{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.982278481012658, "eval_steps": 500, "global_step": 1230, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004050632911392405, "grad_norm": 6.453780829511939, "learning_rate": 3.2520325203252037e-07, "loss": 1.0697, "step": 1 }, { "epoch": 0.00810126582278481, "grad_norm": 6.675101795381871, "learning_rate": 6.504065040650407e-07, "loss": 1.0688, "step": 2 }, { "epoch": 0.012151898734177215, "grad_norm": 6.716803942481356, "learning_rate": 9.75609756097561e-07, "loss": 1.0601, "step": 3 }, { "epoch": 0.01620253164556962, "grad_norm": 6.301448856568784, "learning_rate": 1.3008130081300815e-06, "loss": 1.0401, "step": 4 }, { "epoch": 0.020253164556962026, "grad_norm": 6.2209680043934785, "learning_rate": 1.6260162601626018e-06, "loss": 1.077, "step": 5 }, { "epoch": 0.02430379746835443, "grad_norm": 5.898960927451822, "learning_rate": 1.951219512195122e-06, "loss": 1.0337, "step": 6 }, { "epoch": 0.028354430379746835, "grad_norm": 4.921458532617379, "learning_rate": 2.2764227642276426e-06, "loss": 1.021, "step": 7 }, { "epoch": 0.03240506329113924, "grad_norm": 4.757306242324013, "learning_rate": 2.601626016260163e-06, "loss": 1.0172, "step": 8 }, { "epoch": 0.03645569620253165, "grad_norm": 2.3203174158455524, "learning_rate": 2.926829268292683e-06, "loss": 0.9409, "step": 9 }, { "epoch": 0.04050632911392405, "grad_norm": 2.3001720735010633, "learning_rate": 3.2520325203252037e-06, "loss": 0.9906, "step": 10 }, { "epoch": 0.044556962025316456, "grad_norm": 2.1621652462738656, "learning_rate": 3.577235772357724e-06, "loss": 0.9471, "step": 11 }, { "epoch": 0.04860759493670886, "grad_norm": 4.419539943683975, "learning_rate": 3.902439024390244e-06, "loss": 0.9544, "step": 12 }, { "epoch": 0.052658227848101265, "grad_norm": 4.657725956358886, "learning_rate": 4.227642276422765e-06, "loss": 0.9199, "step": 13 }, { "epoch": 0.05670886075949367, "grad_norm": 4.420533465893256, "learning_rate": 4.552845528455285e-06, "loss": 0.9141, "step": 14 }, { "epoch": 0.060759493670886074, "grad_norm": 3.9937355372306085, "learning_rate": 4.8780487804878055e-06, "loss": 0.8761, "step": 15 }, { "epoch": 0.06481012658227848, "grad_norm": 3.226628278397167, "learning_rate": 5.203252032520326e-06, "loss": 0.8941, "step": 16 }, { "epoch": 0.06886075949367089, "grad_norm": 2.887197032837081, "learning_rate": 5.528455284552846e-06, "loss": 0.8595, "step": 17 }, { "epoch": 0.0729113924050633, "grad_norm": 2.6306842584596466, "learning_rate": 5.853658536585366e-06, "loss": 0.8231, "step": 18 }, { "epoch": 0.0769620253164557, "grad_norm": 2.3383607248734504, "learning_rate": 6.178861788617887e-06, "loss": 0.8451, "step": 19 }, { "epoch": 0.0810126582278481, "grad_norm": 2.360972286080737, "learning_rate": 6.504065040650407e-06, "loss": 0.8383, "step": 20 }, { "epoch": 0.08506329113924051, "grad_norm": 1.7995867158385008, "learning_rate": 6.829268292682928e-06, "loss": 0.7994, "step": 21 }, { "epoch": 0.08911392405063291, "grad_norm": 1.8458810173944342, "learning_rate": 7.154471544715448e-06, "loss": 0.8308, "step": 22 }, { "epoch": 0.09316455696202532, "grad_norm": 1.8553172487782932, "learning_rate": 7.4796747967479676e-06, "loss": 0.8069, "step": 23 }, { "epoch": 0.09721518987341772, "grad_norm": 1.8914230009561015, "learning_rate": 7.804878048780489e-06, "loss": 0.8103, "step": 24 }, { "epoch": 0.10126582278481013, "grad_norm": 1.6048920951387555, "learning_rate": 8.130081300813009e-06, "loss": 0.8109, "step": 25 }, { "epoch": 0.10531645569620253, "grad_norm": 1.4833528887937533, "learning_rate": 8.45528455284553e-06, "loss": 0.8047, "step": 26 }, { "epoch": 0.10936708860759493, "grad_norm": 1.5342794027621796, "learning_rate": 8.78048780487805e-06, "loss": 0.7824, "step": 27 }, { "epoch": 0.11341772151898734, "grad_norm": 1.6212198071243353, "learning_rate": 9.10569105691057e-06, "loss": 0.7686, "step": 28 }, { "epoch": 0.11746835443037974, "grad_norm": 1.4584985747907917, "learning_rate": 9.43089430894309e-06, "loss": 0.7699, "step": 29 }, { "epoch": 0.12151898734177215, "grad_norm": 1.1306456896176218, "learning_rate": 9.756097560975611e-06, "loss": 0.7488, "step": 30 }, { "epoch": 0.12556962025316457, "grad_norm": 0.975605482066259, "learning_rate": 1.008130081300813e-05, "loss": 0.7499, "step": 31 }, { "epoch": 0.12962025316455697, "grad_norm": 1.0747216796727732, "learning_rate": 1.0406504065040652e-05, "loss": 0.7522, "step": 32 }, { "epoch": 0.13367088607594937, "grad_norm": 0.9603563705952372, "learning_rate": 1.0731707317073172e-05, "loss": 0.7473, "step": 33 }, { "epoch": 0.13772151898734178, "grad_norm": 0.7799580079041978, "learning_rate": 1.1056910569105692e-05, "loss": 0.7363, "step": 34 }, { "epoch": 0.14177215189873418, "grad_norm": 0.9752152547278411, "learning_rate": 1.1382113821138213e-05, "loss": 0.769, "step": 35 }, { "epoch": 0.1458227848101266, "grad_norm": 0.8471328351113202, "learning_rate": 1.1707317073170731e-05, "loss": 0.7527, "step": 36 }, { "epoch": 0.149873417721519, "grad_norm": 0.8866072139889343, "learning_rate": 1.2032520325203254e-05, "loss": 0.7446, "step": 37 }, { "epoch": 0.1539240506329114, "grad_norm": 0.7544835734049702, "learning_rate": 1.2357723577235774e-05, "loss": 0.7326, "step": 38 }, { "epoch": 0.1579746835443038, "grad_norm": 0.7393900381711174, "learning_rate": 1.2682926829268294e-05, "loss": 0.7524, "step": 39 }, { "epoch": 0.1620253164556962, "grad_norm": 0.6732854576386147, "learning_rate": 1.3008130081300815e-05, "loss": 0.7146, "step": 40 }, { "epoch": 0.1660759493670886, "grad_norm": 0.7168306156242321, "learning_rate": 1.3333333333333333e-05, "loss": 0.7293, "step": 41 }, { "epoch": 0.17012658227848101, "grad_norm": 0.7395720660908472, "learning_rate": 1.3658536585365855e-05, "loss": 0.7341, "step": 42 }, { "epoch": 0.17417721518987342, "grad_norm": 0.704958981214314, "learning_rate": 1.3983739837398376e-05, "loss": 0.7524, "step": 43 }, { "epoch": 0.17822784810126582, "grad_norm": 0.6487559466739592, "learning_rate": 1.4308943089430896e-05, "loss": 0.7244, "step": 44 }, { "epoch": 0.18227848101265823, "grad_norm": 0.632819841212341, "learning_rate": 1.4634146341463415e-05, "loss": 0.7011, "step": 45 }, { "epoch": 0.18632911392405063, "grad_norm": 0.7506389801814598, "learning_rate": 1.4959349593495935e-05, "loss": 0.7207, "step": 46 }, { "epoch": 0.19037974683544304, "grad_norm": 0.6782737973938024, "learning_rate": 1.528455284552846e-05, "loss": 0.7445, "step": 47 }, { "epoch": 0.19443037974683544, "grad_norm": 0.6238562192792084, "learning_rate": 1.5609756097560978e-05, "loss": 0.7316, "step": 48 }, { "epoch": 0.19848101265822785, "grad_norm": 0.6675602899193114, "learning_rate": 1.5934959349593496e-05, "loss": 0.7342, "step": 49 }, { "epoch": 0.20253164556962025, "grad_norm": 0.6717842029712705, "learning_rate": 1.6260162601626018e-05, "loss": 0.7026, "step": 50 }, { "epoch": 0.20658227848101265, "grad_norm": 0.6439785330422865, "learning_rate": 1.6585365853658537e-05, "loss": 0.709, "step": 51 }, { "epoch": 0.21063291139240506, "grad_norm": 0.7339608666891085, "learning_rate": 1.691056910569106e-05, "loss": 0.7187, "step": 52 }, { "epoch": 0.21468354430379746, "grad_norm": 0.6853317154385894, "learning_rate": 1.7235772357723578e-05, "loss": 0.6995, "step": 53 }, { "epoch": 0.21873417721518987, "grad_norm": 0.9394631732328259, "learning_rate": 1.75609756097561e-05, "loss": 0.7193, "step": 54 }, { "epoch": 0.22278481012658227, "grad_norm": 0.6349375314789558, "learning_rate": 1.788617886178862e-05, "loss": 0.6972, "step": 55 }, { "epoch": 0.22683544303797468, "grad_norm": 0.7042117692040308, "learning_rate": 1.821138211382114e-05, "loss": 0.7002, "step": 56 }, { "epoch": 0.23088607594936708, "grad_norm": 0.6531828212002992, "learning_rate": 1.8536585365853663e-05, "loss": 0.7233, "step": 57 }, { "epoch": 0.23493670886075949, "grad_norm": 0.6836214633148392, "learning_rate": 1.886178861788618e-05, "loss": 0.7009, "step": 58 }, { "epoch": 0.2389873417721519, "grad_norm": 0.686109699718888, "learning_rate": 1.91869918699187e-05, "loss": 0.6986, "step": 59 }, { "epoch": 0.2430379746835443, "grad_norm": 0.6914660113022967, "learning_rate": 1.9512195121951222e-05, "loss": 0.6832, "step": 60 }, { "epoch": 0.2470886075949367, "grad_norm": 0.6882774048043362, "learning_rate": 1.983739837398374e-05, "loss": 0.7065, "step": 61 }, { "epoch": 0.25113924050632913, "grad_norm": 0.7676871527490561, "learning_rate": 2.016260162601626e-05, "loss": 0.6887, "step": 62 }, { "epoch": 0.25518987341772154, "grad_norm": 0.7841437735419633, "learning_rate": 2.048780487804878e-05, "loss": 0.6842, "step": 63 }, { "epoch": 0.25924050632911394, "grad_norm": 0.7365455498426784, "learning_rate": 2.0813008130081303e-05, "loss": 0.6868, "step": 64 }, { "epoch": 0.26329113924050634, "grad_norm": 0.7734378818904084, "learning_rate": 2.1138211382113822e-05, "loss": 0.7046, "step": 65 }, { "epoch": 0.26734177215189875, "grad_norm": 0.9178822184359572, "learning_rate": 2.1463414634146344e-05, "loss": 0.7262, "step": 66 }, { "epoch": 0.27139240506329115, "grad_norm": 0.7968373793679485, "learning_rate": 2.1788617886178863e-05, "loss": 0.704, "step": 67 }, { "epoch": 0.27544303797468356, "grad_norm": 0.7670971218532247, "learning_rate": 2.2113821138211385e-05, "loss": 0.7086, "step": 68 }, { "epoch": 0.27949367088607596, "grad_norm": 0.7538062718852307, "learning_rate": 2.2439024390243907e-05, "loss": 0.698, "step": 69 }, { "epoch": 0.28354430379746837, "grad_norm": 0.8140066600052998, "learning_rate": 2.2764227642276426e-05, "loss": 0.6721, "step": 70 }, { "epoch": 0.28759493670886077, "grad_norm": 0.8959616751516448, "learning_rate": 2.3089430894308948e-05, "loss": 0.6913, "step": 71 }, { "epoch": 0.2916455696202532, "grad_norm": 1.070075671221579, "learning_rate": 2.3414634146341463e-05, "loss": 0.6733, "step": 72 }, { "epoch": 0.2956962025316456, "grad_norm": 0.8514732513315937, "learning_rate": 2.3739837398373985e-05, "loss": 0.6996, "step": 73 }, { "epoch": 0.299746835443038, "grad_norm": 1.1900249172533004, "learning_rate": 2.4065040650406507e-05, "loss": 0.7174, "step": 74 }, { "epoch": 0.3037974683544304, "grad_norm": 0.8497258450382819, "learning_rate": 2.4390243902439026e-05, "loss": 0.664, "step": 75 }, { "epoch": 0.3078481012658228, "grad_norm": 1.3176725372196318, "learning_rate": 2.4715447154471548e-05, "loss": 0.6907, "step": 76 }, { "epoch": 0.3118987341772152, "grad_norm": 0.8035130425958215, "learning_rate": 2.5040650406504066e-05, "loss": 0.6973, "step": 77 }, { "epoch": 0.3159493670886076, "grad_norm": 1.1569084986914338, "learning_rate": 2.536585365853659e-05, "loss": 0.6888, "step": 78 }, { "epoch": 0.32, "grad_norm": 0.8271018768757059, "learning_rate": 2.569105691056911e-05, "loss": 0.7103, "step": 79 }, { "epoch": 0.3240506329113924, "grad_norm": 0.9396250712538629, "learning_rate": 2.601626016260163e-05, "loss": 0.7095, "step": 80 }, { "epoch": 0.3281012658227848, "grad_norm": 0.8750498646704241, "learning_rate": 2.634146341463415e-05, "loss": 0.7185, "step": 81 }, { "epoch": 0.3321518987341772, "grad_norm": 0.6995387463832662, "learning_rate": 2.6666666666666667e-05, "loss": 0.6719, "step": 82 }, { "epoch": 0.3362025316455696, "grad_norm": 0.847458556884751, "learning_rate": 2.699186991869919e-05, "loss": 0.7115, "step": 83 }, { "epoch": 0.34025316455696203, "grad_norm": 0.8303711288286559, "learning_rate": 2.731707317073171e-05, "loss": 0.701, "step": 84 }, { "epoch": 0.34430379746835443, "grad_norm": 1.2387986994914604, "learning_rate": 2.764227642276423e-05, "loss": 0.6872, "step": 85 }, { "epoch": 0.34835443037974684, "grad_norm": 0.7478152995760373, "learning_rate": 2.796747967479675e-05, "loss": 0.6851, "step": 86 }, { "epoch": 0.35240506329113924, "grad_norm": 1.335941433666618, "learning_rate": 2.829268292682927e-05, "loss": 0.6877, "step": 87 }, { "epoch": 0.35645569620253165, "grad_norm": 0.6330537382887311, "learning_rate": 2.8617886178861792e-05, "loss": 0.6752, "step": 88 }, { "epoch": 0.36050632911392405, "grad_norm": 1.2509179573462177, "learning_rate": 2.8943089430894314e-05, "loss": 0.6814, "step": 89 }, { "epoch": 0.36455696202531646, "grad_norm": 0.7608908324670186, "learning_rate": 2.926829268292683e-05, "loss": 0.6658, "step": 90 }, { "epoch": 0.36860759493670886, "grad_norm": 1.2109025379178548, "learning_rate": 2.959349593495935e-05, "loss": 0.6961, "step": 91 }, { "epoch": 0.37265822784810126, "grad_norm": 0.8880051758743864, "learning_rate": 2.991869918699187e-05, "loss": 0.6942, "step": 92 }, { "epoch": 0.37670886075949367, "grad_norm": 0.9973189717213629, "learning_rate": 3.0243902439024392e-05, "loss": 0.6808, "step": 93 }, { "epoch": 0.3807594936708861, "grad_norm": 0.9167532847903516, "learning_rate": 3.056910569105692e-05, "loss": 0.7243, "step": 94 }, { "epoch": 0.3848101265822785, "grad_norm": 0.9375666668098264, "learning_rate": 3.089430894308943e-05, "loss": 0.6903, "step": 95 }, { "epoch": 0.3888607594936709, "grad_norm": 0.7624017661629794, "learning_rate": 3.1219512195121955e-05, "loss": 0.6911, "step": 96 }, { "epoch": 0.3929113924050633, "grad_norm": 0.946393333970265, "learning_rate": 3.154471544715447e-05, "loss": 0.6634, "step": 97 }, { "epoch": 0.3969620253164557, "grad_norm": 0.873286161756802, "learning_rate": 3.186991869918699e-05, "loss": 0.6815, "step": 98 }, { "epoch": 0.4010126582278481, "grad_norm": 0.6555486094954284, "learning_rate": 3.2195121951219514e-05, "loss": 0.6941, "step": 99 }, { "epoch": 0.4050632911392405, "grad_norm": 0.976208136664578, "learning_rate": 3.2520325203252037e-05, "loss": 0.6844, "step": 100 }, { "epoch": 0.4091139240506329, "grad_norm": 0.8140634824219108, "learning_rate": 3.284552845528456e-05, "loss": 0.7212, "step": 101 }, { "epoch": 0.4131645569620253, "grad_norm": 1.0265613411611287, "learning_rate": 3.3170731707317074e-05, "loss": 0.6842, "step": 102 }, { "epoch": 0.4172151898734177, "grad_norm": 1.0363609187071423, "learning_rate": 3.3495934959349596e-05, "loss": 0.7144, "step": 103 }, { "epoch": 0.4212658227848101, "grad_norm": 0.9610663640771493, "learning_rate": 3.382113821138212e-05, "loss": 0.699, "step": 104 }, { "epoch": 0.4253164556962025, "grad_norm": 1.0076106751512468, "learning_rate": 3.414634146341463e-05, "loss": 0.6867, "step": 105 }, { "epoch": 0.4293670886075949, "grad_norm": 1.043084916203189, "learning_rate": 3.4471544715447155e-05, "loss": 0.6886, "step": 106 }, { "epoch": 0.43341772151898733, "grad_norm": 0.919755199596602, "learning_rate": 3.479674796747968e-05, "loss": 0.6973, "step": 107 }, { "epoch": 0.43746835443037974, "grad_norm": 0.7204830083696956, "learning_rate": 3.51219512195122e-05, "loss": 0.6542, "step": 108 }, { "epoch": 0.44151898734177214, "grad_norm": 0.9168849019911613, "learning_rate": 3.544715447154472e-05, "loss": 0.6734, "step": 109 }, { "epoch": 0.44556962025316454, "grad_norm": 0.8306747758408529, "learning_rate": 3.577235772357724e-05, "loss": 0.7149, "step": 110 }, { "epoch": 0.44962025316455695, "grad_norm": 0.9684191881201694, "learning_rate": 3.609756097560976e-05, "loss": 0.6684, "step": 111 }, { "epoch": 0.45367088607594935, "grad_norm": 0.7736072095006138, "learning_rate": 3.642276422764228e-05, "loss": 0.6761, "step": 112 }, { "epoch": 0.45772151898734176, "grad_norm": 0.8738521118062466, "learning_rate": 3.67479674796748e-05, "loss": 0.6816, "step": 113 }, { "epoch": 0.46177215189873416, "grad_norm": 0.8611840558849828, "learning_rate": 3.7073170731707325e-05, "loss": 0.6676, "step": 114 }, { "epoch": 0.46582278481012657, "grad_norm": 0.7347580448942398, "learning_rate": 3.739837398373984e-05, "loss": 0.6989, "step": 115 }, { "epoch": 0.46987341772151897, "grad_norm": 0.7470601839758275, "learning_rate": 3.772357723577236e-05, "loss": 0.6995, "step": 116 }, { "epoch": 0.4739240506329114, "grad_norm": 0.680786124585886, "learning_rate": 3.804878048780488e-05, "loss": 0.6836, "step": 117 }, { "epoch": 0.4779746835443038, "grad_norm": 0.7617735516995223, "learning_rate": 3.83739837398374e-05, "loss": 0.6594, "step": 118 }, { "epoch": 0.4820253164556962, "grad_norm": 0.6462374937281181, "learning_rate": 3.869918699186992e-05, "loss": 0.6819, "step": 119 }, { "epoch": 0.4860759493670886, "grad_norm": 0.742593920233833, "learning_rate": 3.9024390243902444e-05, "loss": 0.6881, "step": 120 }, { "epoch": 0.490126582278481, "grad_norm": 0.7250728488392657, "learning_rate": 3.9349593495934966e-05, "loss": 0.6841, "step": 121 }, { "epoch": 0.4941772151898734, "grad_norm": 0.6916073154393162, "learning_rate": 3.967479674796748e-05, "loss": 0.6864, "step": 122 }, { "epoch": 0.4982278481012658, "grad_norm": 0.726417949810588, "learning_rate": 4e-05, "loss": 0.6764, "step": 123 }, { "epoch": 0.5022784810126583, "grad_norm": 0.8000058724796187, "learning_rate": 3.999991946137476e-05, "loss": 0.7124, "step": 124 }, { "epoch": 0.5063291139240507, "grad_norm": 0.7052521311421759, "learning_rate": 3.999967784614766e-05, "loss": 0.6968, "step": 125 }, { "epoch": 0.5103797468354431, "grad_norm": 0.7883859862615914, "learning_rate": 3.9999275156264656e-05, "loss": 0.6781, "step": 126 }, { "epoch": 0.5144303797468355, "grad_norm": 0.7534878603869163, "learning_rate": 3.999871139496895e-05, "loss": 0.6717, "step": 127 }, { "epoch": 0.5184810126582279, "grad_norm": 0.677228661362829, "learning_rate": 3.9997986566800995e-05, "loss": 0.7009, "step": 128 }, { "epoch": 0.5225316455696203, "grad_norm": 0.6595238431596258, "learning_rate": 3.999710067759846e-05, "loss": 0.6844, "step": 129 }, { "epoch": 0.5265822784810127, "grad_norm": 0.6738218061963113, "learning_rate": 3.999605373449617e-05, "loss": 0.6715, "step": 130 }, { "epoch": 0.5306329113924051, "grad_norm": 0.6994467107329644, "learning_rate": 3.9994845745926075e-05, "loss": 0.6661, "step": 131 }, { "epoch": 0.5346835443037975, "grad_norm": 0.6476183554376367, "learning_rate": 3.999347672161713e-05, "loss": 0.6727, "step": 132 }, { "epoch": 0.5387341772151899, "grad_norm": 0.6182624838073317, "learning_rate": 3.999194667259528e-05, "loss": 0.6612, "step": 133 }, { "epoch": 0.5427848101265823, "grad_norm": 0.6742414747198355, "learning_rate": 3.999025561118334e-05, "loss": 0.6908, "step": 134 }, { "epoch": 0.5468354430379747, "grad_norm": 0.6454706436107736, "learning_rate": 3.998840355100086e-05, "loss": 0.7048, "step": 135 }, { "epoch": 0.5508860759493671, "grad_norm": 0.6613598308901385, "learning_rate": 3.998639050696409e-05, "loss": 0.7029, "step": 136 }, { "epoch": 0.5549367088607595, "grad_norm": 0.6773624268416872, "learning_rate": 3.998421649528582e-05, "loss": 0.6778, "step": 137 }, { "epoch": 0.5589873417721519, "grad_norm": 0.7673500365908585, "learning_rate": 3.9981881533475234e-05, "loss": 0.6994, "step": 138 }, { "epoch": 0.5630379746835443, "grad_norm": 0.6374510331729255, "learning_rate": 3.997938564033779e-05, "loss": 0.6827, "step": 139 }, { "epoch": 0.5670886075949367, "grad_norm": 0.6261245901757932, "learning_rate": 3.9976728835975064e-05, "loss": 0.7125, "step": 140 }, { "epoch": 0.5711392405063291, "grad_norm": 0.8100673106000674, "learning_rate": 3.9973911141784605e-05, "loss": 0.6893, "step": 141 }, { "epoch": 0.5751898734177215, "grad_norm": 0.8321720651523674, "learning_rate": 3.997093258045973e-05, "loss": 0.6983, "step": 142 }, { "epoch": 0.579240506329114, "grad_norm": 0.9805703083446017, "learning_rate": 3.996779317598936e-05, "loss": 0.6904, "step": 143 }, { "epoch": 0.5832911392405064, "grad_norm": 0.7313129470147169, "learning_rate": 3.996449295365782e-05, "loss": 0.6669, "step": 144 }, { "epoch": 0.5873417721518988, "grad_norm": 0.9078626665370907, "learning_rate": 3.996103194004467e-05, "loss": 0.6811, "step": 145 }, { "epoch": 0.5913924050632912, "grad_norm": 0.7278901456691977, "learning_rate": 3.995741016302441e-05, "loss": 0.6659, "step": 146 }, { "epoch": 0.5954430379746836, "grad_norm": 0.9622939836204724, "learning_rate": 3.9953627651766364e-05, "loss": 0.6827, "step": 147 }, { "epoch": 0.599493670886076, "grad_norm": 0.7552772131703843, "learning_rate": 3.9949684436734325e-05, "loss": 0.6552, "step": 148 }, { "epoch": 0.6035443037974684, "grad_norm": 0.9791242979598841, "learning_rate": 3.994558054968643e-05, "loss": 0.6877, "step": 149 }, { "epoch": 0.6075949367088608, "grad_norm": 0.7794266665413238, "learning_rate": 3.994131602367481e-05, "loss": 0.7164, "step": 150 }, { "epoch": 0.6116455696202532, "grad_norm": 0.840923069208803, "learning_rate": 3.9936890893045376e-05, "loss": 0.7014, "step": 151 }, { "epoch": 0.6156962025316456, "grad_norm": 0.6463436407470156, "learning_rate": 3.993230519343752e-05, "loss": 0.6842, "step": 152 }, { "epoch": 0.619746835443038, "grad_norm": 0.6731550881852065, "learning_rate": 3.992755896178383e-05, "loss": 0.6637, "step": 153 }, { "epoch": 0.6237974683544304, "grad_norm": 0.8942351033880038, "learning_rate": 3.992265223630981e-05, "loss": 0.6872, "step": 154 }, { "epoch": 0.6278481012658228, "grad_norm": 0.6757715422786703, "learning_rate": 3.991758505653355e-05, "loss": 0.6581, "step": 155 }, { "epoch": 0.6318987341772152, "grad_norm": 0.5647518481616806, "learning_rate": 3.991235746326543e-05, "loss": 0.6958, "step": 156 }, { "epoch": 0.6359493670886076, "grad_norm": 0.7246308725811692, "learning_rate": 3.9906969498607745e-05, "loss": 0.6378, "step": 157 }, { "epoch": 0.64, "grad_norm": 0.7779129729572584, "learning_rate": 3.990142120595444e-05, "loss": 0.6819, "step": 158 }, { "epoch": 0.6440506329113924, "grad_norm": 0.6752944329837975, "learning_rate": 3.98957126299907e-05, "loss": 0.6869, "step": 159 }, { "epoch": 0.6481012658227848, "grad_norm": 5.610742620704916, "learning_rate": 3.9889843816692596e-05, "loss": 0.662, "step": 160 }, { "epoch": 0.6521518987341772, "grad_norm": 0.8654431187826719, "learning_rate": 3.9883814813326766e-05, "loss": 0.6975, "step": 161 }, { "epoch": 0.6562025316455696, "grad_norm": 0.6368079861410184, "learning_rate": 3.9877625668449956e-05, "loss": 0.6709, "step": 162 }, { "epoch": 0.660253164556962, "grad_norm": 0.6545396912448493, "learning_rate": 3.98712764319087e-05, "loss": 0.673, "step": 163 }, { "epoch": 0.6643037974683544, "grad_norm": 0.8087547473001648, "learning_rate": 3.9864767154838864e-05, "loss": 0.6753, "step": 164 }, { "epoch": 0.6683544303797468, "grad_norm": 0.540136333394773, "learning_rate": 3.9858097889665277e-05, "loss": 0.6767, "step": 165 }, { "epoch": 0.6724050632911392, "grad_norm": 0.7922590877666942, "learning_rate": 3.985126869010129e-05, "loss": 0.6817, "step": 166 }, { "epoch": 0.6764556962025317, "grad_norm": 0.5989471213206892, "learning_rate": 3.984427961114833e-05, "loss": 0.64, "step": 167 }, { "epoch": 0.6805063291139241, "grad_norm": 0.7606407446379871, "learning_rate": 3.9837130709095475e-05, "loss": 0.6898, "step": 168 }, { "epoch": 0.6845569620253165, "grad_norm": 0.6182395605430221, "learning_rate": 3.982982204151901e-05, "loss": 0.6402, "step": 169 }, { "epoch": 0.6886075949367089, "grad_norm": 0.6667235519760539, "learning_rate": 3.982235366728193e-05, "loss": 0.7039, "step": 170 }, { "epoch": 0.6926582278481013, "grad_norm": 0.6198201705892458, "learning_rate": 3.9814725646533505e-05, "loss": 0.679, "step": 171 }, { "epoch": 0.6967088607594937, "grad_norm": 0.7364491625115143, "learning_rate": 3.9806938040708746e-05, "loss": 0.6591, "step": 172 }, { "epoch": 0.7007594936708861, "grad_norm": 0.6664624032435783, "learning_rate": 3.9798990912527976e-05, "loss": 0.6662, "step": 173 }, { "epoch": 0.7048101265822785, "grad_norm": 0.5677832897749546, "learning_rate": 3.979088432599627e-05, "loss": 0.6406, "step": 174 }, { "epoch": 0.7088607594936709, "grad_norm": 0.5980857184826737, "learning_rate": 3.9782618346402964e-05, "loss": 0.6639, "step": 175 }, { "epoch": 0.7129113924050633, "grad_norm": 0.6523925572794472, "learning_rate": 3.977419304032111e-05, "loss": 0.6888, "step": 176 }, { "epoch": 0.7169620253164557, "grad_norm": 0.5999799860179683, "learning_rate": 3.976560847560697e-05, "loss": 0.6592, "step": 177 }, { "epoch": 0.7210126582278481, "grad_norm": 0.7024366481795445, "learning_rate": 3.9756864721399456e-05, "loss": 0.6858, "step": 178 }, { "epoch": 0.7250632911392405, "grad_norm": 0.6183736119358191, "learning_rate": 3.974796184811956e-05, "loss": 0.688, "step": 179 }, { "epoch": 0.7291139240506329, "grad_norm": 0.5953086175434832, "learning_rate": 3.973889992746979e-05, "loss": 0.6774, "step": 180 }, { "epoch": 0.7331645569620253, "grad_norm": 0.6676963526518802, "learning_rate": 3.972967903243361e-05, "loss": 0.6987, "step": 181 }, { "epoch": 0.7372151898734177, "grad_norm": 0.5948303493417515, "learning_rate": 3.972029923727486e-05, "loss": 0.6572, "step": 182 }, { "epoch": 0.7412658227848101, "grad_norm": 0.7160970411925051, "learning_rate": 3.971076061753709e-05, "loss": 0.6432, "step": 183 }, { "epoch": 0.7453164556962025, "grad_norm": 0.6725230309873095, "learning_rate": 3.9701063250043066e-05, "loss": 0.6635, "step": 184 }, { "epoch": 0.7493670886075949, "grad_norm": 0.6546158260468927, "learning_rate": 3.969120721289402e-05, "loss": 0.6532, "step": 185 }, { "epoch": 0.7534177215189873, "grad_norm": 0.5674159767416121, "learning_rate": 3.9681192585469146e-05, "loss": 0.6727, "step": 186 }, { "epoch": 0.7574683544303797, "grad_norm": 0.7356622949385395, "learning_rate": 3.9671019448424865e-05, "loss": 0.6801, "step": 187 }, { "epoch": 0.7615189873417721, "grad_norm": 0.5797481511466879, "learning_rate": 3.966068788369422e-05, "loss": 0.6158, "step": 188 }, { "epoch": 0.7655696202531646, "grad_norm": 0.5838767195321822, "learning_rate": 3.965019797448622e-05, "loss": 0.6536, "step": 189 }, { "epoch": 0.769620253164557, "grad_norm": 0.5149489886519154, "learning_rate": 3.963954980528515e-05, "loss": 0.6873, "step": 190 }, { "epoch": 0.7736708860759494, "grad_norm": 0.5898388763632239, "learning_rate": 3.9628743461849905e-05, "loss": 0.6398, "step": 191 }, { "epoch": 0.7777215189873418, "grad_norm": 0.6157396991285736, "learning_rate": 3.961777903121329e-05, "loss": 0.6825, "step": 192 }, { "epoch": 0.7817721518987342, "grad_norm": 0.4925487749884519, "learning_rate": 3.960665660168131e-05, "loss": 0.6393, "step": 193 }, { "epoch": 0.7858227848101266, "grad_norm": 0.6970344526093646, "learning_rate": 3.9595376262832485e-05, "loss": 0.6395, "step": 194 }, { "epoch": 0.789873417721519, "grad_norm": 0.5516724463677612, "learning_rate": 3.9583938105517127e-05, "loss": 0.6384, "step": 195 }, { "epoch": 0.7939240506329114, "grad_norm": 0.7988024776231932, "learning_rate": 3.957234222185657e-05, "loss": 0.6648, "step": 196 }, { "epoch": 0.7979746835443038, "grad_norm": 0.5236288690316273, "learning_rate": 3.9560588705242474e-05, "loss": 0.6604, "step": 197 }, { "epoch": 0.8020253164556962, "grad_norm": 0.7161437695760979, "learning_rate": 3.954867765033605e-05, "loss": 0.6394, "step": 198 }, { "epoch": 0.8060759493670886, "grad_norm": 0.5655431923215647, "learning_rate": 3.953660915306728e-05, "loss": 0.6297, "step": 199 }, { "epoch": 0.810126582278481, "grad_norm": 0.720264699961498, "learning_rate": 3.952438331063419e-05, "loss": 0.6833, "step": 200 }, { "epoch": 0.8141772151898734, "grad_norm": 0.7094308127186798, "learning_rate": 3.951200022150205e-05, "loss": 0.6759, "step": 201 }, { "epoch": 0.8182278481012658, "grad_norm": 0.6751018061722899, "learning_rate": 3.949945998540253e-05, "loss": 0.657, "step": 202 }, { "epoch": 0.8222784810126582, "grad_norm": 0.6630844565822631, "learning_rate": 3.9486762703332993e-05, "loss": 0.6724, "step": 203 }, { "epoch": 0.8263291139240506, "grad_norm": 0.6235530910083587, "learning_rate": 3.947390847755559e-05, "loss": 0.6835, "step": 204 }, { "epoch": 0.830379746835443, "grad_norm": 0.6014415291679723, "learning_rate": 3.946089741159648e-05, "loss": 0.6643, "step": 205 }, { "epoch": 0.8344303797468354, "grad_norm": 0.5575051233715942, "learning_rate": 3.944772961024501e-05, "loss": 0.6423, "step": 206 }, { "epoch": 0.8384810126582278, "grad_norm": 0.5793968075383072, "learning_rate": 3.943440517955285e-05, "loss": 0.6685, "step": 207 }, { "epoch": 0.8425316455696202, "grad_norm": 0.6168513427367881, "learning_rate": 3.9420924226833126e-05, "loss": 0.6666, "step": 208 }, { "epoch": 0.8465822784810126, "grad_norm": 0.5565509021546496, "learning_rate": 3.9407286860659566e-05, "loss": 0.6149, "step": 209 }, { "epoch": 0.850632911392405, "grad_norm": 0.6099464459853731, "learning_rate": 3.9393493190865657e-05, "loss": 0.6731, "step": 210 }, { "epoch": 0.8546835443037974, "grad_norm": 0.6436579759393125, "learning_rate": 3.937954332854371e-05, "loss": 0.6687, "step": 211 }, { "epoch": 0.8587341772151899, "grad_norm": 0.5269532603288167, "learning_rate": 3.9365437386044016e-05, "loss": 0.6446, "step": 212 }, { "epoch": 0.8627848101265823, "grad_norm": 0.595706695651506, "learning_rate": 3.935117547697387e-05, "loss": 0.6475, "step": 213 }, { "epoch": 0.8668354430379747, "grad_norm": 0.6603698997160408, "learning_rate": 3.933675771619675e-05, "loss": 0.6686, "step": 214 }, { "epoch": 0.8708860759493671, "grad_norm": 0.647098460507547, "learning_rate": 3.932218421983131e-05, "loss": 0.7024, "step": 215 }, { "epoch": 0.8749367088607595, "grad_norm": 0.5147277368565963, "learning_rate": 3.9307455105250484e-05, "loss": 0.6466, "step": 216 }, { "epoch": 0.8789873417721519, "grad_norm": 0.6909093880706737, "learning_rate": 3.929257049108054e-05, "loss": 0.668, "step": 217 }, { "epoch": 0.8830379746835443, "grad_norm": 0.5369874421330744, "learning_rate": 3.927753049720011e-05, "loss": 0.6762, "step": 218 }, { "epoch": 0.8870886075949367, "grad_norm": 0.6975198756188459, "learning_rate": 3.9262335244739234e-05, "loss": 0.6446, "step": 219 }, { "epoch": 0.8911392405063291, "grad_norm": 0.5821568620396593, "learning_rate": 3.92469848560784e-05, "loss": 0.6548, "step": 220 }, { "epoch": 0.8951898734177215, "grad_norm": 0.7468316319398036, "learning_rate": 3.923147945484751e-05, "loss": 0.6748, "step": 221 }, { "epoch": 0.8992405063291139, "grad_norm": 0.5840315828031472, "learning_rate": 3.9215819165924956e-05, "loss": 0.637, "step": 222 }, { "epoch": 0.9032911392405063, "grad_norm": 0.5424263400513026, "learning_rate": 3.920000411543654e-05, "loss": 0.6733, "step": 223 }, { "epoch": 0.9073417721518987, "grad_norm": 0.49685609171275147, "learning_rate": 3.9184034430754495e-05, "loss": 0.6498, "step": 224 }, { "epoch": 0.9113924050632911, "grad_norm": 0.5303490784502848, "learning_rate": 3.916791024049648e-05, "loss": 0.6603, "step": 225 }, { "epoch": 0.9154430379746835, "grad_norm": 0.4826361031607442, "learning_rate": 3.91516316745245e-05, "loss": 0.6466, "step": 226 }, { "epoch": 0.9194936708860759, "grad_norm": 0.43893204972884586, "learning_rate": 3.913519886394389e-05, "loss": 0.658, "step": 227 }, { "epoch": 0.9235443037974683, "grad_norm": 0.546567156294626, "learning_rate": 3.911861194110225e-05, "loss": 0.6672, "step": 228 }, { "epoch": 0.9275949367088607, "grad_norm": 0.7183228468242651, "learning_rate": 3.910187103958837e-05, "loss": 0.6781, "step": 229 }, { "epoch": 0.9316455696202531, "grad_norm": 0.6451040294326185, "learning_rate": 3.908497629423117e-05, "loss": 0.6411, "step": 230 }, { "epoch": 0.9356962025316455, "grad_norm": 0.6831492053422364, "learning_rate": 3.9067927841098614e-05, "loss": 0.6603, "step": 231 }, { "epoch": 0.9397468354430379, "grad_norm": 0.5165391138605248, "learning_rate": 3.9050725817496594e-05, "loss": 0.6598, "step": 232 }, { "epoch": 0.9437974683544303, "grad_norm": 0.5422833289667747, "learning_rate": 3.9033370361967844e-05, "loss": 0.6425, "step": 233 }, { "epoch": 0.9478481012658228, "grad_norm": 0.6088237352638864, "learning_rate": 3.901586161429081e-05, "loss": 0.6528, "step": 234 }, { "epoch": 0.9518987341772152, "grad_norm": 0.5367403335664164, "learning_rate": 3.8998199715478545e-05, "loss": 0.6767, "step": 235 }, { "epoch": 0.9559493670886076, "grad_norm": 0.5968556405744356, "learning_rate": 3.8980384807777564e-05, "loss": 0.6593, "step": 236 }, { "epoch": 0.96, "grad_norm": 0.5875258961055091, "learning_rate": 3.896241703466667e-05, "loss": 0.6437, "step": 237 }, { "epoch": 0.9640506329113924, "grad_norm": 0.5311398634818798, "learning_rate": 3.894429654085585e-05, "loss": 0.6115, "step": 238 }, { "epoch": 0.9681012658227848, "grad_norm": 0.5926264837500645, "learning_rate": 3.892602347228505e-05, "loss": 0.648, "step": 239 }, { "epoch": 0.9721518987341772, "grad_norm": 0.5499472561298915, "learning_rate": 3.890759797612307e-05, "loss": 0.6651, "step": 240 }, { "epoch": 0.9762025316455696, "grad_norm": 0.4982435791678508, "learning_rate": 3.888902020076632e-05, "loss": 0.649, "step": 241 }, { "epoch": 0.980253164556962, "grad_norm": 0.5844170802403849, "learning_rate": 3.887029029583764e-05, "loss": 0.6548, "step": 242 }, { "epoch": 0.9843037974683544, "grad_norm": 0.4622080536527139, "learning_rate": 3.8851408412185125e-05, "loss": 0.6685, "step": 243 }, { "epoch": 0.9883544303797468, "grad_norm": 0.5951107924364848, "learning_rate": 3.8832374701880855e-05, "loss": 0.6344, "step": 244 }, { "epoch": 0.9924050632911392, "grad_norm": 0.518406832758173, "learning_rate": 3.881318931821972e-05, "loss": 0.6156, "step": 245 }, { "epoch": 0.9964556962025316, "grad_norm": 0.6575263354743837, "learning_rate": 3.879385241571817e-05, "loss": 0.6631, "step": 246 }, { "epoch": 1.000506329113924, "grad_norm": 0.5778524159278089, "learning_rate": 3.8774364150112955e-05, "loss": 0.6504, "step": 247 }, { "epoch": 1.0045569620253165, "grad_norm": 0.6179359910798646, "learning_rate": 3.8754724678359884e-05, "loss": 0.5351, "step": 248 }, { "epoch": 1.0086075949367088, "grad_norm": 0.5385129106053866, "learning_rate": 3.873493415863256e-05, "loss": 0.5299, "step": 249 }, { "epoch": 1.0126582278481013, "grad_norm": 0.719896962776251, "learning_rate": 3.871499275032111e-05, "loss": 0.5048, "step": 250 }, { "epoch": 1.0167088607594936, "grad_norm": 0.6767141534263791, "learning_rate": 3.869490061403091e-05, "loss": 0.5492, "step": 251 }, { "epoch": 1.0207594936708861, "grad_norm": 0.6222384582565677, "learning_rate": 3.867465791158124e-05, "loss": 0.5392, "step": 252 }, { "epoch": 1.0248101265822784, "grad_norm": 0.6213812031868863, "learning_rate": 3.865426480600407e-05, "loss": 0.5135, "step": 253 }, { "epoch": 1.028860759493671, "grad_norm": 0.6060704875684018, "learning_rate": 3.863372146154264e-05, "loss": 0.5361, "step": 254 }, { "epoch": 1.0329113924050632, "grad_norm": 0.5787340201062146, "learning_rate": 3.861302804365024e-05, "loss": 0.5304, "step": 255 }, { "epoch": 1.0369620253164558, "grad_norm": 0.6178328023052944, "learning_rate": 3.85921847189888e-05, "loss": 0.523, "step": 256 }, { "epoch": 1.041012658227848, "grad_norm": 0.5275590639611256, "learning_rate": 3.85711916554276e-05, "loss": 0.5094, "step": 257 }, { "epoch": 1.0450632911392406, "grad_norm": 0.6351481350852203, "learning_rate": 3.85500490220419e-05, "loss": 0.5369, "step": 258 }, { "epoch": 1.0491139240506329, "grad_norm": 0.7213760298740912, "learning_rate": 3.852875698911154e-05, "loss": 0.5469, "step": 259 }, { "epoch": 1.0531645569620254, "grad_norm": 0.561866669313103, "learning_rate": 3.850731572811963e-05, "loss": 0.5168, "step": 260 }, { "epoch": 1.0572151898734177, "grad_norm": 0.7657854324487646, "learning_rate": 3.848572541175116e-05, "loss": 0.5718, "step": 261 }, { "epoch": 1.0612658227848102, "grad_norm": 0.5888077222996666, "learning_rate": 3.846398621389154e-05, "loss": 0.5077, "step": 262 }, { "epoch": 1.0653164556962025, "grad_norm": 0.5890366316660003, "learning_rate": 3.84420983096253e-05, "loss": 0.5223, "step": 263 }, { "epoch": 1.069367088607595, "grad_norm": 0.6629229687351528, "learning_rate": 3.8420061875234606e-05, "loss": 0.5091, "step": 264 }, { "epoch": 1.0734177215189873, "grad_norm": 0.5413929759956394, "learning_rate": 3.839787708819787e-05, "loss": 0.5207, "step": 265 }, { "epoch": 1.0774683544303798, "grad_norm": 0.6881657618293532, "learning_rate": 3.8375544127188325e-05, "loss": 0.5595, "step": 266 }, { "epoch": 1.081518987341772, "grad_norm": 0.5602496092167703, "learning_rate": 3.8353063172072564e-05, "loss": 0.5377, "step": 267 }, { "epoch": 1.0855696202531646, "grad_norm": 0.6384417504353617, "learning_rate": 3.8330434403909105e-05, "loss": 0.5377, "step": 268 }, { "epoch": 1.089620253164557, "grad_norm": 0.6189465243874444, "learning_rate": 3.8307658004946934e-05, "loss": 0.5282, "step": 269 }, { "epoch": 1.0936708860759494, "grad_norm": 0.5847489695036894, "learning_rate": 3.8284734158624046e-05, "loss": 0.5416, "step": 270 }, { "epoch": 1.0977215189873417, "grad_norm": 0.5914090937895616, "learning_rate": 3.826166304956594e-05, "loss": 0.5325, "step": 271 }, { "epoch": 1.1017721518987342, "grad_norm": 0.6166546162024094, "learning_rate": 3.8238444863584164e-05, "loss": 0.5443, "step": 272 }, { "epoch": 1.1058227848101265, "grad_norm": 0.5756423386291802, "learning_rate": 3.821507978767479e-05, "loss": 0.533, "step": 273 }, { "epoch": 1.109873417721519, "grad_norm": 0.5720946394394059, "learning_rate": 3.819156801001693e-05, "loss": 0.5083, "step": 274 }, { "epoch": 1.1139240506329113, "grad_norm": 0.5116006087819647, "learning_rate": 3.816790971997121e-05, "loss": 0.5477, "step": 275 }, { "epoch": 1.1179746835443038, "grad_norm": 0.5923287857933178, "learning_rate": 3.8144105108078246e-05, "loss": 0.5341, "step": 276 }, { "epoch": 1.1220253164556961, "grad_norm": 0.5582875072081221, "learning_rate": 3.81201543660571e-05, "loss": 0.5154, "step": 277 }, { "epoch": 1.1260759493670887, "grad_norm": 0.5517232130052614, "learning_rate": 3.809605768680377e-05, "loss": 0.5237, "step": 278 }, { "epoch": 1.130126582278481, "grad_norm": 0.6004663059436123, "learning_rate": 3.807181526438958e-05, "loss": 0.5357, "step": 279 }, { "epoch": 1.1341772151898735, "grad_norm": 0.5532392731730488, "learning_rate": 3.8047427294059697e-05, "loss": 0.5182, "step": 280 }, { "epoch": 1.1382278481012658, "grad_norm": 0.5704165651569253, "learning_rate": 3.802289397223145e-05, "loss": 0.53, "step": 281 }, { "epoch": 1.1422784810126583, "grad_norm": 0.5865095425267831, "learning_rate": 3.7998215496492854e-05, "loss": 0.5598, "step": 282 }, { "epoch": 1.1463291139240506, "grad_norm": 0.5299763295905567, "learning_rate": 3.797339206560096e-05, "loss": 0.5189, "step": 283 }, { "epoch": 1.150379746835443, "grad_norm": 0.518433812218469, "learning_rate": 3.794842387948027e-05, "loss": 0.5199, "step": 284 }, { "epoch": 1.1544303797468354, "grad_norm": 0.5244361127918714, "learning_rate": 3.7923311139221114e-05, "loss": 0.5063, "step": 285 }, { "epoch": 1.158481012658228, "grad_norm": 0.5120084901742993, "learning_rate": 3.7898054047078054e-05, "loss": 0.4969, "step": 286 }, { "epoch": 1.1625316455696202, "grad_norm": 0.6666369943033509, "learning_rate": 3.787265280646825e-05, "loss": 0.5228, "step": 287 }, { "epoch": 1.1665822784810127, "grad_norm": 0.5435909030393782, "learning_rate": 3.7847107621969786e-05, "loss": 0.5253, "step": 288 }, { "epoch": 1.170632911392405, "grad_norm": 0.5328507344767943, "learning_rate": 3.7821418699320064e-05, "loss": 0.5242, "step": 289 }, { "epoch": 1.1746835443037975, "grad_norm": 0.6950310683841994, "learning_rate": 3.7795586245414145e-05, "loss": 0.5379, "step": 290 }, { "epoch": 1.1787341772151898, "grad_norm": 0.578906617808669, "learning_rate": 3.776961046830306e-05, "loss": 0.5061, "step": 291 }, { "epoch": 1.1827848101265823, "grad_norm": 0.5757752885998164, "learning_rate": 3.774349157719215e-05, "loss": 0.5148, "step": 292 }, { "epoch": 1.1868354430379746, "grad_norm": 0.5779129586459061, "learning_rate": 3.7717229782439365e-05, "loss": 0.5036, "step": 293 }, { "epoch": 1.1908860759493671, "grad_norm": 0.5145925526011017, "learning_rate": 3.769082529555359e-05, "loss": 0.5261, "step": 294 }, { "epoch": 1.1949367088607594, "grad_norm": 0.6083227998249197, "learning_rate": 3.766427832919294e-05, "loss": 0.5307, "step": 295 }, { "epoch": 1.198987341772152, "grad_norm": 0.50812761480643, "learning_rate": 3.7637589097163024e-05, "loss": 0.5168, "step": 296 }, { "epoch": 1.2030379746835442, "grad_norm": 0.6013662457150336, "learning_rate": 3.761075781441526e-05, "loss": 0.5408, "step": 297 }, { "epoch": 1.2070886075949367, "grad_norm": 0.5441463557568377, "learning_rate": 3.75837846970451e-05, "loss": 0.5477, "step": 298 }, { "epoch": 1.211139240506329, "grad_norm": 0.5454852868341121, "learning_rate": 3.755666996229032e-05, "loss": 0.5464, "step": 299 }, { "epoch": 1.2151898734177216, "grad_norm": 0.4968817758115996, "learning_rate": 3.752941382852927e-05, "loss": 0.5274, "step": 300 }, { "epoch": 1.2192405063291138, "grad_norm": 0.5252321630890004, "learning_rate": 3.7502016515279115e-05, "loss": 0.5297, "step": 301 }, { "epoch": 1.2232911392405064, "grad_norm": 0.5223202028547868, "learning_rate": 3.7474478243194043e-05, "loss": 0.556, "step": 302 }, { "epoch": 1.2273417721518987, "grad_norm": 0.5119206340731854, "learning_rate": 3.744679923406351e-05, "loss": 0.5177, "step": 303 }, { "epoch": 1.2313924050632912, "grad_norm": 0.5207439094431731, "learning_rate": 3.741897971081043e-05, "loss": 0.5483, "step": 304 }, { "epoch": 1.2354430379746835, "grad_norm": 0.518400600692831, "learning_rate": 3.739101989748946e-05, "loss": 0.53, "step": 305 }, { "epoch": 1.239493670886076, "grad_norm": 0.48780091070671944, "learning_rate": 3.7362920019285066e-05, "loss": 0.5171, "step": 306 }, { "epoch": 1.2435443037974683, "grad_norm": 0.5553469588959229, "learning_rate": 3.73346803025098e-05, "loss": 0.5199, "step": 307 }, { "epoch": 1.2475949367088608, "grad_norm": 0.49221173494947984, "learning_rate": 3.730630097460247e-05, "loss": 0.5297, "step": 308 }, { "epoch": 1.251645569620253, "grad_norm": 0.5634483874341486, "learning_rate": 3.727778226412628e-05, "loss": 0.5351, "step": 309 }, { "epoch": 1.2556962025316456, "grad_norm": 0.5636365864005927, "learning_rate": 3.7249124400767006e-05, "loss": 0.5203, "step": 310 }, { "epoch": 1.259746835443038, "grad_norm": 0.5084999371926144, "learning_rate": 3.722032761533114e-05, "loss": 0.5276, "step": 311 }, { "epoch": 1.2637974683544304, "grad_norm": 0.557514131575457, "learning_rate": 3.719139213974403e-05, "loss": 0.517, "step": 312 }, { "epoch": 1.2678481012658227, "grad_norm": 0.5490247970912866, "learning_rate": 3.7162318207048006e-05, "loss": 0.529, "step": 313 }, { "epoch": 1.2718987341772152, "grad_norm": 0.5126807444528656, "learning_rate": 3.713310605140055e-05, "loss": 0.5331, "step": 314 }, { "epoch": 1.2759493670886077, "grad_norm": 0.5183855763039241, "learning_rate": 3.710375590807233e-05, "loss": 0.5353, "step": 315 }, { "epoch": 1.28, "grad_norm": 0.6513052894884447, "learning_rate": 3.7074268013445365e-05, "loss": 0.5257, "step": 316 }, { "epoch": 1.2840506329113923, "grad_norm": 0.4871511484567439, "learning_rate": 3.7044642605011114e-05, "loss": 0.5284, "step": 317 }, { "epoch": 1.2881012658227848, "grad_norm": 0.5100419257635807, "learning_rate": 3.701487992136854e-05, "loss": 0.531, "step": 318 }, { "epoch": 1.2921518987341774, "grad_norm": 0.5647262316649374, "learning_rate": 3.69849802022222e-05, "loss": 0.5522, "step": 319 }, { "epoch": 1.2962025316455696, "grad_norm": 0.5007829714167397, "learning_rate": 3.6954943688380334e-05, "loss": 0.5316, "step": 320 }, { "epoch": 1.300253164556962, "grad_norm": 0.5775901665036812, "learning_rate": 3.692477062175289e-05, "loss": 0.5236, "step": 321 }, { "epoch": 1.3043037974683545, "grad_norm": 0.4727334858948214, "learning_rate": 3.689446124534958e-05, "loss": 0.5198, "step": 322 }, { "epoch": 1.308354430379747, "grad_norm": 0.6525176072211499, "learning_rate": 3.686401580327799e-05, "loss": 0.5292, "step": 323 }, { "epoch": 1.3124050632911393, "grad_norm": 0.5252024157927745, "learning_rate": 3.683343454074149e-05, "loss": 0.5066, "step": 324 }, { "epoch": 1.3164556962025316, "grad_norm": 0.5523625681396166, "learning_rate": 3.6802717704037386e-05, "loss": 0.5131, "step": 325 }, { "epoch": 1.320506329113924, "grad_norm": 0.6063600204485221, "learning_rate": 3.6771865540554855e-05, "loss": 0.5251, "step": 326 }, { "epoch": 1.3245569620253166, "grad_norm": 0.49260278318455963, "learning_rate": 3.674087829877297e-05, "loss": 0.5262, "step": 327 }, { "epoch": 1.3286075949367089, "grad_norm": 0.5226193988194053, "learning_rate": 3.6709756228258735e-05, "loss": 0.5086, "step": 328 }, { "epoch": 1.3326582278481012, "grad_norm": 0.5174534785267244, "learning_rate": 3.667849957966501e-05, "loss": 0.5295, "step": 329 }, { "epoch": 1.3367088607594937, "grad_norm": 0.5155219835673802, "learning_rate": 3.6647108604728546e-05, "loss": 0.5182, "step": 330 }, { "epoch": 1.3407594936708862, "grad_norm": 0.5155857499448588, "learning_rate": 3.661558355626795e-05, "loss": 0.54, "step": 331 }, { "epoch": 1.3448101265822785, "grad_norm": 0.611233880195229, "learning_rate": 3.658392468818163e-05, "loss": 0.5412, "step": 332 }, { "epoch": 1.3488607594936708, "grad_norm": 0.5150476510499759, "learning_rate": 3.655213225544574e-05, "loss": 0.5195, "step": 333 }, { "epoch": 1.3529113924050633, "grad_norm": 0.4935601206221364, "learning_rate": 3.652020651411218e-05, "loss": 0.5275, "step": 334 }, { "epoch": 1.3569620253164558, "grad_norm": 0.5294919200356014, "learning_rate": 3.6488147721306474e-05, "loss": 0.5342, "step": 335 }, { "epoch": 1.3610126582278481, "grad_norm": 0.5224255980488796, "learning_rate": 3.645595613522574e-05, "loss": 0.5111, "step": 336 }, { "epoch": 1.3650632911392404, "grad_norm": 0.5281068403240731, "learning_rate": 3.642363201513657e-05, "loss": 0.5433, "step": 337 }, { "epoch": 1.369113924050633, "grad_norm": 0.45155108237689856, "learning_rate": 3.6391175621373006e-05, "loss": 0.5128, "step": 338 }, { "epoch": 1.3731645569620254, "grad_norm": 0.5515316933354847, "learning_rate": 3.6358587215334355e-05, "loss": 0.5254, "step": 339 }, { "epoch": 1.3772151898734177, "grad_norm": 0.4504619824999091, "learning_rate": 3.632586705948318e-05, "loss": 0.52, "step": 340 }, { "epoch": 1.38126582278481, "grad_norm": 0.5946536682395476, "learning_rate": 3.629301541734311e-05, "loss": 0.4792, "step": 341 }, { "epoch": 1.3853164556962025, "grad_norm": 0.5199191385278931, "learning_rate": 3.626003255349676e-05, "loss": 0.5096, "step": 342 }, { "epoch": 1.389367088607595, "grad_norm": 0.6024466666896047, "learning_rate": 3.622691873358357e-05, "loss": 0.5211, "step": 343 }, { "epoch": 1.3934177215189874, "grad_norm": 0.5529220207829267, "learning_rate": 3.61936742242977e-05, "loss": 0.5457, "step": 344 }, { "epoch": 1.3974683544303796, "grad_norm": 0.5846965323391649, "learning_rate": 3.6160299293385864e-05, "loss": 0.5037, "step": 345 }, { "epoch": 1.4015189873417722, "grad_norm": 0.5592909060083718, "learning_rate": 3.612679420964516e-05, "loss": 0.529, "step": 346 }, { "epoch": 1.4055696202531647, "grad_norm": 0.5877658817194055, "learning_rate": 3.609315924292092e-05, "loss": 0.5418, "step": 347 }, { "epoch": 1.409620253164557, "grad_norm": 0.5778865581913928, "learning_rate": 3.6059394664104554e-05, "loss": 0.5449, "step": 348 }, { "epoch": 1.4136708860759493, "grad_norm": 0.5274554907344872, "learning_rate": 3.602550074513133e-05, "loss": 0.5167, "step": 349 }, { "epoch": 1.4177215189873418, "grad_norm": 0.5227296728717122, "learning_rate": 3.599147775897822e-05, "loss": 0.5218, "step": 350 }, { "epoch": 1.4217721518987343, "grad_norm": 0.7508776029197932, "learning_rate": 3.595732597966167e-05, "loss": 0.5365, "step": 351 }, { "epoch": 1.4258227848101266, "grad_norm": 0.49200846721234415, "learning_rate": 3.592304568223542e-05, "loss": 0.5228, "step": 352 }, { "epoch": 1.4298734177215189, "grad_norm": 0.5738137030424948, "learning_rate": 3.588863714278826e-05, "loss": 0.5298, "step": 353 }, { "epoch": 1.4339240506329114, "grad_norm": 0.6154317880211864, "learning_rate": 3.585410063844186e-05, "loss": 0.5525, "step": 354 }, { "epoch": 1.437974683544304, "grad_norm": 0.4609472619556876, "learning_rate": 3.581943644734846e-05, "loss": 0.5317, "step": 355 }, { "epoch": 1.4420253164556962, "grad_norm": 0.6015134334245911, "learning_rate": 3.578464484868869e-05, "loss": 0.516, "step": 356 }, { "epoch": 1.4460759493670885, "grad_norm": 0.514470348805945, "learning_rate": 3.5749726122669316e-05, "loss": 0.53, "step": 357 }, { "epoch": 1.450126582278481, "grad_norm": 0.6183635720724077, "learning_rate": 3.5714680550520943e-05, "loss": 0.5337, "step": 358 }, { "epoch": 1.4541772151898735, "grad_norm": 0.44807854034335826, "learning_rate": 3.5679508414495794e-05, "loss": 0.5468, "step": 359 }, { "epoch": 1.4582278481012658, "grad_norm": 0.5236983488359868, "learning_rate": 3.564420999786543e-05, "loss": 0.5262, "step": 360 }, { "epoch": 1.4622784810126581, "grad_norm": 0.5376550928609943, "learning_rate": 3.560878558491842e-05, "loss": 0.5331, "step": 361 }, { "epoch": 1.4663291139240506, "grad_norm": 0.4840433948807855, "learning_rate": 3.5573235460958145e-05, "loss": 0.5041, "step": 362 }, { "epoch": 1.4703797468354431, "grad_norm": 0.5098268756673381, "learning_rate": 3.553755991230039e-05, "loss": 0.5188, "step": 363 }, { "epoch": 1.4744303797468354, "grad_norm": 0.5480160803511368, "learning_rate": 3.5501759226271144e-05, "loss": 0.5133, "step": 364 }, { "epoch": 1.4784810126582277, "grad_norm": 0.5212828119964311, "learning_rate": 3.546583369120419e-05, "loss": 0.5518, "step": 365 }, { "epoch": 1.4825316455696202, "grad_norm": 0.6200237968707886, "learning_rate": 3.5429783596438864e-05, "loss": 0.5128, "step": 366 }, { "epoch": 1.4865822784810128, "grad_norm": 0.4856218196102761, "learning_rate": 3.539360923231766e-05, "loss": 0.5297, "step": 367 }, { "epoch": 1.490632911392405, "grad_norm": 0.6063029270709426, "learning_rate": 3.535731089018394e-05, "loss": 0.53, "step": 368 }, { "epoch": 1.4946835443037974, "grad_norm": 0.6148443050791854, "learning_rate": 3.532088886237956e-05, "loss": 0.5363, "step": 369 }, { "epoch": 1.4987341772151899, "grad_norm": 0.532749042960457, "learning_rate": 3.528434344224253e-05, "loss": 0.5271, "step": 370 }, { "epoch": 1.5027848101265824, "grad_norm": 0.5187922674420072, "learning_rate": 3.524767492410464e-05, "loss": 0.5052, "step": 371 }, { "epoch": 1.5068354430379747, "grad_norm": 0.5376236627601495, "learning_rate": 3.521088360328908e-05, "loss": 0.5497, "step": 372 }, { "epoch": 1.510886075949367, "grad_norm": 0.5267648794054497, "learning_rate": 3.517396977610811e-05, "loss": 0.5308, "step": 373 }, { "epoch": 1.5149367088607595, "grad_norm": 0.5035923056067687, "learning_rate": 3.5136933739860595e-05, "loss": 0.5264, "step": 374 }, { "epoch": 1.518987341772152, "grad_norm": 0.4764432370915513, "learning_rate": 3.509977579282971e-05, "loss": 0.5428, "step": 375 }, { "epoch": 1.5230379746835443, "grad_norm": 0.4795832594138813, "learning_rate": 3.5062496234280424e-05, "loss": 0.5385, "step": 376 }, { "epoch": 1.5270886075949366, "grad_norm": 0.5027332511987848, "learning_rate": 3.502509536445719e-05, "loss": 0.5292, "step": 377 }, { "epoch": 1.531139240506329, "grad_norm": 0.5348092458217297, "learning_rate": 3.498757348458147e-05, "loss": 0.5304, "step": 378 }, { "epoch": 1.5351898734177216, "grad_norm": 0.5391402218103896, "learning_rate": 3.4949930896849324e-05, "loss": 0.5358, "step": 379 }, { "epoch": 1.539240506329114, "grad_norm": 0.5113417452388926, "learning_rate": 3.491216790442899e-05, "loss": 0.5393, "step": 380 }, { "epoch": 1.5432911392405062, "grad_norm": 0.486593774187421, "learning_rate": 3.487428481145839e-05, "loss": 0.5261, "step": 381 }, { "epoch": 1.5473417721518987, "grad_norm": 0.6119913555030619, "learning_rate": 3.483628192304278e-05, "loss": 0.5359, "step": 382 }, { "epoch": 1.5513924050632912, "grad_norm": 0.4455955191228491, "learning_rate": 3.479815954525219e-05, "loss": 0.5294, "step": 383 }, { "epoch": 1.5554430379746835, "grad_norm": 0.5813977595565747, "learning_rate": 3.475991798511899e-05, "loss": 0.5298, "step": 384 }, { "epoch": 1.5594936708860758, "grad_norm": 0.45717936828834943, "learning_rate": 3.4721557550635464e-05, "loss": 0.516, "step": 385 }, { "epoch": 1.5635443037974683, "grad_norm": 0.5673755294059274, "learning_rate": 3.468307855075128e-05, "loss": 0.5172, "step": 386 }, { "epoch": 1.5675949367088609, "grad_norm": 0.5606025476811378, "learning_rate": 3.4644481295371005e-05, "loss": 0.521, "step": 387 }, { "epoch": 1.5716455696202531, "grad_norm": 0.5317884594857084, "learning_rate": 3.460576609535163e-05, "loss": 0.5093, "step": 388 }, { "epoch": 1.5756962025316454, "grad_norm": 0.5021136800911185, "learning_rate": 3.456693326250006e-05, "loss": 0.5242, "step": 389 }, { "epoch": 1.579746835443038, "grad_norm": 0.6018313060818397, "learning_rate": 3.452798310957058e-05, "loss": 0.5443, "step": 390 }, { "epoch": 1.5837974683544305, "grad_norm": 0.5369263723819705, "learning_rate": 3.4488915950262386e-05, "loss": 0.5546, "step": 391 }, { "epoch": 1.5878481012658228, "grad_norm": 0.5253779742511395, "learning_rate": 3.4449732099216985e-05, "loss": 0.5045, "step": 392 }, { "epoch": 1.591898734177215, "grad_norm": 0.5879258946861272, "learning_rate": 3.441043187201574e-05, "loss": 0.5344, "step": 393 }, { "epoch": 1.5959493670886076, "grad_norm": 0.5507219943387571, "learning_rate": 3.437101558517728e-05, "loss": 0.5423, "step": 394 }, { "epoch": 1.6, "grad_norm": 0.5677658966702361, "learning_rate": 3.433148355615496e-05, "loss": 0.5223, "step": 395 }, { "epoch": 1.6040506329113924, "grad_norm": 0.5584604656041914, "learning_rate": 3.4291836103334294e-05, "loss": 0.5194, "step": 396 }, { "epoch": 1.6081012658227847, "grad_norm": 0.5481516110736845, "learning_rate": 3.425207354603043e-05, "loss": 0.5217, "step": 397 }, { "epoch": 1.6121518987341772, "grad_norm": 0.5665929762831696, "learning_rate": 3.421219620448553e-05, "loss": 0.5091, "step": 398 }, { "epoch": 1.6162025316455697, "grad_norm": 0.5193821174756816, "learning_rate": 3.417220439986623e-05, "loss": 0.5336, "step": 399 }, { "epoch": 1.620253164556962, "grad_norm": 0.6316767751751449, "learning_rate": 3.4132098454261024e-05, "loss": 0.5254, "step": 400 }, { "epoch": 1.6243037974683543, "grad_norm": 0.5029010491821517, "learning_rate": 3.4091878690677676e-05, "loss": 0.5056, "step": 401 }, { "epoch": 1.6283544303797468, "grad_norm": 0.5803842860831577, "learning_rate": 3.405154543304065e-05, "loss": 0.5358, "step": 402 }, { "epoch": 1.6324050632911393, "grad_norm": 0.6549858161770844, "learning_rate": 3.401109900618843e-05, "loss": 0.5498, "step": 403 }, { "epoch": 1.6364556962025316, "grad_norm": 0.4118177771524424, "learning_rate": 3.3970539735870996e-05, "loss": 0.5513, "step": 404 }, { "epoch": 1.640506329113924, "grad_norm": 0.5465172468878596, "learning_rate": 3.392986794874714e-05, "loss": 0.5507, "step": 405 }, { "epoch": 1.6445569620253164, "grad_norm": 0.5038860019683068, "learning_rate": 3.388908397238184e-05, "loss": 0.526, "step": 406 }, { "epoch": 1.648607594936709, "grad_norm": 0.5859480389782665, "learning_rate": 3.384818813524362e-05, "loss": 0.5413, "step": 407 }, { "epoch": 1.6526582278481012, "grad_norm": 0.5562698238681647, "learning_rate": 3.380718076670195e-05, "loss": 0.5123, "step": 408 }, { "epoch": 1.6567088607594935, "grad_norm": 0.5896316990055042, "learning_rate": 3.376606219702454e-05, "loss": 0.5221, "step": 409 }, { "epoch": 1.660759493670886, "grad_norm": 0.552252300011831, "learning_rate": 3.372483275737468e-05, "loss": 0.5339, "step": 410 }, { "epoch": 1.6648101265822786, "grad_norm": 0.547883504923108, "learning_rate": 3.368349277980861e-05, "loss": 0.5194, "step": 411 }, { "epoch": 1.6688607594936709, "grad_norm": 0.5932910938939981, "learning_rate": 3.3642042597272844e-05, "loss": 0.5288, "step": 412 }, { "epoch": 1.6729113924050631, "grad_norm": 0.5194474474605526, "learning_rate": 3.360048254360144e-05, "loss": 0.5539, "step": 413 }, { "epoch": 1.6769620253164557, "grad_norm": 0.5084627038580797, "learning_rate": 3.355881295351336e-05, "loss": 0.5362, "step": 414 }, { "epoch": 1.6810126582278482, "grad_norm": 0.5302032500760848, "learning_rate": 3.351703416260975e-05, "loss": 0.5136, "step": 415 }, { "epoch": 1.6850632911392405, "grad_norm": 0.46881416291550254, "learning_rate": 3.347514650737126e-05, "loss": 0.5291, "step": 416 }, { "epoch": 1.6891139240506328, "grad_norm": 0.5344857856974509, "learning_rate": 3.3433150325155295e-05, "loss": 0.5337, "step": 417 }, { "epoch": 1.6931645569620253, "grad_norm": 0.48114591409757285, "learning_rate": 3.339104595419334e-05, "loss": 0.5105, "step": 418 }, { "epoch": 1.6972151898734178, "grad_norm": 0.5963022511285254, "learning_rate": 3.3348833733588204e-05, "loss": 0.5483, "step": 419 }, { "epoch": 1.70126582278481, "grad_norm": 0.5510995028453379, "learning_rate": 3.3306514003311305e-05, "loss": 0.5432, "step": 420 }, { "epoch": 1.7053164556962024, "grad_norm": 0.6764681749181032, "learning_rate": 3.326408710419996e-05, "loss": 0.5439, "step": 421 }, { "epoch": 1.709367088607595, "grad_norm": 0.47167616098722465, "learning_rate": 3.322155337795454e-05, "loss": 0.509, "step": 422 }, { "epoch": 1.7134177215189874, "grad_norm": 0.5926457313315179, "learning_rate": 3.317891316713587e-05, "loss": 0.5227, "step": 423 }, { "epoch": 1.7174683544303797, "grad_norm": 0.4868124938537252, "learning_rate": 3.313616681516231e-05, "loss": 0.5286, "step": 424 }, { "epoch": 1.721518987341772, "grad_norm": 0.5821751521941065, "learning_rate": 3.309331466630713e-05, "loss": 0.4984, "step": 425 }, { "epoch": 1.7255696202531645, "grad_norm": 0.4787139455260197, "learning_rate": 3.305035706569563e-05, "loss": 0.5221, "step": 426 }, { "epoch": 1.729620253164557, "grad_norm": 0.5746762859772903, "learning_rate": 3.3007294359302433e-05, "loss": 0.527, "step": 427 }, { "epoch": 1.7336708860759493, "grad_norm": 0.4632478552191402, "learning_rate": 3.296412689394864e-05, "loss": 0.5081, "step": 428 }, { "epoch": 1.7377215189873416, "grad_norm": 0.576064718501406, "learning_rate": 3.292085501729909e-05, "loss": 0.518, "step": 429 }, { "epoch": 1.7417721518987341, "grad_norm": 0.4906449108992913, "learning_rate": 3.2877479077859534e-05, "loss": 0.5268, "step": 430 }, { "epoch": 1.7458227848101266, "grad_norm": 0.4738980068962735, "learning_rate": 3.283399942497381e-05, "loss": 0.4933, "step": 431 }, { "epoch": 1.749873417721519, "grad_norm": 0.5083420159887837, "learning_rate": 3.279041640882108e-05, "loss": 0.5347, "step": 432 }, { "epoch": 1.7539240506329112, "grad_norm": 0.48522946424177693, "learning_rate": 3.2746730380412964e-05, "loss": 0.5437, "step": 433 }, { "epoch": 1.7579746835443038, "grad_norm": 0.5309611250526683, "learning_rate": 3.2702941691590726e-05, "loss": 0.5421, "step": 434 }, { "epoch": 1.7620253164556963, "grad_norm": 0.43117082718483013, "learning_rate": 3.265905069502244e-05, "loss": 0.5483, "step": 435 }, { "epoch": 1.7660759493670886, "grad_norm": 0.4787687188067286, "learning_rate": 3.261505774420016e-05, "loss": 0.5225, "step": 436 }, { "epoch": 1.7701265822784809, "grad_norm": 0.4597578645003649, "learning_rate": 3.257096319343707e-05, "loss": 0.5034, "step": 437 }, { "epoch": 1.7741772151898734, "grad_norm": 0.4272241609051429, "learning_rate": 3.2526767397864614e-05, "loss": 0.5461, "step": 438 }, { "epoch": 1.7782278481012659, "grad_norm": 0.5719382414937992, "learning_rate": 3.248247071342966e-05, "loss": 0.5462, "step": 439 }, { "epoch": 1.7822784810126582, "grad_norm": 0.43852965878639155, "learning_rate": 3.243807349689161e-05, "loss": 0.5049, "step": 440 }, { "epoch": 1.7863291139240505, "grad_norm": 0.5344136244648044, "learning_rate": 3.2393576105819544e-05, "loss": 0.5038, "step": 441 }, { "epoch": 1.790379746835443, "grad_norm": 0.5103914817341154, "learning_rate": 3.2348978898589333e-05, "loss": 0.546, "step": 442 }, { "epoch": 1.7944303797468355, "grad_norm": 0.5194479748089949, "learning_rate": 3.230428223438075e-05, "loss": 0.5511, "step": 443 }, { "epoch": 1.7984810126582278, "grad_norm": 0.5001453365369749, "learning_rate": 3.225948647317459e-05, "loss": 0.5108, "step": 444 }, { "epoch": 1.80253164556962, "grad_norm": 0.5423214787471682, "learning_rate": 3.2214591975749745e-05, "loss": 0.5471, "step": 445 }, { "epoch": 1.8065822784810126, "grad_norm": 0.5217445947076242, "learning_rate": 3.216959910368034e-05, "loss": 0.5349, "step": 446 }, { "epoch": 1.8106329113924051, "grad_norm": 0.4569515493641169, "learning_rate": 3.212450821933277e-05, "loss": 0.533, "step": 447 }, { "epoch": 1.8146835443037974, "grad_norm": 0.49458800109084045, "learning_rate": 3.207931968586281e-05, "loss": 0.5162, "step": 448 }, { "epoch": 1.81873417721519, "grad_norm": 0.5060876880184041, "learning_rate": 3.203403386721272e-05, "loss": 0.5112, "step": 449 }, { "epoch": 1.8227848101265822, "grad_norm": 0.46584884741270877, "learning_rate": 3.1988651128108245e-05, "loss": 0.5256, "step": 450 }, { "epoch": 1.8268354430379747, "grad_norm": 0.6359186684115345, "learning_rate": 3.194317183405573e-05, "loss": 0.5294, "step": 451 }, { "epoch": 1.8308860759493673, "grad_norm": 0.43783762973714796, "learning_rate": 3.189759635133914e-05, "loss": 0.503, "step": 452 }, { "epoch": 1.8349367088607595, "grad_norm": 0.5762319575537707, "learning_rate": 3.185192504701718e-05, "loss": 0.5209, "step": 453 }, { "epoch": 1.8389873417721518, "grad_norm": 0.5542311320221373, "learning_rate": 3.1806158288920234e-05, "loss": 0.5263, "step": 454 }, { "epoch": 1.8430379746835444, "grad_norm": 0.5836522125393075, "learning_rate": 3.1760296445647477e-05, "loss": 0.5242, "step": 455 }, { "epoch": 1.8470886075949369, "grad_norm": 0.5495841894838467, "learning_rate": 3.1714339886563896e-05, "loss": 0.5402, "step": 456 }, { "epoch": 1.8511392405063292, "grad_norm": 0.5692480595497125, "learning_rate": 3.166828898179731e-05, "loss": 0.5164, "step": 457 }, { "epoch": 1.8551898734177215, "grad_norm": 0.5727606407874347, "learning_rate": 3.162214410223536e-05, "loss": 0.5167, "step": 458 }, { "epoch": 1.859240506329114, "grad_norm": 0.5428154901647474, "learning_rate": 3.157590561952257e-05, "loss": 0.5224, "step": 459 }, { "epoch": 1.8632911392405065, "grad_norm": 0.49457743317890795, "learning_rate": 3.152957390605732e-05, "loss": 0.5377, "step": 460 }, { "epoch": 1.8673417721518988, "grad_norm": 0.5606502720931906, "learning_rate": 3.148314933498886e-05, "loss": 0.5358, "step": 461 }, { "epoch": 1.871392405063291, "grad_norm": 0.4427912297418999, "learning_rate": 3.143663228021431e-05, "loss": 0.5213, "step": 462 }, { "epoch": 1.8754430379746836, "grad_norm": 0.50859235692313, "learning_rate": 3.1390023116375624e-05, "loss": 0.5228, "step": 463 }, { "epoch": 1.879493670886076, "grad_norm": 0.5119036095521933, "learning_rate": 3.134332221885661e-05, "loss": 0.5324, "step": 464 }, { "epoch": 1.8835443037974684, "grad_norm": 0.453535185154042, "learning_rate": 3.129652996377987e-05, "loss": 0.5064, "step": 465 }, { "epoch": 1.8875949367088607, "grad_norm": 0.5530107352867978, "learning_rate": 3.12496467280038e-05, "loss": 0.5339, "step": 466 }, { "epoch": 1.8916455696202532, "grad_norm": 0.4520668318610638, "learning_rate": 3.120267288911952e-05, "loss": 0.5198, "step": 467 }, { "epoch": 1.8956962025316457, "grad_norm": 0.43501689804190213, "learning_rate": 3.11556088254479e-05, "loss": 0.5293, "step": 468 }, { "epoch": 1.899746835443038, "grad_norm": 0.4118789876525115, "learning_rate": 3.11084549160364e-05, "loss": 0.5201, "step": 469 }, { "epoch": 1.9037974683544303, "grad_norm": 0.4844988686066674, "learning_rate": 3.106121154065615e-05, "loss": 0.5308, "step": 470 }, { "epoch": 1.9078481012658228, "grad_norm": 0.43406366026123494, "learning_rate": 3.1013879079798805e-05, "loss": 0.5284, "step": 471 }, { "epoch": 1.9118987341772153, "grad_norm": 0.5487763805283392, "learning_rate": 3.096645791467348e-05, "loss": 0.5304, "step": 472 }, { "epoch": 1.9159493670886076, "grad_norm": 0.43243534819917656, "learning_rate": 3.091894842720373e-05, "loss": 0.5278, "step": 473 }, { "epoch": 1.92, "grad_norm": 0.5211194403380855, "learning_rate": 3.0871351000024425e-05, "loss": 0.5319, "step": 474 }, { "epoch": 1.9240506329113924, "grad_norm": 0.4652115572276765, "learning_rate": 3.0823666016478716e-05, "loss": 0.5272, "step": 475 }, { "epoch": 1.928101265822785, "grad_norm": 0.45416236720491493, "learning_rate": 3.0775893860614896e-05, "loss": 0.5156, "step": 476 }, { "epoch": 1.9321518987341773, "grad_norm": 0.49670175242560877, "learning_rate": 3.0728034917183336e-05, "loss": 0.5478, "step": 477 }, { "epoch": 1.9362025316455695, "grad_norm": 0.5108225142386223, "learning_rate": 3.06800895716334e-05, "loss": 0.5257, "step": 478 }, { "epoch": 1.940253164556962, "grad_norm": 0.5224602786031831, "learning_rate": 3.063205821011029e-05, "loss": 0.5211, "step": 479 }, { "epoch": 1.9443037974683546, "grad_norm": 0.48902996790598136, "learning_rate": 3.0583941219452016e-05, "loss": 0.5227, "step": 480 }, { "epoch": 1.9483544303797469, "grad_norm": 0.514619146858745, "learning_rate": 3.053573898718618e-05, "loss": 0.5345, "step": 481 }, { "epoch": 1.9524050632911392, "grad_norm": 0.4865534089556455, "learning_rate": 3.0487451901526956e-05, "loss": 0.5299, "step": 482 }, { "epoch": 1.9564556962025317, "grad_norm": 0.5010281654679047, "learning_rate": 3.0439080351371875e-05, "loss": 0.5108, "step": 483 }, { "epoch": 1.9605063291139242, "grad_norm": 0.41884876367764184, "learning_rate": 3.0390624726298764e-05, "loss": 0.5476, "step": 484 }, { "epoch": 1.9645569620253165, "grad_norm": 0.5022659026403234, "learning_rate": 3.034208541656255e-05, "loss": 0.5173, "step": 485 }, { "epoch": 1.9686075949367088, "grad_norm": 0.4380281890717205, "learning_rate": 3.029346281309218e-05, "loss": 0.5214, "step": 486 }, { "epoch": 1.9726582278481013, "grad_norm": 0.4541736561800714, "learning_rate": 3.0244757307487415e-05, "loss": 0.528, "step": 487 }, { "epoch": 1.9767088607594938, "grad_norm": 0.444822539134039, "learning_rate": 3.019596929201569e-05, "loss": 0.5128, "step": 488 }, { "epoch": 1.980759493670886, "grad_norm": 0.45487000772338565, "learning_rate": 3.0147099159608985e-05, "loss": 0.5505, "step": 489 }, { "epoch": 1.9848101265822784, "grad_norm": 0.45021018190498086, "learning_rate": 3.0098147303860616e-05, "loss": 0.5082, "step": 490 }, { "epoch": 1.988860759493671, "grad_norm": 0.48265663553702787, "learning_rate": 3.0049114119022117e-05, "loss": 0.5455, "step": 491 }, { "epoch": 1.9929113924050634, "grad_norm": 0.442241225870038, "learning_rate": 3.0000000000000004e-05, "loss": 0.5378, "step": 492 }, { "epoch": 1.9969620253164557, "grad_norm": 0.42488059931623473, "learning_rate": 2.995080534235264e-05, "loss": 0.5331, "step": 493 }, { "epoch": 2.001012658227848, "grad_norm": 0.46338318800367756, "learning_rate": 2.9901530542287044e-05, "loss": 0.5122, "step": 494 }, { "epoch": 2.0050632911392405, "grad_norm": 0.6664588243164679, "learning_rate": 2.9852175996655676e-05, "loss": 0.3795, "step": 495 }, { "epoch": 2.009113924050633, "grad_norm": 0.9902328270398305, "learning_rate": 2.980274210295326e-05, "loss": 0.3832, "step": 496 }, { "epoch": 2.013164556962025, "grad_norm": 0.5844096018828172, "learning_rate": 2.9753229259313578e-05, "loss": 0.357, "step": 497 }, { "epoch": 2.0172151898734176, "grad_norm": 0.589965892625826, "learning_rate": 2.9703637864506274e-05, "loss": 0.3765, "step": 498 }, { "epoch": 2.02126582278481, "grad_norm": 0.5982242299323428, "learning_rate": 2.965396831793362e-05, "loss": 0.3751, "step": 499 }, { "epoch": 2.0253164556962027, "grad_norm": 0.5034739363047425, "learning_rate": 2.9604221019627316e-05, "loss": 0.3555, "step": 500 }, { "epoch": 2.0293670886075947, "grad_norm": 0.6282987243898359, "learning_rate": 2.955439637024526e-05, "loss": 0.3791, "step": 501 }, { "epoch": 2.0334177215189873, "grad_norm": 0.49812306784345867, "learning_rate": 2.9504494771068334e-05, "loss": 0.3647, "step": 502 }, { "epoch": 2.0374683544303798, "grad_norm": 0.5995996635227844, "learning_rate": 2.9454516623997156e-05, "loss": 0.3555, "step": 503 }, { "epoch": 2.0415189873417723, "grad_norm": 0.5049083220919715, "learning_rate": 2.9404462331548847e-05, "loss": 0.371, "step": 504 }, { "epoch": 2.0455696202531644, "grad_norm": 0.563472858583344, "learning_rate": 2.93543322968538e-05, "loss": 0.3847, "step": 505 }, { "epoch": 2.049620253164557, "grad_norm": 0.47874710536934295, "learning_rate": 2.9304126923652428e-05, "loss": 0.3612, "step": 506 }, { "epoch": 2.0536708860759494, "grad_norm": 0.5673118043363085, "learning_rate": 2.9253846616291896e-05, "loss": 0.3675, "step": 507 }, { "epoch": 2.057721518987342, "grad_norm": 0.5671160043959926, "learning_rate": 2.9203491779722896e-05, "loss": 0.3826, "step": 508 }, { "epoch": 2.061772151898734, "grad_norm": 0.4802431501612086, "learning_rate": 2.9153062819496357e-05, "loss": 0.3425, "step": 509 }, { "epoch": 2.0658227848101265, "grad_norm": 0.5057797257631971, "learning_rate": 2.9102560141760178e-05, "loss": 0.3981, "step": 510 }, { "epoch": 2.069873417721519, "grad_norm": 0.4910626467675997, "learning_rate": 2.9051984153256004e-05, "loss": 0.3717, "step": 511 }, { "epoch": 2.0739240506329115, "grad_norm": 0.43553193972151394, "learning_rate": 2.900133526131588e-05, "loss": 0.3827, "step": 512 }, { "epoch": 2.0779746835443036, "grad_norm": 0.5041776992424918, "learning_rate": 2.8950613873859025e-05, "loss": 0.3775, "step": 513 }, { "epoch": 2.082025316455696, "grad_norm": 0.4661482602832351, "learning_rate": 2.8899820399388515e-05, "loss": 0.3539, "step": 514 }, { "epoch": 2.0860759493670886, "grad_norm": 0.45454335909690186, "learning_rate": 2.8848955246988012e-05, "loss": 0.3772, "step": 515 }, { "epoch": 2.090126582278481, "grad_norm": 0.4994769695056931, "learning_rate": 2.879801882631847e-05, "loss": 0.3877, "step": 516 }, { "epoch": 2.094177215189873, "grad_norm": 0.4331787210459789, "learning_rate": 2.8747011547614808e-05, "loss": 0.3479, "step": 517 }, { "epoch": 2.0982278481012657, "grad_norm": 0.43725796048167453, "learning_rate": 2.8695933821682635e-05, "loss": 0.361, "step": 518 }, { "epoch": 2.1022784810126582, "grad_norm": 0.5105672549949197, "learning_rate": 2.864478605989494e-05, "loss": 0.387, "step": 519 }, { "epoch": 2.1063291139240508, "grad_norm": 0.4182341559301544, "learning_rate": 2.8593568674188765e-05, "loss": 0.3538, "step": 520 }, { "epoch": 2.110379746835443, "grad_norm": 0.5092115216071246, "learning_rate": 2.8542282077061892e-05, "loss": 0.3865, "step": 521 }, { "epoch": 2.1144303797468353, "grad_norm": 0.44996762762447484, "learning_rate": 2.8490926681569523e-05, "loss": 0.3759, "step": 522 }, { "epoch": 2.118481012658228, "grad_norm": 0.4736895707773142, "learning_rate": 2.8439502901320956e-05, "loss": 0.3826, "step": 523 }, { "epoch": 2.1225316455696204, "grad_norm": 0.4531331262380268, "learning_rate": 2.8388011150476237e-05, "loss": 0.3634, "step": 524 }, { "epoch": 2.1265822784810124, "grad_norm": 0.46043169384873034, "learning_rate": 2.8336451843742866e-05, "loss": 0.3384, "step": 525 }, { "epoch": 2.130632911392405, "grad_norm": 0.4390959078879765, "learning_rate": 2.8284825396372387e-05, "loss": 0.3693, "step": 526 }, { "epoch": 2.1346835443037975, "grad_norm": 0.4516421951036826, "learning_rate": 2.8233132224157132e-05, "loss": 0.356, "step": 527 }, { "epoch": 2.13873417721519, "grad_norm": 0.49071693649481146, "learning_rate": 2.8181372743426805e-05, "loss": 0.3861, "step": 528 }, { "epoch": 2.1427848101265825, "grad_norm": 0.42747193587988785, "learning_rate": 2.8129547371045128e-05, "loss": 0.367, "step": 529 }, { "epoch": 2.1468354430379746, "grad_norm": 0.43461694266444595, "learning_rate": 2.8077656524406534e-05, "loss": 0.3545, "step": 530 }, { "epoch": 2.150886075949367, "grad_norm": 0.4198992904208118, "learning_rate": 2.802570062143278e-05, "loss": 0.3777, "step": 531 }, { "epoch": 2.1549367088607596, "grad_norm": 0.4691560265275165, "learning_rate": 2.7973680080569555e-05, "loss": 0.337, "step": 532 }, { "epoch": 2.1589873417721517, "grad_norm": 0.48589595306789507, "learning_rate": 2.792159532078314e-05, "loss": 0.3799, "step": 533 }, { "epoch": 2.163037974683544, "grad_norm": 0.41339188625495277, "learning_rate": 2.7869446761557033e-05, "loss": 0.3787, "step": 534 }, { "epoch": 2.1670886075949367, "grad_norm": 0.45649356718142364, "learning_rate": 2.781723482288857e-05, "loss": 0.3685, "step": 535 }, { "epoch": 2.1711392405063292, "grad_norm": 0.44335064033027477, "learning_rate": 2.7764959925285517e-05, "loss": 0.36, "step": 536 }, { "epoch": 2.1751898734177217, "grad_norm": 0.48564043656658595, "learning_rate": 2.771262248976272e-05, "loss": 0.3874, "step": 537 }, { "epoch": 2.179240506329114, "grad_norm": 0.46723187548831197, "learning_rate": 2.7660222937838677e-05, "loss": 0.3788, "step": 538 }, { "epoch": 2.1832911392405063, "grad_norm": 0.4493363204076098, "learning_rate": 2.7607761691532186e-05, "loss": 0.369, "step": 539 }, { "epoch": 2.187341772151899, "grad_norm": 0.4542058593160698, "learning_rate": 2.7555239173358916e-05, "loss": 0.3696, "step": 540 }, { "epoch": 2.191392405063291, "grad_norm": 0.42325483645483103, "learning_rate": 2.7502655806328e-05, "loss": 0.3709, "step": 541 }, { "epoch": 2.1954430379746834, "grad_norm": 0.4163123961500731, "learning_rate": 2.7450012013938648e-05, "loss": 0.395, "step": 542 }, { "epoch": 2.199493670886076, "grad_norm": 0.472542336670121, "learning_rate": 2.739730822017673e-05, "loss": 0.3611, "step": 543 }, { "epoch": 2.2035443037974685, "grad_norm": 0.438732695570904, "learning_rate": 2.7344544849511355e-05, "loss": 0.3819, "step": 544 }, { "epoch": 2.207594936708861, "grad_norm": 0.4595984424251135, "learning_rate": 2.7291722326891456e-05, "loss": 0.401, "step": 545 }, { "epoch": 2.211645569620253, "grad_norm": 0.39985992363981254, "learning_rate": 2.723884107774236e-05, "loss": 0.39, "step": 546 }, { "epoch": 2.2156962025316456, "grad_norm": 0.42035024444187996, "learning_rate": 2.718590152796239e-05, "loss": 0.3894, "step": 547 }, { "epoch": 2.219746835443038, "grad_norm": 0.44280397485709044, "learning_rate": 2.71329041039194e-05, "loss": 0.3873, "step": 548 }, { "epoch": 2.22379746835443, "grad_norm": 0.41636982706050896, "learning_rate": 2.7079849232447357e-05, "loss": 0.3681, "step": 549 }, { "epoch": 2.2278481012658227, "grad_norm": 0.4232588882651215, "learning_rate": 2.7026737340842895e-05, "loss": 0.3666, "step": 550 }, { "epoch": 2.231898734177215, "grad_norm": 0.4206651466981225, "learning_rate": 2.697356885686189e-05, "loss": 0.3751, "step": 551 }, { "epoch": 2.2359493670886077, "grad_norm": 0.38826133783973643, "learning_rate": 2.6920344208716014e-05, "loss": 0.3894, "step": 552 }, { "epoch": 2.24, "grad_norm": 0.44138850445905403, "learning_rate": 2.6867063825069252e-05, "loss": 0.3645, "step": 553 }, { "epoch": 2.2440506329113923, "grad_norm": 0.48322938259347586, "learning_rate": 2.6813728135034494e-05, "loss": 0.3519, "step": 554 }, { "epoch": 2.248101265822785, "grad_norm": 0.42191383147582606, "learning_rate": 2.6760337568170056e-05, "loss": 0.3755, "step": 555 }, { "epoch": 2.2521518987341773, "grad_norm": 0.4907698895920695, "learning_rate": 2.6706892554476226e-05, "loss": 0.3766, "step": 556 }, { "epoch": 2.2562025316455694, "grad_norm": 0.464186131603071, "learning_rate": 2.6653393524391795e-05, "loss": 0.3818, "step": 557 }, { "epoch": 2.260253164556962, "grad_norm": 0.4663346561763228, "learning_rate": 2.6599840908790592e-05, "loss": 0.3835, "step": 558 }, { "epoch": 2.2643037974683544, "grad_norm": 0.46048254023317403, "learning_rate": 2.6546235138978028e-05, "loss": 0.3833, "step": 559 }, { "epoch": 2.268354430379747, "grad_norm": 0.42844310026285964, "learning_rate": 2.6492576646687597e-05, "loss": 0.3682, "step": 560 }, { "epoch": 2.2724050632911394, "grad_norm": 0.41758793597209143, "learning_rate": 2.6438865864077425e-05, "loss": 0.3652, "step": 561 }, { "epoch": 2.2764556962025315, "grad_norm": 0.456584703885217, "learning_rate": 2.6385103223726766e-05, "loss": 0.3743, "step": 562 }, { "epoch": 2.280506329113924, "grad_norm": 0.42551202487089, "learning_rate": 2.6331289158632537e-05, "loss": 0.3996, "step": 563 }, { "epoch": 2.2845569620253166, "grad_norm": 0.396092756062254, "learning_rate": 2.6277424102205817e-05, "loss": 0.3691, "step": 564 }, { "epoch": 2.2886075949367086, "grad_norm": 0.4105329444816766, "learning_rate": 2.6223508488268374e-05, "loss": 0.3626, "step": 565 }, { "epoch": 2.292658227848101, "grad_norm": 0.4251807840184399, "learning_rate": 2.6169542751049148e-05, "loss": 0.3651, "step": 566 }, { "epoch": 2.2967088607594937, "grad_norm": 0.43330696854207296, "learning_rate": 2.6115527325180754e-05, "loss": 0.3844, "step": 567 }, { "epoch": 2.300759493670886, "grad_norm": 0.4128769471507529, "learning_rate": 2.606146264569603e-05, "loss": 0.3456, "step": 568 }, { "epoch": 2.3048101265822787, "grad_norm": 0.4681270378030877, "learning_rate": 2.6007349148024447e-05, "loss": 0.385, "step": 569 }, { "epoch": 2.3088607594936708, "grad_norm": 0.48231874317993084, "learning_rate": 2.5953187267988694e-05, "loss": 0.3855, "step": 570 }, { "epoch": 2.3129113924050633, "grad_norm": 0.4837449368888534, "learning_rate": 2.5898977441801097e-05, "loss": 0.3884, "step": 571 }, { "epoch": 2.316962025316456, "grad_norm": 0.47116670245987274, "learning_rate": 2.584472010606015e-05, "loss": 0.3791, "step": 572 }, { "epoch": 2.321012658227848, "grad_norm": 0.47296730316062935, "learning_rate": 2.5790415697746976e-05, "loss": 0.3859, "step": 573 }, { "epoch": 2.3250632911392404, "grad_norm": 0.47285585347147563, "learning_rate": 2.5736064654221808e-05, "loss": 0.3828, "step": 574 }, { "epoch": 2.329113924050633, "grad_norm": 0.43908967830160145, "learning_rate": 2.568166741322048e-05, "loss": 0.381, "step": 575 }, { "epoch": 2.3331645569620254, "grad_norm": 0.46040812574557144, "learning_rate": 2.56272244128509e-05, "loss": 0.3588, "step": 576 }, { "epoch": 2.337215189873418, "grad_norm": 0.4077733440877704, "learning_rate": 2.55727360915895e-05, "loss": 0.3685, "step": 577 }, { "epoch": 2.34126582278481, "grad_norm": 0.4767186699807804, "learning_rate": 2.5518202888277734e-05, "loss": 0.3709, "step": 578 }, { "epoch": 2.3453164556962025, "grad_norm": 0.4440704277373129, "learning_rate": 2.5463625242118523e-05, "loss": 0.3558, "step": 579 }, { "epoch": 2.349367088607595, "grad_norm": 0.46316689627743285, "learning_rate": 2.5409003592672723e-05, "loss": 0.3689, "step": 580 }, { "epoch": 2.353417721518987, "grad_norm": 0.42319885717821115, "learning_rate": 2.535433837985559e-05, "loss": 0.3607, "step": 581 }, { "epoch": 2.3574683544303796, "grad_norm": 0.457550499437875, "learning_rate": 2.529963004393324e-05, "loss": 0.3806, "step": 582 }, { "epoch": 2.361518987341772, "grad_norm": 0.418940354848276, "learning_rate": 2.524487902551908e-05, "loss": 0.3667, "step": 583 }, { "epoch": 2.3655696202531646, "grad_norm": 0.4199048971634887, "learning_rate": 2.519008576557029e-05, "loss": 0.377, "step": 584 }, { "epoch": 2.369620253164557, "grad_norm": 0.4496023289447349, "learning_rate": 2.5135250705384254e-05, "loss": 0.3747, "step": 585 }, { "epoch": 2.3736708860759492, "grad_norm": 0.44142887517843415, "learning_rate": 2.5080374286595007e-05, "loss": 0.3822, "step": 586 }, { "epoch": 2.3777215189873417, "grad_norm": 0.435800548764163, "learning_rate": 2.5025456951169677e-05, "loss": 0.3793, "step": 587 }, { "epoch": 2.3817721518987343, "grad_norm": 0.4649056060458245, "learning_rate": 2.4970499141404942e-05, "loss": 0.3796, "step": 588 }, { "epoch": 2.3858227848101268, "grad_norm": 0.43760150358330735, "learning_rate": 2.491550129992345e-05, "loss": 0.3739, "step": 589 }, { "epoch": 2.389873417721519, "grad_norm": 0.450454608580885, "learning_rate": 2.486046386967024e-05, "loss": 0.3755, "step": 590 }, { "epoch": 2.3939240506329114, "grad_norm": 0.4175005058704265, "learning_rate": 2.4805387293909214e-05, "loss": 0.3681, "step": 591 }, { "epoch": 2.397974683544304, "grad_norm": 0.4239236983947001, "learning_rate": 2.4750272016219552e-05, "loss": 0.361, "step": 592 }, { "epoch": 2.4020253164556964, "grad_norm": 0.42532604559377696, "learning_rate": 2.4695118480492114e-05, "loss": 0.3605, "step": 593 }, { "epoch": 2.4060759493670885, "grad_norm": 0.39005717434907283, "learning_rate": 2.4639927130925898e-05, "loss": 0.3967, "step": 594 }, { "epoch": 2.410126582278481, "grad_norm": 0.415143914302145, "learning_rate": 2.458469841202444e-05, "loss": 0.3794, "step": 595 }, { "epoch": 2.4141772151898735, "grad_norm": 0.40744113685864497, "learning_rate": 2.452943276859226e-05, "loss": 0.3665, "step": 596 }, { "epoch": 2.418227848101266, "grad_norm": 0.39223119659035527, "learning_rate": 2.447413064573125e-05, "loss": 0.3483, "step": 597 }, { "epoch": 2.422278481012658, "grad_norm": 0.3863788671816459, "learning_rate": 2.4418792488837095e-05, "loss": 0.3684, "step": 598 }, { "epoch": 2.4263291139240506, "grad_norm": 0.4231831351103158, "learning_rate": 2.4363418743595713e-05, "loss": 0.377, "step": 599 }, { "epoch": 2.430379746835443, "grad_norm": 0.46894825625070724, "learning_rate": 2.430800985597963e-05, "loss": 0.3645, "step": 600 }, { "epoch": 2.4344303797468356, "grad_norm": 0.4402547288260218, "learning_rate": 2.4252566272244415e-05, "loss": 0.3698, "step": 601 }, { "epoch": 2.4384810126582277, "grad_norm": 0.4046750462998858, "learning_rate": 2.4197088438925063e-05, "loss": 0.4031, "step": 602 }, { "epoch": 2.44253164556962, "grad_norm": 0.4660850713447749, "learning_rate": 2.4141576802832417e-05, "loss": 0.375, "step": 603 }, { "epoch": 2.4465822784810127, "grad_norm": 0.4391081634854105, "learning_rate": 2.408603181104957e-05, "loss": 0.3726, "step": 604 }, { "epoch": 2.4506329113924052, "grad_norm": 0.4345956051380134, "learning_rate": 2.4030453910928245e-05, "loss": 0.361, "step": 605 }, { "epoch": 2.4546835443037973, "grad_norm": 0.5358525979942607, "learning_rate": 2.397484355008521e-05, "loss": 0.3724, "step": 606 }, { "epoch": 2.45873417721519, "grad_norm": 0.43720243370903356, "learning_rate": 2.3919201176398662e-05, "loss": 0.3748, "step": 607 }, { "epoch": 2.4627848101265823, "grad_norm": 0.475106658813927, "learning_rate": 2.3863527238004633e-05, "loss": 0.3941, "step": 608 }, { "epoch": 2.466835443037975, "grad_norm": 0.467505999091891, "learning_rate": 2.380782218329337e-05, "loss": 0.3718, "step": 609 }, { "epoch": 2.470886075949367, "grad_norm": 0.37876943104076094, "learning_rate": 2.3752086460905725e-05, "loss": 0.372, "step": 610 }, { "epoch": 2.4749367088607594, "grad_norm": 0.4026427017351805, "learning_rate": 2.3696320519729544e-05, "loss": 0.4033, "step": 611 }, { "epoch": 2.478987341772152, "grad_norm": 0.4196410620023269, "learning_rate": 2.3640524808896045e-05, "loss": 0.3713, "step": 612 }, { "epoch": 2.4830379746835445, "grad_norm": 0.426371601078682, "learning_rate": 2.3584699777776222e-05, "loss": 0.3825, "step": 613 }, { "epoch": 2.4870886075949366, "grad_norm": 0.42302933170646984, "learning_rate": 2.3528845875977195e-05, "loss": 0.3919, "step": 614 }, { "epoch": 2.491139240506329, "grad_norm": 0.38533220547056257, "learning_rate": 2.3472963553338614e-05, "loss": 0.3592, "step": 615 }, { "epoch": 2.4951898734177216, "grad_norm": 0.40860682970375306, "learning_rate": 2.341705325992901e-05, "loss": 0.3566, "step": 616 }, { "epoch": 2.499240506329114, "grad_norm": 0.40613846944369136, "learning_rate": 2.336111544604222e-05, "loss": 0.3903, "step": 617 }, { "epoch": 2.503291139240506, "grad_norm": 0.39707656021074544, "learning_rate": 2.33051505621937e-05, "loss": 0.3691, "step": 618 }, { "epoch": 2.5073417721518987, "grad_norm": 0.39849033644637954, "learning_rate": 2.324915905911693e-05, "loss": 0.3715, "step": 619 }, { "epoch": 2.511392405063291, "grad_norm": 0.40362253953840904, "learning_rate": 2.319314138775977e-05, "loss": 0.3948, "step": 620 }, { "epoch": 2.5154430379746833, "grad_norm": 0.3800778998931035, "learning_rate": 2.3137097999280856e-05, "loss": 0.3708, "step": 621 }, { "epoch": 2.519493670886076, "grad_norm": 0.4108863682578557, "learning_rate": 2.308102934504593e-05, "loss": 0.3712, "step": 622 }, { "epoch": 2.5235443037974683, "grad_norm": 0.41178274941826276, "learning_rate": 2.3024935876624222e-05, "loss": 0.386, "step": 623 }, { "epoch": 2.527594936708861, "grad_norm": 0.40523567875891287, "learning_rate": 2.2968818045784813e-05, "loss": 0.3658, "step": 624 }, { "epoch": 2.5316455696202533, "grad_norm": 0.42019246856179043, "learning_rate": 2.2912676304493006e-05, "loss": 0.373, "step": 625 }, { "epoch": 2.5356962025316454, "grad_norm": 0.3984424910747556, "learning_rate": 2.2856511104906668e-05, "loss": 0.3679, "step": 626 }, { "epoch": 2.539746835443038, "grad_norm": 0.4189559601590643, "learning_rate": 2.2800322899372586e-05, "loss": 0.3589, "step": 627 }, { "epoch": 2.5437974683544304, "grad_norm": 0.39978467279069246, "learning_rate": 2.2744112140422844e-05, "loss": 0.4014, "step": 628 }, { "epoch": 2.547848101265823, "grad_norm": 0.4485449817637018, "learning_rate": 2.2687879280771177e-05, "loss": 0.3552, "step": 629 }, { "epoch": 2.5518987341772155, "grad_norm": 0.4274488602918429, "learning_rate": 2.26316247733093e-05, "loss": 0.3797, "step": 630 }, { "epoch": 2.5559493670886075, "grad_norm": 0.4440990299162182, "learning_rate": 2.257534907110328e-05, "loss": 0.3496, "step": 631 }, { "epoch": 2.56, "grad_norm": 0.42941387215419513, "learning_rate": 2.2519052627389882e-05, "loss": 0.3726, "step": 632 }, { "epoch": 2.5640506329113926, "grad_norm": 0.4277514119345334, "learning_rate": 2.246273589557294e-05, "loss": 0.3732, "step": 633 }, { "epoch": 2.5681012658227846, "grad_norm": 0.43311477353078304, "learning_rate": 2.240639932921966e-05, "loss": 0.3741, "step": 634 }, { "epoch": 2.572151898734177, "grad_norm": 0.40788575620410517, "learning_rate": 2.2350043382056995e-05, "loss": 0.3662, "step": 635 }, { "epoch": 2.5762025316455697, "grad_norm": 0.4457833382577792, "learning_rate": 2.2293668507968015e-05, "loss": 0.358, "step": 636 }, { "epoch": 2.580253164556962, "grad_norm": 0.3823820184493904, "learning_rate": 2.2237275160988186e-05, "loss": 0.3712, "step": 637 }, { "epoch": 2.5843037974683547, "grad_norm": 0.4170456508870231, "learning_rate": 2.2180863795301787e-05, "loss": 0.3704, "step": 638 }, { "epoch": 2.5883544303797468, "grad_norm": 0.4413740671226022, "learning_rate": 2.212443486523819e-05, "loss": 0.3864, "step": 639 }, { "epoch": 2.5924050632911393, "grad_norm": 0.3932808927667984, "learning_rate": 2.2067988825268243e-05, "loss": 0.3628, "step": 640 }, { "epoch": 2.596455696202532, "grad_norm": 0.44367953921778874, "learning_rate": 2.2011526130000596e-05, "loss": 0.3349, "step": 641 }, { "epoch": 2.600506329113924, "grad_norm": 0.43411066160775447, "learning_rate": 2.1955047234178038e-05, "loss": 0.3865, "step": 642 }, { "epoch": 2.6045569620253164, "grad_norm": 0.4702456658734154, "learning_rate": 2.1898552592673825e-05, "loss": 0.373, "step": 643 }, { "epoch": 2.608607594936709, "grad_norm": 0.4533100179174241, "learning_rate": 2.184204266048803e-05, "loss": 0.3671, "step": 644 }, { "epoch": 2.6126582278481014, "grad_norm": 0.44384397024774846, "learning_rate": 2.1785517892743887e-05, "loss": 0.3609, "step": 645 }, { "epoch": 2.616708860759494, "grad_norm": 0.39240718307635075, "learning_rate": 2.17289787446841e-05, "loss": 0.3701, "step": 646 }, { "epoch": 2.620759493670886, "grad_norm": 0.4744973896494446, "learning_rate": 2.1672425671667198e-05, "loss": 0.3701, "step": 647 }, { "epoch": 2.6248101265822785, "grad_norm": 0.4133943146910515, "learning_rate": 2.161585912916385e-05, "loss": 0.3941, "step": 648 }, { "epoch": 2.628860759493671, "grad_norm": 0.43857838062590043, "learning_rate": 2.1559279572753214e-05, "loss": 0.3656, "step": 649 }, { "epoch": 2.632911392405063, "grad_norm": 0.4137321397680253, "learning_rate": 2.1502687458119268e-05, "loss": 0.3518, "step": 650 }, { "epoch": 2.6369620253164556, "grad_norm": 0.42422425423609855, "learning_rate": 2.1446083241047116e-05, "loss": 0.3463, "step": 651 }, { "epoch": 2.641012658227848, "grad_norm": 0.411904483273694, "learning_rate": 2.1389467377419333e-05, "loss": 0.3838, "step": 652 }, { "epoch": 2.6450632911392407, "grad_norm": 0.49240658639192103, "learning_rate": 2.133284032321232e-05, "loss": 0.3873, "step": 653 }, { "epoch": 2.649113924050633, "grad_norm": 0.3983820132528654, "learning_rate": 2.1276202534492566e-05, "loss": 0.3601, "step": 654 }, { "epoch": 2.6531645569620252, "grad_norm": 0.42279843521354604, "learning_rate": 2.121955446741306e-05, "loss": 0.3721, "step": 655 }, { "epoch": 2.6572151898734178, "grad_norm": 0.4173248006819661, "learning_rate": 2.1162896578209517e-05, "loss": 0.3687, "step": 656 }, { "epoch": 2.6612658227848103, "grad_norm": 0.40021312984389495, "learning_rate": 2.1106229323196813e-05, "loss": 0.3596, "step": 657 }, { "epoch": 2.6653164556962023, "grad_norm": 0.421119566521401, "learning_rate": 2.1049553158765214e-05, "loss": 0.3629, "step": 658 }, { "epoch": 2.669367088607595, "grad_norm": 0.39812035875358287, "learning_rate": 2.0992868541376764e-05, "loss": 0.3752, "step": 659 }, { "epoch": 2.6734177215189874, "grad_norm": 0.42085443992201205, "learning_rate": 2.093617592756158e-05, "loss": 0.3849, "step": 660 }, { "epoch": 2.67746835443038, "grad_norm": 0.4266239405671444, "learning_rate": 2.0879475773914167e-05, "loss": 0.3662, "step": 661 }, { "epoch": 2.6815189873417724, "grad_norm": 0.3899582119579478, "learning_rate": 2.082276853708978e-05, "loss": 0.3728, "step": 662 }, { "epoch": 2.6855696202531645, "grad_norm": 0.3785459232859425, "learning_rate": 2.076605467380071e-05, "loss": 0.3811, "step": 663 }, { "epoch": 2.689620253164557, "grad_norm": 0.38179549706310895, "learning_rate": 2.0709334640812613e-05, "loss": 0.3691, "step": 664 }, { "epoch": 2.6936708860759495, "grad_norm": 0.395932387889565, "learning_rate": 2.0652608894940824e-05, "loss": 0.3742, "step": 665 }, { "epoch": 2.6977215189873416, "grad_norm": 0.40291622293059337, "learning_rate": 2.0595877893046722e-05, "loss": 0.3675, "step": 666 }, { "epoch": 2.701772151898734, "grad_norm": 0.39659956838507004, "learning_rate": 2.0539142092033985e-05, "loss": 0.3597, "step": 667 }, { "epoch": 2.7058227848101266, "grad_norm": 0.3849031305059263, "learning_rate": 2.048240194884496e-05, "loss": 0.3622, "step": 668 }, { "epoch": 2.709873417721519, "grad_norm": 0.39114812117824926, "learning_rate": 2.042565792045695e-05, "loss": 0.3818, "step": 669 }, { "epoch": 2.7139240506329116, "grad_norm": 0.40491221432742, "learning_rate": 2.036891046387857e-05, "loss": 0.3794, "step": 670 }, { "epoch": 2.7179746835443037, "grad_norm": 0.4215119499417089, "learning_rate": 2.0312160036146036e-05, "loss": 0.3695, "step": 671 }, { "epoch": 2.7220253164556962, "grad_norm": 0.3847678128236736, "learning_rate": 2.025540709431948e-05, "loss": 0.3617, "step": 672 }, { "epoch": 2.7260759493670887, "grad_norm": 0.42569054144948903, "learning_rate": 2.0198652095479298e-05, "loss": 0.3711, "step": 673 }, { "epoch": 2.730126582278481, "grad_norm": 0.4121936501610457, "learning_rate": 2.014189549672245e-05, "loss": 0.3675, "step": 674 }, { "epoch": 2.7341772151898733, "grad_norm": 0.43320010878069015, "learning_rate": 2.0085137755158776e-05, "loss": 0.3356, "step": 675 }, { "epoch": 2.738227848101266, "grad_norm": 0.4045767056760224, "learning_rate": 2.0028379327907327e-05, "loss": 0.3724, "step": 676 }, { "epoch": 2.7422784810126584, "grad_norm": 0.42788867034009725, "learning_rate": 1.9971620672092676e-05, "loss": 0.3693, "step": 677 }, { "epoch": 2.746329113924051, "grad_norm": 0.468272308120219, "learning_rate": 1.991486224484123e-05, "loss": 0.3783, "step": 678 }, { "epoch": 2.750379746835443, "grad_norm": 0.38890789297964456, "learning_rate": 1.985810450327756e-05, "loss": 0.3723, "step": 679 }, { "epoch": 2.7544303797468355, "grad_norm": 0.4242478782458202, "learning_rate": 1.9801347904520706e-05, "loss": 0.3783, "step": 680 }, { "epoch": 2.758481012658228, "grad_norm": 0.40961108832430104, "learning_rate": 1.974459290568053e-05, "loss": 0.375, "step": 681 }, { "epoch": 2.76253164556962, "grad_norm": 0.39379378228097206, "learning_rate": 1.968783996385397e-05, "loss": 0.3794, "step": 682 }, { "epoch": 2.7665822784810126, "grad_norm": 0.41598327350014674, "learning_rate": 1.963108953612143e-05, "loss": 0.3715, "step": 683 }, { "epoch": 2.770632911392405, "grad_norm": 0.3891317727536846, "learning_rate": 1.9574342079543056e-05, "loss": 0.3565, "step": 684 }, { "epoch": 2.7746835443037976, "grad_norm": 0.4103409927283351, "learning_rate": 1.9517598051155046e-05, "loss": 0.3748, "step": 685 }, { "epoch": 2.77873417721519, "grad_norm": 0.41135575208215835, "learning_rate": 1.9460857907966025e-05, "loss": 0.3547, "step": 686 }, { "epoch": 2.782784810126582, "grad_norm": 0.4204920713032355, "learning_rate": 1.9404122106953285e-05, "loss": 0.375, "step": 687 }, { "epoch": 2.7868354430379747, "grad_norm": 0.39113401726066166, "learning_rate": 1.9347391105059176e-05, "loss": 0.3882, "step": 688 }, { "epoch": 2.790886075949367, "grad_norm": 0.39641218767700526, "learning_rate": 1.92906653591874e-05, "loss": 0.3541, "step": 689 }, { "epoch": 2.7949367088607593, "grad_norm": 0.3989946170573458, "learning_rate": 1.9233945326199295e-05, "loss": 0.3567, "step": 690 }, { "epoch": 2.798987341772152, "grad_norm": 0.39430323549967644, "learning_rate": 1.917723146291022e-05, "loss": 0.3578, "step": 691 }, { "epoch": 2.8030379746835443, "grad_norm": 0.39967516740199044, "learning_rate": 1.912052422608584e-05, "loss": 0.3694, "step": 692 }, { "epoch": 2.807088607594937, "grad_norm": 0.42988499871616237, "learning_rate": 1.9063824072438428e-05, "loss": 0.3655, "step": 693 }, { "epoch": 2.8111392405063294, "grad_norm": 0.3989356477400175, "learning_rate": 1.9007131458623246e-05, "loss": 0.3613, "step": 694 }, { "epoch": 2.8151898734177214, "grad_norm": 0.39111194802516314, "learning_rate": 1.895044684123479e-05, "loss": 0.3735, "step": 695 }, { "epoch": 2.819240506329114, "grad_norm": 0.41064978376635425, "learning_rate": 1.8893770676803194e-05, "loss": 0.3738, "step": 696 }, { "epoch": 2.8232911392405065, "grad_norm": 0.38670532184362616, "learning_rate": 1.8837103421790486e-05, "loss": 0.367, "step": 697 }, { "epoch": 2.8273417721518985, "grad_norm": 0.40282363675499194, "learning_rate": 1.8780445532586952e-05, "loss": 0.3806, "step": 698 }, { "epoch": 2.831392405063291, "grad_norm": 0.4097640654376659, "learning_rate": 1.872379746550743e-05, "loss": 0.3848, "step": 699 }, { "epoch": 2.8354430379746836, "grad_norm": 0.3736037869777538, "learning_rate": 1.866715967678769e-05, "loss": 0.3538, "step": 700 }, { "epoch": 2.839493670886076, "grad_norm": 0.42186827866144927, "learning_rate": 1.861053262258067e-05, "loss": 0.3653, "step": 701 }, { "epoch": 2.8435443037974686, "grad_norm": 0.3828521016105029, "learning_rate": 1.8553916758952897e-05, "loss": 0.3436, "step": 702 }, { "epoch": 2.8475949367088607, "grad_norm": 0.3898737733451848, "learning_rate": 1.8497312541880735e-05, "loss": 0.3728, "step": 703 }, { "epoch": 2.851645569620253, "grad_norm": 0.3766955775775389, "learning_rate": 1.8440720427246786e-05, "loss": 0.3766, "step": 704 }, { "epoch": 2.8556962025316457, "grad_norm": 0.3935755981375248, "learning_rate": 1.8384140870836157e-05, "loss": 0.3886, "step": 705 }, { "epoch": 2.8597468354430378, "grad_norm": 0.37085329539081946, "learning_rate": 1.8327574328332806e-05, "loss": 0.3697, "step": 706 }, { "epoch": 2.8637974683544303, "grad_norm": 0.38818712419439905, "learning_rate": 1.8271021255315906e-05, "loss": 0.3829, "step": 707 }, { "epoch": 2.867848101265823, "grad_norm": 0.4289905400809947, "learning_rate": 1.8214482107256117e-05, "loss": 0.3592, "step": 708 }, { "epoch": 2.8718987341772153, "grad_norm": 0.37451178948858105, "learning_rate": 1.8157957339511968e-05, "loss": 0.3993, "step": 709 }, { "epoch": 2.875949367088608, "grad_norm": 0.44222588792983913, "learning_rate": 1.8101447407326182e-05, "loss": 0.3754, "step": 710 }, { "epoch": 2.88, "grad_norm": 0.4047036168756511, "learning_rate": 1.8044952765821966e-05, "loss": 0.366, "step": 711 }, { "epoch": 2.8840506329113924, "grad_norm": 0.38299424086343464, "learning_rate": 1.7988473869999407e-05, "loss": 0.3849, "step": 712 }, { "epoch": 2.888101265822785, "grad_norm": 0.3681593207153196, "learning_rate": 1.7932011174731764e-05, "loss": 0.3635, "step": 713 }, { "epoch": 2.892151898734177, "grad_norm": 0.39905486366346515, "learning_rate": 1.7875565134761817e-05, "loss": 0.3795, "step": 714 }, { "epoch": 2.8962025316455695, "grad_norm": 0.41817541099335387, "learning_rate": 1.7819136204698226e-05, "loss": 0.3837, "step": 715 }, { "epoch": 2.900253164556962, "grad_norm": 0.35831324613586873, "learning_rate": 1.776272483901182e-05, "loss": 0.3557, "step": 716 }, { "epoch": 2.9043037974683545, "grad_norm": 0.410271133343394, "learning_rate": 1.7706331492031995e-05, "loss": 0.3768, "step": 717 }, { "epoch": 2.908354430379747, "grad_norm": 0.38998518843521224, "learning_rate": 1.764995661794301e-05, "loss": 0.3961, "step": 718 }, { "epoch": 2.912405063291139, "grad_norm": 0.4069242750874857, "learning_rate": 1.759360067078035e-05, "loss": 0.3703, "step": 719 }, { "epoch": 2.9164556962025316, "grad_norm": 0.42229565205720937, "learning_rate": 1.7537264104427064e-05, "loss": 0.3718, "step": 720 }, { "epoch": 2.920506329113924, "grad_norm": 0.3861538502354226, "learning_rate": 1.748094737261012e-05, "loss": 0.3482, "step": 721 }, { "epoch": 2.9245569620253162, "grad_norm": 0.4244049899915365, "learning_rate": 1.7424650928896726e-05, "loss": 0.3649, "step": 722 }, { "epoch": 2.9286075949367087, "grad_norm": 0.39830768629566043, "learning_rate": 1.7368375226690712e-05, "loss": 0.3593, "step": 723 }, { "epoch": 2.9326582278481013, "grad_norm": 0.39724334336383826, "learning_rate": 1.731212071922883e-05, "loss": 0.372, "step": 724 }, { "epoch": 2.9367088607594938, "grad_norm": 0.3981795120772432, "learning_rate": 1.7255887859577156e-05, "loss": 0.3687, "step": 725 }, { "epoch": 2.9407594936708863, "grad_norm": 0.4029025679818547, "learning_rate": 1.7199677100627427e-05, "loss": 0.3778, "step": 726 }, { "epoch": 2.9448101265822784, "grad_norm": 0.39004586149521336, "learning_rate": 1.7143488895093343e-05, "loss": 0.3942, "step": 727 }, { "epoch": 2.948860759493671, "grad_norm": 0.37101183793144815, "learning_rate": 1.7087323695506994e-05, "loss": 0.3465, "step": 728 }, { "epoch": 2.9529113924050634, "grad_norm": 0.38189428194537034, "learning_rate": 1.7031181954215194e-05, "loss": 0.3826, "step": 729 }, { "epoch": 2.9569620253164555, "grad_norm": 0.37156770980830045, "learning_rate": 1.6975064123375788e-05, "loss": 0.3812, "step": 730 }, { "epoch": 2.961012658227848, "grad_norm": 0.3565559201926141, "learning_rate": 1.6918970654954084e-05, "loss": 0.3764, "step": 731 }, { "epoch": 2.9650632911392405, "grad_norm": 0.38273458191046733, "learning_rate": 1.686290200071915e-05, "loss": 0.362, "step": 732 }, { "epoch": 2.969113924050633, "grad_norm": 0.3821382236756743, "learning_rate": 1.6806858612240234e-05, "loss": 0.3895, "step": 733 }, { "epoch": 2.9731645569620255, "grad_norm": 0.37791777018567396, "learning_rate": 1.6750840940883078e-05, "loss": 0.3861, "step": 734 }, { "epoch": 2.9772151898734176, "grad_norm": 0.41136655543818945, "learning_rate": 1.6694849437806305e-05, "loss": 0.3703, "step": 735 }, { "epoch": 2.98126582278481, "grad_norm": 0.37296555362419415, "learning_rate": 1.663888455395778e-05, "loss": 0.3674, "step": 736 }, { "epoch": 2.9853164556962026, "grad_norm": 0.40080828889227926, "learning_rate": 1.6582946740070995e-05, "loss": 0.368, "step": 737 }, { "epoch": 2.9893670886075947, "grad_norm": 0.3798034622554824, "learning_rate": 1.6527036446661396e-05, "loss": 0.3646, "step": 738 }, { "epoch": 2.993417721518987, "grad_norm": 0.3731163363333034, "learning_rate": 1.6471154124022818e-05, "loss": 0.3829, "step": 739 }, { "epoch": 2.9974683544303797, "grad_norm": 0.3932129468239548, "learning_rate": 1.6415300222223788e-05, "loss": 0.3817, "step": 740 }, { "epoch": 3.0015189873417722, "grad_norm": 0.43539121321572016, "learning_rate": 1.6359475191103958e-05, "loss": 0.3248, "step": 741 }, { "epoch": 3.0055696202531648, "grad_norm": 0.49700391024323676, "learning_rate": 1.6303679480270466e-05, "loss": 0.2784, "step": 742 }, { "epoch": 3.009620253164557, "grad_norm": 0.389377952678054, "learning_rate": 1.624791353909428e-05, "loss": 0.2712, "step": 743 }, { "epoch": 3.0136708860759494, "grad_norm": 0.713841120055433, "learning_rate": 1.619217781670663e-05, "loss": 0.2816, "step": 744 }, { "epoch": 3.017721518987342, "grad_norm": 0.48104148441435474, "learning_rate": 1.6136472761995373e-05, "loss": 0.2698, "step": 745 }, { "epoch": 3.0217721518987344, "grad_norm": 0.4614399297362673, "learning_rate": 1.608079882360134e-05, "loss": 0.2467, "step": 746 }, { "epoch": 3.0258227848101265, "grad_norm": 0.5075194162317498, "learning_rate": 1.60251564499148e-05, "loss": 0.2534, "step": 747 }, { "epoch": 3.029873417721519, "grad_norm": 0.49161123122393924, "learning_rate": 1.596954608907176e-05, "loss": 0.2473, "step": 748 }, { "epoch": 3.0339240506329115, "grad_norm": 0.4232599373181789, "learning_rate": 1.591396818895043e-05, "loss": 0.2617, "step": 749 }, { "epoch": 3.037974683544304, "grad_norm": 0.4314928165195653, "learning_rate": 1.585842319716759e-05, "loss": 0.2443, "step": 750 }, { "epoch": 3.042025316455696, "grad_norm": 0.4953616838224337, "learning_rate": 1.5802911561074944e-05, "loss": 0.2678, "step": 751 }, { "epoch": 3.0460759493670886, "grad_norm": 0.41002766760933484, "learning_rate": 1.5747433727755595e-05, "loss": 0.2606, "step": 752 }, { "epoch": 3.050126582278481, "grad_norm": 0.3953239698682005, "learning_rate": 1.5691990144020376e-05, "loss": 0.241, "step": 753 }, { "epoch": 3.0541772151898736, "grad_norm": 0.4654809998021321, "learning_rate": 1.5636581256404297e-05, "loss": 0.2532, "step": 754 }, { "epoch": 3.0582278481012657, "grad_norm": 0.39656427335867606, "learning_rate": 1.558120751116291e-05, "loss": 0.2683, "step": 755 }, { "epoch": 3.062278481012658, "grad_norm": 0.4526624242344836, "learning_rate": 1.552586935426876e-05, "loss": 0.2578, "step": 756 }, { "epoch": 3.0663291139240507, "grad_norm": 0.4176674725802229, "learning_rate": 1.547056723140774e-05, "loss": 0.264, "step": 757 }, { "epoch": 3.0703797468354432, "grad_norm": 0.37195800442105237, "learning_rate": 1.5415301587975565e-05, "loss": 0.2572, "step": 758 }, { "epoch": 3.0744303797468353, "grad_norm": 0.4381675431756145, "learning_rate": 1.536007286907411e-05, "loss": 0.2776, "step": 759 }, { "epoch": 3.078481012658228, "grad_norm": 0.3918978114126695, "learning_rate": 1.5304881519507896e-05, "loss": 0.2467, "step": 760 }, { "epoch": 3.0825316455696203, "grad_norm": 0.35607567381340915, "learning_rate": 1.5249727983780453e-05, "loss": 0.2405, "step": 761 }, { "epoch": 3.086582278481013, "grad_norm": 0.39277463410111496, "learning_rate": 1.5194612706090786e-05, "loss": 0.2416, "step": 762 }, { "epoch": 3.090632911392405, "grad_norm": 0.371897549081771, "learning_rate": 1.5139536130329771e-05, "loss": 0.2587, "step": 763 }, { "epoch": 3.0946835443037974, "grad_norm": 0.3843002221361875, "learning_rate": 1.508449870007656e-05, "loss": 0.2559, "step": 764 }, { "epoch": 3.09873417721519, "grad_norm": 0.34660735656738145, "learning_rate": 1.5029500858595056e-05, "loss": 0.2773, "step": 765 }, { "epoch": 3.1027848101265825, "grad_norm": 0.40711956698730173, "learning_rate": 1.4974543048830328e-05, "loss": 0.2217, "step": 766 }, { "epoch": 3.1068354430379745, "grad_norm": 0.3916757829315185, "learning_rate": 1.4919625713405e-05, "loss": 0.2665, "step": 767 }, { "epoch": 3.110886075949367, "grad_norm": 0.3431929990372084, "learning_rate": 1.4864749294615756e-05, "loss": 0.2289, "step": 768 }, { "epoch": 3.1149367088607596, "grad_norm": 0.3428761275630128, "learning_rate": 1.4809914234429716e-05, "loss": 0.2791, "step": 769 }, { "epoch": 3.118987341772152, "grad_norm": 0.3644697373177075, "learning_rate": 1.4755120974480923e-05, "loss": 0.267, "step": 770 }, { "epoch": 3.123037974683544, "grad_norm": 0.32770798162809994, "learning_rate": 1.4700369956066771e-05, "loss": 0.2542, "step": 771 }, { "epoch": 3.1270886075949367, "grad_norm": 0.3473754993432556, "learning_rate": 1.4645661620144413e-05, "loss": 0.2572, "step": 772 }, { "epoch": 3.131139240506329, "grad_norm": 0.3365975082772844, "learning_rate": 1.4590996407327284e-05, "loss": 0.2421, "step": 773 }, { "epoch": 3.1351898734177217, "grad_norm": 0.3572554306554314, "learning_rate": 1.4536374757881487e-05, "loss": 0.2393, "step": 774 }, { "epoch": 3.1392405063291138, "grad_norm": 0.32860114110228333, "learning_rate": 1.4481797111722271e-05, "loss": 0.2409, "step": 775 }, { "epoch": 3.1432911392405063, "grad_norm": 0.34852434292084045, "learning_rate": 1.4427263908410507e-05, "loss": 0.2674, "step": 776 }, { "epoch": 3.147341772151899, "grad_norm": 0.38628503981330914, "learning_rate": 1.4372775587149108e-05, "loss": 0.2503, "step": 777 }, { "epoch": 3.1513924050632913, "grad_norm": 0.34538548736336877, "learning_rate": 1.4318332586779522e-05, "loss": 0.2619, "step": 778 }, { "epoch": 3.1554430379746834, "grad_norm": 0.33270631985367083, "learning_rate": 1.4263935345778202e-05, "loss": 0.2615, "step": 779 }, { "epoch": 3.159493670886076, "grad_norm": 0.35534141368839484, "learning_rate": 1.420958430225303e-05, "loss": 0.2379, "step": 780 }, { "epoch": 3.1635443037974684, "grad_norm": 0.3414612443009216, "learning_rate": 1.415527989393985e-05, "loss": 0.2555, "step": 781 }, { "epoch": 3.167594936708861, "grad_norm": 0.3389320581048556, "learning_rate": 1.410102255819891e-05, "loss": 0.2519, "step": 782 }, { "epoch": 3.171645569620253, "grad_norm": 0.3636706468157261, "learning_rate": 1.404681273201131e-05, "loss": 0.2429, "step": 783 }, { "epoch": 3.1756962025316455, "grad_norm": 0.3485251044190549, "learning_rate": 1.399265085197556e-05, "loss": 0.2301, "step": 784 }, { "epoch": 3.179746835443038, "grad_norm": 0.3396364612249536, "learning_rate": 1.393853735430398e-05, "loss": 0.2431, "step": 785 }, { "epoch": 3.1837974683544306, "grad_norm": 0.34871686144308595, "learning_rate": 1.3884472674819246e-05, "loss": 0.2271, "step": 786 }, { "epoch": 3.1878481012658226, "grad_norm": 0.34084165280517936, "learning_rate": 1.3830457248950864e-05, "loss": 0.256, "step": 787 }, { "epoch": 3.191898734177215, "grad_norm": 0.35144128761677923, "learning_rate": 1.377649151173163e-05, "loss": 0.2287, "step": 788 }, { "epoch": 3.1959493670886077, "grad_norm": 0.3469312172033076, "learning_rate": 1.3722575897794181e-05, "loss": 0.257, "step": 789 }, { "epoch": 3.2, "grad_norm": 0.36807017595172925, "learning_rate": 1.3668710841367472e-05, "loss": 0.254, "step": 790 }, { "epoch": 3.2040506329113922, "grad_norm": 0.33060759423409336, "learning_rate": 1.361489677627324e-05, "loss": 0.2459, "step": 791 }, { "epoch": 3.2081012658227848, "grad_norm": 0.3451167932866548, "learning_rate": 1.3561134135922585e-05, "loss": 0.2554, "step": 792 }, { "epoch": 3.2121518987341773, "grad_norm": 0.36706606739771197, "learning_rate": 1.350742335331241e-05, "loss": 0.2541, "step": 793 }, { "epoch": 3.21620253164557, "grad_norm": 0.3404552309497851, "learning_rate": 1.345376486102198e-05, "loss": 0.2722, "step": 794 }, { "epoch": 3.220253164556962, "grad_norm": 0.3281256999916833, "learning_rate": 1.3400159091209414e-05, "loss": 0.2517, "step": 795 }, { "epoch": 3.2243037974683544, "grad_norm": 0.3595564397939426, "learning_rate": 1.3346606475608216e-05, "loss": 0.2425, "step": 796 }, { "epoch": 3.228354430379747, "grad_norm": 0.35468735762080367, "learning_rate": 1.3293107445523781e-05, "loss": 0.2385, "step": 797 }, { "epoch": 3.2324050632911394, "grad_norm": 0.3611861804982945, "learning_rate": 1.3239662431829949e-05, "loss": 0.2728, "step": 798 }, { "epoch": 3.2364556962025315, "grad_norm": 0.3392920816465932, "learning_rate": 1.3186271864965509e-05, "loss": 0.2618, "step": 799 }, { "epoch": 3.240506329113924, "grad_norm": 0.34507396687249847, "learning_rate": 1.3132936174930756e-05, "loss": 0.22, "step": 800 }, { "epoch": 3.2445569620253165, "grad_norm": 0.353907193155557, "learning_rate": 1.3079655791283995e-05, "loss": 0.2568, "step": 801 }, { "epoch": 3.248607594936709, "grad_norm": 0.3250128471581453, "learning_rate": 1.3026431143138108e-05, "loss": 0.2988, "step": 802 }, { "epoch": 3.252658227848101, "grad_norm": 0.3320456206398761, "learning_rate": 1.2973262659157114e-05, "loss": 0.2535, "step": 803 }, { "epoch": 3.2567088607594936, "grad_norm": 0.35938622251195285, "learning_rate": 1.2920150767552651e-05, "loss": 0.2601, "step": 804 }, { "epoch": 3.260759493670886, "grad_norm": 0.35552376015259884, "learning_rate": 1.2867095896080607e-05, "loss": 0.2438, "step": 805 }, { "epoch": 3.2648101265822786, "grad_norm": 0.37770206477291607, "learning_rate": 1.2814098472037612e-05, "loss": 0.2311, "step": 806 }, { "epoch": 3.2688607594936707, "grad_norm": 0.33806437340004125, "learning_rate": 1.276115892225764e-05, "loss": 0.2687, "step": 807 }, { "epoch": 3.2729113924050632, "grad_norm": 0.3205407403818449, "learning_rate": 1.2708277673108555e-05, "loss": 0.2546, "step": 808 }, { "epoch": 3.2769620253164558, "grad_norm": 0.3460974134643588, "learning_rate": 1.2655455150488649e-05, "loss": 0.2536, "step": 809 }, { "epoch": 3.2810126582278483, "grad_norm": 0.3285936316278642, "learning_rate": 1.2602691779823272e-05, "loss": 0.2638, "step": 810 }, { "epoch": 3.2850632911392403, "grad_norm": 0.3205833322936304, "learning_rate": 1.2549987986061355e-05, "loss": 0.2397, "step": 811 }, { "epoch": 3.289113924050633, "grad_norm": 0.34309236801444165, "learning_rate": 1.2497344193672005e-05, "loss": 0.2501, "step": 812 }, { "epoch": 3.2931645569620254, "grad_norm": 0.32209364647748134, "learning_rate": 1.2444760826641092e-05, "loss": 0.2963, "step": 813 }, { "epoch": 3.297215189873418, "grad_norm": 0.31302694518587426, "learning_rate": 1.2392238308467817e-05, "loss": 0.2662, "step": 814 }, { "epoch": 3.30126582278481, "grad_norm": 0.33747246887752935, "learning_rate": 1.2339777062161326e-05, "loss": 0.2583, "step": 815 }, { "epoch": 3.3053164556962025, "grad_norm": 0.3448098458502483, "learning_rate": 1.2287377510237293e-05, "loss": 0.259, "step": 816 }, { "epoch": 3.309367088607595, "grad_norm": 0.35104558129050334, "learning_rate": 1.2235040074714488e-05, "loss": 0.2506, "step": 817 }, { "epoch": 3.3134177215189875, "grad_norm": 0.3400818378873631, "learning_rate": 1.2182765177111434e-05, "loss": 0.2395, "step": 818 }, { "epoch": 3.3174683544303796, "grad_norm": 0.33589997759512247, "learning_rate": 1.213055323844297e-05, "loss": 0.2756, "step": 819 }, { "epoch": 3.321518987341772, "grad_norm": 0.32735839802600886, "learning_rate": 1.2078404679216864e-05, "loss": 0.2673, "step": 820 }, { "epoch": 3.3255696202531646, "grad_norm": 0.3516644427832681, "learning_rate": 1.2026319919430458e-05, "loss": 0.2229, "step": 821 }, { "epoch": 3.329620253164557, "grad_norm": 0.3344635295264704, "learning_rate": 1.1974299378567227e-05, "loss": 0.2458, "step": 822 }, { "epoch": 3.333670886075949, "grad_norm": 0.3396556212200211, "learning_rate": 1.1922343475593462e-05, "loss": 0.2747, "step": 823 }, { "epoch": 3.3377215189873417, "grad_norm": 0.3357140065767908, "learning_rate": 1.187045262895488e-05, "loss": 0.2684, "step": 824 }, { "epoch": 3.3417721518987342, "grad_norm": 0.3501071568390257, "learning_rate": 1.1818627256573203e-05, "loss": 0.249, "step": 825 }, { "epoch": 3.3458227848101267, "grad_norm": 0.3395889500267171, "learning_rate": 1.1766867775842864e-05, "loss": 0.2696, "step": 826 }, { "epoch": 3.349873417721519, "grad_norm": 0.3331255980396462, "learning_rate": 1.1715174603627615e-05, "loss": 0.2653, "step": 827 }, { "epoch": 3.3539240506329113, "grad_norm": 0.3331650427113013, "learning_rate": 1.1663548156257147e-05, "loss": 0.2449, "step": 828 }, { "epoch": 3.357974683544304, "grad_norm": 0.3444334074273574, "learning_rate": 1.161198884952377e-05, "loss": 0.2367, "step": 829 }, { "epoch": 3.3620253164556964, "grad_norm": 0.3404146587191193, "learning_rate": 1.1560497098679056e-05, "loss": 0.2474, "step": 830 }, { "epoch": 3.3660759493670884, "grad_norm": 0.3492120772457568, "learning_rate": 1.1509073318430479e-05, "loss": 0.2575, "step": 831 }, { "epoch": 3.370126582278481, "grad_norm": 0.3508799215183199, "learning_rate": 1.1457717922938116e-05, "loss": 0.2406, "step": 832 }, { "epoch": 3.3741772151898735, "grad_norm": 0.341633681642782, "learning_rate": 1.1406431325811233e-05, "loss": 0.2329, "step": 833 }, { "epoch": 3.378227848101266, "grad_norm": 0.3131194638224562, "learning_rate": 1.135521394010506e-05, "loss": 0.2882, "step": 834 }, { "epoch": 3.382278481012658, "grad_norm": 0.3404506450317478, "learning_rate": 1.1304066178317367e-05, "loss": 0.2445, "step": 835 }, { "epoch": 3.3863291139240506, "grad_norm": 0.32161042944540297, "learning_rate": 1.1252988452385199e-05, "loss": 0.2666, "step": 836 }, { "epoch": 3.390379746835443, "grad_norm": 0.3436527474355901, "learning_rate": 1.1201981173681536e-05, "loss": 0.2653, "step": 837 }, { "epoch": 3.3944303797468356, "grad_norm": 0.3415294950757706, "learning_rate": 1.1151044753011991e-05, "loss": 0.2426, "step": 838 }, { "epoch": 3.3984810126582277, "grad_norm": 0.33954017028476485, "learning_rate": 1.1100179600611491e-05, "loss": 0.246, "step": 839 }, { "epoch": 3.40253164556962, "grad_norm": 0.33113053449027485, "learning_rate": 1.1049386126140985e-05, "loss": 0.2633, "step": 840 }, { "epoch": 3.4065822784810127, "grad_norm": 0.3219772064443018, "learning_rate": 1.0998664738684128e-05, "loss": 0.2496, "step": 841 }, { "epoch": 3.410632911392405, "grad_norm": 0.34394310560783814, "learning_rate": 1.0948015846744e-05, "loss": 0.2566, "step": 842 }, { "epoch": 3.4146835443037973, "grad_norm": 0.35082598260269265, "learning_rate": 1.0897439858239832e-05, "loss": 0.2379, "step": 843 }, { "epoch": 3.41873417721519, "grad_norm": 0.3255333453368827, "learning_rate": 1.0846937180503652e-05, "loss": 0.2406, "step": 844 }, { "epoch": 3.4227848101265823, "grad_norm": 0.33494178604611585, "learning_rate": 1.0796508220277117e-05, "loss": 0.2905, "step": 845 }, { "epoch": 3.426835443037975, "grad_norm": 0.34094127872225233, "learning_rate": 1.0746153383708107e-05, "loss": 0.2789, "step": 846 }, { "epoch": 3.430886075949367, "grad_norm": 0.3445775471994141, "learning_rate": 1.0695873076347579e-05, "loss": 0.2289, "step": 847 }, { "epoch": 3.4349367088607594, "grad_norm": 0.3218075952096631, "learning_rate": 1.0645667703146205e-05, "loss": 0.275, "step": 848 }, { "epoch": 3.438987341772152, "grad_norm": 0.34132897609023827, "learning_rate": 1.0595537668451161e-05, "loss": 0.2344, "step": 849 }, { "epoch": 3.4430379746835444, "grad_norm": 0.3378666517577763, "learning_rate": 1.0545483376002854e-05, "loss": 0.2861, "step": 850 }, { "epoch": 3.4470886075949365, "grad_norm": 0.334133296468544, "learning_rate": 1.0495505228931676e-05, "loss": 0.2573, "step": 851 }, { "epoch": 3.451139240506329, "grad_norm": 0.34029941936942854, "learning_rate": 1.044560362975474e-05, "loss": 0.2442, "step": 852 }, { "epoch": 3.4551898734177215, "grad_norm": 0.34497711277099974, "learning_rate": 1.0395778980372695e-05, "loss": 0.2738, "step": 853 }, { "epoch": 3.459240506329114, "grad_norm": 0.33655401773411886, "learning_rate": 1.0346031682066381e-05, "loss": 0.245, "step": 854 }, { "epoch": 3.463291139240506, "grad_norm": 0.32242428760415986, "learning_rate": 1.0296362135493724e-05, "loss": 0.2505, "step": 855 }, { "epoch": 3.4673417721518986, "grad_norm": 0.32070895322400084, "learning_rate": 1.0246770740686422e-05, "loss": 0.2553, "step": 856 }, { "epoch": 3.471392405063291, "grad_norm": 0.33630587819088, "learning_rate": 1.0197257897046743e-05, "loss": 0.2526, "step": 857 }, { "epoch": 3.4754430379746837, "grad_norm": 0.3234176230026245, "learning_rate": 1.014782400334433e-05, "loss": 0.2557, "step": 858 }, { "epoch": 3.479493670886076, "grad_norm": 0.33404355800547597, "learning_rate": 1.009846945771296e-05, "loss": 0.2572, "step": 859 }, { "epoch": 3.4835443037974683, "grad_norm": 0.3274124961963357, "learning_rate": 1.0049194657647363e-05, "loss": 0.2666, "step": 860 }, { "epoch": 3.487594936708861, "grad_norm": 0.32507579886688515, "learning_rate": 1.0000000000000006e-05, "loss": 0.254, "step": 861 }, { "epoch": 3.4916455696202533, "grad_norm": 0.32308940247880397, "learning_rate": 9.950885880977891e-06, "loss": 0.2638, "step": 862 }, { "epoch": 3.4956962025316454, "grad_norm": 0.3172709953174434, "learning_rate": 9.901852696139382e-06, "loss": 0.2412, "step": 863 }, { "epoch": 3.499746835443038, "grad_norm": 0.3208537705533938, "learning_rate": 9.852900840391027e-06, "loss": 0.2776, "step": 864 }, { "epoch": 3.5037974683544304, "grad_norm": 0.32594165991158786, "learning_rate": 9.804030707984313e-06, "loss": 0.2372, "step": 865 }, { "epoch": 3.507848101265823, "grad_norm": 0.34370229834548066, "learning_rate": 9.755242692512599e-06, "loss": 0.2677, "step": 866 }, { "epoch": 3.5118987341772154, "grad_norm": 0.31938704383946814, "learning_rate": 9.70653718690782e-06, "loss": 0.2438, "step": 867 }, { "epoch": 3.5159493670886075, "grad_norm": 0.3098910366668536, "learning_rate": 9.657914583437454e-06, "loss": 0.2471, "step": 868 }, { "epoch": 3.52, "grad_norm": 0.34044518653393036, "learning_rate": 9.609375273701246e-06, "loss": 0.261, "step": 869 }, { "epoch": 3.5240506329113925, "grad_norm": 0.36080456859984245, "learning_rate": 9.560919648628133e-06, "loss": 0.2685, "step": 870 }, { "epoch": 3.5281012658227846, "grad_norm": 0.332311365917315, "learning_rate": 9.512548098473047e-06, "loss": 0.2477, "step": 871 }, { "epoch": 3.532151898734177, "grad_norm": 0.39366971938715123, "learning_rate": 9.464261012813825e-06, "loss": 0.2673, "step": 872 }, { "epoch": 3.5362025316455696, "grad_norm": 0.3342477591954936, "learning_rate": 9.416058780547987e-06, "loss": 0.2457, "step": 873 }, { "epoch": 3.540253164556962, "grad_norm": 0.3224140059008321, "learning_rate": 9.367941789889714e-06, "loss": 0.2742, "step": 874 }, { "epoch": 3.5443037974683547, "grad_norm": 0.3399430145990142, "learning_rate": 9.319910428366607e-06, "loss": 0.2656, "step": 875 }, { "epoch": 3.5483544303797467, "grad_norm": 0.33569994801104824, "learning_rate": 9.271965082816667e-06, "loss": 0.2636, "step": 876 }, { "epoch": 3.5524050632911393, "grad_norm": 0.3469685273015137, "learning_rate": 9.224106139385111e-06, "loss": 0.2537, "step": 877 }, { "epoch": 3.5564556962025318, "grad_norm": 0.31826503069020395, "learning_rate": 9.176333983521291e-06, "loss": 0.2588, "step": 878 }, { "epoch": 3.560506329113924, "grad_norm": 0.3309059370508345, "learning_rate": 9.12864899997558e-06, "loss": 0.2561, "step": 879 }, { "epoch": 3.5645569620253164, "grad_norm": 0.32257404675720397, "learning_rate": 9.08105157279628e-06, "loss": 0.2731, "step": 880 }, { "epoch": 3.568607594936709, "grad_norm": 0.33134410350759497, "learning_rate": 9.03354208532653e-06, "loss": 0.254, "step": 881 }, { "epoch": 3.5726582278481014, "grad_norm": 0.3373491648058688, "learning_rate": 8.986120920201205e-06, "loss": 0.2469, "step": 882 }, { "epoch": 3.576708860759494, "grad_norm": 0.3324067400724557, "learning_rate": 8.938788459343852e-06, "loss": 0.2317, "step": 883 }, { "epoch": 3.580759493670886, "grad_norm": 0.3400939872392258, "learning_rate": 8.8915450839636e-06, "loss": 0.2352, "step": 884 }, { "epoch": 3.5848101265822785, "grad_norm": 0.33630953186241164, "learning_rate": 8.844391174552116e-06, "loss": 0.2422, "step": 885 }, { "epoch": 3.588860759493671, "grad_norm": 0.3086629500288403, "learning_rate": 8.797327110880479e-06, "loss": 0.2384, "step": 886 }, { "epoch": 3.592911392405063, "grad_norm": 0.3200574686276472, "learning_rate": 8.750353271996206e-06, "loss": 0.2395, "step": 887 }, { "epoch": 3.5969620253164556, "grad_norm": 0.3263884769739549, "learning_rate": 8.703470036220132e-06, "loss": 0.2506, "step": 888 }, { "epoch": 3.601012658227848, "grad_norm": 0.3477067671548508, "learning_rate": 8.656677781143394e-06, "loss": 0.2577, "step": 889 }, { "epoch": 3.6050632911392406, "grad_norm": 0.3224730436465289, "learning_rate": 8.609976883624377e-06, "loss": 0.2478, "step": 890 }, { "epoch": 3.609113924050633, "grad_norm": 0.3209083072099017, "learning_rate": 8.563367719785698e-06, "loss": 0.2501, "step": 891 }, { "epoch": 3.613164556962025, "grad_norm": 0.3201409948096207, "learning_rate": 8.516850665011138e-06, "loss": 0.2499, "step": 892 }, { "epoch": 3.6172151898734177, "grad_norm": 0.3301019089692246, "learning_rate": 8.47042609394269e-06, "loss": 0.2375, "step": 893 }, { "epoch": 3.6212658227848102, "grad_norm": 0.32586899310866974, "learning_rate": 8.424094380477432e-06, "loss": 0.2555, "step": 894 }, { "epoch": 3.6253164556962023, "grad_norm": 0.333770563088332, "learning_rate": 8.37785589776465e-06, "loss": 0.2578, "step": 895 }, { "epoch": 3.629367088607595, "grad_norm": 0.3211001224861963, "learning_rate": 8.331711018202694e-06, "loss": 0.2423, "step": 896 }, { "epoch": 3.6334177215189873, "grad_norm": 0.33492552872630266, "learning_rate": 8.285660113436104e-06, "loss": 0.2382, "step": 897 }, { "epoch": 3.63746835443038, "grad_norm": 0.331749192839683, "learning_rate": 8.239703554352527e-06, "loss": 0.2703, "step": 898 }, { "epoch": 3.6415189873417724, "grad_norm": 0.3247019754787045, "learning_rate": 8.193841711079775e-06, "loss": 0.2421, "step": 899 }, { "epoch": 3.6455696202531644, "grad_norm": 0.31808486500818345, "learning_rate": 8.148074952982828e-06, "loss": 0.25, "step": 900 }, { "epoch": 3.649620253164557, "grad_norm": 0.3057583708683866, "learning_rate": 8.102403648660859e-06, "loss": 0.2792, "step": 901 }, { "epoch": 3.6536708860759495, "grad_norm": 0.31405053849505976, "learning_rate": 8.056828165944282e-06, "loss": 0.2714, "step": 902 }, { "epoch": 3.6577215189873415, "grad_norm": 0.3445222918887136, "learning_rate": 8.011348871891762e-06, "loss": 0.2355, "step": 903 }, { "epoch": 3.661772151898734, "grad_norm": 0.3203581748472261, "learning_rate": 7.965966132787287e-06, "loss": 0.2404, "step": 904 }, { "epoch": 3.6658227848101266, "grad_norm": 0.3319179845427499, "learning_rate": 7.920680314137189e-06, "loss": 0.2553, "step": 905 }, { "epoch": 3.669873417721519, "grad_norm": 0.32489646982874376, "learning_rate": 7.875491780667246e-06, "loss": 0.2777, "step": 906 }, { "epoch": 3.6739240506329116, "grad_norm": 0.32723571321443273, "learning_rate": 7.830400896319667e-06, "loss": 0.2299, "step": 907 }, { "epoch": 3.6779746835443037, "grad_norm": 0.3031879606167147, "learning_rate": 7.785408024250259e-06, "loss": 0.2628, "step": 908 }, { "epoch": 3.682025316455696, "grad_norm": 0.33417991438410954, "learning_rate": 7.74051352682542e-06, "loss": 0.2352, "step": 909 }, { "epoch": 3.6860759493670887, "grad_norm": 0.3256696695927701, "learning_rate": 7.695717765619257e-06, "loss": 0.2691, "step": 910 }, { "epoch": 3.690126582278481, "grad_norm": 0.3353246632162728, "learning_rate": 7.651021101410673e-06, "loss": 0.2399, "step": 911 }, { "epoch": 3.6941772151898733, "grad_norm": 0.34392776371905687, "learning_rate": 7.606423894180464e-06, "loss": 0.2663, "step": 912 }, { "epoch": 3.698227848101266, "grad_norm": 0.3334005278027404, "learning_rate": 7.56192650310839e-06, "loss": 0.2687, "step": 913 }, { "epoch": 3.7022784810126583, "grad_norm": 0.31912424847475296, "learning_rate": 7.517529286570349e-06, "loss": 0.2187, "step": 914 }, { "epoch": 3.706329113924051, "grad_norm": 0.3241237226224681, "learning_rate": 7.473232602135387e-06, "loss": 0.2219, "step": 915 }, { "epoch": 3.710379746835443, "grad_norm": 0.30754081256096905, "learning_rate": 7.429036806562935e-06, "loss": 0.2728, "step": 916 }, { "epoch": 3.7144303797468354, "grad_norm": 0.3100087361200951, "learning_rate": 7.3849422557998455e-06, "loss": 0.2622, "step": 917 }, { "epoch": 3.718481012658228, "grad_norm": 0.32067395489270095, "learning_rate": 7.340949304977567e-06, "loss": 0.252, "step": 918 }, { "epoch": 3.72253164556962, "grad_norm": 0.31775044111464135, "learning_rate": 7.297058308409282e-06, "loss": 0.2751, "step": 919 }, { "epoch": 3.7265822784810125, "grad_norm": 0.3115212916790627, "learning_rate": 7.25326961958704e-06, "loss": 0.2539, "step": 920 }, { "epoch": 3.730632911392405, "grad_norm": 0.31459817343821606, "learning_rate": 7.209583591178921e-06, "loss": 0.2382, "step": 921 }, { "epoch": 3.7346835443037976, "grad_norm": 0.31815405243816436, "learning_rate": 7.1660005750261925e-06, "loss": 0.2543, "step": 922 }, { "epoch": 3.73873417721519, "grad_norm": 0.3231899557418067, "learning_rate": 7.1225209221404765e-06, "loss": 0.2541, "step": 923 }, { "epoch": 3.742784810126582, "grad_norm": 0.3209181089228571, "learning_rate": 7.079144982700909e-06, "loss": 0.2264, "step": 924 }, { "epoch": 3.7468354430379747, "grad_norm": 0.30972918420829276, "learning_rate": 7.0358731060513695e-06, "loss": 0.2553, "step": 925 }, { "epoch": 3.750886075949367, "grad_norm": 0.3143384035345987, "learning_rate": 6.99270564069757e-06, "loss": 0.2531, "step": 926 }, { "epoch": 3.7549367088607593, "grad_norm": 0.33292405475038533, "learning_rate": 6.949642934304375e-06, "loss": 0.2673, "step": 927 }, { "epoch": 3.7589873417721518, "grad_norm": 0.33374113427530877, "learning_rate": 6.906685333692871e-06, "loss": 0.2544, "step": 928 }, { "epoch": 3.7630379746835443, "grad_norm": 0.3189378249520376, "learning_rate": 6.86383318483769e-06, "loss": 0.2439, "step": 929 }, { "epoch": 3.767088607594937, "grad_norm": 0.3290257666529745, "learning_rate": 6.821086832864139e-06, "loss": 0.2725, "step": 930 }, { "epoch": 3.7711392405063293, "grad_norm": 0.32377540724934933, "learning_rate": 6.77844662204546e-06, "loss": 0.2556, "step": 931 }, { "epoch": 3.7751898734177214, "grad_norm": 0.3344306222218323, "learning_rate": 6.7359128958000455e-06, "loss": 0.2572, "step": 932 }, { "epoch": 3.779240506329114, "grad_norm": 0.3261551280685909, "learning_rate": 6.693485996688695e-06, "loss": 0.2443, "step": 933 }, { "epoch": 3.7832911392405064, "grad_norm": 0.33393376054392027, "learning_rate": 6.651166266411801e-06, "loss": 0.2497, "step": 934 }, { "epoch": 3.7873417721518985, "grad_norm": 0.3205114887809609, "learning_rate": 6.6089540458066725e-06, "loss": 0.2502, "step": 935 }, { "epoch": 3.791392405063291, "grad_norm": 0.32074526012398624, "learning_rate": 6.566849674844711e-06, "loss": 0.2465, "step": 936 }, { "epoch": 3.7954430379746835, "grad_norm": 0.33671401029739184, "learning_rate": 6.524853492628747e-06, "loss": 0.2385, "step": 937 }, { "epoch": 3.799493670886076, "grad_norm": 0.3314801406369514, "learning_rate": 6.4829658373902536e-06, "loss": 0.2511, "step": 938 }, { "epoch": 3.8035443037974686, "grad_norm": 0.3112624667195287, "learning_rate": 6.441187046486648e-06, "loss": 0.2492, "step": 939 }, { "epoch": 3.8075949367088606, "grad_norm": 0.3228041250776733, "learning_rate": 6.399517456398567e-06, "loss": 0.2401, "step": 940 }, { "epoch": 3.811645569620253, "grad_norm": 0.33329176509256564, "learning_rate": 6.357957402727164e-06, "loss": 0.2728, "step": 941 }, { "epoch": 3.8156962025316457, "grad_norm": 0.33218060511772324, "learning_rate": 6.316507220191395e-06, "loss": 0.2667, "step": 942 }, { "epoch": 3.8197468354430377, "grad_norm": 0.31129289432045476, "learning_rate": 6.275167242625331e-06, "loss": 0.2373, "step": 943 }, { "epoch": 3.8237974683544302, "grad_norm": 0.3152172189111534, "learning_rate": 6.233937802975471e-06, "loss": 0.268, "step": 944 }, { "epoch": 3.8278481012658228, "grad_norm": 0.31245449240800355, "learning_rate": 6.192819233298046e-06, "loss": 0.2586, "step": 945 }, { "epoch": 3.8318987341772153, "grad_norm": 0.30908177024504246, "learning_rate": 6.151811864756383e-06, "loss": 0.2616, "step": 946 }, { "epoch": 3.835949367088608, "grad_norm": 0.3188064643649904, "learning_rate": 6.1109160276181655e-06, "loss": 0.237, "step": 947 }, { "epoch": 3.84, "grad_norm": 0.3563016872464952, "learning_rate": 6.070132051252868e-06, "loss": 0.266, "step": 948 }, { "epoch": 3.8440506329113924, "grad_norm": 0.32572180744403917, "learning_rate": 6.0294602641290034e-06, "loss": 0.2627, "step": 949 }, { "epoch": 3.848101265822785, "grad_norm": 0.32203421643018665, "learning_rate": 5.988900993811575e-06, "loss": 0.267, "step": 950 }, { "epoch": 3.852151898734177, "grad_norm": 0.3215739231191963, "learning_rate": 5.948454566959363e-06, "loss": 0.2424, "step": 951 }, { "epoch": 3.8562025316455695, "grad_norm": 0.3335048519905235, "learning_rate": 5.908121309322328e-06, "loss": 0.2295, "step": 952 }, { "epoch": 3.860253164556962, "grad_norm": 0.3234604494816272, "learning_rate": 5.867901545738976e-06, "loss": 0.2489, "step": 953 }, { "epoch": 3.8643037974683545, "grad_norm": 0.32686471078122903, "learning_rate": 5.827795600133774e-06, "loss": 0.2402, "step": 954 }, { "epoch": 3.868354430379747, "grad_norm": 0.3176108750293248, "learning_rate": 5.787803795514466e-06, "loss": 0.2496, "step": 955 }, { "epoch": 3.872405063291139, "grad_norm": 0.33426218345047026, "learning_rate": 5.747926453969576e-06, "loss": 0.2633, "step": 956 }, { "epoch": 3.8764556962025316, "grad_norm": 0.3204110390005298, "learning_rate": 5.708163896665708e-06, "loss": 0.259, "step": 957 }, { "epoch": 3.880506329113924, "grad_norm": 0.3259220026953575, "learning_rate": 5.668516443845047e-06, "loss": 0.2367, "step": 958 }, { "epoch": 3.884556962025316, "grad_norm": 0.333013652025553, "learning_rate": 5.6289844148227225e-06, "loss": 0.2667, "step": 959 }, { "epoch": 3.8886075949367087, "grad_norm": 0.31647479588023963, "learning_rate": 5.5895681279842615e-06, "loss": 0.2367, "step": 960 }, { "epoch": 3.8926582278481012, "grad_norm": 0.3031464790095631, "learning_rate": 5.550267900783019e-06, "loss": 0.2494, "step": 961 }, { "epoch": 3.8967088607594937, "grad_norm": 0.32380555025319097, "learning_rate": 5.511084049737623e-06, "loss": 0.2432, "step": 962 }, { "epoch": 3.9007594936708863, "grad_norm": 0.32732408011500175, "learning_rate": 5.4720168904294215e-06, "loss": 0.2764, "step": 963 }, { "epoch": 3.9048101265822783, "grad_norm": 0.3361853941605347, "learning_rate": 5.433066737499948e-06, "loss": 0.2481, "step": 964 }, { "epoch": 3.908860759493671, "grad_norm": 0.3156480822265876, "learning_rate": 5.394233904648376e-06, "loss": 0.2399, "step": 965 }, { "epoch": 3.9129113924050634, "grad_norm": 0.3251642398185147, "learning_rate": 5.355518704628997e-06, "loss": 0.2595, "step": 966 }, { "epoch": 3.9169620253164554, "grad_norm": 0.3220188229125663, "learning_rate": 5.316921449248731e-06, "loss": 0.2387, "step": 967 }, { "epoch": 3.921012658227848, "grad_norm": 0.3332809417909438, "learning_rate": 5.278442449364538e-06, "loss": 0.2686, "step": 968 }, { "epoch": 3.9250632911392405, "grad_norm": 0.32154599639571124, "learning_rate": 5.240082014881016e-06, "loss": 0.2551, "step": 969 }, { "epoch": 3.929113924050633, "grad_norm": 0.32076973379057794, "learning_rate": 5.201840454747822e-06, "loss": 0.246, "step": 970 }, { "epoch": 3.9331645569620255, "grad_norm": 0.3243525385863737, "learning_rate": 5.163718076957223e-06, "loss": 0.2473, "step": 971 }, { "epoch": 3.9372151898734176, "grad_norm": 0.31481232725161146, "learning_rate": 5.125715188541609e-06, "loss": 0.2365, "step": 972 }, { "epoch": 3.94126582278481, "grad_norm": 0.3209481192135813, "learning_rate": 5.087832095571021e-06, "loss": 0.2572, "step": 973 }, { "epoch": 3.9453164556962026, "grad_norm": 0.3111578395406808, "learning_rate": 5.0500691031506766e-06, "loss": 0.2547, "step": 974 }, { "epoch": 3.9493670886075947, "grad_norm": 0.3084534366469543, "learning_rate": 5.01242651541854e-06, "loss": 0.2721, "step": 975 }, { "epoch": 3.953417721518987, "grad_norm": 0.313035033101485, "learning_rate": 4.974904635542815e-06, "loss": 0.2621, "step": 976 }, { "epoch": 3.9574683544303797, "grad_norm": 0.32511757652079837, "learning_rate": 4.937503765719582e-06, "loss": 0.2479, "step": 977 }, { "epoch": 3.961518987341772, "grad_norm": 0.3128820168948658, "learning_rate": 4.900224207170299e-06, "loss": 0.2602, "step": 978 }, { "epoch": 3.9655696202531647, "grad_norm": 0.30480979852363227, "learning_rate": 4.8630662601394065e-06, "loss": 0.2447, "step": 979 }, { "epoch": 3.969620253164557, "grad_norm": 0.2896640775335413, "learning_rate": 4.8260302238918995e-06, "loss": 0.2342, "step": 980 }, { "epoch": 3.9736708860759493, "grad_norm": 0.3072429015552643, "learning_rate": 4.789116396710924e-06, "loss": 0.266, "step": 981 }, { "epoch": 3.977721518987342, "grad_norm": 0.3280456404233361, "learning_rate": 4.752325075895368e-06, "loss": 0.2308, "step": 982 }, { "epoch": 3.981772151898734, "grad_norm": 0.3045626719483015, "learning_rate": 4.715656557757473e-06, "loss": 0.2638, "step": 983 }, { "epoch": 3.9858227848101264, "grad_norm": 0.3230823320674334, "learning_rate": 4.679111137620442e-06, "loss": 0.2519, "step": 984 }, { "epoch": 3.989873417721519, "grad_norm": 0.314258510426685, "learning_rate": 4.6426891098160585e-06, "loss": 0.245, "step": 985 }, { "epoch": 3.9939240506329114, "grad_norm": 0.322972526439056, "learning_rate": 4.6063907676823474e-06, "loss": 0.2345, "step": 986 }, { "epoch": 3.997974683544304, "grad_norm": 0.31455946146809066, "learning_rate": 4.570216403561141e-06, "loss": 0.235, "step": 987 }, { "epoch": 4.002025316455696, "grad_norm": 0.3684834654539296, "learning_rate": 4.534166308795815e-06, "loss": 0.2304, "step": 988 }, { "epoch": 4.006075949367089, "grad_norm": 0.3932913839996684, "learning_rate": 4.498240773728859e-06, "loss": 0.1914, "step": 989 }, { "epoch": 4.010126582278481, "grad_norm": 0.35711499214151926, "learning_rate": 4.462440087699609e-06, "loss": 0.1974, "step": 990 }, { "epoch": 4.014177215189873, "grad_norm": 0.2847259067914413, "learning_rate": 4.426764539041861e-06, "loss": 0.1936, "step": 991 }, { "epoch": 4.018227848101266, "grad_norm": 0.313209024668645, "learning_rate": 4.391214415081582e-06, "loss": 0.1913, "step": 992 }, { "epoch": 4.022278481012658, "grad_norm": 0.40646343873227225, "learning_rate": 4.355790002134579e-06, "loss": 0.2112, "step": 993 }, { "epoch": 4.02632911392405, "grad_norm": 0.43294105131464533, "learning_rate": 4.320491585504207e-06, "loss": 0.2039, "step": 994 }, { "epoch": 4.030379746835443, "grad_norm": 0.35255928533393227, "learning_rate": 4.2853194494790615e-06, "loss": 0.1901, "step": 995 }, { "epoch": 4.034430379746835, "grad_norm": 0.3229501046942367, "learning_rate": 4.250273877330691e-06, "loss": 0.1938, "step": 996 }, { "epoch": 4.038481012658228, "grad_norm": 0.31329483566392885, "learning_rate": 4.215355151311313e-06, "loss": 0.2021, "step": 997 }, { "epoch": 4.04253164556962, "grad_norm": 0.32931072551759466, "learning_rate": 4.180563552651542e-06, "loss": 0.1801, "step": 998 }, { "epoch": 4.046582278481012, "grad_norm": 0.3351223247789198, "learning_rate": 4.145899361558147e-06, "loss": 0.2148, "step": 999 }, { "epoch": 4.050632911392405, "grad_norm": 0.33738960094801235, "learning_rate": 4.111362857211738e-06, "loss": 0.2066, "step": 1000 }, { "epoch": 4.054683544303797, "grad_norm": 0.2928915085206167, "learning_rate": 4.076954317764592e-06, "loss": 0.2097, "step": 1001 }, { "epoch": 4.0587341772151895, "grad_norm": 0.2801895865391535, "learning_rate": 4.042674020338335e-06, "loss": 0.2025, "step": 1002 }, { "epoch": 4.062784810126582, "grad_norm": 0.2777328866835211, "learning_rate": 4.0085222410217835e-06, "loss": 0.2009, "step": 1003 }, { "epoch": 4.0668354430379745, "grad_norm": 0.32231011529114484, "learning_rate": 3.974499254868674e-06, "loss": 0.2209, "step": 1004 }, { "epoch": 4.0708860759493675, "grad_norm": 0.31569399120056907, "learning_rate": 3.940605335895451e-06, "loss": 0.201, "step": 1005 }, { "epoch": 4.0749367088607595, "grad_norm": 0.26986890104704336, "learning_rate": 3.90684075707908e-06, "loss": 0.1802, "step": 1006 }, { "epoch": 4.078987341772152, "grad_norm": 0.2526217801912494, "learning_rate": 3.8732057903548505e-06, "loss": 0.1763, "step": 1007 }, { "epoch": 4.083037974683545, "grad_norm": 0.258204564514498, "learning_rate": 3.8397007066141375e-06, "loss": 0.1895, "step": 1008 }, { "epoch": 4.087088607594937, "grad_norm": 0.26978981832282445, "learning_rate": 3.806325775702304e-06, "loss": 0.1976, "step": 1009 }, { "epoch": 4.091139240506329, "grad_norm": 0.28275748010471136, "learning_rate": 3.773081266416434e-06, "loss": 0.1981, "step": 1010 }, { "epoch": 4.095189873417722, "grad_norm": 0.2709150901912289, "learning_rate": 3.739967446503245e-06, "loss": 0.1863, "step": 1011 }, { "epoch": 4.099240506329114, "grad_norm": 0.272530901402394, "learning_rate": 3.706984582656894e-06, "loss": 0.2036, "step": 1012 }, { "epoch": 4.103291139240507, "grad_norm": 0.2676923165783581, "learning_rate": 3.6741329405168237e-06, "loss": 0.2071, "step": 1013 }, { "epoch": 4.107341772151899, "grad_norm": 0.25862762966536584, "learning_rate": 3.641412784665648e-06, "loss": 0.2041, "step": 1014 }, { "epoch": 4.111392405063291, "grad_norm": 0.25129781879744445, "learning_rate": 3.608824378627005e-06, "loss": 0.1638, "step": 1015 }, { "epoch": 4.115443037974684, "grad_norm": 0.246820994484394, "learning_rate": 3.5763679848634337e-06, "loss": 0.187, "step": 1016 }, { "epoch": 4.119493670886076, "grad_norm": 0.2524804086717422, "learning_rate": 3.544043864774269e-06, "loss": 0.1714, "step": 1017 }, { "epoch": 4.123544303797468, "grad_norm": 0.258052042924808, "learning_rate": 3.5118522786935282e-06, "loss": 0.1814, "step": 1018 }, { "epoch": 4.127594936708861, "grad_norm": 0.25734968050203716, "learning_rate": 3.479793485887819e-06, "loss": 0.2096, "step": 1019 }, { "epoch": 4.131645569620253, "grad_norm": 0.25445019188266643, "learning_rate": 3.4478677445542653e-06, "loss": 0.1824, "step": 1020 }, { "epoch": 4.135696202531646, "grad_norm": 0.24963511362415589, "learning_rate": 3.4160753118183767e-06, "loss": 0.1934, "step": 1021 }, { "epoch": 4.139746835443038, "grad_norm": 0.2577553452728264, "learning_rate": 3.3844164437320527e-06, "loss": 0.19, "step": 1022 }, { "epoch": 4.14379746835443, "grad_norm": 0.25775404257261975, "learning_rate": 3.3528913952714558e-06, "loss": 0.2075, "step": 1023 }, { "epoch": 4.147848101265823, "grad_norm": 0.23817152789898624, "learning_rate": 3.321500420335e-06, "loss": 0.1961, "step": 1024 }, { "epoch": 4.151898734177215, "grad_norm": 0.24350219698202097, "learning_rate": 3.290243771741275e-06, "loss": 0.1739, "step": 1025 }, { "epoch": 4.155949367088607, "grad_norm": 0.2671587935239976, "learning_rate": 3.2591217012270325e-06, "loss": 0.1939, "step": 1026 }, { "epoch": 4.16, "grad_norm": 0.2676532700825298, "learning_rate": 3.228134459445149e-06, "loss": 0.1927, "step": 1027 }, { "epoch": 4.164050632911392, "grad_norm": 0.25771772564646517, "learning_rate": 3.1972822959626205e-06, "loss": 0.1768, "step": 1028 }, { "epoch": 4.168101265822785, "grad_norm": 0.2645895461558082, "learning_rate": 3.166565459258513e-06, "loss": 0.1902, "step": 1029 }, { "epoch": 4.172151898734177, "grad_norm": 0.25020594284385855, "learning_rate": 3.1359841967220193e-06, "loss": 0.1856, "step": 1030 }, { "epoch": 4.176202531645569, "grad_norm": 0.2557986085157, "learning_rate": 3.105538754650419e-06, "loss": 0.1954, "step": 1031 }, { "epoch": 4.180253164556962, "grad_norm": 0.25956641879459763, "learning_rate": 3.07522937824712e-06, "loss": 0.1949, "step": 1032 }, { "epoch": 4.184303797468354, "grad_norm": 0.24999172271900186, "learning_rate": 3.0450563116196697e-06, "loss": 0.1972, "step": 1033 }, { "epoch": 4.188354430379746, "grad_norm": 0.25749767001916185, "learning_rate": 3.0150197977778008e-06, "loss": 0.1754, "step": 1034 }, { "epoch": 4.192405063291139, "grad_norm": 0.24969501734983326, "learning_rate": 2.985120078631465e-06, "loss": 0.1813, "step": 1035 }, { "epoch": 4.1964556962025314, "grad_norm": 0.2606108213201048, "learning_rate": 2.9553573949888893e-06, "loss": 0.2313, "step": 1036 }, { "epoch": 4.200506329113924, "grad_norm": 0.25132109708330275, "learning_rate": 2.9257319865546384e-06, "loss": 0.1908, "step": 1037 }, { "epoch": 4.2045569620253165, "grad_norm": 0.25900480260733216, "learning_rate": 2.896244091927678e-06, "loss": 0.1981, "step": 1038 }, { "epoch": 4.2086075949367086, "grad_norm": 0.2650150778648152, "learning_rate": 2.8668939485994584e-06, "loss": 0.2315, "step": 1039 }, { "epoch": 4.2126582278481015, "grad_norm": 0.2461964426673046, "learning_rate": 2.837681792951994e-06, "loss": 0.1844, "step": 1040 }, { "epoch": 4.216708860759494, "grad_norm": 0.25529309522177923, "learning_rate": 2.808607860255981e-06, "loss": 0.2076, "step": 1041 }, { "epoch": 4.220759493670886, "grad_norm": 0.25816165608513614, "learning_rate": 2.7796723846688634e-06, "loss": 0.1791, "step": 1042 }, { "epoch": 4.224810126582279, "grad_norm": 0.251362273199925, "learning_rate": 2.7508755992329937e-06, "loss": 0.2123, "step": 1043 }, { "epoch": 4.228860759493671, "grad_norm": 0.24403382580522903, "learning_rate": 2.722217735873718e-06, "loss": 0.2094, "step": 1044 }, { "epoch": 4.232911392405064, "grad_norm": 0.2468860776809563, "learning_rate": 2.6936990253975315e-06, "loss": 0.1613, "step": 1045 }, { "epoch": 4.236962025316456, "grad_norm": 0.2622388346085329, "learning_rate": 2.665319697490205e-06, "loss": 0.1748, "step": 1046 }, { "epoch": 4.241012658227848, "grad_norm": 0.2506768304767062, "learning_rate": 2.637079980714945e-06, "loss": 0.1922, "step": 1047 }, { "epoch": 4.245063291139241, "grad_norm": 0.2603092285792612, "learning_rate": 2.6089801025105453e-06, "loss": 0.2124, "step": 1048 }, { "epoch": 4.249113924050633, "grad_norm": 0.26606567909607803, "learning_rate": 2.581020289189571e-06, "loss": 0.1955, "step": 1049 }, { "epoch": 4.253164556962025, "grad_norm": 0.24782907337839946, "learning_rate": 2.553200765936501e-06, "loss": 0.1987, "step": 1050 }, { "epoch": 4.257215189873418, "grad_norm": 0.249474850646784, "learning_rate": 2.525521756805962e-06, "loss": 0.1997, "step": 1051 }, { "epoch": 4.26126582278481, "grad_norm": 0.24138154134398773, "learning_rate": 2.497983484720885e-06, "loss": 0.2162, "step": 1052 }, { "epoch": 4.265316455696203, "grad_norm": 0.253575097655864, "learning_rate": 2.470586171470728e-06, "loss": 0.182, "step": 1053 }, { "epoch": 4.269367088607595, "grad_norm": 0.25766170158007135, "learning_rate": 2.4433300377096836e-06, "loss": 0.1991, "step": 1054 }, { "epoch": 4.273417721518987, "grad_norm": 0.25297899529284384, "learning_rate": 2.4162153029549073e-06, "loss": 0.1705, "step": 1055 }, { "epoch": 4.27746835443038, "grad_norm": 0.2612042032011959, "learning_rate": 2.3892421855847458e-06, "loss": 0.195, "step": 1056 }, { "epoch": 4.281518987341772, "grad_norm": 0.2548036074173629, "learning_rate": 2.362410902836978e-06, "loss": 0.199, "step": 1057 }, { "epoch": 4.285569620253165, "grad_norm": 0.25642324867394317, "learning_rate": 2.3357216708070653e-06, "loss": 0.1791, "step": 1058 }, { "epoch": 4.289620253164557, "grad_norm": 0.25583219479792235, "learning_rate": 2.309174704446411e-06, "loss": 0.1699, "step": 1059 }, { "epoch": 4.293670886075949, "grad_norm": 0.2618269116532635, "learning_rate": 2.2827702175606437e-06, "loss": 0.1934, "step": 1060 }, { "epoch": 4.297721518987342, "grad_norm": 0.2486650290696773, "learning_rate": 2.256508422807855e-06, "loss": 0.2007, "step": 1061 }, { "epoch": 4.301772151898734, "grad_norm": 0.2584314143924437, "learning_rate": 2.230389531696946e-06, "loss": 0.1974, "step": 1062 }, { "epoch": 4.305822784810126, "grad_norm": 0.24847222519459278, "learning_rate": 2.204413754585857e-06, "loss": 0.1996, "step": 1063 }, { "epoch": 4.309873417721519, "grad_norm": 0.2613814021537022, "learning_rate": 2.1785813006799406e-06, "loss": 0.1784, "step": 1064 }, { "epoch": 4.313924050632911, "grad_norm": 0.2503202870094682, "learning_rate": 2.1528923780302224e-06, "loss": 0.1974, "step": 1065 }, { "epoch": 4.317974683544303, "grad_norm": 0.26007276982989125, "learning_rate": 2.127347193531757e-06, "loss": 0.2042, "step": 1066 }, { "epoch": 4.322025316455696, "grad_norm": 0.25111775492810867, "learning_rate": 2.101945952921942e-06, "loss": 0.184, "step": 1067 }, { "epoch": 4.326075949367088, "grad_norm": 0.24867176417411596, "learning_rate": 2.0766888607788906e-06, "loss": 0.1837, "step": 1068 }, { "epoch": 4.330126582278481, "grad_norm": 0.25412199137341446, "learning_rate": 2.0515761205197337e-06, "loss": 0.1678, "step": 1069 }, { "epoch": 4.334177215189873, "grad_norm": 0.26049217653271606, "learning_rate": 2.0266079343990453e-06, "loss": 0.1967, "step": 1070 }, { "epoch": 4.3382278481012655, "grad_norm": 0.2550113298938145, "learning_rate": 2.0017845035071494e-06, "loss": 0.2196, "step": 1071 }, { "epoch": 4.3422784810126585, "grad_norm": 0.25130008312147994, "learning_rate": 1.9771060277685537e-06, "loss": 0.1769, "step": 1072 }, { "epoch": 4.3463291139240505, "grad_norm": 0.2570901654741051, "learning_rate": 1.95257270594031e-06, "loss": 0.2032, "step": 1073 }, { "epoch": 4.3503797468354435, "grad_norm": 0.26286995383286765, "learning_rate": 1.9281847356104188e-06, "loss": 0.2028, "step": 1074 }, { "epoch": 4.3544303797468356, "grad_norm": 0.25684034082405294, "learning_rate": 1.9039423131962365e-06, "loss": 0.1855, "step": 1075 }, { "epoch": 4.358481012658228, "grad_norm": 0.24427653289505194, "learning_rate": 1.8798456339429027e-06, "loss": 0.1746, "step": 1076 }, { "epoch": 4.362531645569621, "grad_norm": 0.24694524638423596, "learning_rate": 1.8558948919217612e-06, "loss": 0.2018, "step": 1077 }, { "epoch": 4.366582278481013, "grad_norm": 0.26318802594446516, "learning_rate": 1.8320902800287954e-06, "loss": 0.1798, "step": 1078 }, { "epoch": 4.370632911392405, "grad_norm": 0.25773716720602396, "learning_rate": 1.8084319899830726e-06, "loss": 0.1847, "step": 1079 }, { "epoch": 4.374683544303798, "grad_norm": 0.24716457501418332, "learning_rate": 1.7849202123252097e-06, "loss": 0.188, "step": 1080 }, { "epoch": 4.37873417721519, "grad_norm": 0.2606614882076809, "learning_rate": 1.7615551364158401e-06, "loss": 0.2108, "step": 1081 }, { "epoch": 4.382784810126582, "grad_norm": 0.24500823228590507, "learning_rate": 1.738336950434061e-06, "loss": 0.2132, "step": 1082 }, { "epoch": 4.386835443037975, "grad_norm": 0.25014811855810287, "learning_rate": 1.715265841375957e-06, "loss": 0.2052, "step": 1083 }, { "epoch": 4.390886075949367, "grad_norm": 0.24832347053825474, "learning_rate": 1.6923419950530684e-06, "loss": 0.2079, "step": 1084 }, { "epoch": 4.39493670886076, "grad_norm": 0.24657969125926904, "learning_rate": 1.6695655960909008e-06, "loss": 0.1919, "step": 1085 }, { "epoch": 4.398987341772152, "grad_norm": 0.24963423189324757, "learning_rate": 1.646936827927441e-06, "loss": 0.1813, "step": 1086 }, { "epoch": 4.403037974683544, "grad_norm": 0.25455125382245036, "learning_rate": 1.6244558728116766e-06, "loss": 0.193, "step": 1087 }, { "epoch": 4.407088607594937, "grad_norm": 0.2510620298082756, "learning_rate": 1.6021229118021265e-06, "loss": 0.2007, "step": 1088 }, { "epoch": 4.411139240506329, "grad_norm": 0.2571815552892949, "learning_rate": 1.5799381247653967e-06, "loss": 0.2092, "step": 1089 }, { "epoch": 4.415189873417722, "grad_norm": 0.25904471342381247, "learning_rate": 1.5579016903747013e-06, "loss": 0.2253, "step": 1090 }, { "epoch": 4.419240506329114, "grad_norm": 0.25788991307572084, "learning_rate": 1.5360137861084656e-06, "loss": 0.1825, "step": 1091 }, { "epoch": 4.423291139240506, "grad_norm": 0.24196023531955846, "learning_rate": 1.5142745882488475e-06, "loss": 0.1772, "step": 1092 }, { "epoch": 4.427341772151899, "grad_norm": 0.2546241918144218, "learning_rate": 1.4926842718803691e-06, "loss": 0.2074, "step": 1093 }, { "epoch": 4.431392405063291, "grad_norm": 0.2526658216390659, "learning_rate": 1.4712430108884657e-06, "loss": 0.1979, "step": 1094 }, { "epoch": 4.435443037974683, "grad_norm": 0.25425608468554634, "learning_rate": 1.4499509779581078e-06, "loss": 0.2066, "step": 1095 }, { "epoch": 4.439493670886076, "grad_norm": 0.24150964569597866, "learning_rate": 1.4288083445723988e-06, "loss": 0.1983, "step": 1096 }, { "epoch": 4.443544303797468, "grad_norm": 0.24505799722662305, "learning_rate": 1.4078152810112045e-06, "loss": 0.2053, "step": 1097 }, { "epoch": 4.44759493670886, "grad_norm": 0.2457682784004233, "learning_rate": 1.3869719563497697e-06, "loss": 0.192, "step": 1098 }, { "epoch": 4.451645569620253, "grad_norm": 0.24974024243700038, "learning_rate": 1.3662785384573663e-06, "loss": 0.1873, "step": 1099 }, { "epoch": 4.455696202531645, "grad_norm": 0.2445107284393789, "learning_rate": 1.3457351939959383e-06, "loss": 0.1831, "step": 1100 }, { "epoch": 4.459746835443038, "grad_norm": 0.2560436141969455, "learning_rate": 1.3253420884187551e-06, "loss": 0.1742, "step": 1101 }, { "epoch": 4.46379746835443, "grad_norm": 0.25573064910414933, "learning_rate": 1.3050993859690953e-06, "loss": 0.1997, "step": 1102 }, { "epoch": 4.467848101265822, "grad_norm": 0.24267765250368786, "learning_rate": 1.2850072496788869e-06, "loss": 0.1996, "step": 1103 }, { "epoch": 4.471898734177215, "grad_norm": 0.24859383855159228, "learning_rate": 1.2650658413674434e-06, "loss": 0.174, "step": 1104 }, { "epoch": 4.4759493670886075, "grad_norm": 0.25211542127551945, "learning_rate": 1.2452753216401226e-06, "loss": 0.1941, "step": 1105 }, { "epoch": 4.48, "grad_norm": 0.2481744424372317, "learning_rate": 1.2256358498870503e-06, "loss": 0.1897, "step": 1106 }, { "epoch": 4.4840506329113925, "grad_norm": 0.24495818021259205, "learning_rate": 1.2061475842818337e-06, "loss": 0.1879, "step": 1107 }, { "epoch": 4.488101265822785, "grad_norm": 0.25415808569850984, "learning_rate": 1.1868106817802816e-06, "loss": 0.1972, "step": 1108 }, { "epoch": 4.4921518987341775, "grad_norm": 0.2448783952757281, "learning_rate": 1.1676252981191482e-06, "loss": 0.194, "step": 1109 }, { "epoch": 4.49620253164557, "grad_norm": 0.24800345901816565, "learning_rate": 1.1485915878148823e-06, "loss": 0.1886, "step": 1110 }, { "epoch": 4.500253164556962, "grad_norm": 0.25572429025719096, "learning_rate": 1.1297097041623584e-06, "loss": 0.2112, "step": 1111 }, { "epoch": 4.504303797468355, "grad_norm": 0.24298064314976014, "learning_rate": 1.1109797992336847e-06, "loss": 0.2056, "step": 1112 }, { "epoch": 4.508354430379747, "grad_norm": 0.23983800941794825, "learning_rate": 1.092402023876933e-06, "loss": 0.2054, "step": 1113 }, { "epoch": 4.512405063291139, "grad_norm": 0.25819490698916797, "learning_rate": 1.0739765277149527e-06, "loss": 0.2073, "step": 1114 }, { "epoch": 4.516455696202532, "grad_norm": 0.2437762148557435, "learning_rate": 1.0557034591441596e-06, "loss": 0.193, "step": 1115 }, { "epoch": 4.520506329113924, "grad_norm": 0.2894169260943825, "learning_rate": 1.0375829653333324e-06, "loss": 0.1871, "step": 1116 }, { "epoch": 4.524556962025317, "grad_norm": 0.2598854051877481, "learning_rate": 1.0196151922224385e-06, "loss": 0.2003, "step": 1117 }, { "epoch": 4.528607594936709, "grad_norm": 0.2479882285303769, "learning_rate": 1.0018002845214526e-06, "loss": 0.1839, "step": 1118 }, { "epoch": 4.532658227848101, "grad_norm": 0.2391855077737903, "learning_rate": 9.841383857091947e-07, "loss": 0.1945, "step": 1119 }, { "epoch": 4.536708860759494, "grad_norm": 0.25354217826210224, "learning_rate": 9.666296380321616e-07, "loss": 0.1781, "step": 1120 }, { "epoch": 4.540759493670886, "grad_norm": 0.25532473810986905, "learning_rate": 9.492741825034124e-07, "loss": 0.1886, "step": 1121 }, { "epoch": 4.544810126582279, "grad_norm": 0.2587122616642573, "learning_rate": 9.320721589013892e-07, "loss": 0.1629, "step": 1122 }, { "epoch": 4.548860759493671, "grad_norm": 0.24773118312974354, "learning_rate": 9.150237057688339e-07, "loss": 0.1733, "step": 1123 }, { "epoch": 4.552911392405063, "grad_norm": 0.24628369642632286, "learning_rate": 8.981289604116328e-07, "loss": 0.1938, "step": 1124 }, { "epoch": 4.556962025316456, "grad_norm": 0.25301322726880776, "learning_rate": 8.813880588977542e-07, "loss": 0.1654, "step": 1125 }, { "epoch": 4.561012658227848, "grad_norm": 0.2595447751396129, "learning_rate": 8.648011360561126e-07, "loss": 0.184, "step": 1126 }, { "epoch": 4.56506329113924, "grad_norm": 0.25740343056894893, "learning_rate": 8.483683254755037e-07, "loss": 0.1921, "step": 1127 }, { "epoch": 4.569113924050633, "grad_norm": 0.23984180921552806, "learning_rate": 8.320897595035227e-07, "loss": 0.1949, "step": 1128 }, { "epoch": 4.573164556962025, "grad_norm": 0.2411222963542181, "learning_rate": 8.159655692455093e-07, "loss": 0.1734, "step": 1129 }, { "epoch": 4.577215189873417, "grad_norm": 0.2556006186716069, "learning_rate": 7.999958845634648e-07, "loss": 0.1795, "step": 1130 }, { "epoch": 4.58126582278481, "grad_norm": 0.2516296639349781, "learning_rate": 7.841808340750478e-07, "loss": 0.2107, "step": 1131 }, { "epoch": 4.585316455696202, "grad_norm": 0.24465930475082784, "learning_rate": 7.685205451524869e-07, "loss": 0.2011, "step": 1132 }, { "epoch": 4.589367088607595, "grad_norm": 0.26063685182615737, "learning_rate": 7.530151439216027e-07, "loss": 0.196, "step": 1133 }, { "epoch": 4.593417721518987, "grad_norm": 0.24569174141144454, "learning_rate": 7.376647552607675e-07, "loss": 0.189, "step": 1134 }, { "epoch": 4.597468354430379, "grad_norm": 0.24506672786783196, "learning_rate": 7.224695027998963e-07, "loss": 0.1956, "step": 1135 }, { "epoch": 4.601518987341772, "grad_norm": 0.24636171369222432, "learning_rate": 7.07429508919466e-07, "loss": 0.1847, "step": 1136 }, { "epoch": 4.605569620253164, "grad_norm": 0.24946185178826694, "learning_rate": 6.925448947495206e-07, "loss": 0.2018, "step": 1137 }, { "epoch": 4.609620253164557, "grad_norm": 0.24108010050134063, "learning_rate": 6.778157801686936e-07, "loss": 0.2081, "step": 1138 }, { "epoch": 4.613670886075949, "grad_norm": 0.24595640741320057, "learning_rate": 6.632422838032515e-07, "loss": 0.2039, "step": 1139 }, { "epoch": 4.6177215189873415, "grad_norm": 0.2599839673589836, "learning_rate": 6.488245230261281e-07, "loss": 0.1789, "step": 1140 }, { "epoch": 4.6217721518987345, "grad_norm": 0.25079675737881135, "learning_rate": 6.345626139559868e-07, "loss": 0.1863, "step": 1141 }, { "epoch": 4.6258227848101265, "grad_norm": 0.2549043107821604, "learning_rate": 6.204566714562866e-07, "loss": 0.179, "step": 1142 }, { "epoch": 4.629873417721519, "grad_norm": 0.24345209116745425, "learning_rate": 6.06506809134344e-07, "loss": 0.199, "step": 1143 }, { "epoch": 4.633924050632912, "grad_norm": 0.2577570862615088, "learning_rate": 5.927131393404373e-07, "loss": 0.2075, "step": 1144 }, { "epoch": 4.637974683544304, "grad_norm": 0.23950032551476938, "learning_rate": 5.790757731668817e-07, "loss": 0.1837, "step": 1145 }, { "epoch": 4.642025316455696, "grad_norm": 0.24066845807908607, "learning_rate": 5.655948204471507e-07, "loss": 0.1934, "step": 1146 }, { "epoch": 4.646075949367089, "grad_norm": 0.23880445192271857, "learning_rate": 5.522703897549875e-07, "loss": 0.1901, "step": 1147 }, { "epoch": 4.650126582278481, "grad_norm": 0.26102459640508074, "learning_rate": 5.391025884035239e-07, "loss": 0.1596, "step": 1148 }, { "epoch": 4.654177215189874, "grad_norm": 0.24486432158672133, "learning_rate": 5.260915224444207e-07, "loss": 0.1829, "step": 1149 }, { "epoch": 4.658227848101266, "grad_norm": 0.24766900087213078, "learning_rate": 5.132372966670129e-07, "loss": 0.2022, "step": 1150 }, { "epoch": 4.662278481012658, "grad_norm": 0.2306919447933508, "learning_rate": 5.005400145974704e-07, "loss": 0.1904, "step": 1151 }, { "epoch": 4.666329113924051, "grad_norm": 0.24819794383180485, "learning_rate": 4.879997784979562e-07, "loss": 0.1887, "step": 1152 }, { "epoch": 4.670379746835443, "grad_norm": 0.24588738945154673, "learning_rate": 4.7561668936580984e-07, "loss": 0.1919, "step": 1153 }, { "epoch": 4.674430379746836, "grad_norm": 0.24038772114130297, "learning_rate": 4.6339084693272306e-07, "loss": 0.1935, "step": 1154 }, { "epoch": 4.678481012658228, "grad_norm": 0.24922281594919646, "learning_rate": 4.5132234966395847e-07, "loss": 0.1684, "step": 1155 }, { "epoch": 4.68253164556962, "grad_norm": 0.2691627631454181, "learning_rate": 4.3941129475752795e-07, "loss": 0.1907, "step": 1156 }, { "epoch": 4.686582278481013, "grad_norm": 0.25696194063999184, "learning_rate": 4.27657778143431e-07, "loss": 0.2086, "step": 1157 }, { "epoch": 4.690632911392405, "grad_norm": 0.24943578957538123, "learning_rate": 4.1606189448287757e-07, "loss": 0.1851, "step": 1158 }, { "epoch": 4.694683544303797, "grad_norm": 0.2468884328589498, "learning_rate": 4.046237371675177e-07, "loss": 0.1735, "step": 1159 }, { "epoch": 4.69873417721519, "grad_norm": 0.25155097566254847, "learning_rate": 3.9334339831869963e-07, "loss": 0.1455, "step": 1160 }, { "epoch": 4.702784810126582, "grad_norm": 0.2499276982860605, "learning_rate": 3.8222096878671955e-07, "loss": 0.2044, "step": 1161 }, { "epoch": 4.706835443037974, "grad_norm": 0.24720669348309696, "learning_rate": 3.7125653815009545e-07, "loss": 0.2002, "step": 1162 }, { "epoch": 4.710886075949367, "grad_norm": 0.2541141559545816, "learning_rate": 3.6045019471484974e-07, "loss": 0.2135, "step": 1163 }, { "epoch": 4.714936708860759, "grad_norm": 0.24650054530782625, "learning_rate": 3.498020255137813e-07, "loss": 0.1928, "step": 1164 }, { "epoch": 4.718987341772152, "grad_norm": 0.24627183128296729, "learning_rate": 3.393121163057811e-07, "loss": 0.1987, "step": 1165 }, { "epoch": 4.723037974683544, "grad_norm": 0.2574248244694804, "learning_rate": 3.289805515751399e-07, "loss": 0.174, "step": 1166 }, { "epoch": 4.727088607594936, "grad_norm": 0.254719513350089, "learning_rate": 3.188074145308573e-07, "loss": 0.2082, "step": 1167 }, { "epoch": 4.731139240506329, "grad_norm": 0.25823530934963873, "learning_rate": 3.087927871059804e-07, "loss": 0.1917, "step": 1168 }, { "epoch": 4.735189873417721, "grad_norm": 0.2504115177182913, "learning_rate": 2.989367499569418e-07, "loss": 0.1856, "step": 1169 }, { "epoch": 4.739240506329114, "grad_norm": 0.24102407112045954, "learning_rate": 2.8923938246290917e-07, "loss": 0.2121, "step": 1170 }, { "epoch": 4.743291139240506, "grad_norm": 0.257210499559504, "learning_rate": 2.7970076272514804e-07, "loss": 0.2107, "step": 1171 }, { "epoch": 4.7473417721518985, "grad_norm": 0.26200761144648566, "learning_rate": 2.703209675663887e-07, "loss": 0.1714, "step": 1172 }, { "epoch": 4.751392405063291, "grad_norm": 0.25111139351320677, "learning_rate": 2.6110007253021374e-07, "loss": 0.1794, "step": 1173 }, { "epoch": 4.7554430379746835, "grad_norm": 0.2669849669316202, "learning_rate": 2.520381518804471e-07, "loss": 0.1814, "step": 1174 }, { "epoch": 4.759493670886076, "grad_norm": 0.25003617742946566, "learning_rate": 2.4313527860054585e-07, "loss": 0.1853, "step": 1175 }, { "epoch": 4.7635443037974685, "grad_norm": 0.24969129651478897, "learning_rate": 2.343915243930317e-07, "loss": 0.2055, "step": 1176 }, { "epoch": 4.767594936708861, "grad_norm": 0.26477771207759243, "learning_rate": 2.2580695967889367e-07, "loss": 0.1887, "step": 1177 }, { "epoch": 4.7716455696202535, "grad_norm": 0.24416598823613936, "learning_rate": 2.1738165359704189e-07, "loss": 0.1888, "step": 1178 }, { "epoch": 4.775696202531646, "grad_norm": 0.24724832685087597, "learning_rate": 2.0911567400373257e-07, "loss": 0.1862, "step": 1179 }, { "epoch": 4.779746835443038, "grad_norm": 0.24723093006989483, "learning_rate": 2.0100908747202607e-07, "loss": 0.1737, "step": 1180 }, { "epoch": 4.783797468354431, "grad_norm": 0.24422112773843363, "learning_rate": 1.9306195929125638e-07, "loss": 0.1737, "step": 1181 }, { "epoch": 4.787848101265823, "grad_norm": 0.24819489763273186, "learning_rate": 1.8527435346650247e-07, "loss": 0.1718, "step": 1182 }, { "epoch": 4.791898734177215, "grad_norm": 0.2670034297323699, "learning_rate": 1.7764633271807108e-07, "loss": 0.1804, "step": 1183 }, { "epoch": 4.795949367088608, "grad_norm": 0.2773792515012924, "learning_rate": 1.7017795848099262e-07, "loss": 0.1819, "step": 1184 }, { "epoch": 4.8, "grad_norm": 0.23679549367996752, "learning_rate": 1.6286929090452596e-07, "loss": 0.1761, "step": 1185 }, { "epoch": 4.804050632911393, "grad_norm": 0.2572647677506535, "learning_rate": 1.557203888516745e-07, "loss": 0.1747, "step": 1186 }, { "epoch": 4.808101265822785, "grad_norm": 0.24619216728497725, "learning_rate": 1.487313098987131e-07, "loss": 0.1743, "step": 1187 }, { "epoch": 4.812151898734177, "grad_norm": 0.24935889177339324, "learning_rate": 1.4190211033472402e-07, "loss": 0.1782, "step": 1188 }, { "epoch": 4.81620253164557, "grad_norm": 0.24982753157353968, "learning_rate": 1.3523284516113955e-07, "loss": 0.172, "step": 1189 }, { "epoch": 4.820253164556962, "grad_norm": 0.25596541745075707, "learning_rate": 1.2872356809130682e-07, "loss": 0.1835, "step": 1190 }, { "epoch": 4.824303797468355, "grad_norm": 0.24966044774946128, "learning_rate": 1.2237433155004807e-07, "loss": 0.1879, "step": 1191 }, { "epoch": 4.828354430379747, "grad_norm": 0.2502194164065979, "learning_rate": 1.1618518667323886e-07, "loss": 0.2141, "step": 1192 }, { "epoch": 4.832405063291139, "grad_norm": 0.2571324788226258, "learning_rate": 1.1015618330740385e-07, "loss": 0.2327, "step": 1193 }, { "epoch": 4.836455696202532, "grad_norm": 0.2504586119969248, "learning_rate": 1.042873700093061e-07, "loss": 0.1925, "step": 1194 }, { "epoch": 4.840506329113924, "grad_norm": 0.2418885640917078, "learning_rate": 9.857879404556291e-08, "loss": 0.1933, "step": 1195 }, { "epoch": 4.844556962025316, "grad_norm": 0.24757515801499072, "learning_rate": 9.303050139225722e-08, "loss": 0.1813, "step": 1196 }, { "epoch": 4.848607594936709, "grad_norm": 0.25085853697145033, "learning_rate": 8.76425367345779e-08, "loss": 0.1788, "step": 1197 }, { "epoch": 4.852658227848101, "grad_norm": 0.2520093785530845, "learning_rate": 8.241494346644897e-08, "loss": 0.2029, "step": 1198 }, { "epoch": 4.856708860759493, "grad_norm": 0.24748109733162307, "learning_rate": 7.734776369019204e-08, "loss": 0.1816, "step": 1199 }, { "epoch": 4.860759493670886, "grad_norm": 0.2508642447972379, "learning_rate": 7.244103821617332e-08, "loss": 0.1692, "step": 1200 }, { "epoch": 4.864810126582278, "grad_norm": 0.255562704067379, "learning_rate": 6.769480656248606e-08, "loss": 0.2071, "step": 1201 }, { "epoch": 4.868860759493671, "grad_norm": 0.24446201458003403, "learning_rate": 6.310910695462635e-08, "loss": 0.1749, "step": 1202 }, { "epoch": 4.872911392405063, "grad_norm": 0.25634665823362285, "learning_rate": 5.8683976325191185e-08, "loss": 0.1852, "step": 1203 }, { "epoch": 4.876962025316455, "grad_norm": 0.25020774864393164, "learning_rate": 5.4419450313571984e-08, "loss": 0.1888, "step": 1204 }, { "epoch": 4.881012658227848, "grad_norm": 0.24524525699355976, "learning_rate": 5.031556326567488e-08, "loss": 0.1949, "step": 1205 }, { "epoch": 4.88506329113924, "grad_norm": 0.24971887883411947, "learning_rate": 4.637234823364312e-08, "loss": 0.2055, "step": 1206 }, { "epoch": 4.889113924050633, "grad_norm": 0.2451485035829408, "learning_rate": 4.258983697558838e-08, "loss": 0.1661, "step": 1207 }, { "epoch": 4.8931645569620255, "grad_norm": 0.23798148716160764, "learning_rate": 3.896805995533548e-08, "loss": 0.1804, "step": 1208 }, { "epoch": 4.8972151898734175, "grad_norm": 0.24344563589544557, "learning_rate": 3.550704634218028e-08, "loss": 0.1609, "step": 1209 }, { "epoch": 4.9012658227848105, "grad_norm": 0.25893627109421097, "learning_rate": 3.2206824010647676e-08, "loss": 0.2002, "step": 1210 }, { "epoch": 4.905316455696203, "grad_norm": 0.26139101976843726, "learning_rate": 2.9067419540278476e-08, "loss": 0.1943, "step": 1211 }, { "epoch": 4.909367088607595, "grad_norm": 0.24320155544009664, "learning_rate": 2.6088858215400638e-08, "loss": 0.1835, "step": 1212 }, { "epoch": 4.913417721518988, "grad_norm": 0.26399096305427505, "learning_rate": 2.3271164024940564e-08, "loss": 0.1922, "step": 1213 }, { "epoch": 4.91746835443038, "grad_norm": 0.2420817654038418, "learning_rate": 2.061435966221881e-08, "loss": 0.1897, "step": 1214 }, { "epoch": 4.921518987341772, "grad_norm": 0.24872003060184175, "learning_rate": 1.811846652477245e-08, "loss": 0.1751, "step": 1215 }, { "epoch": 4.925569620253165, "grad_norm": 0.25520321935548895, "learning_rate": 1.5783504714184106e-08, "loss": 0.1896, "step": 1216 }, { "epoch": 4.929620253164557, "grad_norm": 0.2295009943599803, "learning_rate": 1.360949303591097e-08, "loss": 0.1659, "step": 1217 }, { "epoch": 4.93367088607595, "grad_norm": 0.2508154351771549, "learning_rate": 1.1596448999144916e-08, "loss": 0.2018, "step": 1218 }, { "epoch": 4.937721518987342, "grad_norm": 0.2501707610565857, "learning_rate": 9.744388816668172e-09, "loss": 0.2136, "step": 1219 }, { "epoch": 4.941772151898734, "grad_norm": 0.2363468133820221, "learning_rate": 8.05332740472009e-09, "loss": 0.1704, "step": 1220 }, { "epoch": 4.945822784810127, "grad_norm": 0.25149805093059724, "learning_rate": 6.523278382872811e-09, "loss": 0.1798, "step": 1221 }, { "epoch": 4.949873417721519, "grad_norm": 0.24627736883491036, "learning_rate": 5.15425407393133e-09, "loss": 0.1704, "step": 1222 }, { "epoch": 4.953924050632912, "grad_norm": 0.2630131561034908, "learning_rate": 3.94626550383137e-09, "loss": 0.1907, "step": 1223 }, { "epoch": 4.957974683544304, "grad_norm": 0.24072922555580006, "learning_rate": 2.899322401546112e-09, "loss": 0.1945, "step": 1224 }, { "epoch": 4.962025316455696, "grad_norm": 0.24782698622664837, "learning_rate": 2.013433199010706e-09, "loss": 0.2039, "step": 1225 }, { "epoch": 4.966075949367089, "grad_norm": 0.24549532883350864, "learning_rate": 1.2886050310556563e-09, "loss": 0.1993, "step": 1226 }, { "epoch": 4.970126582278481, "grad_norm": 0.2583017781737512, "learning_rate": 7.248437353468695e-10, "loss": 0.2022, "step": 1227 }, { "epoch": 4.974177215189873, "grad_norm": 0.24377501264616105, "learning_rate": 3.221538523412449e-10, "loss": 0.1932, "step": 1228 }, { "epoch": 4.978227848101266, "grad_norm": 0.2517049798789256, "learning_rate": 8.053862524670663e-11, "loss": 0.1888, "step": 1229 }, { "epoch": 4.982278481012658, "grad_norm": 0.2599825324868731, "learning_rate": 0.0, "loss": 0.1988, "step": 1230 }, { "epoch": 4.982278481012658, "step": 1230, "total_flos": 2.525762970561757e+18, "train_loss": 0.0, "train_runtime": 1.7951, "train_samples_per_second": 88017.078, "train_steps_per_second": 685.196 } ], "logging_steps": 1, "max_steps": 1230, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.525762970561757e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }