step": 501 }, { "epoch": 2.0334177215189873, "grad_norm": 0.6957840652831951, "learning_rate": 2.9504494771068334e-05, "loss": 0.3273, "step": 502 }, { "epoch": 2.0374683544303798, "grad_norm": 0.5722929233712102, "learning_rate": 2.9454516623997156e-05, "loss": 0.3446, "step": 503 }, { "epoch": 2.0415189873417723, "grad_norm": 0.7322311128953626, "learning_rate": 2.9404462331548847e-05, "loss": 0.3475, "step": 504 }, { "epoch": 2.0455696202531644, "grad_norm": 0.5481873378380616, "learning_rate": 2.93543322968538e-05, "loss": 0.3368, "step": 505 }, { "epoch": 2.049620253164557, "grad_norm": 0.6284885792024753, "learning_rate": 2.9304126923652428e-05, "loss": 0.3348, "step": 506 }, { "epoch": 2.0536708860759494, "grad_norm": 0.6190568536739653, "learning_rate": 2.9253846616291896e-05, "loss": 0.3641, "step": 507 }, { "epoch": 2.057721518987342, "grad_norm": 0.556952492951388, "learning_rate": 2.9203491779722896e-05, "loss": 0.3312, "step": 508 }, { "epoch": 2.061772151898734, "grad_norm": 0.6003393130887994, "learning_rate": 2.9153062819496357e-05, "loss": 0.3201, "step": 509 }, { "epoch": 2.0658227848101265, "grad_norm": 0.6234554003776085, "learning_rate": 2.9102560141760178e-05, "loss": 0.3319, "step": 510 }, { "epoch": 2.069873417721519, "grad_norm": 0.5383799131236141, "learning_rate": 2.9051984153256004e-05, "loss": 0.3216, "step": 511 }, { "epoch": 2.0739240506329115, "grad_norm": 0.5467740598865294, "learning_rate": 2.900133526131588e-05, "loss": 0.3566, "step": 512 }, { "epoch": 2.0779746835443036, "grad_norm": 0.5602170601006238, "learning_rate": 2.8950613873859025e-05, "loss": 0.3186, "step": 513 }, { "epoch": 2.082025316455696, "grad_norm": 0.46801532545335206, "learning_rate": 2.8899820399388515e-05, "loss": 0.35, "step": 514 }, { "epoch": 2.0860759493670886, "grad_norm": 0.5531480886413815, "learning_rate": 2.8848955246988012e-05, "loss": 0.3425, "step": 515 }, { "epoch": 2.090126582278481, "grad_norm": 0.46490665979186224, "learning_rate": 2.879801882631847e-05, "loss": 0.3376, "step": 516 }, { "epoch": 2.094177215189873, "grad_norm": 0.599255551654325, "learning_rate": 2.8747011547614808e-05, "loss": 0.3682, "step": 517 }, { "epoch": 2.0982278481012657, "grad_norm": 0.47223876270785736, "learning_rate": 2.8695933821682635e-05, "loss": 0.3077, "step": 518 }, { "epoch": 2.1022784810126582, "grad_norm": 0.5083312282493865, "learning_rate": 2.864478605989494e-05, "loss": 0.3293, "step": 519 }, { "epoch": 2.1063291139240508, "grad_norm": 0.48359017966256695, "learning_rate": 2.8593568674188765e-05, "loss": 0.3228, "step": 520 }, { "epoch": 2.110379746835443, "grad_norm": 0.5138604666810999, "learning_rate": 2.8542282077061892e-05, "loss": 0.3306, "step": 521 }, { "epoch": 2.1144303797468353, "grad_norm": 0.48405142106487165, "learning_rate": 2.8490926681569523e-05, "loss": 0.3473, "step": 522 }, { "epoch": 2.118481012658228, "grad_norm": 0.5135225345240109, "learning_rate": 2.8439502901320956e-05, "loss": 0.3219, "step": 523 }, { "epoch": 2.1225316455696204, "grad_norm": 0.5570440818934411, "learning_rate": 2.8388011150476237e-05, "loss": 0.3303, "step": 524 }, { "epoch": 2.1265822784810124, "grad_norm": 0.5048882386041803, "learning_rate": 2.8336451843742866e-05, "loss": 0.3258, "step": 525 }, { "epoch": 2.130632911392405, "grad_norm": 0.5100071898240148, "learning_rate": 2.8284825396372387e-05, "loss": 0.3392, "step": 526 }, { "epoch": 2.1346835443037975, "grad_norm": 0.5014782996776539, "learning_rate": 2.8233132224157132e-05, "loss": 0.3193, "step": 527 }, { "epoch": 2.13873417721519, "grad_norm": 0.5376787537589963, "learning_rate": 2.8181372743426805e-05, "loss": 0.3446, "step": 528 }, { "epoch": 2.1427848101265825, "grad_norm": 0.47511068442873494, "learning_rate": 2.8129547371045128e-05, "loss": 0.3085, "step": 529 }, { "epoch": 2.1468354430379746, "grad_norm": 0.5116812126278271, "learning_rate": 2.8077656524406534e-05, "loss": 0.3488, "step": 530 }, { "epoch": 2.150886075949367, "grad_norm": 0.4829690198238697, "learning_rate": 2.802570062143278e-05, "loss": 0.3352, "step": 531 }, { "epoch": 2.1549367088607596, "grad_norm": 0.5362654750358382, "learning_rate": 2.7973680080569555e-05, "loss": 0.3316, "step": 532 }, { "epoch": 2.1589873417721517, "grad_norm": 0.5481249836726396, "learning_rate": 2.792159532078314e-05, "loss": 0.321, "step": 533 }, { "epoch": 2.163037974683544, "grad_norm": 0.5885316541087774, "learning_rate": 2.7869446761557033e-05, "loss": 0.3086, "step": 534 }, { "epoch": 2.1670886075949367, "grad_norm": 0.5057498619205884, "learning_rate": 2.781723482288857e-05, "loss": 0.3367, "step": 535 }, { "epoch": 2.1711392405063292, "grad_norm": 0.548803887507212, "learning_rate": 2.7764959925285517e-05, "loss": 0.338, "step": 536 }, { "epoch": 2.1751898734177217, "grad_norm": 0.5378364221746507, "learning_rate": 2.771262248976272e-05, "loss": 0.3247, "step": 537 }, { "epoch": 2.179240506329114, "grad_norm": 0.5829079210792917, "learning_rate": 2.7660222937838677e-05, "loss": 0.3294, "step": 538 }, { "epoch": 2.1832911392405063, "grad_norm": 0.5410502541261837, "learning_rate": 2.7607761691532186e-05, "loss": 0.3592, "step": 539 }, { "epoch": 2.187341772151899, "grad_norm": 0.494388788341032, "learning_rate": 2.7555239173358916e-05, "loss": 0.3282, "step": 540 }, { "epoch": 2.191392405063291, "grad_norm": 0.5232114389248864, "learning_rate": 2.7502655806328e-05, "loss": 0.3286, "step": 541 }, { "epoch": 2.1954430379746834, "grad_norm": 0.4980708603439869, "learning_rate": 2.7450012013938648e-05, "loss": 0.3331, "step": 542 }, { "epoch": 2.199493670886076, "grad_norm": 0.4675622883463297, "learning_rate": 2.739730822017673e-05, "loss": 0.3207, "step": 543 }, { "epoch": 2.2035443037974685, "grad_norm": 0.5137258496807349, "learning_rate": 2.7344544849511355e-05, "loss": 0.3375, "step": 544 }, { "epoch": 2.207594936708861, "grad_norm": 0.5229202627459274, "learning_rate": 2.7291722326891456e-05, "loss": 0.343, "step": 545 }, { "epoch": 2.211645569620253, "grad_norm": 0.5075495325301088, "learning_rate": 2.723884107774236e-05, "loss": 0.3277, "step": 546 }, { "epoch": 2.2156962025316456, "grad_norm": 0.5337464898220666, "learning_rate": 2.718590152796239e-05, "loss": 0.3387, "step": 547 }, { "epoch": 2.219746835443038, "grad_norm": 0.4616393905877938, "learning_rate": 2.71329041039194e-05, "loss": 0.3225, "step": 548 }, { "epoch": 2.22379746835443, "grad_norm": 0.4906496421063016, "learning_rate": 2.7079849232447357e-05, "loss": 0.333, "step": 549 }, { "epoch": 2.2278481012658227, "grad_norm": 0.4805709246443842, "learning_rate": 2.7026737340842895e-05, "loss": 0.3213, "step": 550 }, { "epoch": 2.231898734177215, "grad_norm": 0.442525621404461, "learning_rate": 2.697356885686189e-05, "loss": 0.3471, "step": 551 }, { "epoch": 2.2359493670886077, "grad_norm": 0.47064477469616417, "learning_rate": 2.6920344208716014e-05, "loss": 0.3257, "step": 552 }, { "epoch": 2.24, "grad_norm": 0.5173899598836933, "learning_rate": 2.6867063825069252e-05, "loss": 0.3321, "step": 553 }, { "epoch": 2.2440506329113923, "grad_norm": 0.4905321825235531, "learning_rate": 2.6813728135034494e-05, "loss": 0.3522, "step": 554 }, { "epoch": 2.248101265822785, "grad_norm": 0.49789428332976315, "learning_rate": 2.6760337568170056e-05, "loss": 0.3506, "step": 555 }, { "epoch": 2.2521518987341773, "grad_norm": 0.4810359613256881, "learning_rate": 2.6706892554476226e-05, "loss": 0.3293, "step": 556 }, { "epoch": 2.2562025316455694, "grad_norm": 0.5024965695658149, "learning_rate": 2.6653393524391795e-05, "loss": 0.3359, "step": 557 }, { "epoch": 2.260253164556962, "grad_norm": 0.4981664469184139, "learning_rate": 2.6599840908790592e-05, "loss": 0.3309, "step": 558 }, { "epoch": 2.2643037974683544, "grad_norm": 0.4636538960209751, "learning_rate": 2.6546235138978028e-05, "loss": 0.3269, "step": 559 }, { "epoch": 2.268354430379747, "grad_norm": 0.4907193241389402, "learning_rate": 2.6492576646687597e-05, "loss": 0.328, "step": 560 }, { "epoch": 2.2724050632911394, "grad_norm": 0.48700776616131436, "learning_rate": 2.6438865864077425e-05, "loss": 0.3383, "step": 561 }, { "epoch": 2.2764556962025315, "grad_norm": 0.47319260426757803, "learning_rate": 2.6385103223726766e-05, "loss": 0.3411, "step": 562 }, { "epoch": 2.280506329113924, "grad_norm": 0.5073811005570288, "learning_rate": 2.6331289158632537e-05, "loss": 0.3381, "step": 563 }, { "epoch": 2.2845569620253166, "grad_norm": 0.5577672337784305, "learning_rate": 2.6277424102205817e-05, "loss": 0.3344, "step": 564 }, { "epoch": 2.2886075949367086, "grad_norm": 0.45882878634029567, "learning_rate": 2.6223508488268374e-05, "loss": 0.3284, "step": 565 }, { "epoch": 2.292658227848101, "grad_norm": 0.5531917168117474, "learning_rate": 2.6169542751049148e-05, "loss": 0.3303, "step": 566 }, { "epoch": 2.2967088607594937, "grad_norm": 0.4837308706238954, "learning_rate": 2.6115527325180754e-05, "loss": 0.3385, "step": 567 }, { "epoch": 2.300759493670886, "grad_norm": 0.500660594878238, "learning_rate": 2.606146264569603e-05, "loss": 0.3274, "step": 568 }, { "epoch": 2.3048101265822787, "grad_norm": 0.5125561847222024, "learning_rate": 2.6007349148024447e-05, "loss": 0.3511, "step": 569 }, { "epoch": 2.3088607594936708, "grad_norm": 0.4730649769967394, "learning_rate": 2.5953187267988694e-05, "loss": 0.3412, "step": 570 }, { "epoch": 2.3129113924050633, "grad_norm": 0.4917319132519689, "learning_rate": 2.5898977441801097e-05, "loss": 0.3336, "step": 571 }, { "epoch": 2.316962025316456, "grad_norm": 0.4594516689413567, "learning_rate": 2.584472010606015e-05, "loss": 0.3279, "step": 572 }, { "epoch": 2.321012658227848, "grad_norm": 0.4501024650047215, "learning_rate": 2.5790415697746976e-05, "loss": 0.3222, "step": 573 }, { "epoch": 2.3250632911392404, "grad_norm": 0.4630968348405583, "learning_rate": 2.5736064654221808e-05, "loss": 0.3286, "step": 574 }, { "epoch": 2.329113924050633, "grad_norm": 0.45603261221972907, "learning_rate": 2.568166741322048e-05, "loss": 0.3399, "step": 575 }, { "epoch": 2.3331645569620254, "grad_norm": 0.47732256924528527, "learning_rate": 2.56272244128509e-05, "loss": 0.3432, "step": 576 }, { "epoch": 2.337215189873418, "grad_norm": 0.49195441631135967, "learning_rate": 2.55727360915895e-05, "loss": 0.303, "step": 577 }, { "epoch": 2.34126582278481, "grad_norm": 0.495604372741258, "learning_rate": 2.5518202888277734e-05, "loss": 0.3316, "step": 578 }, { "epoch": 2.3453164556962025, "grad_norm": 0.49862243684588775, "learning_rate": 2.5463625242118523e-05, "loss": 0.3282, "step": 579 }, { "epoch": 2.349367088607595, "grad_norm": 0.501234539445182, "learning_rate": 2.5409003592672723e-05, "loss": 0.3391, "step": 580 }, { "epoch": 2.353417721518987, "grad_norm": 0.45732452882352415, "learning_rate": 2.535433837985559e-05, "loss": 0.3525, "step": 581 }, { "epoch": 2.3574683544303796, "grad_norm": 0.46388447306421327, "learning_rate": 2.529963004393324e-05, "loss": 0.3303, "step": 582 }, { "epoch": 2.361518987341772, "grad_norm": 0.45481137756693535, "learning_rate": 2.524487902551908e-05, "loss": 0.3435, "step": 583 }, { "epoch": 2.3655696202531646, "grad_norm": 0.4991201230077768, "learning_rate": 2.519008576557029e-05, "loss": 0.328, "step": 584 }, { "epoch": 2.369620253164557, "grad_norm": 0.4977386096991617, "learning_rate": 2.5135250705384254e-05, "loss": 0.3268, "step": 585 }, { "epoch": 2.3736708860759492, "grad_norm": 0.4409644613041826, "learning_rate": 2.5080374286595007e-05, "loss": 0.3437, "step": 586 }, { "epoch": 2.3777215189873417, "grad_norm": 0.519081183910752, "learning_rate": 2.5025456951169677e-05, "loss": 0.3477, "step": 587 }, { "epoch": 2.3817721518987343, "grad_norm": 0.5029166789210064, "learning_rate": 2.4970499141404942e-05, "loss": 0.3425, "step": 588 }, { "epoch": 2.3858227848101268, "grad_norm": 0.5086357624797734, "learning_rate": 2.491550129992345e-05, "loss": 0.3488, "step": 589 }, { "epoch": 2.389873417721519, "grad_norm": 0.4884439407438649, "learning_rate": 2.486046386967024e-05, "loss": 0.3346, "step": 590 }, { "epoch": 2.3939240506329114, "grad_norm": 0.5017034683970019, "learning_rate": 2.4805387293909214e-05, "loss": 0.373, "step": 591 }, { "epoch": 2.397974683544304, "grad_norm": 0.5273016364865629, "learning_rate": 2.4750272016219552e-05, "loss": 0.357, "step": 592 }, { "epoch": 2.4020253164556964, "grad_norm": 0.4533199013566723, "learning_rate": 2.4695118480492114e-05, "loss": 0.3278, "step": 593 }, { "epoch": 2.4060759493670885, "grad_norm": 0.4977401035653804, "learning_rate": 2.4639927130925898e-05, "loss": 0.3504, "step": 594 }, { "epoch": 2.410126582278481, "grad_norm": 0.4802832950050078, "learning_rate": 2.458469841202444e-05, "loss": 0.336, "step": 595 }, { "epoch": 2.4141772151898735, "grad_norm": 0.5226685551650897, "learning_rate": 2.452943276859226e-05, "loss": 0.3441, "step": 596 }, { "epoch": 2.418227848101266, "grad_norm": 0.49401564205583587, "learning_rate": 2.447413064573125e-05, "loss": 0.3323, "step": 597 }, { "epoch": 2.422278481012658, "grad_norm": 0.470041644692283, "learning_rate": 2.4418792488837095e-05, "loss": 0.3372, "step": 598 }, { "epoch": 2.4263291139240506, "grad_norm": 0.47307369139040345, "learning_rate": 2.4363418743595713e-05, "loss": 0.3281, "step": 599 }, { "epoch": 2.430379746835443, "grad_norm": 0.4768171571875576, "learning_rate": 2.430800985597963e-05, "loss": 0.3365, "step": 600 }, { "epoch": 2.4344303797468356, "grad_norm": 0.4737998415332814, "learning_rate": 2.4252566272244415e-05, "loss": 0.3428, "step": 601 }, { "epoch": 2.4384810126582277, "grad_norm": 0.4526577295982331, "learning_rate": 2.4197088438925063e-05, "loss": 0.3298, "step": 602 }, { "epoch": 2.44253164556962, "grad_norm": 0.47347654827642593, "learning_rate": 2.4141576802832417e-05, "loss": 0.3346, "step": 603 }, { "epoch": 2.4465822784810127, "grad_norm": 0.45341133967907365, "learning_rate": 2.408603181104957e-05, "loss": 0.3175, "step": 604 }, { "epoch": 2.4506329113924052, "grad_norm": 0.4592390188472575, "learning_rate": 2.4030453910928245e-05, "loss": 0.3497, "step": 605 }, { "epoch": 2.4546835443037973, "grad_norm": 0.48154244561356796, "learning_rate": 2.397484355008521e-05, "loss": 0.3402, "step": 606 }, { "epoch": 2.45873417721519, "grad_norm": 0.49487797373237147, "learning_rate": 2.3919201176398662e-05, "loss": 0.3225, "step": 607 }, { "epoch": 2.4627848101265823, "grad_norm": 0.4673059348331689, "learning_rate": 2.3863527238004633e-05, "loss": 0.3177, "step": 608 }, { "epoch": 2.466835443037975, "grad_norm": 0.5323321463210262, "learning_rate": 2.380782218329337e-05, "loss": 0.3345, "step": 609 }, { "epoch": 2.470886075949367, "grad_norm": 0.4458466989629582, "learning_rate": 2.3752086460905725e-05, "loss": 0.3178, "step": 610 }, { "epoch": 2.4749367088607594, "grad_norm": 0.47753296992239963, "learning_rate": 2.3696320519729544e-05, "loss": 0.3353, "step": 611 }, { "epoch": 2.478987341772152, "grad_norm": 0.4470026259730284, "learning_rate": 2.3640524808896045e-05, "loss": 0.329, "step": 612 }, { "epoch": 2.4830379746835445, "grad_norm": 0.4768902693456096, "learning_rate": 2.3584699777776222e-05, "loss": 0.3271, "step": 613 }, { "epoch": 2.4870886075949366, "grad_norm": 0.48001020914867776, "learning_rate": 2.3528845875977195e-05, "loss": 0.3241, "step": 614 }, { "epoch": 2.491139240506329, "grad_norm": 0.4332835777981813, "learning_rate": 2.3472963553338614e-05, "loss": 0.328, "step": 615 }, { "epoch": 2.4951898734177216, "grad_norm": 0.4585876252930197, "learning_rate": 2.341705325992901e-05, "loss": 0.3299, "step": 616 }, { "epoch": 2.499240506329114, "grad_norm": 0.47172179320187246, "learning_rate": 2.336111544604222e-05, "loss": 0.3163, "step": 617 }, { "epoch": 2.503291139240506, "grad_norm": 0.4848937931155089, "learning_rate": 2.33051505621937e-05, "loss": 0.3301, "step": 618 }, { "epoch": 2.5073417721518987, "grad_norm": 0.47010927861271706, "learning_rate": 2.324915905911693e-05, "loss": 0.3574, "step": 619 }, { "epoch": 2.511392405063291, "grad_norm": 0.45487008538089363, "learning_rate": 2.319314138775977e-05, "loss": 0.349, "step": 620 }, { "epoch": 2.5154430379746833, "grad_norm": 0.4569228865178084, "learning_rate": 2.3137097999280856e-05, "loss": 0.3384, "step": 621 }, { "epoch": 2.519493670886076, "grad_norm": 0.4711859397038869, "learning_rate": 2.308102934504593e-05, "loss": 0.3246, "step": 622 }, { "epoch": 2.5235443037974683, "grad_norm": 0.4668091607696809, "learning_rate": 2.3024935876624222e-05, "loss": 0.3292, "step": 623 }, { "epoch": 2.527594936708861, "grad_norm": 0.467097683146022, "learning_rate": 2.2968818045784813e-05, "loss": 0.3406, "step": 624 }, { "epoch": 2.5316455696202533, "grad_norm": 0.4381586882224799, "learning_rate": 2.2912676304493006e-05, "loss": 0.3341, "step": 625 }, { "epoch": 2.5356962025316454, "grad_norm": 0.45330717766382317, "learning_rate": 2.2856511104906668e-05, "loss": 0.3272, "step": 626 }, { "epoch": 2.539746835443038, "grad_norm": 0.4575903537150798, "learning_rate": 2.2800322899372586e-05, "loss": 0.3332, "step": 627 }, { "epoch": 2.5437974683544304, "grad_norm": 0.4381642809828461, "learning_rate": 2.2744112140422844e-05, "loss": 0.3194, "step": 628 }, { "epoch": 2.547848101265823, "grad_norm": 0.451383967086043, "learning_rate": 2.2687879280771177e-05, "loss": 0.3395, "step": 629 }, { "epoch": 2.5518987341772155, "grad_norm": 0.46375169299057795, "learning_rate": 2.26316247733093e-05, "loss": 0.3056, "step": 630 }, { "epoch": 2.5559493670886075, "grad_norm": 0.4850707196217635, "learning_rate": 2.257534907110328e-05, "loss": 0.321, "step": 631 }, { "epoch": 2.56, "grad_norm": 0.48014583383876397, "learning_rate": 2.2519052627389882e-05, "loss": 0.341, "step": 632 }, { "epoch": 2.5640506329113926, "grad_norm": 0.4478958173943492, "learning_rate": 2.246273589557294e-05, "loss": 0.3362, "step": 633 }, { "epoch": 2.5681012658227846, "grad_norm": 0.47163077405398035, "learning_rate": 2.240639932921966e-05, "loss": 0.3363, "step": 634 }, { "epoch": 2.572151898734177, "grad_norm": 0.5098832960643037, "learning_rate": 2.2350043382056995e-05, "loss": 0.3529, "step": 635 }, { "epoch": 2.5762025316455697, "grad_norm": 0.4602509053816043, "learning_rate": 2.2293668507968015e-05, "loss": 0.3253, "step": 636 }, { "epoch": 2.580253164556962, "grad_norm": 0.4617049469466833, "learning_rate": 2.2237275160988186e-05, "loss": 0.3087, "step": 637 }, { "epoch": 2.5843037974683547, "grad_norm": 0.564155741657289, "learning_rate": 2.2180863795301787e-05, "loss": 0.3481, "step": 638 }, { "epoch": 2.5883544303797468, "grad_norm": 0.5175267178503384, "learning_rate": 2.212443486523819e-05, "loss": 0.3204, "step": 639 }, { "epoch": 2.5924050632911393, "grad_norm": 0.5163436684446966, "learning_rate": 2.2067988825268243e-05, "loss": 0.3348, "step": 640 }, { "epoch": 2.596455696202532, "grad_norm": 0.5207497405365927, "learning_rate": 2.2011526130000596e-05, "loss": 0.3496, "step": 641 }, { "epoch": 2.600506329113924, "grad_norm": 0.44128438897851735, "learning_rate": 2.1955047234178038e-05, "loss": 0.331, "step": 642 }, { "epoch": 2.6045569620253164, "grad_norm": 0.5038892322374781, "learning_rate": 2.1898552592673825e-05, "loss": 0.3388, "step": 643 }, { "epoch": 2.608607594936709, "grad_norm": 0.5080872210025166, "learning_rate": 2.184204266048803e-05, "loss": 0.3288, "step": 644 }, { "epoch": 2.6126582278481014, "grad_norm": 0.4798242251438223, "learning_rate": 2.1785517892743887e-05, "loss": 0.337, "step": 645 }, { "epoch": 2.616708860759494, "grad_norm": 0.4742552958520806, "learning_rate": 2.17289787446841e-05, "loss": 0.364, "step": 646 }, { "epoch": 2.620759493670886, "grad_norm": 0.4760120675070021, "learning_rate": 2.1672425671667198e-05, "loss": 0.3477, "step": 647 }, { "epoch": 2.6248101265822785, "grad_norm": 0.47627870860983973, "learning_rate": 2.161585912916385e-05, "loss": 0.326, "step": 648 }, { "epoch": 2.628860759493671, "grad_norm": 0.46922653937189635, "learning_rate": 2.1559279572753214e-05, "loss": 0.3616, "step": 649 }, { "epoch": 2.632911392405063, "grad_norm": 0.46956929440600825, "learning_rate": 2.1502687458119268e-05, "loss": 0.3491, "step": 650 }, { "epoch": 2.6369620253164556, "grad_norm": 0.5193671180759981, "learning_rate": 2.1446083241047116e-05, "loss": 0.3348, "step": 651 }, { "epoch": 2.641012658227848, "grad_norm": 0.48513835639169406, "learning_rate": 2.1389467377419333e-05, "loss": 0.3319, "step": 652 }, { "epoch": 2.6450632911392407, "grad_norm": 0.4610468577016605, "learning_rate": 2.133284032321232e-05, "loss": 0.3121, "step": 653 }, { "epoch": 2.649113924050633, "grad_norm": 0.4626550084521656, "learning_rate": 2.1276202534492566e-05, "loss": 0.3371, "step": 654 }, { "epoch": 2.6531645569620252, "grad_norm": 0.4680966928515342, "learning_rate": 2.121955446741306e-05, "loss": 0.3266, "step": 655 }, { "epoch": 2.6572151898734178, "grad_norm": 0.4790944280695413, "learning_rate": 2.1162896578209517e-05, "loss": 0.3349, "step": 656 }, { "epoch": 2.6612658227848103, "grad_norm": 0.46837900208212613, "learning_rate": 2.1106229323196813e-05, "loss": 0.3416, "step": 657 }, { "epoch": 2.6653164556962023, "grad_norm": 0.47144127007078823, "learning_rate": 2.1049553158765214e-05, "loss": 0.323, "step": 658 }, { "epoch": 2.669367088607595, "grad_norm": 0.46789347065362125, "learning_rate": 2.0992868541376764e-05, "loss": 0.3498, "step": 659 }, { "epoch": 2.6734177215189874, "grad_norm": 0.47763021899461616, "learning_rate": 2.093617592756158e-05, "loss": 0.3291, "step": 660 }, { "epoch": 2.67746835443038, "grad_norm": 0.4713463123774971, "learning_rate": 2.0879475773914167e-05, "loss": 0.3359, "step": 661 }, { "epoch": 2.6815189873417724, "grad_norm": 0.4391235819243107, "learning_rate": 2.082276853708978e-05, "loss": 0.3715, "step": 662 }, { "epoch": 2.6855696202531645, "grad_norm": 0.4792488133502194, "learning_rate": 2.076605467380071e-05, "loss": 0.3224, "step": 663 }, { "epoch": 2.689620253164557, "grad_norm": 0.4495573284349851, "learning_rate": 2.0709334640812613e-05, "loss": 0.3276, "step": 664 }, { "epoch": 2.6936708860759495, "grad_norm": 0.471389623809447, "learning_rate": 2.0652608894940824e-05, "loss": 0.3213, "step": 665 }, { "epoch": 2.6977215189873416, "grad_norm": 0.46053243110360137, "learning_rate": 2.0595877893046722e-05, "loss": 0.2972, "step": 666 }, { "epoch": 2.701772151898734, "grad_norm": 0.46241431474608835, "learning_rate": 2.0539142092033985e-05, "loss": 0.3551, "step": 667 }, { "epoch": 2.7058227848101266, "grad_norm": 0.47218644469297594, "learning_rate": 2.048240194884496e-05, "loss": 0.3413, "step": 668 }, { "epoch": 2.709873417721519, "grad_norm": 0.44269397557471585, "learning_rate": 2.042565792045695e-05, "loss": 0.3558, "step": 669 }, { "epoch": 2.7139240506329116, "grad_norm": 0.4949060347747654, "learning_rate": 2.036891046387857e-05, "loss": 0.3614, "step": 670 }, { "epoch": 2.7179746835443037, "grad_norm": 0.4426005666187541, "learning_rate": 2.0312160036146036e-05, "loss": 0.3484, "step": 671 }, { "epoch": 2.7220253164556962, "grad_norm": 0.47907596763738924, "learning_rate": 2.025540709431948e-05, "loss": 0.3519, "step": 672 }, { "epoch": 2.7260759493670887, "grad_norm": 0.4877643249536718, "learning_rate": 2.0198652095479298e-05, "loss": 0.3347, "step": 673 }, { "epoch": 2.730126582278481, "grad_norm": 0.45255258521926395, "learning_rate": 2.014189549672245e-05, "loss": 0.3438, "step": 674 }, { "epoch": 2.7341772151898733, "grad_norm": 0.4928460653117533, "learning_rate": 2.0085137755158776e-05, "loss": 0.3229, "step": 675 }, { "epoch": 2.738227848101266, "grad_norm": 0.44713596929173827, "learning_rate": 2.0028379327907327e-05, "loss": 0.3403, "step": 676 }, { "epoch": 2.7422784810126584, "grad_norm": 0.44307197392357134, "learning_rate": 1.9971620672092676e-05, "loss": 0.3445, "step": 677 }, { "epoch": 2.746329113924051, "grad_norm": 0.4554638792759767, "learning_rate": 1.991486224484123e-05, "loss": 0.3281, "step": 678 }, { "epoch": 2.750379746835443, "grad_norm": 0.4427229686045872, "learning_rate": 1.985810450327756e-05, "loss": 0.3611, "step": 679 }, { "epoch": 2.7544303797468355, "grad_norm": 0.4842182541300778, "learning_rate": 1.9801347904520706e-05, "loss": 0.3402, "step": 680 }, { "epoch": 2.758481012658228, "grad_norm": 0.43671460471577894, "learning_rate": 1.974459290568053e-05, "loss": 0.3535, "step": 681 }, { "epoch": 2.76253164556962, "grad_norm": 0.4703272892975504, "learning_rate": 1.968783996385397e-05, "loss": 0.3325, "step": 682 }, { "epoch": 2.7665822784810126, "grad_norm": 0.430258586771915, "learning_rate": 1.963108953612143e-05, "loss": 0.3414, "step": 683 }, { "epoch": 2.770632911392405, "grad_norm": 0.46015795580735125, "learning_rate": 1.9574342079543056e-05, "loss": 0.3265, "step": 684 }, { "epoch": 2.7746835443037976, "grad_norm": 0.4628340091451206, "learning_rate": 1.9517598051155046e-05, "loss": 0.3282, "step": 685 }, { "epoch": 2.77873417721519, "grad_norm": 0.47235507798884707, "learning_rate": 1.9460857907966025e-05, "loss": 0.3191, "step": 686 }, { "epoch": 2.782784810126582, "grad_norm": 0.46730107501115126, "learning_rate": 1.9404122106953285e-05, "loss": 0.3546, "step": 687 }, { "epoch": 2.7868354430379747, "grad_norm": 0.4350317979316587, "learning_rate": 1.9347391105059176e-05, "loss": 0.3283, "step": 688 }, { "epoch": 2.790886075949367, "grad_norm": 0.4876479807415117, "learning_rate": 1.92906653591874e-05, "loss": 0.3317, "step": 689 }, { "epoch": 2.7949367088607593, "grad_norm": 0.4903315494066247, "learning_rate": 1.9233945326199295e-05, "loss": 0.351, "step": 690 }, { "epoch": 2.798987341772152, "grad_norm": 0.46299827208840766, "learning_rate": 1.917723146291022e-05, "loss": 0.3566, "step": 691 }, { "epoch": 2.8030379746835443, "grad_norm": 0.4726976865135495, "learning_rate": 1.912052422608584e-05, "loss": 0.3362, "step": 692 }, { "epoch": 2.807088607594937, "grad_norm": 0.4485454021261557, "learning_rate": 1.9063824072438428e-05, "loss": 0.3382, "step": 693 }, { "epoch": 2.8111392405063294, "grad_norm": 0.45875683514511045, "learning_rate": 1.9007131458623246e-05, "loss": 0.3264, "step": 694 }, { "epoch": 2.8151898734177214, "grad_norm": 0.4725476148714043, "learning_rate": 1.895044684123479e-05, "loss": 0.3699, "step": 695 }, { "epoch": 2.819240506329114, "grad_norm": 0.4628716541008037, "learning_rate": 1.8893770676803194e-05, "loss": 0.3172, "step": 696 }, { "epoch": 2.8232911392405065, "grad_norm": 0.4472507119814178, "learning_rate": 1.8837103421790486e-05, "loss": 0.3445, "step": 697 }, { "epoch": 2.8273417721518985, "grad_norm": 0.46046946768286834, "learning_rate": 1.8780445532586952e-05, "loss": 0.3545, "step": 698 }, { "epoch": 2.831392405063291, "grad_norm": 0.44464031194862247, "learning_rate": 1.872379746550743e-05, "loss": 0.3189, "step": 699 }, { "epoch": 2.8354430379746836, "grad_norm": 0.44802204601435724, "learning_rate": 1.866715967678769e-05, "loss": 0.3505, "step": 700 }, { "epoch": 2.839493670886076, "grad_norm": 0.4591963956176586, "learning_rate": 1.861053262258067e-05, "loss": 0.3271, "step": 701 }, { "epoch": 2.8435443037974686, "grad_norm": 0.4663180679098435, "learning_rate": 1.8553916758952897e-05, "loss": 0.3268, "step": 702 }, { "epoch": 2.8475949367088607, "grad_norm": 0.5021122293849087, "learning_rate": 1.8497312541880735e-05, "loss": 0.3499, "step": 703 }, { "epoch": 2.851645569620253, "grad_norm": 0.46037537884097296, "learning_rate": 1.8440720427246786e-05, "loss": 0.3401, "step": 704 }, { "epoch": 2.8556962025316457, "grad_norm": 0.49062530037946483, "learning_rate": 1.8384140870836157e-05, "loss": 0.3128, "step": 705 }, { "epoch": 2.8597468354430378, "grad_norm": 0.49547497799495654, "learning_rate": 1.8327574328332806e-05, "loss": 0.3088, "step": 706 }, { "epoch": 2.8637974683544303, "grad_norm": 0.45222541800781124, "learning_rate": 1.8271021255315906e-05, "loss": 0.3269, "step": 707 }, { "epoch": 2.867848101265823, "grad_norm": 0.46188378574108, "learning_rate": 1.8214482107256117e-05, "loss": 0.3558, "step": 708 }, { "epoch": 2.8718987341772153, "grad_norm": 0.45497084049122494, "learning_rate": 1.8157957339511968e-05, "loss": 0.3104, "step": 709 }, { "epoch": 2.875949367088608, "grad_norm": 0.4596038075922333, "learning_rate": 1.8101447407326182e-05, "loss": 0.3283, "step": 710 }, { "epoch": 2.88, "grad_norm": 0.44433420129476836, "learning_rate": 1.8044952765821966e-05, "loss": 0.3192, "step": 711 }, { "epoch": 2.8840506329113924, "grad_norm": 0.4727489195252207, "learning_rate": 1.7988473869999407e-05, "loss": 0.3372, "step": 712 }, { "epoch": 2.888101265822785, "grad_norm": 0.4875334028398875, "learning_rate": 1.7932011174731764e-05, "loss": 0.3481, "step": 713 }, { "epoch": 2.892151898734177, "grad_norm": 0.47743594002152534, "learning_rate": 1.7875565134761817e-05, "loss": 0.3275, "step": 714 }, { "epoch": 2.8962025316455695, "grad_norm": 0.4957571842482822, "learning_rate": 1.7819136204698226e-05, "loss": 0.3315, "step": 715 }, { "epoch": 2.900253164556962, "grad_norm": 0.49112436588791153, "learning_rate": 1.776272483901182e-05, "loss": 0.3434, "step": 716 }, { "epoch": 2.9043037974683545, "grad_norm": 0.4321302945422766, "learning_rate": 1.7706331492031995e-05, "loss": 0.3253, "step": 717 }, { "epoch": 2.908354430379747, "grad_norm": 0.4708383064984885, "learning_rate": 1.764995661794301e-05, "loss": 0.3052, "step": 718 }, { "epoch": 2.912405063291139, "grad_norm": 0.48762000843964587, "learning_rate": 1.759360067078035e-05, "loss": 0.3378, "step": 719 }, { "epoch": 2.9164556962025316, "grad_norm": 0.4247556431375652, "learning_rate": 1.7537264104427064e-05, "loss": 0.3584, "step": 720 }, { "epoch": 2.920506329113924, "grad_norm": 0.45957023837771205, "learning_rate": 1.748094737261012e-05, "loss": 0.3321, "step": 721 }, { "epoch": 2.9245569620253162, "grad_norm": 0.4626369437384553, "learning_rate": 1.7424650928896726e-05, "loss": 0.3302, "step": 722 }, { "epoch": 2.9286075949367087, "grad_norm": 0.47657488695223343, "learning_rate": 1.7368375226690712e-05, "loss": 0.3196, "step": 723 }, { "epoch": 2.9326582278481013, "grad_norm": 0.46658651814396723, "learning_rate": 1.731212071922883e-05, "loss": 0.325, "step": 724 }, { "epoch": 2.9367088607594938, "grad_norm": 0.4221670431136887, "learning_rate": 1.7255887859577156e-05, "loss": 0.3376, "step": 725 }, { "epoch": 2.9407594936708863, "grad_norm": 0.44446355035052276, "learning_rate": 1.7199677100627427e-05, "loss": 0.339, "step": 726 }, { "epoch": 2.9448101265822784, "grad_norm": 0.4653438796390546, "learning_rate": 1.7143488895093343e-05, "loss": 0.3371, "step": 727 }, { "epoch": 2.948860759493671, "grad_norm": 0.4596287519731211, "learning_rate": 1.7087323695506994e-05, "loss": 0.3514, "step": 728 }, { "epoch": 2.9529113924050634, "grad_norm": 0.4581715180993889, "learning_rate": 1.7031181954215194e-05, "loss": 0.2947, "step": 729 }, { "epoch": 2.9569620253164555, "grad_norm": 0.46940333027138215, "learning_rate": 1.6975064123375788e-05, "loss": 0.3358, "step": 730 }, { "epoch": 2.961012658227848, "grad_norm": 0.46679810798002613, "learning_rate": 1.6918970654954084e-05, "loss": 0.3237, "step": 731 }, { "epoch": 2.9650632911392405, "grad_norm": 0.4728745358845672, "learning_rate": 1.686290200071915e-05, "loss": 0.3222, "step": 732 }, { "epoch": 2.969113924050633, "grad_norm": 0.4403905339757148, "learning_rate": 1.6806858612240234e-05, "loss": 0.3279, "step": 733 }, { "epoch": 2.9731645569620255, "grad_norm": 0.4547183013183085, "learning_rate": 1.6750840940883078e-05, "loss": 0.3317, "step": 734 }, { "epoch": 2.9772151898734176, "grad_norm": 0.46689224293264836, "learning_rate": 1.6694849437806305e-05, "loss": 0.3221, "step": 735 }, { "epoch": 2.98126582278481, "grad_norm": 0.43340766241087364, "learning_rate": 1.663888455395778e-05, "loss": 0.3339, "step": 736 }, { "epoch": 2.9853164556962026, "grad_norm": 0.4599339381793361, "learning_rate": 1.6582946740070995e-05, "loss": 0.3255, "step": 737 }, { "epoch": 2.9893670886075947, "grad_norm": 0.43824703126289816, "learning_rate": 1.6527036446661396e-05, "loss": 0.3271, "step": 738 }, { "epoch": 2.993417721518987, "grad_norm": 0.46071830509624034, "learning_rate": 1.6471154124022818e-05, "loss": 0.3402, "step": 739 }, { "epoch": 2.9974683544303797, "grad_norm": 0.4725761918802243, "learning_rate": 1.6415300222223788e-05, "loss": 0.3178, "step": 740 }, { "epoch": 3.0015189873417722, "grad_norm": 0.44626920477966514, "learning_rate": 1.6359475191103958e-05, "loss": 0.2995, "step": 741 }, { "epoch": 3.0055696202531648, "grad_norm": 0.5634196114430154, "learning_rate": 1.6303679480270466e-05, "loss": 0.2389, "step": 742 }, { "epoch": 3.009620253164557, "grad_norm": 0.413672501914683, "learning_rate": 1.624791353909428e-05, "loss": 0.2051, "step": 743 }, { "epoch": 3.0136708860759494, "grad_norm": 0.5165660404771778, "learning_rate": 1.619217781670663e-05, "loss": 0.2356, "step": 744 }, { "epoch": 3.017721518987342, "grad_norm": 0.6541924681185921, "learning_rate": 1.6136472761995373e-05, "loss": 0.2098, "step": 745 }, { "epoch": 3.0217721518987344, "grad_norm": 0.5763283151224857, "learning_rate": 1.608079882360134e-05, "loss": 0.2297, "step": 746 }, { "epoch": 3.0258227848101265, "grad_norm": 0.43311800315003024, "learning_rate": 1.60251564499148e-05, "loss": 0.2315, "step": 747 }, { "epoch": 3.029873417721519, "grad_norm": 0.5400159436307796, "learning_rate": 1.596954608907176e-05, "loss": 0.2022, "step": 748 }, { "epoch": 3.0339240506329115, "grad_norm": 0.5140017964870089, "learning_rate": 1.591396818895043e-05, "loss": 0.2239, "step": 749 }, { "epoch": 3.037974683544304, "grad_norm": 0.41767033104660295, "learning_rate": 1.585842319716759e-05, "loss": 0.2196, "step": 750 }, { "epoch": 3.042025316455696, "grad_norm": 0.4156976417095046, "learning_rate": 1.5802911561074944e-05, "loss": 0.2202, "step": 751 }, { "epoch": 3.0460759493670886, "grad_norm": 0.45808360647532936, "learning_rate": 1.5747433727755595e-05, "loss": 0.1931, "step": 752 }, { "epoch": 3.050126582278481, "grad_norm": 0.46604406859963715, "learning_rate": 1.5691990144020376e-05, "loss": 0.2057, "step": 753 }, { "epoch": 3.0541772151898736, "grad_norm": 0.42925888370823617, "learning_rate": 1.5636581256404297e-05, "loss": 0.196, "step": 754 }, { "epoch": 3.0582278481012657, "grad_norm": 0.386373293619866, "learning_rate": 1.558120751116291e-05, "loss": 0.2043, "step": 755 }, { "epoch": 3.062278481012658, "grad_norm": 0.409654292375935, "learning_rate": 1.552586935426876e-05, "loss": 0.2187, "step": 756 }, { "epoch": 3.0663291139240507, "grad_norm": 0.4123075076219994, "learning_rate": 1.547056723140774e-05, "loss": 0.2167, "step": 757 }, { "epoch": 3.0703797468354432, "grad_norm": 0.40832978233195805, "learning_rate": 1.5415301587975565e-05, "loss": 0.2035, "step": 758 }, { "epoch": 3.0744303797468353, "grad_norm": 0.40024752800746916, "learning_rate": 1.536007286907411e-05, "loss": 0.2179, "step": 759 }, { "epoch": 3.078481012658228, "grad_norm": 0.3739434897068548, "learning_rate": 1.5304881519507896e-05, "loss": 0.1973, "step": 760 }, { "epoch": 3.0825316455696203, "grad_norm": 0.36794747191960875, "learning_rate": 1.5249727983780453e-05, "loss": 0.199, "step": 761 }, { "epoch": 3.086582278481013, "grad_norm": 0.39823169645031686, "learning_rate": 1.5194612706090786e-05, "loss": 0.2073, "step": 762 }, { "epoch": 3.090632911392405, "grad_norm": 0.3911540095932236, "learning_rate": 1.5139536130329771e-05, "loss": 0.1996, "step": 763 }, { "epoch": 3.0946835443037974, "grad_norm": 0.3737036476889381, "learning_rate": 1.508449870007656e-05, "loss": 0.1993, "step": 764 }, { "epoch": 3.09873417721519, "grad_norm": 0.3905427335308818, "learning_rate": 1.5029500858595056e-05, "loss": 0.205, "step": 765 }, { "epoch": 3.1027848101265825, "grad_norm": 0.36833992653563724, "learning_rate": 1.4974543048830328e-05, "loss": 0.2199, "step": 766 }, { "epoch": 3.1068354430379745, "grad_norm": 0.3768193558905288, "learning_rate": 1.4919625713405e-05, "loss": 0.2036, "step": 767 }, { "epoch": 3.110886075949367, "grad_norm": 0.39038401521879934, "learning_rate": 1.4864749294615756e-05, "loss": 0.2266, "step": 768 }, { "epoch": 3.1149367088607596, "grad_norm": 0.39445823212776293, "learning_rate": 1.4809914234429716e-05, "loss": 0.2012, "step": 769 }, { "epoch": 3.118987341772152, "grad_norm": 0.3572310489210772, "learning_rate": 1.4755120974480923e-05, "loss": 0.2097, "step": 770 }, { "epoch": 3.123037974683544, "grad_norm": 0.386369810500324, "learning_rate": 1.4700369956066771e-05, "loss": 0.2021, "step": 771 }, { "epoch": 3.1270886075949367, "grad_norm": 0.40258560040404706, "learning_rate": 1.4645661620144413e-05, "loss": 0.2056, "step": 772 }, { "epoch": 3.131139240506329, "grad_norm": 0.3819305003832404, "learning_rate": 1.4590996407327284e-05, "loss": 0.2095, "step": 773 }, { "epoch": 3.1351898734177217, "grad_norm": 0.36644415866979574, "learning_rate": 1.4536374757881487e-05, "loss": 0.2001, "step": 774 }, { "epoch": 3.1392405063291138, "grad_norm": 0.36676323419344126, "learning_rate": 1.4481797111722271e-05, "loss": 0.1925, "step": 775 }, { "epoch": 3.1432911392405063, "grad_norm": 0.3702296106997539, "learning_rate": 1.4427263908410507e-05, "loss": 0.2054, "step": 776 }, { "epoch": 3.147341772151899, "grad_norm": 0.3769054833604013, "learning_rate": 1.4372775587149108e-05, "loss": 0.2083, "step": 777 }, { "epoch": 3.1513924050632913, "grad_norm": 0.3711336203899813, "learning_rate": 1.4318332586779522e-05, "loss": 0.1777, "step": 778 }, { "epoch": 3.1554430379746834, "grad_norm": 0.3831216957754994, "learning_rate": 1.4263935345778202e-05, "loss": 0.1876, "step": 779 }, { "epoch": 3.159493670886076, "grad_norm": 0.38260411728954274, "learning_rate": 1.420958430225303e-05, "loss": 0.2072, "step": 780 }, { "epoch": 3.1635443037974684, "grad_norm": 0.3653184361953038, "learning_rate": 1.415527989393985e-05, "loss": 0.1836, "step": 781 }, { "epoch": 3.167594936708861, "grad_norm": 0.3701044425332199, "learning_rate": 1.410102255819891e-05, "loss": 0.2026, "step": 782 }, { "epoch": 3.171645569620253, "grad_norm": 0.378947264545475, "learning_rate": 1.404681273201131e-05, "loss": 0.2013, "step": 783 }, { "epoch": 3.1756962025316455, "grad_norm": 0.38296549536660907, "learning_rate": 1.399265085197556e-05, "loss": 0.218, "step": 784 }, { "epoch": 3.179746835443038, "grad_norm": 0.37427082868464695, "learning_rate": 1.393853735430398e-05, "loss": 0.1891, "step": 785 }, { "epoch": 3.1837974683544306, "grad_norm": 0.40024582305555906, "learning_rate": 1.3884472674819246e-05, "loss": 0.218, "step": 786 }, { "epoch": 3.1878481012658226, "grad_norm": 0.3764465172472838, "learning_rate": 1.3830457248950864e-05, "loss": 0.2113, "step": 787 }, { "epoch": 3.191898734177215, "grad_norm": 0.38323265201289697, "learning_rate": 1.377649151173163e-05, "loss": 0.2094, "step": 788 }, { "epoch": 3.1959493670886077, "grad_norm": 0.3727134329892552, "learning_rate": 1.3722575897794181e-05, "loss": 0.1875, "step": 789 }, { "epoch": 3.2, "grad_norm": 0.3913048014586674, "learning_rate": 1.3668710841367472e-05, "loss": 0.2043, "step": 790 }, { "epoch": 3.2040506329113922, "grad_norm": 0.3768418836463161, "learning_rate": 1.361489677627324e-05, "loss": 0.1896, "step": 791 }, { "epoch": 3.2081012658227848, "grad_norm": 0.37387442238867713, "learning_rate": 1.3561134135922585e-05, "loss": 0.2064, "step": 792 }, { "epoch": 3.2121518987341773, "grad_norm": 0.3753935930040192, "learning_rate": 1.350742335331241e-05, "loss": 0.2232, "step": 793 }, { "epoch": 3.21620253164557, "grad_norm": 0.39373926644079954, "learning_rate": 1.345376486102198e-05, "loss": 0.2419, "step": 794 }, { "epoch": 3.220253164556962, "grad_norm": 0.37191360614700136, "learning_rate": 1.3400159091209414e-05, "loss": 0.1983, "step": 795 }, { "epoch": 3.2243037974683544, "grad_norm": 0.3630769529158678, "learning_rate": 1.3346606475608216e-05, "loss": 0.2154, "step": 796 }, { "epoch": 3.228354430379747, "grad_norm": 0.3874298576313179, "learning_rate": 1.3293107445523781e-05, "loss": 0.1979, "step": 797 }, { "epoch": 3.2324050632911394, "grad_norm": 0.378043406136212, "learning_rate": 1.3239662431829949e-05, "loss": 0.2389, "step": 798 }, { "epoch": 3.2364556962025315, "grad_norm": 0.39801357170200763, "learning_rate": 1.3186271864965509e-05, "loss": 0.2047, "step": 799 }, { "epoch": 3.240506329113924, "grad_norm": 0.37284677383293896, "learning_rate": 1.3132936174930756e-05, "loss": 0.2034, "step": 800 }, { "epoch": 3.2445569620253165, "grad_norm": 0.3613055490380255, "learning_rate": 1.3079655791283995e-05, "loss": 0.2231, "step": 801 }, { "epoch": 3.248607594936709, "grad_norm": 0.3847424424391112, "learning_rate": 1.3026431143138108e-05, "loss": 0.2178, "step": 802 }, { "epoch": 3.252658227848101, "grad_norm": 0.3685848718477499, "learning_rate": 1.2973262659157114e-05, "loss": 0.1965, "step": 803 }, { "epoch": 3.2567088607594936, "grad_norm": 0.3576720012285304, "learning_rate": 1.2920150767552651e-05, "loss": 0.1943, "step": 804 }, { "epoch": 3.260759493670886, "grad_norm": 0.37194765876936536, "learning_rate": 1.2867095896080607e-05, "loss": 0.2055, "step": 805 }, { "epoch": 3.2648101265822786, "grad_norm": 0.36429490213016846, "learning_rate": 1.2814098472037612e-05, "loss": 0.2018, "step": 806 }, { "epoch": 3.2688607594936707, "grad_norm": 0.3686062595811564, "learning_rate": 1.276115892225764e-05, "loss": 0.2126, "step": 807 }, { "epoch": 3.2729113924050632, "grad_norm": 0.3549349670876417, "learning_rate": 1.2708277673108555e-05, "loss": 0.1982, "step": 808 }, { "epoch": 3.2769620253164558, "grad_norm": 0.3690166789851096, "learning_rate": 1.2655455150488649e-05, "loss": 0.1966, "step": 809 }, { "epoch": 3.2810126582278483, "grad_norm": 0.375542124592948, "learning_rate": 1.2602691779823272e-05, "loss": 0.1781, "step": 810 }, { "epoch": 3.2850632911392403, "grad_norm": 0.3805472861371583, "learning_rate": 1.2549987986061355e-05, "loss": 0.2311, "step": 811 }, { "epoch": 3.289113924050633, "grad_norm": 0.3746564082703525, "learning_rate": 1.2497344193672005e-05, "loss": 0.1971, "step": 812 }, { "epoch": 3.2931645569620254, "grad_norm": 0.3561546292178041, "learning_rate": 1.2444760826641092e-05, "loss": 0.211, "step": 813 }, { "epoch": 3.297215189873418, "grad_norm": 0.3553859648278934, "learning_rate": 1.2392238308467817e-05, "loss": 0.2128, "step": 814 }, { "epoch": 3.30126582278481, "grad_norm": 0.3525359740562525, "learning_rate": 1.2339777062161326e-05, "loss": 0.1974, "step": 815 }, { "epoch": 3.3053164556962025, "grad_norm": 0.3637069599345277, "learning_rate": 1.2287377510237293e-05, "loss": 0.2264, "step": 816 }, { "epoch": 3.309367088607595, "grad_norm": 0.37279396934010506, "learning_rate": 1.2235040074714488e-05, "loss": 0.1728, "step": 817 }, { "epoch": 3.3134177215189875, "grad_norm": 0.3939424799988102, "learning_rate": 1.2182765177111434e-05, "loss": 0.2067, "step": 818 }, { "epoch": 3.3174683544303796, "grad_norm": 0.3645782582803095, "learning_rate": 1.213055323844297e-05, "loss": 0.1953, "step": 819 }, { "epoch": 3.321518987341772, "grad_norm": 0.3690282695785605, "learning_rate": 1.2078404679216864e-05, "loss": 0.1853, "step": 820 }, { "epoch": 3.3255696202531646, "grad_norm": 0.35243765846392794, "learning_rate": 1.2026319919430458e-05, "loss": 0.1918, "step": 821 }, { "epoch": 3.329620253164557, "grad_norm": 0.3704607200179192, "learning_rate": 1.1974299378567227e-05, "loss": 0.2075, "step": 822 }, { "epoch": 3.333670886075949, "grad_norm": 0.3763573140286447, "learning_rate": 1.1922343475593462e-05, "loss": 0.2072, "step": 823 }, { "epoch": 3.3377215189873417, "grad_norm": 0.365061978672052, "learning_rate": 1.187045262895488e-05, "loss": 0.1911, "step": 824 }, { "epoch": 3.3417721518987342, "grad_norm": 0.3553036731893888, "learning_rate": 1.1818627256573203e-05, "loss": 0.1958, "step": 825 }, { "epoch": 3.3458227848101267, "grad_norm": 0.37021734973171105, "learning_rate": 1.1766867775842864e-05, "loss": 0.2056, "step": 826 }, { "epoch": 3.349873417721519, "grad_norm": 0.37522675922756177, "learning_rate": 1.1715174603627615e-05, "loss": 0.212, "step": 827 }, { "epoch": 3.3539240506329113, "grad_norm": 0.3697166779385055, "learning_rate": 1.1663548156257147e-05, "loss": 0.2234, "step": 828 }, { "epoch": 3.357974683544304, "grad_norm": 0.36660296723459324, "learning_rate": 1.161198884952377e-05, "loss": 0.2191, "step": 829 }, { "epoch": 3.3620253164556964, "grad_norm": 0.3582259930541447, "learning_rate": 1.1560497098679056e-05, "loss": 0.2031, "step": 830 }, { "epoch": 3.3660759493670884, "grad_norm": 0.371563297175724, "learning_rate": 1.1509073318430479e-05, "loss": 0.2126, "step": 831 }, { "epoch": 3.370126582278481, "grad_norm": 0.37457981791238115, "learning_rate": 1.1457717922938116e-05, "loss": 0.2231, "step": 832 }, { "epoch": 3.3741772151898735, "grad_norm": 0.3897650417550062, "learning_rate": 1.1406431325811233e-05, "loss": 0.2015, "step": 833 }, { "epoch": 3.378227848101266, "grad_norm": 0.366714928811111, "learning_rate": 1.135521394010506e-05, "loss": 0.2137, "step": 834 }, { "epoch": 3.382278481012658, "grad_norm": 0.349068453915876, "learning_rate": 1.1304066178317367e-05, "loss": 0.2099, "step": 835 }, { "epoch": 3.3863291139240506, "grad_norm": 0.3654305083879714, "learning_rate": 1.1252988452385199e-05, "loss": 0.1845, "step": 836 }, { "epoch": 3.390379746835443, "grad_norm": 0.3715664628116246, "learning_rate": 1.1201981173681536e-05, "loss": 0.2074, "step": 837 }, { "epoch": 3.3944303797468356, "grad_norm": 0.34516871391214693, "learning_rate": 1.1151044753011991e-05, "loss": 0.2091, "step": 838 }, { "epoch": 3.3984810126582277, "grad_norm": 0.35041124201035007, "learning_rate": 1.1100179600611491e-05, "loss": 0.1899, "step": 839 }, { "epoch": 3.40253164556962, "grad_norm": 0.3633547688364299, "learning_rate": 1.1049386126140985e-05, "loss": 0.2051, "step": 840 }, { "epoch": 3.4065822784810127, "grad_norm": 0.36993197358514, "learning_rate": 1.0998664738684128e-05, "loss": 0.1877, "step": 841 }, { "epoch": 3.410632911392405, "grad_norm": 0.35922218027386127, "learning_rate": 1.0948015846744e-05, "loss": 0.2229, "step": 842 }, { "epoch": 3.4146835443037973, "grad_norm": 0.34886903367261407, "learning_rate": 1.0897439858239832e-05, "loss": 0.2035, "step": 843 }, { "epoch": 3.41873417721519, "grad_norm": 0.3550843352799001, "learning_rate": 1.0846937180503652e-05, "loss": 0.2154, "step": 844 }, { "epoch": 3.4227848101265823, "grad_norm": 0.3668469803234125, "learning_rate": 1.0796508220277117e-05, "loss": 0.1844, "step": 845 }, { "epoch": 3.426835443037975, "grad_norm": 0.3582221090358602, "learning_rate": 1.0746153383708107e-05, "loss": 0.2122, "step": 846 }, { "epoch": 3.430886075949367, "grad_norm": 0.3543123007379759, "learning_rate": 1.0695873076347579e-05, "loss": 0.1994, "step": 847 }, { "epoch": 3.4349367088607594, "grad_norm": 0.37102262278472503, "learning_rate": 1.0645667703146205e-05, "loss": 0.2043, "step": 848 }, { "epoch": 3.438987341772152, "grad_norm": 0.3760324713673791, "learning_rate": 1.0595537668451161e-05, "loss": 0.1958, "step": 849 }, { "epoch": 3.4430379746835444, "grad_norm": 0.3684987368528513, "learning_rate": 1.0545483376002854e-05, "loss": 0.2281, "step": 850 }, { "epoch": 3.4470886075949365, "grad_norm": 0.3763153596019779, "learning_rate": 1.0495505228931676e-05, "loss": 0.219, "step": 851 }, { "epoch": 3.451139240506329, "grad_norm": 0.36906909249958747, "learning_rate": 1.044560362975474e-05, "loss": 0.1944, "step": 852 }, { "epoch": 3.4551898734177215, "grad_norm": 0.37644005667657443, "learning_rate": 1.0395778980372695e-05, "loss": 0.2062, "step": 853 }, { "epoch": 3.459240506329114, "grad_norm": 0.3680202467185528, "learning_rate": 1.0346031682066381e-05, "loss": 0.2399, "step": 854 }, { "epoch": 3.463291139240506, "grad_norm": 0.357953569417173, "learning_rate": 1.0296362135493724e-05, "loss": 0.1977, "step": 855 }, { "epoch": 3.4673417721518986, "grad_norm": 0.35788599805943494, "learning_rate": 1.0246770740686422e-05, "loss": 0.2076, "step": 856 }, { "epoch": 3.471392405063291, "grad_norm": 0.3641280404250653, "learning_rate": 1.0197257897046743e-05, "loss": 0.2097, "step": 857 }, { "epoch": 3.4754430379746837, "grad_norm": 0.35869665983168114, "learning_rate": 1.014782400334433e-05, "loss": 0.2131, "step": 858 }, { "epoch": 3.479493670886076, "grad_norm": 0.3560164908843638, "learning_rate": 1.009846945771296e-05, "loss": 0.2179, "step": 859 }, { "epoch": 3.4835443037974683, "grad_norm": 0.3643155325805106, "learning_rate": 1.0049194657647363e-05, "loss": 0.2109, "step": 860 }, { "epoch": 3.487594936708861, "grad_norm": 0.3865269583772945, "learning_rate": 1.0000000000000006e-05, "loss": 0.1935, "step": 861 }, { "epoch": 3.4916455696202533, "grad_norm": 0.37801622773212495, "learning_rate": 9.950885880977891e-06, "loss": 0.1953, "step": 862 }, { "epoch": 3.4956962025316454, "grad_norm": 0.3561259078976693, "learning_rate": 9.901852696139382e-06, "loss": 0.2033, "step": 863 }, { "epoch": 3.499746835443038, "grad_norm": 0.39549248787452157, "learning_rate": 9.852900840391027e-06, "loss": 0.1915, "step": 864 }, { "epoch": 3.5037974683544304, "grad_norm": 0.3661558621355308, "learning_rate": 9.804030707984313e-06, "loss": 0.222, "step": 865 }, { "epoch": 3.507848101265823, "grad_norm": 0.3773383051373528, "learning_rate": 9.755242692512599e-06, "loss": 0.2107, "step": 866 }, { "epoch": 3.5118987341772154, "grad_norm": 0.38365435231830997, "learning_rate": 9.70653718690782e-06, "loss": 0.1959, "step": 867 }, { "epoch": 3.5159493670886075, "grad_norm": 0.36725092100372914, "learning_rate": 9.657914583437454e-06, "loss": 0.2141, "step": 868 }, { "epoch": 3.52, "grad_norm": 0.35638642149672334, "learning_rate": 9.609375273701246e-06, "loss": 0.2103, "step": 869 }, { "epoch": 3.5240506329113925, "grad_norm": 0.34536814833862267, "learning_rate": 9.560919648628133e-06, "loss": 0.213, "step": 870 }, { "epoch": 3.5281012658227846, "grad_norm": 0.3617098601416293, "learning_rate": 9.512548098473047e-06, "loss": 0.2164, "step": 871 }, { "epoch": 3.532151898734177, "grad_norm": 0.3539840754081385, "learning_rate": 9.464261012813825e-06, "loss": 0.1999, "step": 872 }, { "epoch": 3.5362025316455696, "grad_norm": 0.35222536972308993, "learning_rate": 9.416058780547987e-06, "loss": 0.2278, "step": 873 }, { "epoch": 3.540253164556962, "grad_norm": 0.3642077141859908, "learning_rate": 9.367941789889714e-06, "loss": 0.2015, "step": 874 }, { "epoch": 3.5443037974683547, "grad_norm": 0.36587627604517836, "learning_rate": 9.319910428366607e-06, "loss": 0.2122, "step": 875 }, { "epoch": 3.5483544303797467, "grad_norm": 0.36285897312504256, "learning_rate": 9.271965082816667e-06, "loss": 0.1996, "step": 876 }, { "epoch": 3.5524050632911393, "grad_norm": 0.3580447383210128, "learning_rate": 9.224106139385111e-06, "loss": 0.1964, "step": 877 }, { "epoch": 3.5564556962025318, "grad_norm": 0.3681509413768268, "learning_rate": 9.176333983521291e-06, "loss": 0.198, "step": 878 }, { "epoch": 3.560506329113924, "grad_norm": 0.36192735918853036, "learning_rate": 9.12864899997558e-06, "loss": 0.2086, "step": 879 }, { "epoch": 3.5645569620253164, "grad_norm": 0.35009671321439106, "learning_rate": 9.08105157279628e-06, "loss": 0.2221, "step": 880 }, { "epoch": 3.568607594936709, "grad_norm": 0.38081951311660023, "learning_rate": 9.03354208532653e-06, "loss": 0.1852, "step": 881 }, { "epoch": 3.5726582278481014, "grad_norm": 0.36188585884813906, "learning_rate": 8.986120920201205e-06, "loss": 0.2131, "step": 882 }, { "epoch": 3.576708860759494, "grad_norm": 0.36615326469011367, "learning_rate": 8.938788459343852e-06, "loss": 0.2016, "step": 883 }, { "epoch": 3.580759493670886, "grad_norm": 0.34691148217330653, "learning_rate": 8.8915450839636e-06, "loss": 0.1883, "step": 884 }, { "epoch": 3.5848101265822785, "grad_norm": 0.36982366063561745, "learning_rate": 8.844391174552116e-06, "loss": 0.1911, "step": 885 }, { "epoch": 3.588860759493671, "grad_norm": 0.3660872290199626, "learning_rate": 8.797327110880479e-06, "loss": 0.2267, "step": 886 }, { "epoch": 3.592911392405063, "grad_norm": 0.3547281627540221, "learning_rate": 8.750353271996206e-06, "loss": 0.2071, "step": 887 }, { "epoch": 3.5969620253164556, "grad_norm": 0.3678478967001335, "learning_rate": 8.703470036220132e-06, "loss": 0.2184, "step": 888 }, { "epoch": 3.601012658227848, "grad_norm": 0.35977690981757543, "learning_rate": 8.656677781143394e-06, "loss": 0.2074, "step": 889 }, { "epoch": 3.6050632911392406, "grad_norm": 0.36562253048402, "learning_rate": 8.609976883624377e-06, "loss": 0.1973, "step": 890 }, { "epoch": 3.609113924050633, "grad_norm": 0.356243321898863, "learning_rate": 8.563367719785698e-06, "loss": 0.2114, "step": 891 }, { "epoch": 3.613164556962025, "grad_norm": 0.35464010978441435, "learning_rate": 8.516850665011138e-06, "loss": 0.1967, "step": 892 }, { "epoch": 3.6172151898734177, "grad_norm": 0.3552172208133949, "learning_rate": 8.47042609394269e-06, "loss": 0.2045, "step": 893 }, { "epoch": 3.6212658227848102, "grad_norm": 0.3503567804592338, "learning_rate": 8.424094380477432e-06, "loss": 0.2088, "step": 894 }, { "epoch": 3.6253164556962023, "grad_norm": 0.3485222135742759, "learning_rate": 8.37785589776465e-06, "loss": 0.2218, "step": 895 }, { "epoch": 3.629367088607595, "grad_norm": 0.3503366024709579, "learning_rate": 8.331711018202694e-06, "loss": 0.1812, "step": 896 }, { "epoch": 3.6334177215189873, "grad_norm": 0.3570397419712602, "learning_rate": 8.285660113436104e-06, "loss": 0.2183, "step": 897 }, { "epoch": 3.63746835443038, "grad_norm": 0.34816759067957515, "learning_rate": 8.239703554352527e-06, "loss": 0.2215, "step": 898 }, { "epoch": 3.6415189873417724, "grad_norm": 0.33841854386281517, "learning_rate": 8.193841711079775e-06, "loss": 0.2214, "step": 899 }, { "epoch": 3.6455696202531644, "grad_norm": 0.3469257441774425, "learning_rate": 8.148074952982828e-06, "loss": 0.2126, "step": 900 }, { "epoch": 3.649620253164557, "grad_norm": 0.36727261553978197, "learning_rate": 8.102403648660859e-06, "loss": 0.19, "step": 901 }, { "epoch": 3.6536708860759495, "grad_norm": 0.33593904263337815, "learning_rate": 8.056828165944282e-06, "loss": 0.218, "step": 902 }, { "epoch": 3.6577215189873415, "grad_norm": 0.35303653051009826, "learning_rate": 8.011348871891762e-06, "loss": 0.2054, "step": 903 }, { "epoch": 3.661772151898734, "grad_norm": 0.3492385855536161, "learning_rate": 7.965966132787287e-06, "loss": 0.2191, "step": 904 }, { "epoch": 3.6658227848101266, "grad_norm": 0.37157353956595784, "learning_rate": 7.920680314137189e-06, "loss": 0.2069, "step": 905 }, { "epoch": 3.669873417721519, "grad_norm": 0.369136859477543, "learning_rate": 7.875491780667246e-06, "loss": 0.2131, "step": 906 }, { "epoch": 3.6739240506329116, "grad_norm": 0.35691709513411174, "learning_rate": 7.830400896319667e-06, "loss": 0.1925, "step": 907 }, { "epoch": 3.6779746835443037, "grad_norm": 0.35597486732653283, "learning_rate": 7.785408024250259e-06, "loss": 0.1799, "step": 908 }, { "epoch": 3.682025316455696, "grad_norm": 0.34994776684339124, "learning_rate": 7.74051352682542e-06, "loss": 0.2222, "step": 909 }, { "epoch": 3.6860759493670887, "grad_norm": 0.371655331513241, "learning_rate": 7.695717765619257e-06, "loss": 0.2162, "step": 910 }, { "epoch": 3.690126582278481, "grad_norm": 0.3520611132989271, "learning_rate": 7.651021101410673e-06, "loss": 0.1911, "step": 911 }, { "epoch": 3.6941772151898733, "grad_norm": 0.3612428308343892, "learning_rate": 7.606423894180464e-06, "loss": 0.2036, "step": 912 }, { "epoch": 3.698227848101266, "grad_norm": 0.3512409010263383, "learning_rate": 7.56192650310839e-06, "loss": 0.2241, "step": 913 }, { "epoch": 3.7022784810126583, "grad_norm": 0.37166768107506, "learning_rate": 7.517529286570349e-06, "loss": 0.1825, "step": 914 }, { "epoch": 3.706329113924051, "grad_norm": 0.3522613841169301, "learning_rate": 7.473232602135387e-06, "loss": 0.2183, "step": 915 }, { "epoch": 3.710379746835443, "grad_norm": 0.3512681966062517, "learning_rate": 7.429036806562935e-06, "loss": 0.2122, "step": 916 }, { "epoch": 3.7144303797468354, "grad_norm": 0.3467955527427946, "learning_rate": 7.3849422557998455e-06, "loss": 0.2247, "step": 917 }, { "epoch": 3.718481012658228, "grad_norm": 0.3646332359083175, "learning_rate": 7.340949304977567e-06, "loss": 0.2114, "step": 918 }, { "epoch": 3.72253164556962, "grad_norm": 0.36006409709952086, "learning_rate": 7.297058308409282e-06, "loss": 0.2115, "step": 919 }, { "epoch": 3.7265822784810125, "grad_norm": 0.3542167862146001, "learning_rate": 7.25326961958704e-06, "loss": 0.205, "step": 920 }, { "epoch": 3.730632911392405, "grad_norm": 0.3623723774519372, "learning_rate": 7.209583591178921e-06, "loss": 0.2079, "step": 921 }, { "epoch": 3.7346835443037976, "grad_norm": 0.35026982179437643, "learning_rate": 7.1660005750261925e-06, "loss": 0.1973, "step": 922 }, { "epoch": 3.73873417721519, "grad_norm": 0.35262523582315863, "learning_rate": 7.1225209221404765e-06, "loss": 0.2006, "step": 923 }, { "epoch": 3.742784810126582, "grad_norm": 0.35620954958730655, "learning_rate": 7.079144982700909e-06, "loss": 0.1895, "step": 924 }, { "epoch": 3.7468354430379747, "grad_norm": 0.34755989175722557, "learning_rate": 7.0358731060513695e-06, "loss": 0.2129, "step": 925 }, { "epoch": 3.750886075949367, "grad_norm": 0.3524271709660351, "learning_rate": 6.99270564069757e-06, "loss": 0.2285, "step": 926 }, { "epoch": 3.7549367088607593, "grad_norm": 0.34356773883771274, "learning_rate": 6.949642934304375e-06, "loss": 0.2174, "step": 927 }, { "epoch": 3.7589873417721518, "grad_norm": 0.34804006734133364, "learning_rate": 6.906685333692871e-06, "loss": 0.199, "step": 928 }, { "epoch": 3.7630379746835443, "grad_norm": 0.34912625646772844, "learning_rate": 6.86383318483769e-06, "loss": 0.2232, "step": 929 }, { "epoch": 3.767088607594937, "grad_norm": 0.3603674632158573, "learning_rate": 6.821086832864139e-06, "loss": 0.1899, "step": 930 }, { "epoch": 3.7711392405063293, "grad_norm": 0.3433799623498648, "learning_rate": 6.77844662204546e-06, "loss": 0.1896, "step": 931 }, { "epoch": 3.7751898734177214, "grad_norm": 0.3452083890364528, "learning_rate": 6.7359128958000455e-06, "loss": 0.2137, "step": 932 }, { "epoch": 3.779240506329114, "grad_norm": 0.34713999487524716, "learning_rate": 6.693485996688695e-06, "loss": 0.2002, "step": 933 }, { "epoch": 3.7832911392405064, "grad_norm": 0.3598715008793953, "learning_rate": 6.651166266411801e-06, "loss": 0.1932, "step": 934 }, { "epoch": 3.7873417721518985, "grad_norm": 0.34485314990491306, "learning_rate": 6.6089540458066725e-06, "loss": 0.201, "step": 935 }, { "epoch": 3.791392405063291, "grad_norm": 0.34267207401963873, "learning_rate": 6.566849674844711e-06, "loss": 0.1888, "step": 936 }, { "epoch": 3.7954430379746835, "grad_norm": 0.34952973674395754, "learning_rate": 6.524853492628747e-06, "loss": 0.1945, "step": 937 }, { "epoch": 3.799493670886076, "grad_norm": 0.3412471456559445, "learning_rate": 6.4829658373902536e-06, "loss": 0.1834, "step": 938 }, { "epoch": 3.8035443037974686, "grad_norm": 0.3434950298928902, "learning_rate": 6.441187046486648e-06, "loss": 0.2115, "step": 939 }, { "epoch": 3.8075949367088606, "grad_norm": 0.35700864693640794, "learning_rate": 6.399517456398567e-06, "loss": 0.1948, "step": 940 }, { "epoch": 3.811645569620253, "grad_norm": 0.3675102576015912, "learning_rate": 6.357957402727164e-06, "loss": 0.2096, "step": 941 }, { "epoch": 3.8156962025316457, "grad_norm": 0.3666074567312601, "learning_rate": 6.316507220191395e-06, "loss": 0.2062, "step": 942 }, { "epoch": 3.8197468354430377, "grad_norm": 0.34597456670043436, "learning_rate": 6.275167242625331e-06, "loss": 0.1981, "step": 943 }, { "epoch": 3.8237974683544302, "grad_norm": 0.3609033260512613, "learning_rate": 6.233937802975471e-06, "loss": 0.1884, "step": 944 }, { "epoch": 3.8278481012658228, "grad_norm": 0.34704103728636454, "learning_rate": 6.192819233298046e-06, "loss": 0.2268, "step": 945 }, { "epoch": 3.8318987341772153, "grad_norm": 0.3424809299187772, "learning_rate": 6.151811864756383e-06, "loss": 0.1951, "step": 946 }, { "epoch": 3.835949367088608, "grad_norm": 0.3357130938672213, "learning_rate": 6.1109160276181655e-06, "loss": 0.2137, "step": 947 }, { "epoch": 3.84, "grad_norm": 0.34661446396083023, "learning_rate": 6.070132051252868e-06, "loss": 0.1966, "step": 948 }, { "epoch": 3.8440506329113924, "grad_norm": 0.3479902171496827, "learning_rate": 6.0294602641290034e-06, "loss": 0.1925, "step": 949 }, { "epoch": 3.848101265822785, "grad_norm": 0.34447081619257297, "learning_rate": 5.988900993811575e-06, "loss": 0.2004, "step": 950 }, { "epoch": 3.852151898734177, "grad_norm": 0.35001049647280963, "learning_rate": 5.948454566959363e-06, "loss": 0.2222, "step": 951 }, { "epoch": 3.8562025316455695, "grad_norm": 0.3495393247538705, "learning_rate": 5.908121309322328e-06, "loss": 0.1846, "step": 952 }, { "epoch": 3.860253164556962, "grad_norm": 0.33065996258687086, "learning_rate": 5.867901545738976e-06, "loss": 0.214, "step": 953 }, { "epoch": 3.8643037974683545, "grad_norm": 0.36112551493895434, "learning_rate": 5.827795600133774e-06, "loss": 0.2235, "step": 954 }, { "epoch": 3.868354430379747, "grad_norm": 0.3562484462370998, "learning_rate": 5.787803795514466e-06, "loss": 0.1829, "step": 955 }, { "epoch": 3.872405063291139, "grad_norm": 0.35167503353168666, "learning_rate": 5.747926453969576e-06, "loss": 0.1826, "step": 956 }, { "epoch": 3.8764556962025316, "grad_norm": 0.34332729993034816, "learning_rate": 5.708163896665708e-06, "loss": 0.2137, "step": 957 }, { "epoch": 3.880506329113924, "grad_norm": 0.33265325360716896, "learning_rate": 5.668516443845047e-06, "loss": 0.1955, "step": 958 }, { "epoch": 3.884556962025316, "grad_norm": 0.35399050377258734, "learning_rate": 5.6289844148227225e-06, "loss": 0.2004, "step": 959 }, { "epoch": 3.8886075949367087, "grad_norm": 0.3412614673814382, "learning_rate": 5.5895681279842615e-06, "loss": 0.2134, "step": 960 }, { "epoch": 3.8926582278481012, "grad_norm": 0.3640433894052695, "learning_rate": 5.550267900783019e-06, "loss": 0.2041, "step": 961 }, { "epoch": 3.8967088607594937, "grad_norm": 0.3453770591372446, "learning_rate": 5.511084049737623e-06, "loss": 0.2098, "step": 962 }, { "epoch": 3.9007594936708863, "grad_norm": 0.34910049727075, "learning_rate": 5.4720168904294215e-06, "loss": 0.2031, "step": 963 }, { "epoch": 3.9048101265822783, "grad_norm": 0.3554662236224141, "learning_rate": 5.433066737499948e-06, "loss": 0.2334, "step": 964 }, { "epoch": 3.908860759493671, "grad_norm": 0.35718613737061566, "learning_rate": 5.394233904648376e-06, "loss": 0.2119, "step": 965 }, { "epoch": 3.9129113924050634, "grad_norm": 0.35959569583525475, "learning_rate": 5.355518704628997e-06, "loss": 0.2103, "step": 966 }, { "epoch": 3.9169620253164554, "grad_norm": 0.3567478449771476, "learning_rate": 5.316921449248731e-06, "loss": 0.19, "step": 967 }, { "epoch": 3.921012658227848, "grad_norm": 0.3446005742640722, "learning_rate": 5.278442449364538e-06, "loss": 0.1868, "step": 968 }, { "epoch": 3.9250632911392405, "grad_norm": 0.3374159396927407, "learning_rate": 5.240082014881016e-06, "loss": 0.1816, "step": 969 }, { "epoch": 3.929113924050633, "grad_norm": 0.37860865228244656, "learning_rate": 5.201840454747822e-06, "loss": 0.2009, "step": 970 }, { "epoch": 3.9331645569620255, "grad_norm": 0.365780305449999, "learning_rate": 5.163718076957223e-06, "loss": 0.2229, "step": 971 }, { "epoch": 3.9372151898734176, "grad_norm": 0.3556910783720755, "learning_rate": 5.125715188541609e-06, "loss": 0.2068, "step": 972 }, { "epoch": 3.94126582278481, "grad_norm": 0.3412237422851564, "learning_rate": 5.087832095571021e-06, "loss": 0.2023, "step": 973 }, { "epoch": 3.9453164556962026, "grad_norm": 0.34115596425384626, "learning_rate": 5.0500691031506766e-06, "loss": 0.1797, "step": 974 }, { "epoch": 3.9493670886075947, "grad_norm": 0.3518889034929599, "learning_rate": 5.01242651541854e-06, "loss": 0.1917, "step": 975 }, { "epoch": 3.953417721518987, "grad_norm": 0.3469902849024469, "learning_rate": 4.974904635542815e-06, "loss": 0.2128, "step": 976 }, { "epoch": 3.9574683544303797, "grad_norm": 0.33310515795353457, "learning_rate": 4.937503765719582e-06, "loss": 0.2157, "step": 977 }, { "epoch": 3.961518987341772, "grad_norm": 0.3467702020182612, "learning_rate": 4.900224207170299e-06, "loss": 0.2039, "step": 978 }, { "epoch": 3.9655696202531647, "grad_norm": 0.34602217745402725, "learning_rate": 4.8630662601394065e-06, "loss": 0.2231, "step": 979 }, { "epoch": 3.969620253164557, "grad_norm": 0.35361436599198204, "learning_rate": 4.8260302238918995e-06, "loss": 0.187, "step": 980 }, { "epoch": 3.9736708860759493, "grad_norm": 0.3618185991524441, "learning_rate": 4.789116396710924e-06, "loss": 0.2054, "step": 981 }, { "epoch": 3.977721518987342, "grad_norm": 0.357411021187434, "learning_rate": 4.752325075895368e-06, "loss": 0.2076, "step": 982 }, { "epoch": 3.981772151898734, "grad_norm": 0.34665768473875946, "learning_rate": 4.715656557757473e-06, "loss": 0.1968, "step": 983 }, { "epoch": 3.9858227848101264, "grad_norm": 0.3417916767338192, "learning_rate": 4.679111137620442e-06, "loss": 0.1956, "step": 984 }, { "epoch": 3.989873417721519, "grad_norm": 0.3224550061764723, "learning_rate": 4.6426891098160585e-06, "loss": 0.2158, "step": 985 }, { "epoch": 3.9939240506329114, "grad_norm": 0.33279189801387604, "learning_rate": 4.6063907676823474e-06, "loss": 0.2191, "step": 986 }, { "epoch": 3.997974683544304, "grad_norm": 0.35490920669064135, "learning_rate": 4.570216403561141e-06, "loss": 0.2005, "step": 987 }, { "epoch": 4.002025316455696, "grad_norm": 0.3649232338615962, "learning_rate": 4.534166308795815e-06, "loss": 0.1713, "step": 988 }, { "epoch": 4.006075949367089, "grad_norm": 0.4166008432771379, "learning_rate": 4.498240773728859e-06, "loss": 0.1514, "step": 989 }, { "epoch": 4.010126582278481, "grad_norm": 0.37844397275447245, "learning_rate": 4.462440087699609e-06, "loss": 0.1417, "step": 990 }, { "epoch": 4.014177215189873, "grad_norm": 0.2881510086982815, "learning_rate": 4.426764539041861e-06, "loss": 0.1715, "step": 991 }, { "epoch": 4.018227848101266, "grad_norm": 0.26335512166022956, "learning_rate": 4.391214415081582e-06, "loss": 0.1164, "step": 992 }, { "epoch": 4.022278481012658, "grad_norm": 0.35540022542317495, "learning_rate": 4.355790002134579e-06, "loss": 0.1564, "step": 993 }, { "epoch": 4.02632911392405, "grad_norm": 0.3926574379736324, "learning_rate": 4.320491585504207e-06, "loss": 0.169, "step": 994 }, { "epoch": 4.030379746835443, "grad_norm": 0.4123933154849183, "learning_rate": 4.2853194494790615e-06, "loss": 0.1433, "step": 995 }, { "epoch": 4.034430379746835, "grad_norm": 0.41166292099060936, "learning_rate": 4.250273877330691e-06, "loss": 0.1637, "step": 996 }, { "epoch": 4.038481012658228, "grad_norm": 0.34037167348687036, "learning_rate": 4.215355151311313e-06, "loss": 0.151, "step": 997 }, { "epoch": 4.04253164556962, "grad_norm": 0.29742655773376947, "learning_rate": 4.180563552651542e-06, "loss": 0.122, "step": 998 }, { "epoch": 4.046582278481012, "grad_norm": 0.32297521593685063, "learning_rate": 4.145899361558147e-06, "loss": 0.1466, "step": 999 }, { "epoch": 4.050632911392405, "grad_norm": 0.3240278354601214, "learning_rate": 4.111362857211738e-06, "loss": 0.1381, "step": 1000 }, { "epoch": 4.054683544303797, "grad_norm": 0.30748009256815395, "learning_rate": 4.076954317764592e-06, "loss": 0.1342, "step": 1001 }, { "epoch": 4.0587341772151895, "grad_norm": 0.3002122794291397, "learning_rate": 4.042674020338335e-06, "loss": 0.1357, "step": 1002 }, { "epoch": 4.062784810126582, "grad_norm": 0.27570187134699753, "learning_rate": 4.0085222410217835e-06, "loss": 0.1241, "step": 1003 }, { "epoch": 4.0668354430379745, "grad_norm": 0.2933145900011125, "learning_rate": 3.974499254868674e-06, "loss": 0.1635, "step": 1004 }, { "epoch": 4.0708860759493675, "grad_norm": 0.3013625723663537, "learning_rate": 3.940605335895451e-06, "loss": 0.1345, "step": 1005 }, { "epoch": 4.0749367088607595, "grad_norm": 0.28089167761542555, "learning_rate": 3.90684075707908e-06, "loss": 0.1511, "step": 1006 }, { "epoch": 4.078987341772152, "grad_norm": 0.2880625024130324, "learning_rate": 3.8732057903548505e-06, "loss": 0.1257, "step": 1007 }, { "epoch": 4.083037974683545, "grad_norm": 0.2996072270150012, "learning_rate": 3.8397007066141375e-06, "loss": 0.1375, "step": 1008 }, { "epoch": 4.087088607594937, "grad_norm": 0.296051280376566, "learning_rate": 3.806325775702304e-06, "loss": 0.141, "step": 1009 }, { "epoch": 4.091139240506329, "grad_norm": 0.3015823112589402, "learning_rate": 3.773081266416434e-06, "loss": 0.1669, "step": 1010 }, { "epoch": 4.095189873417722, "grad_norm": 0.2990027814233672, "learning_rate": 3.739967446503245e-06, "loss": 0.168, "step": 1011 }, { "epoch": 4.099240506329114, "grad_norm": 0.2764650594411568, "learning_rate": 3.706984582656894e-06, "loss": 0.139, "step": 1012 }, { "epoch": 4.103291139240507, "grad_norm": 0.2872610401510725, "learning_rate": 3.6741329405168237e-06, "loss": 0.139, "step": 1013 }, { "epoch": 4.107341772151899, "grad_norm": 0.27576040585272854, "learning_rate": 3.641412784665648e-06, "loss": 0.1549, "step": 1014 }, { "epoch": 4.111392405063291, "grad_norm": 0.27574357388225657, "learning_rate": 3.608824378627005e-06, "loss": 0.1232, "step": 1015 }, { "epoch": 4.115443037974684, "grad_norm": 0.2877219532760588, "learning_rate": 3.5763679848634337e-06, "loss": 0.1484, "step": 1016 }, { "epoch": 4.119493670886076, "grad_norm": 0.28739548619808847, "learning_rate": 3.544043864774269e-06, "loss": 0.1447, "step": 1017 }, { "epoch": 4.123544303797468, "grad_norm": 0.2751388493465771, "learning_rate": 3.5118522786935282e-06, "loss": 0.1676, "step": 1018 }, { "epoch": 4.127594936708861, "grad_norm": 0.2534157428944682, "learning_rate": 3.479793485887819e-06, "loss": 0.1374, "step": 1019 }, { "epoch": 4.131645569620253, "grad_norm": 0.2623387856521008, "learning_rate": 3.4478677445542653e-06, "loss": 0.1261, "step": 1020 }, { "epoch": 4.135696202531646, "grad_norm": 0.2678420573521524, "learning_rate": 3.4160753118183767e-06, "loss": 0.1183, "step": 1021 }, { "epoch": 4.139746835443038, "grad_norm": 0.28130713763687193, "learning_rate": 3.3844164437320527e-06, "loss": 0.1415, "step": 1022 }, { "epoch": 4.14379746835443, "grad_norm": 0.2761177992745471, "learning_rate": 3.3528913952714558e-06, "loss": 0.1613, "step": 1023 }, { "epoch": 4.147848101265823, "grad_norm": 0.2622850966547674, "learning_rate": 3.321500420335e-06, "loss": 0.1275, "step": 1024 }, { "epoch": 4.151898734177215, "grad_norm": 0.2777717795557654, "learning_rate": 3.290243771741275e-06, "loss": 0.1384, "step": 1025 }, { "epoch": 4.155949367088607, "grad_norm": 0.25659321460931955, "learning_rate": 3.2591217012270325e-06, "loss": 0.1207, "step": 1026 }, { "epoch": 4.16, "grad_norm": 0.2726118562822005, "learning_rate": 3.228134459445149e-06, "loss": 0.1638, "step": 1027 }, { "epoch": 4.164050632911392, "grad_norm": 0.27757156164226277, "learning_rate": 3.1972822959626205e-06, "loss": 0.1387, "step": 1028 }, { "epoch": 4.168101265822785, "grad_norm": 0.2600498519525614, "learning_rate": 3.166565459258513e-06, "loss": 0.1472, "step": 1029 }, { "epoch": 4.172151898734177, "grad_norm": 0.25692920020489485, "learning_rate": 3.1359841967220193e-06, "loss": 0.1372, "step": 1030 }, { "epoch": 4.176202531645569, "grad_norm": 0.25768901942363304, "learning_rate": 3.105538754650419e-06, "loss": 0.1301, "step": 1031 }, { "epoch": 4.180253164556962, "grad_norm": 0.2663061824636883, "learning_rate": 3.07522937824712e-06, "loss": 0.1689, "step": 1032 }, { "epoch": 4.184303797468354, "grad_norm": 0.26381753036908573, "learning_rate": 3.0450563116196697e-06, "loss": 0.1559, "step": 1033 }, { "epoch": 4.188354430379746, "grad_norm": 0.26187646775235734, "learning_rate": 3.0150197977778008e-06, "loss": 0.1407, "step": 1034 }, { "epoch": 4.192405063291139, "grad_norm": 0.2704698621671206, "learning_rate": 2.985120078631465e-06, "loss": 0.1467, "step": 1035 }, { "epoch": 4.1964556962025314, "grad_norm": 0.28374684922672355, "learning_rate": 2.9553573949888893e-06, "loss": 0.1547, "step": 1036 }, { "epoch": 4.200506329113924, "grad_norm": 0.28763365085507886, "learning_rate": 2.9257319865546384e-06, "loss": 0.1568, "step": 1037 }, { "epoch": 4.2045569620253165, "grad_norm": 0.2641105907970253, "learning_rate": 2.896244091927678e-06, "loss": 0.1444, "step": 1038 }, { "epoch": 4.2086075949367086, "grad_norm": 0.2566187250252698, "learning_rate": 2.8668939485994584e-06, "loss": 0.1202, "step": 1039 }, { "epoch": 4.2126582278481015, "grad_norm": 0.24840393603848743, "learning_rate": 2.837681792951994e-06, "loss": 0.1489, "step": 1040 }, { "epoch": 4.216708860759494, "grad_norm": 0.2641629082138823, "learning_rate": 2.808607860255981e-06, "loss": 0.1389, "step": 1041 }, { "epoch": 4.220759493670886, "grad_norm": 0.2661789141665539, "learning_rate": 2.7796723846688634e-06, "loss": 0.14, "step": 1042 }, { "epoch": 4.224810126582279, "grad_norm": 0.27957209835180225, "learning_rate": 2.7508755992329937e-06, "loss": 0.1603, "step": 1043 }, { "epoch": 4.228860759493671, "grad_norm": 0.26941006475328333, "learning_rate": 2.722217735873718e-06, "loss": 0.1469, "step": 1044 }, { "epoch": 4.232911392405064, "grad_norm": 0.25123603664702454, "learning_rate": 2.6936990253975315e-06, "loss": 0.1422, "step": 1045 }, { "epoch": 4.236962025316456, "grad_norm": 0.2577555672143441, "learning_rate": 2.665319697490205e-06, "loss": 0.149, "step": 1046 }, { "epoch": 4.241012658227848, "grad_norm": 0.2608668102091253, "learning_rate": 2.637079980714945e-06, "loss": 0.1226, "step": 1047 }, { "epoch": 4.245063291139241, "grad_norm": 0.2696367914353844, "learning_rate": 2.6089801025105453e-06, "loss": 0.1234, "step": 1048 }, { "epoch": 4.249113924050633, "grad_norm": 0.25952707112970635, "learning_rate": 2.581020289189571e-06, "loss": 0.1353, "step": 1049 }, { "epoch": 4.253164556962025, "grad_norm": 0.2688536032431187, "learning_rate": 2.553200765936501e-06, "loss": 0.1461, "step": 1050 }, { "epoch": 4.257215189873418, "grad_norm": 0.264870321493564, "learning_rate": 2.525521756805962e-06, "loss": 0.1373, "step": 1051 }, { "epoch": 4.26126582278481, "grad_norm": 0.2678874695607001, "learning_rate": 2.497983484720885e-06, "loss": 0.1558, "step": 1052 }, { "epoch": 4.265316455696203, "grad_norm": 0.25732914646190386, "learning_rate": 2.470586171470728e-06, "loss": 0.1419, "step": 1053 }, { "epoch": 4.269367088607595, "grad_norm": 0.260846287261723, "learning_rate": 2.4433300377096836e-06, "loss": 0.1441, "step": 1054 }, { "epoch": 4.273417721518987, "grad_norm": 0.25961436145891065, "learning_rate": 2.4162153029549073e-06, "loss": 0.1415, "step": 1055 }, { "epoch": 4.27746835443038, "grad_norm": 0.2697875908820821, "learning_rate": 2.3892421855847458e-06, "loss": 0.1384, "step": 1056 }, { "epoch": 4.281518987341772, "grad_norm": 0.25758504373895996, "learning_rate": 2.362410902836978e-06, "loss": 0.1474, "step": 1057 }, { "epoch": 4.285569620253165, "grad_norm": 0.2699421410001445, "learning_rate": 2.3357216708070653e-06, "loss": 0.1485, "step": 1058 }, { "epoch": 4.289620253164557, "grad_norm": 0.2649407914529636, "learning_rate": 2.309174704446411e-06, "loss": 0.1392, "step": 1059 }, { "epoch": 4.293670886075949, "grad_norm": 0.27164827483008236, "learning_rate": 2.2827702175606437e-06, "loss": 0.1388, "step": 1060 }, { "epoch": 4.297721518987342, "grad_norm": 0.2726215218199984, "learning_rate": 2.256508422807855e-06, "loss": 0.1478, "step": 1061 }, { "epoch": 4.301772151898734, "grad_norm": 0.26585906394920567, "learning_rate": 2.230389531696946e-06, "loss": 0.1557, "step": 1062 }, { "epoch": 4.305822784810126, "grad_norm": 0.26548574991342333, "learning_rate": 2.204413754585857e-06, "loss": 0.1457, "step": 1063 }, { "epoch": 4.309873417721519, "grad_norm": 0.2527671304525562, "learning_rate": 2.1785813006799406e-06, "loss": 0.1258, "step": 1064 }, { "epoch": 4.313924050632911, "grad_norm": 0.2599890968381186, "learning_rate": 2.1528923780302224e-06, "loss": 0.1318, "step": 1065 }, { "epoch": 4.317974683544303, "grad_norm": 0.25365920919581825, "learning_rate": 2.127347193531757e-06, "loss": 0.1328, "step": 1066 }, { "epoch": 4.322025316455696, "grad_norm": 0.2555495924905704, "learning_rate": 2.101945952921942e-06, "loss": 0.1272, "step": 1067 }, { "epoch": 4.326075949367088, "grad_norm": 0.26100384888268097, "learning_rate": 2.0766888607788906e-06, "loss": 0.1444, "step": 1068 }, { "epoch": 4.330126582278481, "grad_norm": 0.2685022471616596, "learning_rate": 2.0515761205197337e-06, "loss": 0.1415, "step": 1069 }, { "epoch": 4.334177215189873, "grad_norm": 0.25459108765585675, "learning_rate": 2.0266079343990453e-06, "loss": 0.1284, "step": 1070 }, { "epoch": 4.3382278481012655, "grad_norm": 0.2456585831665607, "learning_rate": 2.0017845035071494e-06, "loss": 0.1481, "step": 1071 }, { "epoch": 4.3422784810126585, "grad_norm": 0.2677030106893549, "learning_rate": 1.9771060277685537e-06, "loss": 0.1723, "step": 1072 }, { "epoch": 4.3463291139240505, "grad_norm": 0.2590584307166148, "learning_rate": 1.95257270594031e-06, "loss": 0.1587, "step": 1073 }, { "epoch": 4.3503797468354435, "grad_norm": 0.263662915728639, "learning_rate": 1.9281847356104188e-06, "loss": 0.1326, "step": 1074 }, { "epoch": 4.3544303797468356, "grad_norm": 0.2624443595982689, "learning_rate": 1.9039423131962365e-06, "loss": 0.169, "step": 1075 }, { "epoch": 4.358481012658228, "grad_norm": 0.26459301359978693, "learning_rate": 1.8798456339429027e-06, "loss": 0.143, "step": 1076 }, { "epoch": 4.362531645569621, "grad_norm": 0.2656021811842008, "learning_rate": 1.8558948919217612e-06, "loss": 0.1443, "step": 1077 }, { "epoch": 4.366582278481013, "grad_norm": 0.2601144936993541, "learning_rate": 1.8320902800287954e-06, "loss": 0.1331, "step": 1078 }, { "epoch": 4.370632911392405, "grad_norm": 0.2652343246084245, "learning_rate": 1.8084319899830726e-06, "loss": 0.1357, "step": 1079 }, { "epoch": 4.374683544303798, "grad_norm": 0.26391573931647333, "learning_rate": 1.7849202123252097e-06, "loss": 0.1503, "step": 1080 }, { "epoch": 4.37873417721519, "grad_norm": 0.26734724643934055, "learning_rate": 1.7615551364158401e-06, "loss": 0.136, "step": 1081 }, { "epoch": 4.382784810126582, "grad_norm": 0.2576484470992114, "learning_rate": 1.738336950434061e-06, "loss": 0.1492, "step": 1082 }, { "epoch": 4.386835443037975, "grad_norm": 0.262556648991898, "learning_rate": 1.715265841375957e-06, "loss": 0.1221, "step": 1083 }, { "epoch": 4.390886075949367, "grad_norm": 0.26120375553227615, "learning_rate": 1.6923419950530684e-06, "loss": 0.135, "step": 1084 }, { "epoch": 4.39493670886076, "grad_norm": 0.2733742553020859, "learning_rate": 1.6695655960909008e-06, "loss": 0.1487, "step": 1085 }, { "epoch": 4.398987341772152, "grad_norm": 0.26735099228252235, "learning_rate": 1.646936827927441e-06, "loss": 0.147, "step": 1086 }, { "epoch": 4.403037974683544, "grad_norm": 0.2662361892185209, "learning_rate": 1.6244558728116766e-06, "loss": 0.1347, "step": 1087 }, { "epoch": 4.407088607594937, "grad_norm": 0.25572707044899495, "learning_rate": 1.6021229118021265e-06, "loss": 0.1452, "step": 1088 }, { "epoch": 4.411139240506329, "grad_norm": 0.26391722799235073, "learning_rate": 1.5799381247653967e-06, "loss": 0.1665, "step": 1089 }, { "epoch": 4.415189873417722, "grad_norm": 0.2616110278307747, "learning_rate": 1.5579016903747013e-06, "loss": 0.158, "step": 1090 }, { "epoch": 4.419240506329114, "grad_norm": 0.2749493212265253, "learning_rate": 1.5360137861084656e-06, "loss": 0.132, "step": 1091 }, { "epoch": 4.423291139240506, "grad_norm": 0.46997974557693134, "learning_rate": 1.5142745882488475e-06, "loss": 0.1143, "step": 1092 }, { "epoch": 4.427341772151899, "grad_norm": 0.25933221822017255, "learning_rate": 1.4926842718803691e-06, "loss": 0.1524, "step": 1093 }, { "epoch": 4.431392405063291, "grad_norm": 0.24053436992126484, "learning_rate": 1.4712430108884657e-06, "loss": 0.1137, "step": 1094 }, { "epoch": 4.435443037974683, "grad_norm": 0.26078435312675763, "learning_rate": 1.4499509779581078e-06, "loss": 0.1289, "step": 1095 }, { "epoch": 4.439493670886076, "grad_norm": 0.26888478146439526, "learning_rate": 1.4288083445723988e-06, "loss": 0.1686, "step": 1096 }, { "epoch": 4.443544303797468, "grad_norm": 0.25937259402753526, "learning_rate": 1.4078152810112045e-06, "loss": 0.1343, "step": 1097 }, { "epoch": 4.44759493670886, "grad_norm": 0.26930273131861604, "learning_rate": 1.3869719563497697e-06, "loss": 0.1303, "step": 1098 }, { "epoch": 4.451645569620253, "grad_norm": 0.2540555360927144, "learning_rate": 1.3662785384573663e-06, "loss": 0.1514, "step": 1099 }, { "epoch": 4.455696202531645, "grad_norm": 0.25583721875206733, "learning_rate": 1.3457351939959383e-06, "loss": 0.1356, "step": 1100 }, { "epoch": 4.459746835443038, "grad_norm": 0.25835727539909964, "learning_rate": 1.3253420884187551e-06, "loss": 0.1639, "step": 1101 }, { "epoch": 4.46379746835443, "grad_norm": 0.2726330599256951, "learning_rate": 1.3050993859690953e-06, "loss": 0.1425, "step": 1102 }, { "epoch": 4.467848101265822, "grad_norm": 0.24837712275495094, "learning_rate": 1.2850072496788869e-06, "loss": 0.1535, "step": 1103 }, { "epoch": 4.471898734177215, "grad_norm": 0.2719592384050176, "learning_rate": 1.2650658413674434e-06, "loss": 0.1537, "step": 1104 }, { "epoch": 4.4759493670886075, "grad_norm": 0.25559335516399306, "learning_rate": 1.2452753216401226e-06, "loss": 0.1363, "step": 1105 }, { "epoch": 4.48, "grad_norm": 0.26781811451644616, "learning_rate": 1.2256358498870503e-06, "loss": 0.168, "step": 1106 }, { "epoch": 4.4840506329113925, "grad_norm": 0.2518054789167052, "learning_rate": 1.2061475842818337e-06, "loss": 0.1512, "step": 1107 }, { "epoch": 4.488101265822785, "grad_norm": 0.26277016202074904, "learning_rate": 1.1868106817802816e-06, "loss": 0.1776, "step": 1108 }, { "epoch": 4.4921518987341775, "grad_norm": 0.2643223976625923, "learning_rate": 1.1676252981191482e-06, "loss": 0.1539, "step": 1109 }, { "epoch": 4.49620253164557, "grad_norm": 0.2583504231835119, "learning_rate": 1.1485915878148823e-06, "loss": 0.1598, "step": 1110 }, { "epoch": 4.500253164556962, "grad_norm": 0.2562830235265347, "learning_rate": 1.1297097041623584e-06, "loss": 0.1363, "step": 1111 }, { "epoch": 4.504303797468355, "grad_norm": 0.25311037214607085, "learning_rate": 1.1109797992336847e-06, "loss": 0.1526, "step": 1112 }, { "epoch": 4.508354430379747, "grad_norm": 0.25820839882903546, "learning_rate": 1.092402023876933e-06, "loss": 0.1394, "step": 1113 }, { "epoch": 4.512405063291139, "grad_norm": 0.2758660131299476, "learning_rate": 1.0739765277149527e-06, "loss": 0.1586, "step": 1114 }, { "epoch": 4.516455696202532, "grad_norm": 0.26528253542086394, "learning_rate": 1.0557034591441596e-06, "loss": 0.1486, "step": 1115 }, { "epoch": 4.520506329113924, "grad_norm": 0.2760653370041277, "learning_rate": 1.0375829653333324e-06, "loss": 0.1627, "step": 1116 }, { "epoch": 4.524556962025317, "grad_norm": 0.2506443662978397, "learning_rate": 1.0196151922224385e-06, "loss": 0.1436, "step": 1117 }, { "epoch": 4.528607594936709, "grad_norm": 0.24821385212324826, "learning_rate": 1.0018002845214526e-06, "loss": 0.1467, "step": 1118 }, { "epoch": 4.532658227848101, "grad_norm": 0.2677597334643499, "learning_rate": 9.841383857091947e-07, "loss": 0.1444, "step": 1119 }, { "epoch": 4.536708860759494, "grad_norm": 0.26935344858898214, "learning_rate": 9.666296380321616e-07, "loss": 0.1439, "step": 1120 }, { "epoch": 4.540759493670886, "grad_norm": 0.2598666452892773, "learning_rate": 9.492741825034124e-07, "loss": 0.137, "step": 1121 }, { "epoch": 4.544810126582279, "grad_norm": 0.26873587765186235, "learning_rate": 9.320721589013892e-07, "loss": 0.171, "step": 1122 }, { "epoch": 4.548860759493671, "grad_norm": 0.29689648399396534, "learning_rate": 9.150237057688339e-07, "loss": 0.1367, "step": 1123 }, { "epoch": 4.552911392405063, "grad_norm": 0.26893547746210317, "learning_rate": 8.981289604116328e-07, "loss": 0.1735, "step": 1124 }, { "epoch": 4.556962025316456, "grad_norm": 0.2642923583855211, "learning_rate": 8.813880588977542e-07, "loss": 0.1606, "step": 1125 }, { "epoch": 4.561012658227848, "grad_norm": 0.26698211508708997, "learning_rate": 8.648011360561126e-07, "loss": 0.1706, "step": 1126 }, { "epoch": 4.56506329113924, "grad_norm": 0.2618430410461064, "learning_rate": 8.483683254755037e-07, "loss": 0.1458, "step": 1127 }, { "epoch": 4.569113924050633, "grad_norm": 0.24978692697273575, "learning_rate": 8.320897595035227e-07, "loss": 0.1384, "step": 1128 }, { "epoch": 4.573164556962025, "grad_norm": 0.2665347675625368, "learning_rate": 8.159655692455093e-07, "loss": 0.1291, "step": 1129 }, { "epoch": 4.577215189873417, "grad_norm": 0.27878997833997876, "learning_rate": 7.999958845634648e-07, "loss": 0.1521, "step": 1130 }, { "epoch": 4.58126582278481, "grad_norm": 0.26318511009259454, "learning_rate": 7.841808340750478e-07, "loss": 0.1709, "step": 1131 }, { "epoch": 4.585316455696202, "grad_norm": 0.26567993877719526, "learning_rate": 7.685205451524869e-07, "loss": 0.1479, "step": 1132 }, { "epoch": 4.589367088607595, "grad_norm": 0.27407124802829613, "learning_rate": 7.530151439216027e-07, "loss": 0.1664, "step": 1133 }, { "epoch": 4.593417721518987, "grad_norm": 0.26362434234973225, "learning_rate": 7.376647552607675e-07, "loss": 0.1195, "step": 1134 }, { "epoch": 4.597468354430379, "grad_norm": 0.2814634343161971, "learning_rate": 7.224695027998963e-07, "loss": 0.1529, "step": 1135 }, { "epoch": 4.601518987341772, "grad_norm": 0.27656178748045, "learning_rate": 7.07429508919466e-07, "loss": 0.1287, "step": 1136 }, { "epoch": 4.605569620253164, "grad_norm": 0.25921622035404174, "learning_rate": 6.925448947495206e-07, "loss": 0.1345, "step": 1137 }, { "epoch": 4.609620253164557, "grad_norm": 0.2510210233769021, "learning_rate": 6.778157801686936e-07, "loss": 0.1271, "step": 1138 }, { "epoch": 4.613670886075949, "grad_norm": 0.24781086628995, "learning_rate": 6.632422838032515e-07, "loss": 0.1457, "step": 1139 }, { "epoch": 4.6177215189873415, "grad_norm": 0.25931837793693213, "learning_rate": 6.488245230261281e-07, "loss": 0.1228, "step": 1140 }, { "epoch": 4.6217721518987345, "grad_norm": 0.2490716469207613, "learning_rate": 6.345626139559868e-07, "loss": 0.1289, "step": 1141 }, { "epoch": 4.6258227848101265, "grad_norm": 0.2652147469314528, "learning_rate": 6.204566714562866e-07, "loss": 0.1453, "step": 1142 }, { "epoch": 4.629873417721519, "grad_norm": 0.2733970145965379, "learning_rate": 6.06506809134344e-07, "loss": 0.1389, "step": 1143 }, { "epoch": 4.633924050632912, "grad_norm": 0.2629602427992611, "learning_rate": 5.927131393404373e-07, "loss": 0.1548, "step": 1144 }, { "epoch": 4.637974683544304, "grad_norm": 0.25763849105672476, "learning_rate": 5.790757731668817e-07, "loss": 0.1417, "step": 1145 }, { "epoch": 4.642025316455696, "grad_norm": 0.26240189782132284, "learning_rate": 5.655948204471507e-07, "loss": 0.1567, "step": 1146 }, { "epoch": 4.646075949367089, "grad_norm": 0.24729048657118996, "learning_rate": 5.522703897549875e-07, "loss": 0.1466, "step": 1147 }, { "epoch": 4.650126582278481, "grad_norm": 0.25115368840750696, "learning_rate": 5.391025884035239e-07, "loss": 0.1177, "step": 1148 }, { "epoch": 4.654177215189874, "grad_norm": 0.257632409770631, "learning_rate": 5.260915224444207e-07, "loss": 0.1308, "step": 1149 }, { "epoch": 4.658227848101266, "grad_norm": 0.2749379090850938, "learning_rate": 5.132372966670129e-07, "loss": 0.1642, "step": 1150 }, { "epoch": 4.662278481012658, "grad_norm": 0.26722706472375646, "learning_rate": 5.005400145974704e-07, "loss": 0.1473, "step": 1151 }, { "epoch": 4.666329113924051, "grad_norm": 0.2681901408223529, "learning_rate": 4.879997784979562e-07, "loss": 0.1504, "step": 1152 }, { "epoch": 4.670379746835443, "grad_norm": 0.26389180254656025, "learning_rate": 4.7561668936580984e-07, "loss": 0.1349, "step": 1153 }, { "epoch": 4.674430379746836, "grad_norm": 0.2681993285625705, "learning_rate": 4.6339084693272306e-07, "loss": 0.1421, "step": 1154 }, { "epoch": 4.678481012658228, "grad_norm": 0.26522466370485565, "learning_rate": 4.5132234966395847e-07, "loss": 0.1518, "step": 1155 }, { "epoch": 4.68253164556962, "grad_norm": 0.257605167706092, "learning_rate": 4.3941129475752795e-07, "loss": 0.1447, "step": 1156 }, { "epoch": 4.686582278481013, "grad_norm": 0.25735609301479573, "learning_rate": 4.27657778143431e-07, "loss": 0.1363, "step": 1157 }, { "epoch": 4.690632911392405, "grad_norm": 0.2560781335255791, "learning_rate": 4.1606189448287757e-07, "loss": 0.1483, "step": 1158 }, { "epoch": 4.694683544303797, "grad_norm": 0.26379434865468465, "learning_rate": 4.046237371675177e-07, "loss": 0.175, "step": 1159 }, { "epoch": 4.69873417721519, "grad_norm": 0.268167817536295, "learning_rate": 3.9334339831869963e-07, "loss": 0.1482, "step": 1160 }, { "epoch": 4.702784810126582, "grad_norm": 0.25841494106616686, "learning_rate": 3.8222096878671955e-07, "loss": 0.1477, "step": 1161 }, { "epoch": 4.706835443037974, "grad_norm": 0.26500334558856076, "learning_rate": 3.7125653815009545e-07, "loss": 0.1587, "step": 1162 }, { "epoch": 4.710886075949367, "grad_norm": 0.2510788170061026, "learning_rate": 3.6045019471484974e-07, "loss": 0.1172, "step": 1163 }, { "epoch": 4.714936708860759, "grad_norm": 0.261060013666619, "learning_rate": 3.498020255137813e-07, "loss": 0.1247, "step": 1164 }, { "epoch": 4.718987341772152, "grad_norm": 0.2721740252934908, "learning_rate": 3.393121163057811e-07, "loss": 0.1405, "step": 1165 }, { "epoch": 4.723037974683544, "grad_norm": 0.26147015933457823, "learning_rate": 3.289805515751399e-07, "loss": 0.1321, "step": 1166 }, { "epoch": 4.727088607594936, "grad_norm": 0.255040808380827, "learning_rate": 3.188074145308573e-07, "loss": 0.1186, "step": 1167 }, { "epoch": 4.731139240506329, "grad_norm": 0.27317671852477293, "learning_rate": 3.087927871059804e-07, "loss": 0.1431, "step": 1168 }, { "epoch": 4.735189873417721, "grad_norm": 0.2652441531188345, "learning_rate": 2.989367499569418e-07, "loss": 0.148, "step": 1169 }, { "epoch": 4.739240506329114, "grad_norm": 0.2610657056865796, "learning_rate": 2.8923938246290917e-07, "loss": 0.1293, "step": 1170 }, { "epoch": 4.743291139240506, "grad_norm": 0.26318528623760057, "learning_rate": 2.7970076272514804e-07, "loss": 0.142, "step": 1171 }, { "epoch": 4.7473417721518985, "grad_norm": 0.24009347353975788, "learning_rate": 2.703209675663887e-07, "loss": 0.1472, "step": 1172 }, { "epoch": 4.751392405063291, "grad_norm": 0.26529365145528633, "learning_rate": 2.6110007253021374e-07, "loss": 0.1684, "step": 1173 }, { "epoch": 4.7554430379746835, "grad_norm": 0.2566556413078877, "learning_rate": 2.520381518804471e-07, "loss": 0.1404, "step": 1174 }, { "epoch": 4.759493670886076, "grad_norm": 0.2676416002028604, "learning_rate": 2.4313527860054585e-07, "loss": 0.1387, "step": 1175 }, { "epoch": 4.7635443037974685, "grad_norm": 0.2619961336805734, "learning_rate": 2.343915243930317e-07, "loss": 0.1327, "step": 1176 }, { "epoch": 4.767594936708861, "grad_norm": 0.2698564229613806, "learning_rate": 2.2580695967889367e-07, "loss": 0.1424, "step": 1177 }, { "epoch": 4.7716455696202535, "grad_norm": 0.2673340950080637, "learning_rate": 2.1738165359704189e-07, "loss": 0.1445, "step": 1178 }, { "epoch": 4.775696202531646, "grad_norm": 0.2749637533057212, "learning_rate": 2.0911567400373257e-07, "loss": 0.1479, "step": 1179 }, { "epoch": 4.779746835443038, "grad_norm": 0.2584534511171279, "learning_rate": 2.0100908747202607e-07, "loss": 0.1282, "step": 1180 }, { "epoch": 4.783797468354431, "grad_norm": 0.26824629369666847, "learning_rate": 1.9306195929125638e-07, "loss": 0.1547, "step": 1181 }, { "epoch": 4.787848101265823, "grad_norm": 0.25783802536328254, "learning_rate": 1.8527435346650247e-07, "loss": 0.1436, "step": 1182 }, { "epoch": 4.791898734177215, "grad_norm": 0.2592115160725605, "learning_rate": 1.7764633271807108e-07, "loss": 0.1482, "step": 1183 }, { "epoch": 4.795949367088608, "grad_norm": 0.27301301806446704, "learning_rate": 1.7017795848099262e-07, "loss": 0.1676, "step": 1184 }, { "epoch": 4.8, "grad_norm": 0.27255770324247347, "learning_rate": 1.6286929090452596e-07, "loss": 0.1535, "step": 1185 }, { "epoch": 4.804050632911393, "grad_norm": 0.26637233768374025, "learning_rate": 1.557203888516745e-07, "loss": 0.1421, "step": 1186 }, { "epoch": 4.808101265822785, "grad_norm": 0.2615483104744582, "learning_rate": 1.487313098987131e-07, "loss": 0.1353, "step": 1187 }, { "epoch": 4.812151898734177, "grad_norm": 0.26518125469373904, "learning_rate": 1.4190211033472402e-07, "loss": 0.1521, "step": 1188 }, { "epoch": 4.81620253164557, "grad_norm": 0.2569994038258014, "learning_rate": 1.3523284516113955e-07, "loss": 0.1516, "step": 1189 }, { "epoch": 4.820253164556962, "grad_norm": 0.26954090068593495, "learning_rate": 1.2872356809130682e-07, "loss": 0.139, "step": 1190 }, { "epoch": 4.824303797468355, "grad_norm": 0.2631435092093801, "learning_rate": 1.2237433155004807e-07, "loss": 0.167, "step": 1191 }, { "epoch": 4.828354430379747, "grad_norm": 0.24970186455036306, "learning_rate": 1.1618518667323886e-07, "loss": 0.1505, "step": 1192 }, { "epoch": 4.832405063291139, "grad_norm": 0.26014377534494354, "learning_rate": 1.1015618330740385e-07, "loss": 0.1573, "step": 1193 }, { "epoch": 4.836455696202532, "grad_norm": 0.27126012888719464, "learning_rate": 1.042873700093061e-07, "loss": 0.1388, "step": 1194 }, { "epoch": 4.840506329113924, "grad_norm": 0.2616202437404257, "learning_rate": 9.857879404556291e-08, "loss": 0.1827, "step": 1195 }, { "epoch": 4.844556962025316, "grad_norm": 0.26557494974773505, "learning_rate": 9.303050139225722e-08, "loss": 0.1611, "step": 1196 }, { "epoch": 4.848607594936709, "grad_norm": 0.25911156322192475, "learning_rate": 8.76425367345779e-08, "loss": 0.1435, "step": 1197 }, { "epoch": 4.852658227848101, "grad_norm": 0.25871009218824376, "learning_rate": 8.241494346644897e-08, "loss": 0.1236, "step": 1198 }, { "epoch": 4.856708860759493, "grad_norm": 0.2637718820526756, "learning_rate": 7.734776369019204e-08, "loss": 0.1241, "step": 1199 }, { "epoch": 4.860759493670886, "grad_norm": 0.2419741570633733, "learning_rate": 7.244103821617332e-08, "loss": 0.123, "step": 1200 }, { "epoch": 4.864810126582278, "grad_norm": 0.26432831743694896, "learning_rate": 6.769480656248606e-08, "loss": 0.1487, "step": 1201 }, { "epoch": 4.868860759493671, "grad_norm": 0.26283826036445906, "learning_rate": 6.310910695462635e-08, "loss": 0.1397, "step": 1202 }, { "epoch": 4.872911392405063, "grad_norm": 0.26067445436463343, "learning_rate": 5.8683976325191185e-08, "loss": 0.1521, "step": 1203 }, { "epoch": 4.876962025316455, "grad_norm": 0.27906558316535235, "learning_rate": 5.4419450313571984e-08, "loss": 0.1542, "step": 1204 }, { "epoch": 4.881012658227848, "grad_norm": 0.2583829570159428, "learning_rate": 5.031556326567488e-08, "loss": 0.1486, "step": 1205 }, { "epoch": 4.88506329113924, "grad_norm": 0.26434479030714153, "learning_rate": 4.637234823364312e-08, "loss": 0.142, "step": 1206 }, { "epoch": 4.889113924050633, "grad_norm": 0.2523505146714843, "learning_rate": 4.258983697558838e-08, "loss": 0.1539, "step": 1207 }, { "epoch": 4.8931645569620255, "grad_norm": 0.25895676305441145, "learning_rate": 3.896805995533548e-08, "loss": 0.1313, "step": 1208 }, { "epoch": 4.8972151898734175, "grad_norm": 0.2524693086049537, "learning_rate": 3.550704634218028e-08, "loss": 0.1398, "step": 1209 }, { "epoch": 4.9012658227848105, "grad_norm": 0.2622051719124061, "learning_rate": 3.2206824010647676e-08, "loss": 0.1646, "step": 1210 }, { "epoch": 4.905316455696203, "grad_norm": 0.25317833406699264, "learning_rate": 2.9067419540278476e-08, "loss": 0.1435, "step": 1211 }, { "epoch": 4.909367088607595, "grad_norm": 0.25731069288777964, "learning_rate": 2.6088858215400638e-08, "loss": 0.1201, "step": 1212 }, { "epoch": 4.913417721518988, "grad_norm": 0.26991217053145516, "learning_rate": 2.3271164024940564e-08, "loss": 0.1513, "step": 1213 }, { "epoch": 4.91746835443038, "grad_norm": 0.26664261742729817, "learning_rate": 2.061435966221881e-08, "loss": 0.1515, "step": 1214 }, { "epoch": 4.921518987341772, "grad_norm": 0.25771781218386813, "learning_rate": 1.811846652477245e-08, "loss": 0.1547, "step": 1215 }, { "epoch": 4.925569620253165, "grad_norm": 0.24805773997192598, "learning_rate": 1.5783504714184106e-08, "loss": 0.1281, "step": 1216 }, { "epoch": 4.929620253164557, "grad_norm": 0.2542861527866738, "learning_rate": 1.360949303591097e-08, "loss": 0.1505, "step": 1217 }, { "epoch": 4.93367088607595, "grad_norm": 0.2608368681048683, "learning_rate": 1.1596448999144916e-08, "loss": 0.1255, "step": 1218 }, { "epoch": 4.937721518987342, "grad_norm": 0.24929628658060046, "learning_rate": 9.744388816668172e-09, "loss": 0.1378, "step": 1219 }, { "epoch": 4.941772151898734, "grad_norm": 0.2661945381704372, "learning_rate": 8.05332740472009e-09, "loss": 0.1219, "step": 1220 }, { "epoch": 4.945822784810127, "grad_norm": 0.2642052161919977, "learning_rate": 6.523278382872811e-09, "loss": 0.1343, "step": 1221 }, { "epoch": 4.949873417721519, "grad_norm": 0.26626456381998936, "learning_rate": 5.15425407393133e-09, "loss": 0.1822, "step": 1222 }, { "epoch": 4.953924050632912, "grad_norm": 0.27145934278287376, "learning_rate": 3.94626550383137e-09, "loss": 0.1496, "step": 1223 }, { "epoch": 4.957974683544304, "grad_norm": 0.2869935458891249, "learning_rate": 2.899322401546112e-09, "loss": 0.1382, "step": 1224 }, { "epoch": 4.962025316455696, "grad_norm": 0.2531930901030747, "learning_rate": 2.013433199010706e-09, "loss": 0.123, "step": 1225 }, { "epoch": 4.966075949367089, "grad_norm": 0.27070054523657816, "learning_rate": 1.2886050310556563e-09, "loss": 0.1691, "step": 1226 }, { "epoch": 4.970126582278481, "grad_norm": 0.26632884143864827, "learning_rate": 7.248437353468695e-10, "loss": 0.1344, "step": 1227 }, { "epoch": 4.974177215189873, "grad_norm": 0.25294447923999, "learning_rate": 3.221538523412449e-10, "loss": 0.1705, "step": 1228 }, { "epoch": 4.978227848101266, "grad_norm": 0.2631658029399062, "learning_rate": 8.053862524670663e-11, "loss": 0.1394, "step": 1229 }, { "epoch": 4.982278481012658, "grad_norm": 0.2547122749352606, "learning_rate": 0.0, "loss": 0.1401, "step": 1230 }, { "epoch": 4.982278481012658, "step": 1230, "total_flos": 1.565878669438296e+18, "train_loss": 0.38663404108426436, "train_runtime": 28103.5168, "train_samples_per_second": 5.622, "train_steps_per_second": 0.044 } ], "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": 1.565878669438296e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }