{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5216357584403233,
  "eval_steps": 100,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 5e-05,
      "loss": 1.8229,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.9999950203346446e-05,
      "loss": 1.8352,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999980081358417e-05,
      "loss": 1.742,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999955183130829e-05,
      "loss": 1.6315,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999920325751068e-05,
      "loss": 1.6204,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999875509357998e-05,
      "loss": 1.5485,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999820734130155e-05,
      "loss": 1.4713,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999756000285748e-05,
      "loss": 1.4675,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9996813080826606e-05,
      "loss": 1.5091,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999596657818445e-05,
      "loss": 1.4009,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9995020498303275e-05,
      "loss": 1.2992,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999397484495198e-05,
      "loss": 1.2111,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.99928296222962e-05,
      "loss": 1.2281,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.999158483489818e-05,
      "loss": 1.2099,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.99902404877168e-05,
      "loss": 1.1259,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.998879658610761e-05,
      "loss": 1.022,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.998725313582272e-05,
      "loss": 1.1276,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.998561014301081e-05,
      "loss": 1.1276,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.998386761421714e-05,
      "loss": 1.2404,
      "step": 19
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.998202555638346e-05,
      "loss": 1.1622,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.998008397684806e-05,
      "loss": 1.1335,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.997804288334565e-05,
      "loss": 1.2187,
      "step": 22
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9975902284007405e-05,
      "loss": 1.0678,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.997366218736091e-05,
      "loss": 1.0195,
      "step": 24
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.99713226023301e-05,
      "loss": 1.0138,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9968883538235264e-05,
      "loss": 1.0706,
      "step": 26
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.996634500479297e-05,
      "loss": 0.9617,
      "step": 27
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.996370701211607e-05,
      "loss": 1.034,
      "step": 28
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.996096957071361e-05,
      "loss": 0.9952,
      "step": 29
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9958132691490816e-05,
      "loss": 0.9598,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.995519638574907e-05,
      "loss": 1.0342,
      "step": 31
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9952160665185825e-05,
      "loss": 0.9147,
      "step": 32
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.994902554189458e-05,
      "loss": 0.924,
      "step": 33
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.994579102836482e-05,
      "loss": 0.9021,
      "step": 34
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.994245713748198e-05,
      "loss": 1.0732,
      "step": 35
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.993902388252739e-05,
      "loss": 0.926,
      "step": 36
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.9935491277178236e-05,
      "loss": 0.9082,
      "step": 37
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.993185933550745e-05,
      "loss": 0.8735,
      "step": 38
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.992812807198372e-05,
      "loss": 1.0212,
      "step": 39
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.9924297501471414e-05,
      "loss": 0.9495,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.9920367639230483e-05,
      "loss": 0.9101,
      "step": 41
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.991633850091645e-05,
      "loss": 1.0533,
      "step": 42
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.991221010258034e-05,
      "loss": 0.8759,
      "step": 43
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.990798246066856e-05,
      "loss": 0.969,
      "step": 44
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9903655592022916e-05,
      "loss": 0.8463,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9899229513880494e-05,
      "loss": 0.844,
      "step": 46
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.989470424387361e-05,
      "loss": 0.8386,
      "step": 47
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.989007980002973e-05,
      "loss": 0.93,
      "step": 48
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.988535620077138e-05,
      "loss": 0.8551,
      "step": 49
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.988053346491613e-05,
      "loss": 0.8633,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.987561161167648e-05,
      "loss": 0.9056,
      "step": 51
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.9870590660659755e-05,
      "loss": 0.9366,
      "step": 52
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.986547063186808e-05,
      "loss": 1.0469,
      "step": 53
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.98602515456983e-05,
      "loss": 0.8723,
      "step": 54
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.985493342294184e-05,
      "loss": 0.9484,
      "step": 55
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.9849516284784676e-05,
      "loss": 0.8346,
      "step": 56
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.984400015280724e-05,
      "loss": 0.789,
      "step": 57
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.983838504898433e-05,
      "loss": 0.8986,
      "step": 58
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.9832670995685006e-05,
      "loss": 0.8799,
      "step": 59
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.9826858015672536e-05,
      "loss": 0.9028,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.982094613210428e-05,
      "loss": 0.8908,
      "step": 61
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.9814935368531586e-05,
      "loss": 0.8273,
      "step": 62
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.980882574889973e-05,
      "loss": 0.784,
      "step": 63
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.980261729754781e-05,
      "loss": 0.9336,
      "step": 64
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.9796310039208623e-05,
      "loss": 0.8943,
      "step": 65
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.978990399900861e-05,
      "loss": 1.1,
      "step": 66
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.9783399202467714e-05,
      "loss": 0.877,
      "step": 67
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.9776795675499296e-05,
      "loss": 0.8291,
      "step": 68
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.9770093444410046e-05,
      "loss": 0.7997,
      "step": 69
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.9763292535899866e-05,
      "loss": 0.7911,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.9756392977061736e-05,
      "loss": 0.8996,
      "step": 71
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.974939479538166e-05,
      "loss": 0.8631,
      "step": 72
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.974229801873854e-05,
      "loss": 0.8303,
      "step": 73
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.9735102675404004e-05,
      "loss": 0.8708,
      "step": 74
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.972780879404239e-05,
      "loss": 0.998,
      "step": 75
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.972041640371056e-05,
      "loss": 1.1049,
      "step": 76
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.971292553385783e-05,
      "loss": 0.774,
      "step": 77
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.970533621432581e-05,
      "loss": 0.8142,
      "step": 78
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.969764847534832e-05,
      "loss": 0.9968,
      "step": 79
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.9689862347551255e-05,
      "loss": 0.9622,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.9681977861952464e-05,
      "loss": 0.8342,
      "step": 81
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.967399504996162e-05,
      "loss": 0.9,
      "step": 82
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.966591394338012e-05,
      "loss": 0.8515,
      "step": 83
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.965773457440092e-05,
      "loss": 0.7937,
      "step": 84
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.964945697560844e-05,
      "loss": 0.9577,
      "step": 85
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.9641081179978424e-05,
      "loss": 0.8233,
      "step": 86
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.963260722087779e-05,
      "loss": 0.9769,
      "step": 87
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.9624035132064526e-05,
      "loss": 0.8927,
      "step": 88
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.961536494768754e-05,
      "loss": 0.9383,
      "step": 89
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.960659670228652e-05,
      "loss": 0.9177,
      "step": 90
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.959773043079181e-05,
      "loss": 0.8026,
      "step": 91
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.958876616852427e-05,
      "loss": 0.9647,
      "step": 92
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.9579703951195113e-05,
      "loss": 0.7545,
      "step": 93
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.957054381490579e-05,
      "loss": 0.7836,
      "step": 94
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.9561285796147824e-05,
      "loss": 0.8803,
      "step": 95
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.955192993180269e-05,
      "loss": 0.8988,
      "step": 96
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.9542476259141656e-05,
      "loss": 0.8418,
      "step": 97
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.953292481582561e-05,
      "loss": 0.9004,
      "step": 98
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.9523275639904944e-05,
      "loss": 0.9159,
      "step": 99
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.951352876981939e-05,
      "loss": 0.7605,
      "step": 100
    },
    {
      "epoch": 0.19,
      "eval_loss": 0.7751120924949646,
      "eval_runtime": 2.7398,
      "eval_samples_per_second": 3.285,
      "eval_steps_per_second": 0.73,
      "step": 100
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.9503684244397894e-05,
      "loss": 0.8228,
      "step": 101
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.949374210285838e-05,
      "loss": 0.7176,
      "step": 102
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.948370238480769e-05,
      "loss": 0.9403,
      "step": 103
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.9473565130241376e-05,
      "loss": 0.7711,
      "step": 104
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.946333037954354e-05,
      "loss": 0.8349,
      "step": 105
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.945299817348669e-05,
      "loss": 0.7899,
      "step": 106
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.944256855323157e-05,
      "loss": 0.913,
      "step": 107
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.9432041560326995e-05,
      "loss": 0.9574,
      "step": 108
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.942141723670969e-05,
      "loss": 0.8848,
      "step": 109
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.941069562470411e-05,
      "loss": 0.9267,
      "step": 110
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.939987676702229e-05,
      "loss": 0.7779,
      "step": 111
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.938896070676366e-05,
      "loss": 0.9766,
      "step": 112
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.9377947487414886e-05,
      "loss": 0.8737,
      "step": 113
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.936683715284968e-05,
      "loss": 0.7962,
      "step": 114
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.935562974732865e-05,
      "loss": 0.8711,
      "step": 115
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.934432531549909e-05,
      "loss": 0.8212,
      "step": 116
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.933292390239483e-05,
      "loss": 0.8364,
      "step": 117
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.9321425553436054e-05,
      "loss": 0.8737,
      "step": 118
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.9309830314429095e-05,
      "loss": 0.8382,
      "step": 119
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.92981382315663e-05,
      "loss": 0.9143,
      "step": 120
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.9286349351425774e-05,
      "loss": 0.9366,
      "step": 121
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.927446372097127e-05,
      "loss": 0.7771,
      "step": 122
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.9262481387551976e-05,
      "loss": 0.8218,
      "step": 123
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.925040239890227e-05,
      "loss": 0.9309,
      "step": 124
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.923822680314162e-05,
      "loss": 0.8345,
      "step": 125
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.922595464877435e-05,
      "loss": 0.8479,
      "step": 126
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.921358598468942e-05,
      "loss": 0.8879,
      "step": 127
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.920112086016029e-05,
      "loss": 0.8235,
      "step": 128
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.918855932484468e-05,
      "loss": 0.8693,
      "step": 129
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.917590142878437e-05,
      "loss": 0.8928,
      "step": 130
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.916314722240504e-05,
      "loss": 0.9152,
      "step": 131
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.915029675651604e-05,
      "loss": 0.9386,
      "step": 132
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.913735008231016e-05,
      "loss": 0.8565,
      "step": 133
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.9124307251363525e-05,
      "loss": 0.8073,
      "step": 134
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.911116831563524e-05,
      "loss": 0.8975,
      "step": 135
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.909793332746733e-05,
      "loss": 0.7949,
      "step": 136
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.908460233958444e-05,
      "loss": 0.8059,
      "step": 137
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.907117540509366e-05,
      "loss": 0.8424,
      "step": 138
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.9057652577484293e-05,
      "loss": 0.7911,
      "step": 139
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.9044033910627676e-05,
      "loss": 0.858,
      "step": 140
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.9030319458776926e-05,
      "loss": 0.977,
      "step": 141
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.9016509276566746e-05,
      "loss": 0.8803,
      "step": 142
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.9002603419013205e-05,
      "loss": 0.9155,
      "step": 143
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.8988601941513526e-05,
      "loss": 0.6968,
      "step": 144
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.897450489984583e-05,
      "loss": 0.8425,
      "step": 145
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.896031235016897e-05,
      "loss": 0.9646,
      "step": 146
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.894602434902226e-05,
      "loss": 0.8387,
      "step": 147
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.893164095332527e-05,
      "loss": 0.9245,
      "step": 148
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.89171622203776e-05,
      "loss": 0.861,
      "step": 149
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.890258820785865e-05,
      "loss": 0.7925,
      "step": 150
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.8887918973827375e-05,
      "loss": 0.8197,
      "step": 151
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.887315457672208e-05,
      "loss": 0.8404,
      "step": 152
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.8858295075360175e-05,
      "loss": 0.8094,
      "step": 153
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.884334052893793e-05,
      "loss": 0.8282,
      "step": 154
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.882829099703026e-05,
      "loss": 0.7838,
      "step": 155
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.881314653959046e-05,
      "loss": 0.8562,
      "step": 156
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.8797907216950015e-05,
      "loss": 0.818,
      "step": 157
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.878257308981827e-05,
      "loss": 0.7874,
      "step": 158
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.8767144219282325e-05,
      "loss": 0.9106,
      "step": 159
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.875162066680664e-05,
      "loss": 0.9026,
      "step": 160
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.8736002494232904e-05,
      "loss": 0.7882,
      "step": 161
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.872028976377974e-05,
      "loss": 1.0285,
      "step": 162
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.870448253804244e-05,
      "loss": 0.8034,
      "step": 163
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.868858087999279e-05,
      "loss": 0.7977,
      "step": 164
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.86725848529787e-05,
      "loss": 0.885,
      "step": 165
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.86564945207241e-05,
      "loss": 0.804,
      "step": 166
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.864030994732852e-05,
      "loss": 0.9618,
      "step": 167
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.862403119726702e-05,
      "loss": 0.8042,
      "step": 168
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.860765833538974e-05,
      "loss": 1.0271,
      "step": 169
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.85911914269218e-05,
      "loss": 0.799,
      "step": 170
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.8574630537462954e-05,
      "loss": 0.7454,
      "step": 171
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.855797573298734e-05,
      "loss": 0.7428,
      "step": 172
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.8541227079843246e-05,
      "loss": 0.9079,
      "step": 173
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.852438464475283e-05,
      "loss": 0.7964,
      "step": 174
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.8507448494811834e-05,
      "loss": 0.9262,
      "step": 175
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.849041869748935e-05,
      "loss": 0.7817,
      "step": 176
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.847329532062753e-05,
      "loss": 0.759,
      "step": 177
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.845607843244132e-05,
      "loss": 0.9029,
      "step": 178
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.843876810151821e-05,
      "loss": 0.7191,
      "step": 179
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.8421364396817905e-05,
      "loss": 0.8861,
      "step": 180
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.840386738767211e-05,
      "loss": 0.982,
      "step": 181
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.838627714378423e-05,
      "loss": 0.8453,
      "step": 182
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.8368593735229074e-05,
      "loss": 0.9402,
      "step": 183
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.8350817232452625e-05,
      "loss": 0.7882,
      "step": 184
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.8332947706271706e-05,
      "loss": 0.8458,
      "step": 185
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.831498522787372e-05,
      "loss": 0.8955,
      "step": 186
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.829692986881638e-05,
      "loss": 0.7777,
      "step": 187
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.8278781701027395e-05,
      "loss": 0.7341,
      "step": 188
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.826054079680422e-05,
      "loss": 0.8234,
      "step": 189
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.824220722881371e-05,
      "loss": 0.7693,
      "step": 190
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.8223781070091914e-05,
      "loss": 0.8162,
      "step": 191
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.8205262394043705e-05,
      "loss": 0.8983,
      "step": 192
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.818665127444253e-05,
      "loss": 0.9481,
      "step": 193
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.816794778543011e-05,
      "loss": 0.9685,
      "step": 194
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.814915200151614e-05,
      "loss": 0.9092,
      "step": 195
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.813026399757799e-05,
      "loss": 0.7715,
      "step": 196
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.811128384886041e-05,
      "loss": 0.8279,
      "step": 197
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.809221163097523e-05,
      "loss": 0.7468,
      "step": 198
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.807304741990106e-05,
      "loss": 0.7938,
      "step": 199
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.805379129198299e-05,
      "loss": 0.9049,
      "step": 200
    },
    {
      "epoch": 0.38,
      "eval_loss": 0.7435702681541443,
      "eval_runtime": 2.8319,
      "eval_samples_per_second": 3.178,
      "eval_steps_per_second": 0.706,
      "step": 200
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.803444332393227e-05,
      "loss": 0.8812,
      "step": 201
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.801500359282605e-05,
      "loss": 0.84,
      "step": 202
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.7995472176106974e-05,
      "loss": 0.8609,
      "step": 203
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.797584915158301e-05,
      "loss": 0.8207,
      "step": 204
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.795613459742702e-05,
      "loss": 0.7714,
      "step": 205
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.7936328592176516e-05,
      "loss": 0.7537,
      "step": 206
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.7916431214733314e-05,
      "loss": 0.8651,
      "step": 207
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.7896442544363246e-05,
      "loss": 0.8055,
      "step": 208
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.787636266069582e-05,
      "loss": 0.8936,
      "step": 209
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.785619164372391e-05,
      "loss": 0.701,
      "step": 210
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.783592957380346e-05,
      "loss": 0.7145,
      "step": 211
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.781557653165313e-05,
      "loss": 0.896,
      "step": 212
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.779513259835399e-05,
      "loss": 0.7178,
      "step": 213
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.777459785534918e-05,
      "loss": 0.8032,
      "step": 214
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.7753972384443644e-05,
      "loss": 0.8792,
      "step": 215
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.773325626780373e-05,
      "loss": 0.7246,
      "step": 216
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.771244958795688e-05,
      "loss": 0.8574,
      "step": 217
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.7691552427791365e-05,
      "loss": 0.7291,
      "step": 218
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.7670564870555864e-05,
      "loss": 0.8259,
      "step": 219
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.7649486999859185e-05,
      "loss": 0.7818,
      "step": 220
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.762831889966992e-05,
      "loss": 0.8693,
      "step": 221
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.760706065431612e-05,
      "loss": 0.8281,
      "step": 222
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.758571234848494e-05,
      "loss": 0.8359,
      "step": 223
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.7564274067222314e-05,
      "loss": 0.8119,
      "step": 224
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.754274589593262e-05,
      "loss": 0.8577,
      "step": 225
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.752112792037832e-05,
      "loss": 0.7509,
      "step": 226
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.7499420226679646e-05,
      "loss": 0.7648,
      "step": 227
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.747762290131424e-05,
      "loss": 0.7964,
      "step": 228
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.7455736031116804e-05,
      "loss": 0.8229,
      "step": 229
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.7433759703278785e-05,
      "loss": 0.7705,
      "step": 230
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.741169400534797e-05,
      "loss": 0.8954,
      "step": 231
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.7389539025228217e-05,
      "loss": 0.8405,
      "step": 232
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.7367294851179e-05,
      "loss": 0.7539,
      "step": 233
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.734496157181518e-05,
      "loss": 0.7844,
      "step": 234
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.732253927610657e-05,
      "loss": 0.7417,
      "step": 235
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.7300028053377564e-05,
      "loss": 0.8239,
      "step": 236
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.7277427993306867e-05,
      "loss": 0.7526,
      "step": 237
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.7254739185927066e-05,
      "loss": 0.8431,
      "step": 238
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.7231961721624296e-05,
      "loss": 0.737,
      "step": 239
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.720909569113787e-05,
      "loss": 0.751,
      "step": 240
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.718614118555993e-05,
      "loss": 0.8756,
      "step": 241
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.71630982963351e-05,
      "loss": 0.7679,
      "step": 242
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.713996711526005e-05,
      "loss": 0.7593,
      "step": 243
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.7116747734483245e-05,
      "loss": 0.8194,
      "step": 244
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.7093440246504465e-05,
      "loss": 0.9187,
      "step": 245
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.70700447441745e-05,
      "loss": 0.7543,
      "step": 246
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.704656132069478e-05,
      "loss": 0.6961,
      "step": 247
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.7022990069616973e-05,
      "loss": 0.8313,
      "step": 248
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.699933108484262e-05,
      "loss": 0.8524,
      "step": 249
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.69755844606228e-05,
      "loss": 0.7614,
      "step": 250
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.695175029155771e-05,
      "loss": 0.7678,
      "step": 251
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.692782867259627e-05,
      "loss": 0.9097,
      "step": 252
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.690381969903583e-05,
      "loss": 0.8819,
      "step": 253
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.6879723466521706e-05,
      "loss": 0.883,
      "step": 254
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.685554007104684e-05,
      "loss": 0.7365,
      "step": 255
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.683126960895141e-05,
      "loss": 0.8576,
      "step": 256
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.680691217692242e-05,
      "loss": 0.8227,
      "step": 257
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.678246787199338e-05,
      "loss": 0.7949,
      "step": 258
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.6757936791543846e-05,
      "loss": 0.8524,
      "step": 259
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.6733319033299075e-05,
      "loss": 0.7235,
      "step": 260
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.670861469532963e-05,
      "loss": 0.8348,
      "step": 261
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.668382387605098e-05,
      "loss": 0.7539,
      "step": 262
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.665894667422311e-05,
      "loss": 0.7968,
      "step": 263
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.663398318895013e-05,
      "loss": 1.0207,
      "step": 264
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.660893351967988e-05,
      "loss": 0.7758,
      "step": 265
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.658379776620354e-05,
      "loss": 0.8379,
      "step": 266
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.6558576028655226e-05,
      "loss": 0.8968,
      "step": 267
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.6533268407511586e-05,
      "loss": 0.8639,
      "step": 268
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.650787500359141e-05,
      "loss": 0.713,
      "step": 269
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.6482395918055197e-05,
      "loss": 0.9117,
      "step": 270
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.6456831252404844e-05,
      "loss": 0.7259,
      "step": 271
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.64311811084831e-05,
      "loss": 0.7107,
      "step": 272
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.64054455884733e-05,
      "loss": 0.8522,
      "step": 273
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.637962479489883e-05,
      "loss": 0.764,
      "step": 274
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.635371883062286e-05,
      "loss": 0.8385,
      "step": 275
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.6327727798847785e-05,
      "loss": 0.9269,
      "step": 276
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.630165180311493e-05,
      "loss": 0.7428,
      "step": 277
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.6275490947304084e-05,
      "loss": 0.8363,
      "step": 278
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.6249245335633086e-05,
      "loss": 0.8526,
      "step": 279
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.6222915072657424e-05,
      "loss": 0.8759,
      "step": 280
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.6196500263269824e-05,
      "loss": 0.7692,
      "step": 281
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.617000101269982e-05,
      "loss": 0.8109,
      "step": 282
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.614341742651332e-05,
      "loss": 0.6978,
      "step": 283
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.6116749610612214e-05,
      "loss": 0.7617,
      "step": 284
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.6089997671233955e-05,
      "loss": 0.8812,
      "step": 285
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.606316171495109e-05,
      "loss": 0.7013,
      "step": 286
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.60362418486709e-05,
      "loss": 0.8073,
      "step": 287
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.6009238179634916e-05,
      "loss": 0.8615,
      "step": 288
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.598215081541853e-05,
      "loss": 0.9124,
      "step": 289
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.595497986393055e-05,
      "loss": 0.8016,
      "step": 290
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.592772543341276e-05,
      "loss": 0.8414,
      "step": 291
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.590038763243953e-05,
      "loss": 0.7662,
      "step": 292
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.587296656991734e-05,
      "loss": 0.7667,
      "step": 293
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.584546235508436e-05,
      "loss": 0.8404,
      "step": 294
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.581787509751001e-05,
      "loss": 0.9285,
      "step": 295
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.5790204907094554e-05,
      "loss": 0.863,
      "step": 296
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.5762451894068606e-05,
      "loss": 0.941,
      "step": 297
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.573461616899275e-05,
      "loss": 0.9033,
      "step": 298
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.570669784275706e-05,
      "loss": 0.8648,
      "step": 299
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.567869702658067e-05,
      "loss": 0.8397,
      "step": 300
    },
    {
      "epoch": 0.57,
      "eval_loss": 0.7216992974281311,
      "eval_runtime": 2.8122,
      "eval_samples_per_second": 3.2,
      "eval_steps_per_second": 0.711,
      "step": 300
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.565061383201135e-05,
      "loss": 0.7869,
      "step": 301
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.562244837092501e-05,
      "loss": 0.8699,
      "step": 302
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.559420075552532e-05,
      "loss": 0.7533,
      "step": 303
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.5565871098343206e-05,
      "loss": 0.7445,
      "step": 304
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.553745951223645e-05,
      "loss": 0.8536,
      "step": 305
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.55089661103892e-05,
      "loss": 0.8168,
      "step": 306
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.548039100631153e-05,
      "loss": 0.7869,
      "step": 307
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.5451734313839026e-05,
      "loss": 0.7409,
      "step": 308
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.5422996147132257e-05,
      "loss": 0.8334,
      "step": 309
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.53941766206764e-05,
      "loss": 0.7438,
      "step": 310
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.536527584928073e-05,
      "loss": 0.8303,
      "step": 311
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.533629394807819e-05,
      "loss": 0.7954,
      "step": 312
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.5307231032524897e-05,
      "loss": 0.694,
      "step": 313
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.5278087218399735e-05,
      "loss": 0.8333,
      "step": 314
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.524886262180387e-05,
      "loss": 0.8683,
      "step": 315
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.5219557359160244e-05,
      "loss": 0.8963,
      "step": 316
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.519017154721321e-05,
      "loss": 0.8737,
      "step": 317
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.516070530302795e-05,
      "loss": 0.8319,
      "step": 318
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.51311587439901e-05,
      "loss": 0.7937,
      "step": 319
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.510153198780524e-05,
      "loss": 0.7702,
      "step": 320
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.507182515249845e-05,
      "loss": 0.9189,
      "step": 321
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.504203835641379e-05,
      "loss": 0.8915,
      "step": 322
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.501217171821389e-05,
      "loss": 0.8164,
      "step": 323
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.4982225356879436e-05,
      "loss": 0.8632,
      "step": 324
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.4952199391708716e-05,
      "loss": 0.7958,
      "step": 325
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.492209394231714e-05,
      "loss": 0.7706,
      "step": 326
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.489190912863675e-05,
      "loss": 0.8457,
      "step": 327
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.486164507091578e-05,
      "loss": 0.8253,
      "step": 328
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.483130188971812e-05,
      "loss": 0.8703,
      "step": 329
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.4800879705922885e-05,
      "loss": 0.7406,
      "step": 330
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.4770378640723904e-05,
      "loss": 0.8331,
      "step": 331
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.4739798815629264e-05,
      "loss": 0.8479,
      "step": 332
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.47091403524608e-05,
      "loss": 0.8482,
      "step": 333
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.4678403373353614e-05,
      "loss": 0.848,
      "step": 334
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.464758800075561e-05,
      "loss": 0.8397,
      "step": 335
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.461669435742698e-05,
      "loss": 0.7962,
      "step": 336
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.458572256643973e-05,
      "loss": 0.8888,
      "step": 337
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.455467275117718e-05,
      "loss": 0.7731,
      "step": 338
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.452354503533348e-05,
      "loss": 0.9121,
      "step": 339
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.449233954291313e-05,
      "loss": 0.7023,
      "step": 340
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.446105639823044e-05,
      "loss": 0.7888,
      "step": 341
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.442969572590909e-05,
      "loss": 0.7791,
      "step": 342
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.439825765088161e-05,
      "loss": 0.8437,
      "step": 343
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.436674229838887e-05,
      "loss": 1.0018,
      "step": 344
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.433514979397959e-05,
      "loss": 0.8058,
      "step": 345
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.4303480263509855e-05,
      "loss": 0.6082,
      "step": 346
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.42717338331426e-05,
      "loss": 0.8858,
      "step": 347
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.4239910629347096e-05,
      "loss": 0.8144,
      "step": 348
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.420801077889848e-05,
      "loss": 0.8518,
      "step": 349
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.41760344088772e-05,
      "loss": 0.7277,
      "step": 350
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.414398164666856e-05,
      "loss": 0.9246,
      "step": 351
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.41118526199622e-05,
      "loss": 0.8504,
      "step": 352
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.407964745675153e-05,
      "loss": 0.7957,
      "step": 353
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.404736628533332e-05,
      "loss": 0.7425,
      "step": 354
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.401500923430712e-05,
      "loss": 0.9097,
      "step": 355
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.398257643257474e-05,
      "loss": 0.7344,
      "step": 356
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.395006800933978e-05,
      "loss": 0.8781,
      "step": 357
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.391748409410712e-05,
      "loss": 0.8264,
      "step": 358
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.388482481668232e-05,
      "loss": 0.7782,
      "step": 359
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.385209030717123e-05,
      "loss": 0.9151,
      "step": 360
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.3819280695979354e-05,
      "loss": 0.7878,
      "step": 361
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.37863961138114e-05,
      "loss": 0.8142,
      "step": 362
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.3753436691670746e-05,
      "loss": 0.707,
      "step": 363
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.372040256085891e-05,
      "loss": 0.7494,
      "step": 364
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.368729385297501e-05,
      "loss": 0.9402,
      "step": 365
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.365411069991528e-05,
      "loss": 0.8291,
      "step": 366
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.3620853233872525e-05,
      "loss": 0.9221,
      "step": 367
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.3587521587335586e-05,
      "loss": 0.775,
      "step": 368
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.355411589308881e-05,
      "loss": 0.8099,
      "step": 369
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.352063628421155e-05,
      "loss": 0.8428,
      "step": 370
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.3487082894077594e-05,
      "loss": 0.8306,
      "step": 371
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.345345585635468e-05,
      "loss": 0.9234,
      "step": 372
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.3419755305003904e-05,
      "loss": 0.8925,
      "step": 373
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.3385981374279264e-05,
      "loss": 0.8707,
      "step": 374
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.3352134198727036e-05,
      "loss": 0.7951,
      "step": 375
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.331821391318532e-05,
      "loss": 0.7105,
      "step": 376
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.328422065278346e-05,
      "loss": 0.6983,
      "step": 377
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.325015455294148e-05,
      "loss": 0.7357,
      "step": 378
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.321601574936962e-05,
      "loss": 0.8573,
      "step": 379
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.3181804378067726e-05,
      "loss": 0.9227,
      "step": 380
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.314752057532475e-05,
      "loss": 0.791,
      "step": 381
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.3113164477718174e-05,
      "loss": 0.7773,
      "step": 382
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.3078736222113496e-05,
      "loss": 0.9276,
      "step": 383
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.304423594566368e-05,
      "loss": 0.7723,
      "step": 384
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.300966378580858e-05,
      "loss": 0.8327,
      "step": 385
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.297501988027442e-05,
      "loss": 0.7469,
      "step": 386
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.294030436707327e-05,
      "loss": 0.6427,
      "step": 387
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.290551738450241e-05,
      "loss": 0.8161,
      "step": 388
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.2870659071143894e-05,
      "loss": 0.7147,
      "step": 389
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.2835729565863884e-05,
      "loss": 0.8505,
      "step": 390
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.2800729007812196e-05,
      "loss": 0.8531,
      "step": 391
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.2765657536421675e-05,
      "loss": 0.7539,
      "step": 392
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.273051529140767e-05,
      "loss": 0.8358,
      "step": 393
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.269530241276749e-05,
      "loss": 0.7724,
      "step": 394
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.2660019040779805e-05,
      "loss": 0.8011,
      "step": 395
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.262466531600413e-05,
      "loss": 0.7952,
      "step": 396
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.258924137928023e-05,
      "loss": 0.7196,
      "step": 397
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.2553747371727606e-05,
      "loss": 0.7226,
      "step": 398
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.251818343474486e-05,
      "loss": 0.7577,
      "step": 399
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.24825497100092e-05,
      "loss": 0.7186,
      "step": 400
    },
    {
      "epoch": 0.76,
      "eval_loss": 0.7108685374259949,
      "eval_runtime": 2.7837,
      "eval_samples_per_second": 3.233,
      "eval_steps_per_second": 0.718,
      "step": 400
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.244684633947586e-05,
      "loss": 0.8418,
      "step": 401
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.241107346537748e-05,
      "loss": 0.8305,
      "step": 402
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.237523123022365e-05,
      "loss": 1.0274,
      "step": 403
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.233931977680021e-05,
      "loss": 0.8431,
      "step": 404
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.230333924816881e-05,
      "loss": 0.8005,
      "step": 405
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.22672897876662e-05,
      "loss": 0.8787,
      "step": 406
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.223117153890381e-05,
      "loss": 0.9091,
      "step": 407
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.2194984645767065e-05,
      "loss": 0.7993,
      "step": 408
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.215872925241486e-05,
      "loss": 0.9422,
      "step": 409
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.212240550327898e-05,
      "loss": 0.7923,
      "step": 410
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.2086013543063504e-05,
      "loss": 0.8263,
      "step": 411
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.204955351674428e-05,
      "loss": 0.7529,
      "step": 412
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.201302556956827e-05,
      "loss": 1.0105,
      "step": 413
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.197642984705305e-05,
      "loss": 0.7613,
      "step": 414
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.1939766494986174e-05,
      "loss": 0.7851,
      "step": 415
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.190303565942463e-05,
      "loss": 0.687,
      "step": 416
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.1866237486694225e-05,
      "loss": 0.7759,
      "step": 417
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.182937212338903e-05,
      "loss": 0.8702,
      "step": 418
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.1792439716370786e-05,
      "loss": 0.8531,
      "step": 419
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.175544041276831e-05,
      "loss": 0.8694,
      "step": 420
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.1718374359976926e-05,
      "loss": 0.7487,
      "step": 421
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.1681241705657865e-05,
      "loss": 0.7525,
      "step": 422
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.164404259773768e-05,
      "loss": 0.8515,
      "step": 423
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.160677718440765e-05,
      "loss": 0.7136,
      "step": 424
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.156944561412323e-05,
      "loss": 0.9546,
      "step": 425
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.1532048035603376e-05,
      "loss": 0.6966,
      "step": 426
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.149458459783004e-05,
      "loss": 0.8917,
      "step": 427
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.1457055450047534e-05,
      "loss": 0.7036,
      "step": 428
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.141946074176192e-05,
      "loss": 0.7952,
      "step": 429
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.138180062274045e-05,
      "loss": 0.7388,
      "step": 430
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.134407524301098e-05,
      "loss": 0.8248,
      "step": 431
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.13062847528613e-05,
      "loss": 0.698,
      "step": 432
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.126842930283862e-05,
      "loss": 0.8154,
      "step": 433
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.123050904374891e-05,
      "loss": 0.8472,
      "step": 434
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.1192524126656337e-05,
      "loss": 0.946,
      "step": 435
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.1154474702882626e-05,
      "loss": 0.8445,
      "step": 436
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.111636092400652e-05,
      "loss": 0.7753,
      "step": 437
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.107818294186308e-05,
      "loss": 0.8108,
      "step": 438
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.10399409085432e-05,
      "loss": 0.7051,
      "step": 439
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.100163497639288e-05,
      "loss": 0.9362,
      "step": 440
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.096326529801271e-05,
      "loss": 0.7638,
      "step": 441
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.09248320262572e-05,
      "loss": 0.7786,
      "step": 442
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.088633531423423e-05,
      "loss": 0.8217,
      "step": 443
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.084777531530439e-05,
      "loss": 0.8158,
      "step": 444
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.08091521830804e-05,
      "loss": 0.7217,
      "step": 445
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.077046607142646e-05,
      "loss": 0.7779,
      "step": 446
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.07317171344577e-05,
      "loss": 0.7776,
      "step": 447
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.069290552653951e-05,
      "loss": 0.8132,
      "step": 448
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.065403140228693e-05,
      "loss": 0.768,
      "step": 449
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.0615094916564087e-05,
      "loss": 0.7917,
      "step": 450
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.057609622448349e-05,
      "loss": 0.7716,
      "step": 451
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.053703548140551e-05,
      "loss": 0.7192,
      "step": 452
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.049791284293768e-05,
      "loss": 0.7797,
      "step": 453
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.045872846493412e-05,
      "loss": 0.8675,
      "step": 454
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.0419482503494896e-05,
      "loss": 0.7104,
      "step": 455
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.0380175114965426e-05,
      "loss": 0.8268,
      "step": 456
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.034080645593581e-05,
      "loss": 0.8496,
      "step": 457
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.030137668324024e-05,
      "loss": 0.7655,
      "step": 458
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.026188595395639e-05,
      "loss": 0.783,
      "step": 459
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.0222334425404757e-05,
      "loss": 0.7517,
      "step": 460
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.018272225514802e-05,
      "loss": 0.7921,
      "step": 461
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.014304960099048e-05,
      "loss": 0.7849,
      "step": 462
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.010331662097736e-05,
      "loss": 0.781,
      "step": 463
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.0063523473394215e-05,
      "loss": 0.8017,
      "step": 464
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.00236703167663e-05,
      "loss": 0.7774,
      "step": 465
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.998375730985791e-05,
      "loss": 0.8126,
      "step": 466
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.994378461167178e-05,
      "loss": 0.7426,
      "step": 467
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.9903752381448465e-05,
      "loss": 0.7115,
      "step": 468
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.986366077866562e-05,
      "loss": 0.8825,
      "step": 469
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.9823509963037464e-05,
      "loss": 0.8392,
      "step": 470
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.978330009451411e-05,
      "loss": 0.9632,
      "step": 471
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.97430313332809e-05,
      "loss": 0.7299,
      "step": 472
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.97027038397578e-05,
      "loss": 0.7646,
      "step": 473
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.966231777459875e-05,
      "loss": 0.7527,
      "step": 474
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.962187329869102e-05,
      "loss": 0.9925,
      "step": 475
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.958137057315457e-05,
      "loss": 0.8299,
      "step": 476
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.9540809759341426e-05,
      "loss": 0.8115,
      "step": 477
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.9500191018835e-05,
      "loss": 0.7775,
      "step": 478
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.945951451344948e-05,
      "loss": 0.7463,
      "step": 479
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.941878040522918e-05,
      "loss": 0.912,
      "step": 480
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.937798885644789e-05,
      "loss": 0.8419,
      "step": 481
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.93371400296082e-05,
      "loss": 0.9328,
      "step": 482
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.929623408744092e-05,
      "loss": 0.7434,
      "step": 483
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.925527119290436e-05,
      "loss": 0.7526,
      "step": 484
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.9214251509183733e-05,
      "loss": 0.7491,
      "step": 485
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.917317519969046e-05,
      "loss": 0.7936,
      "step": 486
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.913204242806158e-05,
      "loss": 0.8184,
      "step": 487
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.909085335815904e-05,
      "loss": 0.7352,
      "step": 488
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.904960815406906e-05,
      "loss": 0.7438,
      "step": 489
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.900830698010149e-05,
      "loss": 0.7998,
      "step": 490
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.896695000078917e-05,
      "loss": 0.7039,
      "step": 491
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.892553738088721e-05,
      "loss": 0.9362,
      "step": 492
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.888406928537242e-05,
      "loss": 0.7281,
      "step": 493
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.884254587944258e-05,
      "loss": 0.7993,
      "step": 494
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.880096732851581e-05,
      "loss": 0.6587,
      "step": 495
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.8759333798229955e-05,
      "loss": 0.8164,
      "step": 496
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.8717645454441836e-05,
      "loss": 0.7832,
      "step": 497
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.867590246322665e-05,
      "loss": 0.8283,
      "step": 498
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.863410499087731e-05,
      "loss": 0.9244,
      "step": 499
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.859225320390375e-05,
      "loss": 0.7304,
      "step": 500
    },
    {
      "epoch": 0.95,
      "eval_loss": 0.700370192527771,
      "eval_runtime": 2.8512,
      "eval_samples_per_second": 3.157,
      "eval_steps_per_second": 0.701,
      "step": 500
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.8550347269032285e-05,
      "loss": 0.8409,
      "step": 501
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.850838735320494e-05,
      "loss": 0.7045,
      "step": 502
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.84663736235788e-05,
      "loss": 0.8243,
      "step": 503
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.842430624752529e-05,
      "loss": 0.7521,
      "step": 504
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.83821853926296e-05,
      "loss": 0.7212,
      "step": 505
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.834001122668992e-05,
      "loss": 0.8555,
      "step": 506
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.829778391771684e-05,
      "loss": 0.748,
      "step": 507
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.825550363393268e-05,
      "loss": 0.7956,
      "step": 508
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.8213170543770724e-05,
      "loss": 0.7905,
      "step": 509
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.8170784815874705e-05,
      "loss": 0.7764,
      "step": 510
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.812834661909801e-05,
      "loss": 0.8791,
      "step": 511
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.808585612250305e-05,
      "loss": 0.8355,
      "step": 512
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.8043313495360586e-05,
      "loss": 0.7779,
      "step": 513
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.800071890714906e-05,
      "loss": 0.9408,
      "step": 514
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.79580725275539e-05,
      "loss": 0.92,
      "step": 515
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.791537452646687e-05,
      "loss": 0.857,
      "step": 516
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.787262507398538e-05,
      "loss": 0.8673,
      "step": 517
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.7829824340411795e-05,
      "loss": 0.8399,
      "step": 518
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.778697249625279e-05,
      "loss": 0.7836,
      "step": 519
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.774406971221863e-05,
      "loss": 1.0116,
      "step": 520
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.770111615922253e-05,
      "loss": 0.8791,
      "step": 521
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.765811200837994e-05,
      "loss": 0.7788,
      "step": 522
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.7615057431007885e-05,
      "loss": 0.8853,
      "step": 523
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.757195259862427e-05,
      "loss": 0.7102,
      "step": 524
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.7528797682947206e-05,
      "loss": 0.7532,
      "step": 525
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.7485592855894346e-05,
      "loss": 0.7091,
      "step": 526
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.744233828958213e-05,
      "loss": 0.8155,
      "step": 527
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.739903415632518e-05,
      "loss": 0.8474,
      "step": 528
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.735568062863557e-05,
      "loss": 0.8274,
      "step": 529
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.731227787922214e-05,
      "loss": 0.8146,
      "step": 530
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.726882608098984e-05,
      "loss": 0.7811,
      "step": 531
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.722532540703898e-05,
      "loss": 0.669,
      "step": 532
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.718177603066462e-05,
      "loss": 0.6793,
      "step": 533
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.71381781253558e-05,
      "loss": 0.7047,
      "step": 534
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.709453186479491e-05,
      "loss": 0.6797,
      "step": 535
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.705083742285697e-05,
      "loss": 0.7729,
      "step": 536
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.700709497360894e-05,
      "loss": 0.8578,
      "step": 537
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.6963304691309026e-05,
      "loss": 0.7326,
      "step": 538
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.691946675040598e-05,
      "loss": 0.7918,
      "step": 539
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.6875581325538436e-05,
      "loss": 0.7694,
      "step": 540
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.6831648591534166e-05,
      "loss": 0.8746,
      "step": 541
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.678766872340943e-05,
      "loss": 0.8269,
      "step": 542
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.674364189636824e-05,
      "loss": 0.8922,
      "step": 543
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.66995682858017e-05,
      "loss": 0.7966,
      "step": 544
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.665544806728726e-05,
      "loss": 0.7073,
      "step": 545
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.661128141658807e-05,
      "loss": 0.8515,
      "step": 546
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.656706850965225e-05,
      "loss": 0.8462,
      "step": 547
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.652280952261216e-05,
      "loss": 0.7801,
      "step": 548
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.647850463178378e-05,
      "loss": 0.8474,
      "step": 549
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.643415401366591e-05,
      "loss": 0.7059,
      "step": 550
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.638975784493957e-05,
      "loss": 0.7343,
      "step": 551
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.634531630246718e-05,
      "loss": 0.7755,
      "step": 552
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.630082956329197e-05,
      "loss": 0.7483,
      "step": 553
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.6256297804637185e-05,
      "loss": 0.7652,
      "step": 554
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.621172120390544e-05,
      "loss": 0.7683,
      "step": 555
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.616709993867796e-05,
      "loss": 0.7455,
      "step": 556
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.612243418671395e-05,
      "loss": 0.6761,
      "step": 557
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.607772412594978e-05,
      "loss": 0.8251,
      "step": 558
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.6032969934498376e-05,
      "loss": 0.7908,
      "step": 559
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.5988171790648454e-05,
      "loss": 0.7453,
      "step": 560
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.594332987286383e-05,
      "loss": 0.812,
      "step": 561
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.589844435978269e-05,
      "loss": 0.7476,
      "step": 562
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.585351543021691e-05,
      "loss": 0.8996,
      "step": 563
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.58085432631513e-05,
      "loss": 0.6811,
      "step": 564
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.576352803774296e-05,
      "loss": 0.7718,
      "step": 565
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.571846993332048e-05,
      "loss": 0.8054,
      "step": 566
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.567336912938329e-05,
      "loss": 0.7993,
      "step": 567
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.5628225805600914e-05,
      "loss": 0.7635,
      "step": 568
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.558304014181228e-05,
      "loss": 0.8685,
      "step": 569
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.553781231802497e-05,
      "loss": 0.7903,
      "step": 570
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.549254251441451e-05,
      "loss": 0.7809,
      "step": 571
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.5447230911323694e-05,
      "loss": 0.6816,
      "step": 572
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.540187768926182e-05,
      "loss": 0.7613,
      "step": 573
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.5356483028903976e-05,
      "loss": 0.6891,
      "step": 574
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.5311047111090346e-05,
      "loss": 0.8444,
      "step": 575
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.5265570116825455e-05,
      "loss": 0.7576,
      "step": 576
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.5220052227277467e-05,
      "loss": 0.7738,
      "step": 577
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.517449362377748e-05,
      "loss": 0.8101,
      "step": 578
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.512889448781876e-05,
      "loss": 0.7547,
      "step": 579
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.5083255001056074e-05,
      "loss": 0.8112,
      "step": 580
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.503757534530491e-05,
      "loss": 0.7774,
      "step": 581
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.499185570254078e-05,
      "loss": 0.7974,
      "step": 582
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.4946096254898516e-05,
      "loss": 0.7291,
      "step": 583
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.490029718467149e-05,
      "loss": 0.833,
      "step": 584
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.485445867431095e-05,
      "loss": 0.7575,
      "step": 585
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.4808580906425254e-05,
      "loss": 0.8991,
      "step": 586
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.4762664063779135e-05,
      "loss": 0.7575,
      "step": 587
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.4716708329293e-05,
      "loss": 0.7832,
      "step": 588
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.46707138860422e-05,
      "loss": 0.7383,
      "step": 589
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.462468091725628e-05,
      "loss": 0.879,
      "step": 590
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.4578609606318265e-05,
      "loss": 0.8216,
      "step": 591
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.453250013676392e-05,
      "loss": 0.6724,
      "step": 592
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.4486352692281035e-05,
      "loss": 0.8348,
      "step": 593
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.4440167456708665e-05,
      "loss": 0.9279,
      "step": 594
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.439394461403644e-05,
      "loss": 0.7776,
      "step": 595
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.4347684348403766e-05,
      "loss": 0.6902,
      "step": 596
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.430138684409918e-05,
      "loss": 0.7233,
      "step": 597
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.425505228555954e-05,
      "loss": 0.8372,
      "step": 598
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.42086808573693e-05,
      "loss": 0.7619,
      "step": 599
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.416227274425985e-05,
      "loss": 0.7765,
      "step": 600
    },
    {
      "epoch": 1.14,
      "eval_loss": 0.6920838952064514,
      "eval_runtime": 2.7184,
      "eval_samples_per_second": 3.311,
      "eval_steps_per_second": 0.736,
      "step": 600
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.4115828131108665e-05,
      "loss": 0.832,
      "step": 601
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.406934720293865e-05,
      "loss": 0.8499,
      "step": 602
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.402283014491741e-05,
      "loss": 0.7741,
      "step": 603
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.39762771423564e-05,
      "loss": 0.7704,
      "step": 604
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.392968838071036e-05,
      "loss": 0.714,
      "step": 605
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.388306404557642e-05,
      "loss": 0.859,
      "step": 606
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.383640432269346e-05,
      "loss": 0.6714,
      "step": 607
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.378970939794133e-05,
      "loss": 0.7763,
      "step": 608
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.37429794573401e-05,
      "loss": 0.7375,
      "step": 609
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.3696214687049345e-05,
      "loss": 0.7542,
      "step": 610
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.364941527336739e-05,
      "loss": 0.7633,
      "step": 611
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.3602581402730574e-05,
      "loss": 0.8715,
      "step": 612
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.355571326171249e-05,
      "loss": 0.925,
      "step": 613
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.350881103702327e-05,
      "loss": 0.8448,
      "step": 614
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.346187491550883e-05,
      "loss": 0.7896,
      "step": 615
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.34149050841501e-05,
      "loss": 0.8109,
      "step": 616
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.336790173006232e-05,
      "loss": 0.7915,
      "step": 617
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.3320865040494266e-05,
      "loss": 0.7159,
      "step": 618
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.3273795202827514e-05,
      "loss": 0.6816,
      "step": 619
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.32266924045757e-05,
      "loss": 0.7911,
      "step": 620
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.317955683338376e-05,
      "loss": 0.6496,
      "step": 621
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.3132388677027196e-05,
      "loss": 0.6928,
      "step": 622
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.308518812341131e-05,
      "loss": 0.741,
      "step": 623
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.303795536057047e-05,
      "loss": 0.8024,
      "step": 624
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.299069057666736e-05,
      "loss": 0.7628,
      "step": 625
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.294339395999224e-05,
      "loss": 0.7485,
      "step": 626
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.2896065698962145e-05,
      "loss": 0.7243,
      "step": 627
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.2848705982120204e-05,
      "loss": 0.9272,
      "step": 628
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.2801314998134855e-05,
      "loss": 0.6828,
      "step": 629
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.275389293579908e-05,
      "loss": 0.8215,
      "step": 630
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.27064399840297e-05,
      "loss": 0.7792,
      "step": 631
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.265895633186657e-05,
      "loss": 0.8034,
      "step": 632
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.2611442168471817e-05,
      "loss": 0.8222,
      "step": 633
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.256389768312917e-05,
      "loss": 0.7199,
      "step": 634
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.2516323065243135e-05,
      "loss": 0.7743,
      "step": 635
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.246871850433824e-05,
      "loss": 0.7197,
      "step": 636
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.242108419005832e-05,
      "loss": 0.8729,
      "step": 637
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.237342031216574e-05,
      "loss": 0.8425,
      "step": 638
    },
    {
      "epoch": 1.22,
      "learning_rate": 3.23257270605406e-05,
      "loss": 0.7835,
      "step": 639
    },
    {
      "epoch": 1.22,
      "learning_rate": 3.227800462518007e-05,
      "loss": 0.7397,
      "step": 640
    },
    {
      "epoch": 1.22,
      "learning_rate": 3.223025319619755e-05,
      "loss": 0.8645,
      "step": 641
    },
    {
      "epoch": 1.22,
      "learning_rate": 3.2182472963821954e-05,
      "loss": 0.8268,
      "step": 642
    },
    {
      "epoch": 1.22,
      "learning_rate": 3.213466411839693e-05,
      "loss": 0.8185,
      "step": 643
    },
    {
      "epoch": 1.22,
      "learning_rate": 3.208682685038011e-05,
      "loss": 0.8279,
      "step": 644
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.203896135034238e-05,
      "loss": 0.75,
      "step": 645
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.199106780896707e-05,
      "loss": 0.781,
      "step": 646
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.1943146417049236e-05,
      "loss": 0.7298,
      "step": 647
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.189519736549486e-05,
      "loss": 0.802,
      "step": 648
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.184722084532013e-05,
      "loss": 0.712,
      "step": 649
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.1799217047650664e-05,
      "loss": 0.7124,
      "step": 650
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.175118616372074e-05,
      "loss": 0.7176,
      "step": 651
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.1703128384872535e-05,
      "loss": 0.833,
      "step": 652
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.165504390255538e-05,
      "loss": 0.7863,
      "step": 653
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.1606932908324974e-05,
      "loss": 0.8052,
      "step": 654
    },
    {
      "epoch": 1.25,
      "learning_rate": 3.155879559384265e-05,
      "loss": 0.7619,
      "step": 655
    },
    {
      "epoch": 1.25,
      "learning_rate": 3.151063215087456e-05,
      "loss": 0.811,
      "step": 656
    },
    {
      "epoch": 1.25,
      "learning_rate": 3.146244277129099e-05,
      "loss": 0.9439,
      "step": 657
    },
    {
      "epoch": 1.25,
      "learning_rate": 3.141422764706552e-05,
      "loss": 0.7671,
      "step": 658
    },
    {
      "epoch": 1.25,
      "learning_rate": 3.136598697027429e-05,
      "loss": 0.772,
      "step": 659
    },
    {
      "epoch": 1.26,
      "learning_rate": 3.131772093309524e-05,
      "loss": 0.9286,
      "step": 660
    },
    {
      "epoch": 1.26,
      "learning_rate": 3.1269429727807356e-05,
      "loss": 0.8236,
      "step": 661
    },
    {
      "epoch": 1.26,
      "learning_rate": 3.122111354678985e-05,
      "loss": 0.7815,
      "step": 662
    },
    {
      "epoch": 1.26,
      "learning_rate": 3.117277258252147e-05,
      "loss": 0.6822,
      "step": 663
    },
    {
      "epoch": 1.26,
      "learning_rate": 3.112440702757967e-05,
      "loss": 0.7596,
      "step": 664
    },
    {
      "epoch": 1.26,
      "learning_rate": 3.107601707463987e-05,
      "loss": 0.6976,
      "step": 665
    },
    {
      "epoch": 1.27,
      "learning_rate": 3.102760291647469e-05,
      "loss": 0.7869,
      "step": 666
    },
    {
      "epoch": 1.27,
      "learning_rate": 3.097916474595318e-05,
      "loss": 0.6983,
      "step": 667
    },
    {
      "epoch": 1.27,
      "learning_rate": 3.093070275604004e-05,
      "loss": 0.6471,
      "step": 668
    },
    {
      "epoch": 1.27,
      "learning_rate": 3.088221713979485e-05,
      "loss": 0.8774,
      "step": 669
    },
    {
      "epoch": 1.27,
      "learning_rate": 3.083370809037135e-05,
      "loss": 0.8367,
      "step": 670
    },
    {
      "epoch": 1.28,
      "learning_rate": 3.078517580101659e-05,
      "loss": 0.8485,
      "step": 671
    },
    {
      "epoch": 1.28,
      "learning_rate": 3.0736620465070224e-05,
      "loss": 0.6802,
      "step": 672
    },
    {
      "epoch": 1.28,
      "learning_rate": 3.068804227596371e-05,
      "loss": 0.7254,
      "step": 673
    },
    {
      "epoch": 1.28,
      "learning_rate": 3.063944142721954e-05,
      "loss": 0.6942,
      "step": 674
    },
    {
      "epoch": 1.28,
      "learning_rate": 3.0590818112450496e-05,
      "loss": 0.7767,
      "step": 675
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.0542172525358833e-05,
      "loss": 0.6698,
      "step": 676
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.049350485973557e-05,
      "loss": 0.822,
      "step": 677
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.044481530945964e-05,
      "loss": 0.7565,
      "step": 678
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.0396104068497172e-05,
      "loss": 0.7559,
      "step": 679
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.0347371330900727e-05,
      "loss": 0.6684,
      "step": 680
    },
    {
      "epoch": 1.3,
      "learning_rate": 3.0298617290808472e-05,
      "loss": 0.767,
      "step": 681
    },
    {
      "epoch": 1.3,
      "learning_rate": 3.024984214244345e-05,
      "loss": 0.8836,
      "step": 682
    },
    {
      "epoch": 1.3,
      "learning_rate": 3.02010460801128e-05,
      "loss": 0.8231,
      "step": 683
    },
    {
      "epoch": 1.3,
      "learning_rate": 3.0152229298206973e-05,
      "loss": 0.7628,
      "step": 684
    },
    {
      "epoch": 1.3,
      "learning_rate": 3.0103391991198954e-05,
      "loss": 0.7916,
      "step": 685
    },
    {
      "epoch": 1.3,
      "learning_rate": 3.0054534353643494e-05,
      "loss": 0.8659,
      "step": 686
    },
    {
      "epoch": 1.31,
      "learning_rate": 3.0005656580176355e-05,
      "loss": 0.8002,
      "step": 687
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.995675886551349e-05,
      "loss": 0.7897,
      "step": 688
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.9907841404450315e-05,
      "loss": 0.658,
      "step": 689
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.985890439186088e-05,
      "loss": 0.8164,
      "step": 690
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.9809948022697158e-05,
      "loss": 0.6619,
      "step": 691
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.9760972491988213e-05,
      "loss": 0.7705,
      "step": 692
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.9711977994839448e-05,
      "loss": 0.8147,
      "step": 693
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.966296472643182e-05,
      "loss": 0.6752,
      "step": 694
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.961393288202107e-05,
      "loss": 0.7082,
      "step": 695
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.9564882656936947e-05,
      "loss": 0.8384,
      "step": 696
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.9515814246582402e-05,
      "loss": 0.8222,
      "step": 697
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.9466727846432856e-05,
      "loss": 0.7317,
      "step": 698
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.9417623652035386e-05,
      "loss": 0.8472,
      "step": 699
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.9368501859007948e-05,
      "loss": 0.8283,
      "step": 700
    },
    {
      "epoch": 1.33,
      "eval_loss": 0.688589870929718,
      "eval_runtime": 2.8028,
      "eval_samples_per_second": 3.211,
      "eval_steps_per_second": 0.714,
      "step": 700
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.931936266303863e-05,
      "loss": 0.7819,
      "step": 701
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.9270206259884815e-05,
      "loss": 0.6657,
      "step": 702
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.922103284537247e-05,
      "loss": 0.7602,
      "step": 703
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.91718426153953e-05,
      "loss": 0.6639,
      "step": 704
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.912263576591402e-05,
      "loss": 0.7266,
      "step": 705
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.907341249295554e-05,
      "loss": 0.6518,
      "step": 706
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.9024172992612214e-05,
      "loss": 0.8892,
      "step": 707
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.897491746104101e-05,
      "loss": 0.8929,
      "step": 708
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.8925646094462794e-05,
      "loss": 0.9271,
      "step": 709
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.8876359089161498e-05,
      "loss": 0.7644,
      "step": 710
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.8827056641483347e-05,
      "loss": 0.87,
      "step": 711
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.8777738947836103e-05,
      "loss": 0.7929,
      "step": 712
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.8728406204688253e-05,
      "loss": 0.7706,
      "step": 713
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.8679058608568232e-05,
      "loss": 0.6968,
      "step": 714
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.8629696356063663e-05,
      "loss": 0.6761,
      "step": 715
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.858031964382053e-05,
      "loss": 0.7972,
      "step": 716
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.853092866854245e-05,
      "loss": 0.7544,
      "step": 717
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.8481523626989842e-05,
      "loss": 0.7911,
      "step": 718
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.8432104715979152e-05,
      "loss": 0.821,
      "step": 719
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.838267213238211e-05,
      "loss": 0.7393,
      "step": 720
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.8333226073124893e-05,
      "loss": 0.7582,
      "step": 721
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.828376673518735e-05,
      "loss": 0.7258,
      "step": 722
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.8234294315602245e-05,
      "loss": 0.8525,
      "step": 723
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.818480901145447e-05,
      "loss": 0.8147,
      "step": 724
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.813531101988021e-05,
      "loss": 0.7536,
      "step": 725
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.808580053806622e-05,
      "loss": 0.8148,
      "step": 726
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.8036277763249007e-05,
      "loss": 0.7732,
      "step": 727
    },
    {
      "epoch": 1.38,
      "learning_rate": 2.798674289271404e-05,
      "loss": 0.7813,
      "step": 728
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.793719612379499e-05,
      "loss": 0.7391,
      "step": 729
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.7887637653872916e-05,
      "loss": 0.9156,
      "step": 730
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.7838067680375495e-05,
      "loss": 0.7615,
      "step": 731
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.7788486400776233e-05,
      "loss": 0.8723,
      "step": 732
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.7738894012593662e-05,
      "loss": 0.7906,
      "step": 733
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.7689290713390598e-05,
      "loss": 0.817,
      "step": 734
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.76396767007733e-05,
      "loss": 0.8896,
      "step": 735
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.7590052172390708e-05,
      "loss": 0.7621,
      "step": 736
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.7540417325933655e-05,
      "loss": 0.8028,
      "step": 737
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.7490772359134093e-05,
      "loss": 0.7157,
      "step": 738
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.744111746976426e-05,
      "loss": 0.8162,
      "step": 739
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.7391452855635958e-05,
      "loss": 0.7835,
      "step": 740
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.7341778714599708e-05,
      "loss": 0.7614,
      "step": 741
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.729209524454399e-05,
      "loss": 0.8477,
      "step": 742
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.724240264339445e-05,
      "loss": 0.7091,
      "step": 743
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.7192701109113105e-05,
      "loss": 0.7915,
      "step": 744
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.7142990839697564e-05,
      "loss": 0.7741,
      "step": 745
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.7093272033180222e-05,
      "loss": 0.6316,
      "step": 746
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.704354488762751e-05,
      "loss": 0.7003,
      "step": 747
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.6993809601139053e-05,
      "loss": 0.7132,
      "step": 748
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.6944066371846917e-05,
      "loss": 0.7494,
      "step": 749
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.689431539791482e-05,
      "loss": 0.7249,
      "step": 750
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.6844556877537304e-05,
      "loss": 0.708,
      "step": 751
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.679479100893901e-05,
      "loss": 0.8788,
      "step": 752
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.6745017990373835e-05,
      "loss": 0.7451,
      "step": 753
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.6695238020124146e-05,
      "loss": 0.7337,
      "step": 754
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.664545129650004e-05,
      "loss": 0.8061,
      "step": 755
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.6595658017838472e-05,
      "loss": 0.7314,
      "step": 756
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.6545858382502547e-05,
      "loss": 0.7077,
      "step": 757
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.6496052588880677e-05,
      "loss": 0.8084,
      "step": 758
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.644624083538581e-05,
      "loss": 0.8214,
      "step": 759
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.6396423320454627e-05,
      "loss": 0.7688,
      "step": 760
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.6346600242546793e-05,
      "loss": 0.8176,
      "step": 761
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.6296771800144093e-05,
      "loss": 0.8393,
      "step": 762
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.6246938191749704e-05,
      "loss": 0.9029,
      "step": 763
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.6197099615887394e-05,
      "loss": 0.719,
      "step": 764
    },
    {
      "epoch": 1.46,
      "learning_rate": 2.614725627110069e-05,
      "loss": 0.8233,
      "step": 765
    },
    {
      "epoch": 1.46,
      "learning_rate": 2.6097408355952142e-05,
      "loss": 0.7085,
      "step": 766
    },
    {
      "epoch": 1.46,
      "learning_rate": 2.6047556069022493e-05,
      "loss": 0.711,
      "step": 767
    },
    {
      "epoch": 1.46,
      "learning_rate": 2.5997699608909913e-05,
      "loss": 0.7867,
      "step": 768
    },
    {
      "epoch": 1.46,
      "learning_rate": 2.5947839174229198e-05,
      "loss": 0.8321,
      "step": 769
    },
    {
      "epoch": 1.46,
      "learning_rate": 2.589797496361096e-05,
      "loss": 0.7958,
      "step": 770
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.584810717570087e-05,
      "loss": 0.6435,
      "step": 771
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.5798236009158837e-05,
      "loss": 0.8112,
      "step": 772
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.574836166265826e-05,
      "loss": 0.7119,
      "step": 773
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.5698484334885153e-05,
      "loss": 0.7362,
      "step": 774
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.5648604224537458e-05,
      "loss": 0.8092,
      "step": 775
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.559872153032417e-05,
      "loss": 0.6548,
      "step": 776
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.554883645096459e-05,
      "loss": 0.7224,
      "step": 777
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.5498949185187533e-05,
      "loss": 0.6886,
      "step": 778
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.5449059931730483e-05,
      "loss": 0.7935,
      "step": 779
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.5399168889338897e-05,
      "loss": 0.8734,
      "step": 780
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.534927625676532e-05,
      "loss": 0.6876,
      "step": 781
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.5299382232768633e-05,
      "loss": 0.7049,
      "step": 782
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.5249487016113288e-05,
      "loss": 0.7669,
      "step": 783
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.5199590805568463e-05,
      "loss": 0.6549,
      "step": 784
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.51496937999073e-05,
      "loss": 0.8337,
      "step": 785
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.5099796197906106e-05,
      "loss": 0.7316,
      "step": 786
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.5049898198343586e-05,
      "loss": 0.7525,
      "step": 787
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.5e-05,
      "loss": 0.8389,
      "step": 788
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.4950101801656416e-05,
      "loss": 0.7193,
      "step": 789
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.490020380209389e-05,
      "loss": 0.7287,
      "step": 790
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.4850306200092714e-05,
      "loss": 0.6943,
      "step": 791
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.480040919443155e-05,
      "loss": 0.767,
      "step": 792
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.4750512983886718e-05,
      "loss": 0.8149,
      "step": 793
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.470061776723137e-05,
      "loss": 0.7885,
      "step": 794
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.4650723743234684e-05,
      "loss": 0.6995,
      "step": 795
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.460083111066111e-05,
      "loss": 0.8069,
      "step": 796
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.4550940068269522e-05,
      "loss": 0.7725,
      "step": 797
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.450105081481248e-05,
      "loss": 0.8232,
      "step": 798
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.4451163549035412e-05,
      "loss": 0.7017,
      "step": 799
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.4401278469675835e-05,
      "loss": 0.8166,
      "step": 800
    },
    {
      "epoch": 1.52,
      "eval_loss": 0.6844746470451355,
      "eval_runtime": 2.748,
      "eval_samples_per_second": 3.275,
      "eval_steps_per_second": 0.728,
      "step": 800
    }
  ],
  "logging_steps": 1,
  "max_steps": 1575,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 1.12483141551548e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}