{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 18.2105595953209,
  "eval_steps": 500,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.00019987244897959184,
      "loss": 3.2215,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019974489795918367,
      "loss": 2.8365,
      "step": 2
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019961734693877553,
      "loss": 2.602,
      "step": 3
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019948979591836736,
      "loss": 2.4196,
      "step": 4
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001993622448979592,
      "loss": 2.2574,
      "step": 5
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019923469387755102,
      "loss": 2.2239,
      "step": 6
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019910714285714288,
      "loss": 2.1661,
      "step": 7
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001989795918367347,
      "loss": 2.0987,
      "step": 8
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019885204081632654,
      "loss": 2.015,
      "step": 9
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019872448979591837,
      "loss": 1.9771,
      "step": 10
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019859693877551023,
      "loss": 2.0271,
      "step": 11
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019846938775510203,
      "loss": 1.9812,
      "step": 12
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001983418367346939,
      "loss": 2.0834,
      "step": 13
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019821428571428572,
      "loss": 1.9174,
      "step": 14
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019808673469387755,
      "loss": 1.8409,
      "step": 15
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019795918367346938,
      "loss": 1.929,
      "step": 16
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019783163265306124,
      "loss": 2.0041,
      "step": 17
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019770408163265305,
      "loss": 1.9385,
      "step": 18
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001975765306122449,
      "loss": 1.9592,
      "step": 19
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019744897959183674,
      "loss": 1.9701,
      "step": 20
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001973214285714286,
      "loss": 1.9277,
      "step": 21
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019719387755102042,
      "loss": 1.8394,
      "step": 22
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019706632653061226,
      "loss": 1.8666,
      "step": 23
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019693877551020409,
      "loss": 1.8997,
      "step": 24
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019681122448979592,
      "loss": 1.9432,
      "step": 25
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019668367346938777,
      "loss": 1.9137,
      "step": 26
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001965561224489796,
      "loss": 1.905,
      "step": 27
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019642857142857144,
      "loss": 1.8708,
      "step": 28
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019630102040816327,
      "loss": 1.9097,
      "step": 29
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019617346938775513,
      "loss": 1.896,
      "step": 30
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019604591836734696,
      "loss": 1.8834,
      "step": 31
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001959183673469388,
      "loss": 1.8323,
      "step": 32
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019579081632653062,
      "loss": 1.804,
      "step": 33
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019566326530612248,
      "loss": 1.8906,
      "step": 34
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019553571428571428,
      "loss": 1.8693,
      "step": 35
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019540816326530614,
      "loss": 1.9308,
      "step": 36
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019528061224489797,
      "loss": 1.8082,
      "step": 37
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001951530612244898,
      "loss": 1.848,
      "step": 38
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019502551020408163,
      "loss": 1.8866,
      "step": 39
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001948979591836735,
      "loss": 1.7844,
      "step": 40
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001947704081632653,
      "loss": 1.8485,
      "step": 41
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00019464285714285715,
      "loss": 1.7917,
      "step": 42
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00019451530612244898,
      "loss": 1.7342,
      "step": 43
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019438775510204084,
      "loss": 1.8479,
      "step": 44
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019426020408163267,
      "loss": 1.8639,
      "step": 45
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001941326530612245,
      "loss": 1.8166,
      "step": 46
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00019400510204081633,
      "loss": 1.7566,
      "step": 47
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00019387755102040816,
      "loss": 1.8071,
      "step": 48
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00019375000000000002,
      "loss": 1.8612,
      "step": 49
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00019362244897959185,
      "loss": 1.7819,
      "step": 50
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00019349489795918368,
      "loss": 1.8647,
      "step": 51
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001933673469387755,
      "loss": 1.8196,
      "step": 52
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00019323979591836737,
      "loss": 1.8027,
      "step": 53
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00019311224489795917,
      "loss": 1.8927,
      "step": 54
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00019298469387755103,
      "loss": 1.8481,
      "step": 55
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00019285714285714286,
      "loss": 1.7781,
      "step": 56
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00019272959183673472,
      "loss": 1.8101,
      "step": 57
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00019260204081632653,
      "loss": 1.7257,
      "step": 58
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00019247448979591838,
      "loss": 1.8185,
      "step": 59
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00019234693877551021,
      "loss": 1.8557,
      "step": 60
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00019221938775510204,
      "loss": 1.7418,
      "step": 61
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00019209183673469388,
      "loss": 1.6879,
      "step": 62
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00019196428571428573,
      "loss": 1.7651,
      "step": 63
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00019183673469387756,
      "loss": 1.7759,
      "step": 64
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001917091836734694,
      "loss": 1.7691,
      "step": 65
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00019158163265306123,
      "loss": 1.7794,
      "step": 66
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00019145408163265306,
      "loss": 1.8152,
      "step": 67
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00019132653061224492,
      "loss": 1.8052,
      "step": 68
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00019119897959183675,
      "loss": 1.8054,
      "step": 69
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00019107142857142858,
      "loss": 1.8114,
      "step": 70
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001909438775510204,
      "loss": 1.7749,
      "step": 71
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00019081632653061227,
      "loss": 1.777,
      "step": 72
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001906887755102041,
      "loss": 1.7896,
      "step": 73
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00019056122448979593,
      "loss": 1.8335,
      "step": 74
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00019043367346938776,
      "loss": 1.8155,
      "step": 75
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00019030612244897962,
      "loss": 1.8224,
      "step": 76
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00019017857142857142,
      "loss": 1.7889,
      "step": 77
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00019005102040816328,
      "loss": 1.8866,
      "step": 78
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001899234693877551,
      "loss": 1.8439,
      "step": 79
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00018979591836734697,
      "loss": 1.7906,
      "step": 80
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00018966836734693877,
      "loss": 1.8627,
      "step": 81
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00018954081632653063,
      "loss": 1.7497,
      "step": 82
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00018941326530612246,
      "loss": 1.7936,
      "step": 83
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0001892857142857143,
      "loss": 1.8341,
      "step": 84
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00018915816326530612,
      "loss": 1.7868,
      "step": 85
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00018903061224489798,
      "loss": 1.7493,
      "step": 86
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001889030612244898,
      "loss": 1.7926,
      "step": 87
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00018877551020408164,
      "loss": 1.8278,
      "step": 88
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00018864795918367347,
      "loss": 1.7387,
      "step": 89
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001885204081632653,
      "loss": 1.7669,
      "step": 90
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00018839285714285716,
      "loss": 1.7686,
      "step": 91
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.000188265306122449,
      "loss": 1.7759,
      "step": 92
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00018813775510204082,
      "loss": 1.7016,
      "step": 93
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00018801020408163265,
      "loss": 1.8123,
      "step": 94
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001878826530612245,
      "loss": 1.8315,
      "step": 95
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00018775510204081634,
      "loss": 1.7679,
      "step": 96
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00018762755102040817,
      "loss": 1.7874,
      "step": 97
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0001875,
      "loss": 1.8008,
      "step": 98
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00018737244897959186,
      "loss": 1.7177,
      "step": 99
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00018724489795918367,
      "loss": 1.7272,
      "step": 100
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00018711734693877552,
      "loss": 1.7848,
      "step": 101
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00018698979591836735,
      "loss": 1.744,
      "step": 102
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00018686224489795919,
      "loss": 1.7005,
      "step": 103
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00018673469387755102,
      "loss": 1.8247,
      "step": 104
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00018660714285714287,
      "loss": 1.6855,
      "step": 105
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0001864795918367347,
      "loss": 1.7627,
      "step": 106
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00018635204081632654,
      "loss": 1.7564,
      "step": 107
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00018622448979591837,
      "loss": 1.8237,
      "step": 108
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00018609693877551022,
      "loss": 1.7421,
      "step": 109
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00018596938775510206,
      "loss": 1.7517,
      "step": 110
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0001858418367346939,
      "loss": 1.7515,
      "step": 111
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00018571428571428572,
      "loss": 1.7842,
      "step": 112
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00018558673469387755,
      "loss": 1.8001,
      "step": 113
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0001854591836734694,
      "loss": 1.7653,
      "step": 114
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00018533163265306124,
      "loss": 1.694,
      "step": 115
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00018520408163265307,
      "loss": 1.7457,
      "step": 116
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0001850765306122449,
      "loss": 1.7899,
      "step": 117
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00018494897959183676,
      "loss": 1.7473,
      "step": 118
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001848214285714286,
      "loss": 1.6639,
      "step": 119
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00018469387755102042,
      "loss": 1.762,
      "step": 120
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00018456632653061225,
      "loss": 1.7378,
      "step": 121
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0001844387755102041,
      "loss": 1.672,
      "step": 122
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0001843112244897959,
      "loss": 1.7267,
      "step": 123
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00018418367346938777,
      "loss": 1.7825,
      "step": 124
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0001840561224489796,
      "loss": 1.7566,
      "step": 125
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.00018392857142857143,
      "loss": 1.8169,
      "step": 126
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.00018380102040816326,
      "loss": 1.6801,
      "step": 127
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00018367346938775512,
      "loss": 1.7292,
      "step": 128
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00018354591836734695,
      "loss": 1.737,
      "step": 129
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.00018341836734693878,
      "loss": 1.7696,
      "step": 130
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0001832908163265306,
      "loss": 1.7239,
      "step": 131
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00018316326530612247,
      "loss": 1.7441,
      "step": 132
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0001830357142857143,
      "loss": 1.7825,
      "step": 133
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.00018290816326530613,
      "loss": 1.7411,
      "step": 134
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.00018278061224489796,
      "loss": 1.7119,
      "step": 135
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0001826530612244898,
      "loss": 1.7443,
      "step": 136
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.00018252551020408165,
      "loss": 1.7197,
      "step": 137
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.00018239795918367348,
      "loss": 1.7273,
      "step": 138
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.0001822704081632653,
      "loss": 1.7681,
      "step": 139
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.00018214285714285714,
      "loss": 1.8088,
      "step": 140
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.000182015306122449,
      "loss": 1.7301,
      "step": 141
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.00018188775510204083,
      "loss": 1.6853,
      "step": 142
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.00018176020408163266,
      "loss": 1.6966,
      "step": 143
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0001816326530612245,
      "loss": 1.7938,
      "step": 144
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00018150510204081635,
      "loss": 1.7639,
      "step": 145
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.00018137755102040816,
      "loss": 1.7527,
      "step": 146
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.00018125000000000001,
      "loss": 1.7386,
      "step": 147
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00018112244897959185,
      "loss": 1.7223,
      "step": 148
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.00018099489795918368,
      "loss": 1.7571,
      "step": 149
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0001808673469387755,
      "loss": 1.7054,
      "step": 150
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.00018073979591836737,
      "loss": 1.6581,
      "step": 151
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.00018061224489795917,
      "loss": 1.681,
      "step": 152
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.00018048469387755103,
      "loss": 1.7425,
      "step": 153
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.00018035714285714286,
      "loss": 1.7108,
      "step": 154
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.00018022959183673472,
      "loss": 1.7194,
      "step": 155
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.00018010204081632655,
      "loss": 1.6953,
      "step": 156
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.00017997448979591838,
      "loss": 1.669,
      "step": 157
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0001798469387755102,
      "loss": 1.744,
      "step": 158
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.00017971938775510204,
      "loss": 1.6467,
      "step": 159
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.0001795918367346939,
      "loss": 1.7103,
      "step": 160
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.00017946428571428573,
      "loss": 1.6662,
      "step": 161
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.00017933673469387756,
      "loss": 1.6657,
      "step": 162
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.0001792091836734694,
      "loss": 1.791,
      "step": 163
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.00017908163265306125,
      "loss": 1.7704,
      "step": 164
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.00017895408163265305,
      "loss": 1.7229,
      "step": 165
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0001788265306122449,
      "loss": 1.76,
      "step": 166
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.00017869897959183674,
      "loss": 1.6482,
      "step": 167
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0001785714285714286,
      "loss": 1.8076,
      "step": 168
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.0001784438775510204,
      "loss": 1.7368,
      "step": 169
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.00017831632653061226,
      "loss": 1.6264,
      "step": 170
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0001781887755102041,
      "loss": 1.6289,
      "step": 171
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.00017806122448979592,
      "loss": 1.7913,
      "step": 172
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.00017793367346938775,
      "loss": 1.6985,
      "step": 173
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.0001778061224489796,
      "loss": 1.6936,
      "step": 174
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.00017767857142857141,
      "loss": 1.8068,
      "step": 175
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.00017755102040816327,
      "loss": 1.7243,
      "step": 176
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.0001774234693877551,
      "loss": 1.6893,
      "step": 177
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.00017729591836734696,
      "loss": 1.8122,
      "step": 178
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.0001771683673469388,
      "loss": 1.6562,
      "step": 179
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.00017704081632653062,
      "loss": 1.6999,
      "step": 180
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.00017691326530612245,
      "loss": 1.7229,
      "step": 181
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.00017678571428571428,
      "loss": 1.6764,
      "step": 182
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.00017665816326530614,
      "loss": 1.6982,
      "step": 183
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.00017653061224489797,
      "loss": 1.696,
      "step": 184
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.0001764030612244898,
      "loss": 1.6797,
      "step": 185
    },
    {
      "epoch": 3.76,
      "learning_rate": 0.00017627551020408164,
      "loss": 1.637,
      "step": 186
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.0001761479591836735,
      "loss": 1.7074,
      "step": 187
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.0001760204081632653,
      "loss": 1.705,
      "step": 188
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.00017589285714285716,
      "loss": 1.6153,
      "step": 189
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.00017576530612244899,
      "loss": 1.7354,
      "step": 190
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.00017563775510204084,
      "loss": 1.6941,
      "step": 191
    },
    {
      "epoch": 3.88,
      "learning_rate": 0.00017551020408163265,
      "loss": 1.7231,
      "step": 192
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.0001753826530612245,
      "loss": 1.7663,
      "step": 193
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.00017525510204081634,
      "loss": 1.6532,
      "step": 194
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.00017512755102040817,
      "loss": 1.7115,
      "step": 195
    },
    {
      "epoch": 3.97,
      "learning_rate": 0.000175,
      "loss": 1.6955,
      "step": 196
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.00017487244897959186,
      "loss": 1.6863,
      "step": 197
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.00017474489795918366,
      "loss": 1.7012,
      "step": 198
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.00017461734693877552,
      "loss": 1.5927,
      "step": 199
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.00017448979591836735,
      "loss": 1.6272,
      "step": 200
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.00017436224489795918,
      "loss": 1.5994,
      "step": 201
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.00017423469387755104,
      "loss": 1.7141,
      "step": 202
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.00017410714285714287,
      "loss": 1.7547,
      "step": 203
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.0001739795918367347,
      "loss": 1.6254,
      "step": 204
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.00017385204081632653,
      "loss": 1.6686,
      "step": 205
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.0001737244897959184,
      "loss": 1.6684,
      "step": 206
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.00017359693877551022,
      "loss": 1.6724,
      "step": 207
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.00017346938775510205,
      "loss": 1.7361,
      "step": 208
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.00017334183673469388,
      "loss": 1.7167,
      "step": 209
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.00017321428571428574,
      "loss": 1.7226,
      "step": 210
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.00017308673469387754,
      "loss": 1.7133,
      "step": 211
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0001729591836734694,
      "loss": 1.649,
      "step": 212
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.00017283163265306123,
      "loss": 1.7104,
      "step": 213
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.00017270408163265306,
      "loss": 1.6861,
      "step": 214
    },
    {
      "epoch": 4.35,
      "learning_rate": 0.0001725765306122449,
      "loss": 1.648,
      "step": 215
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.00017244897959183675,
      "loss": 1.6215,
      "step": 216
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.00017232142857142858,
      "loss": 1.6334,
      "step": 217
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.0001721938775510204,
      "loss": 1.6283,
      "step": 218
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.00017206632653061224,
      "loss": 1.6462,
      "step": 219
    },
    {
      "epoch": 4.45,
      "learning_rate": 0.0001719387755102041,
      "loss": 1.7233,
      "step": 220
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.0001718112244897959,
      "loss": 1.7839,
      "step": 221
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.00017168367346938776,
      "loss": 1.7204,
      "step": 222
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.0001715561224489796,
      "loss": 1.7671,
      "step": 223
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.6824,
      "step": 224
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.00017130102040816328,
      "loss": 1.7068,
      "step": 225
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.00017117346938775511,
      "loss": 1.6515,
      "step": 226
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.00017104591836734694,
      "loss": 1.6586,
      "step": 227
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.00017091836734693878,
      "loss": 1.6355,
      "step": 228
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.00017079081632653063,
      "loss": 1.7173,
      "step": 229
    },
    {
      "epoch": 4.65,
      "learning_rate": 0.00017066326530612246,
      "loss": 1.6585,
      "step": 230
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.0001705357142857143,
      "loss": 1.5856,
      "step": 231
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.00017040816326530613,
      "loss": 1.5923,
      "step": 232
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.00017028061224489798,
      "loss": 1.7128,
      "step": 233
    },
    {
      "epoch": 4.73,
      "learning_rate": 0.0001701530612244898,
      "loss": 1.6971,
      "step": 234
    },
    {
      "epoch": 4.75,
      "learning_rate": 0.00017002551020408165,
      "loss": 1.6416,
      "step": 235
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.00016989795918367348,
      "loss": 1.645,
      "step": 236
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.0001697704081632653,
      "loss": 1.6792,
      "step": 237
    },
    {
      "epoch": 4.82,
      "learning_rate": 0.00016964285714285714,
      "loss": 1.6522,
      "step": 238
    },
    {
      "epoch": 4.84,
      "learning_rate": 0.000169515306122449,
      "loss": 1.6315,
      "step": 239
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.00016938775510204083,
      "loss": 1.6622,
      "step": 240
    },
    {
      "epoch": 4.88,
      "learning_rate": 0.00016926020408163266,
      "loss": 1.6566,
      "step": 241
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.0001691326530612245,
      "loss": 1.7141,
      "step": 242
    },
    {
      "epoch": 4.92,
      "learning_rate": 0.00016900510204081635,
      "loss": 1.5873,
      "step": 243
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.00016887755102040818,
      "loss": 1.6571,
      "step": 244
    },
    {
      "epoch": 4.96,
      "learning_rate": 0.00016875,
      "loss": 1.6829,
      "step": 245
    },
    {
      "epoch": 4.98,
      "learning_rate": 0.00016862244897959184,
      "loss": 1.6935,
      "step": 246
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00016849489795918367,
      "loss": 1.6782,
      "step": 247
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.00016836734693877553,
      "loss": 1.622,
      "step": 248
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.00016823979591836736,
      "loss": 1.6596,
      "step": 249
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.0001681122448979592,
      "loss": 1.5821,
      "step": 250
    },
    {
      "epoch": 5.08,
      "learning_rate": 0.00016798469387755102,
      "loss": 1.7292,
      "step": 251
    },
    {
      "epoch": 5.1,
      "learning_rate": 0.00016785714285714288,
      "loss": 1.646,
      "step": 252
    },
    {
      "epoch": 5.12,
      "learning_rate": 0.0001677295918367347,
      "loss": 1.6969,
      "step": 253
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.00016760204081632654,
      "loss": 1.6082,
      "step": 254
    },
    {
      "epoch": 5.16,
      "learning_rate": 0.00016747448979591837,
      "loss": 1.5843,
      "step": 255
    },
    {
      "epoch": 5.18,
      "learning_rate": 0.00016734693877551023,
      "loss": 1.6827,
      "step": 256
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.00016721938775510203,
      "loss": 1.5824,
      "step": 257
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.0001670918367346939,
      "loss": 1.6795,
      "step": 258
    },
    {
      "epoch": 5.24,
      "learning_rate": 0.00016696428571428572,
      "loss": 1.5639,
      "step": 259
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.00016683673469387755,
      "loss": 1.592,
      "step": 260
    },
    {
      "epoch": 5.28,
      "learning_rate": 0.00016670918367346938,
      "loss": 1.65,
      "step": 261
    },
    {
      "epoch": 5.3,
      "learning_rate": 0.00016658163265306124,
      "loss": 1.5592,
      "step": 262
    },
    {
      "epoch": 5.32,
      "learning_rate": 0.00016645408163265305,
      "loss": 1.5091,
      "step": 263
    },
    {
      "epoch": 5.34,
      "learning_rate": 0.0001663265306122449,
      "loss": 1.6138,
      "step": 264
    },
    {
      "epoch": 5.36,
      "learning_rate": 0.00016619897959183673,
      "loss": 1.625,
      "step": 265
    },
    {
      "epoch": 5.38,
      "learning_rate": 0.0001660714285714286,
      "loss": 1.5757,
      "step": 266
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.00016594387755102042,
      "loss": 1.6372,
      "step": 267
    },
    {
      "epoch": 5.42,
      "learning_rate": 0.00016581632653061225,
      "loss": 1.5891,
      "step": 268
    },
    {
      "epoch": 5.44,
      "learning_rate": 0.00016568877551020409,
      "loss": 1.6893,
      "step": 269
    },
    {
      "epoch": 5.46,
      "learning_rate": 0.00016556122448979592,
      "loss": 1.6662,
      "step": 270
    },
    {
      "epoch": 5.48,
      "learning_rate": 0.00016543367346938777,
      "loss": 1.7132,
      "step": 271
    },
    {
      "epoch": 5.5,
      "learning_rate": 0.0001653061224489796,
      "loss": 1.5835,
      "step": 272
    },
    {
      "epoch": 5.52,
      "learning_rate": 0.00016517857142857144,
      "loss": 1.6342,
      "step": 273
    },
    {
      "epoch": 5.54,
      "learning_rate": 0.00016505102040816327,
      "loss": 1.6717,
      "step": 274
    },
    {
      "epoch": 5.56,
      "learning_rate": 0.00016492346938775512,
      "loss": 1.6248,
      "step": 275
    },
    {
      "epoch": 5.58,
      "learning_rate": 0.00016479591836734696,
      "loss": 1.6117,
      "step": 276
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.0001646683673469388,
      "loss": 1.6798,
      "step": 277
    },
    {
      "epoch": 5.63,
      "learning_rate": 0.00016454081632653062,
      "loss": 1.6406,
      "step": 278
    },
    {
      "epoch": 5.65,
      "learning_rate": 0.00016441326530612248,
      "loss": 1.6512,
      "step": 279
    },
    {
      "epoch": 5.67,
      "learning_rate": 0.00016428571428571428,
      "loss": 1.6102,
      "step": 280
    },
    {
      "epoch": 5.69,
      "learning_rate": 0.00016415816326530614,
      "loss": 1.6113,
      "step": 281
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.00016403061224489797,
      "loss": 1.7116,
      "step": 282
    },
    {
      "epoch": 5.73,
      "learning_rate": 0.0001639030612244898,
      "loss": 1.6846,
      "step": 283
    },
    {
      "epoch": 5.75,
      "learning_rate": 0.00016377551020408163,
      "loss": 1.6911,
      "step": 284
    },
    {
      "epoch": 5.77,
      "learning_rate": 0.0001636479591836735,
      "loss": 1.6202,
      "step": 285
    },
    {
      "epoch": 5.79,
      "learning_rate": 0.0001635204081632653,
      "loss": 1.5715,
      "step": 286
    },
    {
      "epoch": 5.81,
      "learning_rate": 0.00016339285714285715,
      "loss": 1.6461,
      "step": 287
    },
    {
      "epoch": 5.83,
      "learning_rate": 0.00016326530612244898,
      "loss": 1.6624,
      "step": 288
    },
    {
      "epoch": 5.85,
      "learning_rate": 0.00016313775510204084,
      "loss": 1.6535,
      "step": 289
    },
    {
      "epoch": 5.87,
      "learning_rate": 0.00016301020408163267,
      "loss": 1.6275,
      "step": 290
    },
    {
      "epoch": 5.89,
      "learning_rate": 0.0001628826530612245,
      "loss": 1.6636,
      "step": 291
    },
    {
      "epoch": 5.91,
      "learning_rate": 0.00016275510204081633,
      "loss": 1.6546,
      "step": 292
    },
    {
      "epoch": 5.93,
      "learning_rate": 0.00016262755102040816,
      "loss": 1.7274,
      "step": 293
    },
    {
      "epoch": 5.95,
      "learning_rate": 0.00016250000000000002,
      "loss": 1.5901,
      "step": 294
    },
    {
      "epoch": 5.97,
      "learning_rate": 0.00016237244897959185,
      "loss": 1.6046,
      "step": 295
    },
    {
      "epoch": 5.99,
      "learning_rate": 0.00016224489795918368,
      "loss": 1.5828,
      "step": 296
    },
    {
      "epoch": 6.01,
      "learning_rate": 0.0001621173469387755,
      "loss": 1.6435,
      "step": 297
    },
    {
      "epoch": 6.03,
      "learning_rate": 0.00016198979591836737,
      "loss": 1.6263,
      "step": 298
    },
    {
      "epoch": 6.05,
      "learning_rate": 0.00016186224489795917,
      "loss": 1.4944,
      "step": 299
    },
    {
      "epoch": 6.07,
      "learning_rate": 0.00016173469387755103,
      "loss": 1.6286,
      "step": 300
    },
    {
      "epoch": 6.09,
      "learning_rate": 0.00016160714285714286,
      "loss": 1.694,
      "step": 301
    },
    {
      "epoch": 6.11,
      "learning_rate": 0.00016147959183673472,
      "loss": 1.6197,
      "step": 302
    },
    {
      "epoch": 6.13,
      "learning_rate": 0.00016135204081632652,
      "loss": 1.5597,
      "step": 303
    },
    {
      "epoch": 6.15,
      "learning_rate": 0.00016122448979591838,
      "loss": 1.5487,
      "step": 304
    },
    {
      "epoch": 6.17,
      "learning_rate": 0.0001610969387755102,
      "loss": 1.5769,
      "step": 305
    },
    {
      "epoch": 6.19,
      "learning_rate": 0.00016096938775510204,
      "loss": 1.6367,
      "step": 306
    },
    {
      "epoch": 6.21,
      "learning_rate": 0.00016084183673469388,
      "loss": 1.583,
      "step": 307
    },
    {
      "epoch": 6.23,
      "learning_rate": 0.00016071428571428573,
      "loss": 1.6201,
      "step": 308
    },
    {
      "epoch": 6.25,
      "learning_rate": 0.00016058673469387754,
      "loss": 1.6586,
      "step": 309
    },
    {
      "epoch": 6.27,
      "learning_rate": 0.0001604591836734694,
      "loss": 1.6711,
      "step": 310
    },
    {
      "epoch": 6.29,
      "learning_rate": 0.00016033163265306123,
      "loss": 1.6402,
      "step": 311
    },
    {
      "epoch": 6.31,
      "learning_rate": 0.00016020408163265306,
      "loss": 1.5247,
      "step": 312
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.00016007653061224491,
      "loss": 1.5356,
      "step": 313
    },
    {
      "epoch": 6.35,
      "learning_rate": 0.00015994897959183675,
      "loss": 1.564,
      "step": 314
    },
    {
      "epoch": 6.37,
      "learning_rate": 0.00015982142857142858,
      "loss": 1.563,
      "step": 315
    },
    {
      "epoch": 6.39,
      "learning_rate": 0.0001596938775510204,
      "loss": 1.5198,
      "step": 316
    },
    {
      "epoch": 6.41,
      "learning_rate": 0.00015956632653061227,
      "loss": 1.6558,
      "step": 317
    },
    {
      "epoch": 6.43,
      "learning_rate": 0.0001594387755102041,
      "loss": 1.5534,
      "step": 318
    },
    {
      "epoch": 6.45,
      "learning_rate": 0.00015931122448979593,
      "loss": 1.6239,
      "step": 319
    },
    {
      "epoch": 6.47,
      "learning_rate": 0.00015918367346938776,
      "loss": 1.5645,
      "step": 320
    },
    {
      "epoch": 6.5,
      "learning_rate": 0.00015905612244897962,
      "loss": 1.5713,
      "step": 321
    },
    {
      "epoch": 6.52,
      "learning_rate": 0.00015892857142857142,
      "loss": 1.6176,
      "step": 322
    },
    {
      "epoch": 6.54,
      "learning_rate": 0.00015880102040816328,
      "loss": 1.502,
      "step": 323
    },
    {
      "epoch": 6.56,
      "learning_rate": 0.0001586734693877551,
      "loss": 1.645,
      "step": 324
    },
    {
      "epoch": 6.58,
      "learning_rate": 0.00015854591836734697,
      "loss": 1.5904,
      "step": 325
    },
    {
      "epoch": 6.6,
      "learning_rate": 0.00015841836734693877,
      "loss": 1.6149,
      "step": 326
    },
    {
      "epoch": 6.62,
      "learning_rate": 0.00015829081632653063,
      "loss": 1.6757,
      "step": 327
    },
    {
      "epoch": 6.64,
      "learning_rate": 0.00015816326530612246,
      "loss": 1.541,
      "step": 328
    },
    {
      "epoch": 6.66,
      "learning_rate": 0.0001580357142857143,
      "loss": 1.5898,
      "step": 329
    },
    {
      "epoch": 6.68,
      "learning_rate": 0.00015790816326530612,
      "loss": 1.5441,
      "step": 330
    },
    {
      "epoch": 6.7,
      "learning_rate": 0.00015778061224489798,
      "loss": 1.61,
      "step": 331
    },
    {
      "epoch": 6.72,
      "learning_rate": 0.00015765306122448978,
      "loss": 1.615,
      "step": 332
    },
    {
      "epoch": 6.74,
      "learning_rate": 0.00015752551020408164,
      "loss": 1.6575,
      "step": 333
    },
    {
      "epoch": 6.76,
      "learning_rate": 0.00015739795918367347,
      "loss": 1.6702,
      "step": 334
    },
    {
      "epoch": 6.78,
      "learning_rate": 0.0001572704081632653,
      "loss": 1.6009,
      "step": 335
    },
    {
      "epoch": 6.8,
      "learning_rate": 0.00015714285714285716,
      "loss": 1.5568,
      "step": 336
    },
    {
      "epoch": 6.82,
      "learning_rate": 0.000157015306122449,
      "loss": 1.619,
      "step": 337
    },
    {
      "epoch": 6.84,
      "learning_rate": 0.00015688775510204082,
      "loss": 1.5563,
      "step": 338
    },
    {
      "epoch": 6.86,
      "learning_rate": 0.00015676020408163265,
      "loss": 1.6328,
      "step": 339
    },
    {
      "epoch": 6.88,
      "learning_rate": 0.0001566326530612245,
      "loss": 1.5726,
      "step": 340
    },
    {
      "epoch": 6.9,
      "learning_rate": 0.00015650510204081634,
      "loss": 1.6199,
      "step": 341
    },
    {
      "epoch": 6.92,
      "learning_rate": 0.00015637755102040817,
      "loss": 1.5722,
      "step": 342
    },
    {
      "epoch": 6.94,
      "learning_rate": 0.00015625,
      "loss": 1.5685,
      "step": 343
    },
    {
      "epoch": 6.96,
      "learning_rate": 0.00015612244897959186,
      "loss": 1.5615,
      "step": 344
    },
    {
      "epoch": 6.98,
      "learning_rate": 0.00015599489795918366,
      "loss": 1.5994,
      "step": 345
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.00015586734693877552,
      "loss": 1.5579,
      "step": 346
    },
    {
      "epoch": 7.02,
      "learning_rate": 0.00015573979591836735,
      "loss": 1.547,
      "step": 347
    },
    {
      "epoch": 7.04,
      "learning_rate": 0.00015561224489795918,
      "loss": 1.5292,
      "step": 348
    },
    {
      "epoch": 7.06,
      "learning_rate": 0.00015548469387755102,
      "loss": 1.6032,
      "step": 349
    },
    {
      "epoch": 7.08,
      "learning_rate": 0.00015535714285714287,
      "loss": 1.5149,
      "step": 350
    },
    {
      "epoch": 7.1,
      "learning_rate": 0.0001552295918367347,
      "loss": 1.6093,
      "step": 351
    },
    {
      "epoch": 7.12,
      "learning_rate": 0.00015510204081632654,
      "loss": 1.5421,
      "step": 352
    },
    {
      "epoch": 7.14,
      "learning_rate": 0.00015497448979591837,
      "loss": 1.5733,
      "step": 353
    },
    {
      "epoch": 7.16,
      "learning_rate": 0.00015484693877551022,
      "loss": 1.5703,
      "step": 354
    },
    {
      "epoch": 7.18,
      "learning_rate": 0.00015471938775510203,
      "loss": 1.6141,
      "step": 355
    },
    {
      "epoch": 7.2,
      "learning_rate": 0.00015459183673469389,
      "loss": 1.5526,
      "step": 356
    },
    {
      "epoch": 7.22,
      "learning_rate": 0.00015446428571428572,
      "loss": 1.5347,
      "step": 357
    },
    {
      "epoch": 7.24,
      "learning_rate": 0.00015433673469387755,
      "loss": 1.5682,
      "step": 358
    },
    {
      "epoch": 7.26,
      "learning_rate": 0.0001542091836734694,
      "loss": 1.5292,
      "step": 359
    },
    {
      "epoch": 7.28,
      "learning_rate": 0.00015408163265306124,
      "loss": 1.499,
      "step": 360
    },
    {
      "epoch": 7.3,
      "learning_rate": 0.00015395408163265307,
      "loss": 1.5624,
      "step": 361
    },
    {
      "epoch": 7.32,
      "learning_rate": 0.0001538265306122449,
      "loss": 1.627,
      "step": 362
    },
    {
      "epoch": 7.34,
      "learning_rate": 0.00015369897959183676,
      "loss": 1.5327,
      "step": 363
    },
    {
      "epoch": 7.37,
      "learning_rate": 0.0001535714285714286,
      "loss": 1.5622,
      "step": 364
    },
    {
      "epoch": 7.39,
      "learning_rate": 0.00015344387755102042,
      "loss": 1.5659,
      "step": 365
    },
    {
      "epoch": 7.41,
      "learning_rate": 0.00015331632653061225,
      "loss": 1.5019,
      "step": 366
    },
    {
      "epoch": 7.43,
      "learning_rate": 0.0001531887755102041,
      "loss": 1.5921,
      "step": 367
    },
    {
      "epoch": 7.45,
      "learning_rate": 0.0001530612244897959,
      "loss": 1.5914,
      "step": 368
    },
    {
      "epoch": 7.47,
      "learning_rate": 0.00015293367346938777,
      "loss": 1.5045,
      "step": 369
    },
    {
      "epoch": 7.49,
      "learning_rate": 0.0001528061224489796,
      "loss": 1.6209,
      "step": 370
    },
    {
      "epoch": 7.51,
      "learning_rate": 0.00015267857142857143,
      "loss": 1.5198,
      "step": 371
    },
    {
      "epoch": 7.53,
      "learning_rate": 0.00015255102040816326,
      "loss": 1.5363,
      "step": 372
    },
    {
      "epoch": 7.55,
      "learning_rate": 0.00015242346938775512,
      "loss": 1.5391,
      "step": 373
    },
    {
      "epoch": 7.57,
      "learning_rate": 0.00015229591836734695,
      "loss": 1.4546,
      "step": 374
    },
    {
      "epoch": 7.59,
      "learning_rate": 0.00015216836734693878,
      "loss": 1.5546,
      "step": 375
    },
    {
      "epoch": 7.61,
      "learning_rate": 0.0001520408163265306,
      "loss": 1.5629,
      "step": 376
    },
    {
      "epoch": 7.63,
      "learning_rate": 0.00015191326530612247,
      "loss": 1.6002,
      "step": 377
    },
    {
      "epoch": 7.65,
      "learning_rate": 0.00015178571428571427,
      "loss": 1.5543,
      "step": 378
    },
    {
      "epoch": 7.67,
      "learning_rate": 0.00015165816326530613,
      "loss": 1.5925,
      "step": 379
    },
    {
      "epoch": 7.69,
      "learning_rate": 0.00015153061224489796,
      "loss": 1.5631,
      "step": 380
    },
    {
      "epoch": 7.71,
      "learning_rate": 0.0001514030612244898,
      "loss": 1.5677,
      "step": 381
    },
    {
      "epoch": 7.73,
      "learning_rate": 0.00015127551020408165,
      "loss": 1.5828,
      "step": 382
    },
    {
      "epoch": 7.75,
      "learning_rate": 0.00015114795918367348,
      "loss": 1.6494,
      "step": 383
    },
    {
      "epoch": 7.77,
      "learning_rate": 0.0001510204081632653,
      "loss": 1.553,
      "step": 384
    },
    {
      "epoch": 7.79,
      "learning_rate": 0.00015089285714285714,
      "loss": 1.6156,
      "step": 385
    },
    {
      "epoch": 7.81,
      "learning_rate": 0.000150765306122449,
      "loss": 1.5001,
      "step": 386
    },
    {
      "epoch": 7.83,
      "learning_rate": 0.00015063775510204083,
      "loss": 1.5321,
      "step": 387
    },
    {
      "epoch": 7.85,
      "learning_rate": 0.00015051020408163266,
      "loss": 1.5307,
      "step": 388
    },
    {
      "epoch": 7.87,
      "learning_rate": 0.0001503826530612245,
      "loss": 1.5639,
      "step": 389
    },
    {
      "epoch": 7.89,
      "learning_rate": 0.00015025510204081635,
      "loss": 1.517,
      "step": 390
    },
    {
      "epoch": 7.91,
      "learning_rate": 0.00015012755102040816,
      "loss": 1.4776,
      "step": 391
    },
    {
      "epoch": 7.93,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.5368,
      "step": 392
    },
    {
      "epoch": 7.95,
      "learning_rate": 0.00014987244897959184,
      "loss": 1.5636,
      "step": 393
    },
    {
      "epoch": 7.97,
      "learning_rate": 0.00014974489795918368,
      "loss": 1.6004,
      "step": 394
    },
    {
      "epoch": 7.99,
      "learning_rate": 0.0001496173469387755,
      "loss": 1.5524,
      "step": 395
    },
    {
      "epoch": 8.01,
      "learning_rate": 0.00014948979591836736,
      "loss": 1.5307,
      "step": 396
    },
    {
      "epoch": 8.03,
      "learning_rate": 0.00014936224489795917,
      "loss": 1.5123,
      "step": 397
    },
    {
      "epoch": 8.05,
      "learning_rate": 0.00014923469387755103,
      "loss": 1.5132,
      "step": 398
    },
    {
      "epoch": 8.07,
      "learning_rate": 0.00014910714285714286,
      "loss": 1.5109,
      "step": 399
    },
    {
      "epoch": 8.09,
      "learning_rate": 0.00014897959183673472,
      "loss": 1.5302,
      "step": 400
    },
    {
      "epoch": 8.11,
      "learning_rate": 0.00014885204081632652,
      "loss": 1.5238,
      "step": 401
    },
    {
      "epoch": 8.13,
      "learning_rate": 0.00014872448979591838,
      "loss": 1.4781,
      "step": 402
    },
    {
      "epoch": 8.15,
      "learning_rate": 0.0001485969387755102,
      "loss": 1.5446,
      "step": 403
    },
    {
      "epoch": 8.17,
      "learning_rate": 0.00014846938775510204,
      "loss": 1.5,
      "step": 404
    },
    {
      "epoch": 8.19,
      "learning_rate": 0.0001483418367346939,
      "loss": 1.5458,
      "step": 405
    },
    {
      "epoch": 8.21,
      "learning_rate": 0.00014821428571428573,
      "loss": 1.5257,
      "step": 406
    },
    {
      "epoch": 8.24,
      "learning_rate": 0.00014808673469387756,
      "loss": 1.4607,
      "step": 407
    },
    {
      "epoch": 8.26,
      "learning_rate": 0.0001479591836734694,
      "loss": 1.4282,
      "step": 408
    },
    {
      "epoch": 8.28,
      "learning_rate": 0.00014783163265306125,
      "loss": 1.4519,
      "step": 409
    },
    {
      "epoch": 8.3,
      "learning_rate": 0.00014770408163265305,
      "loss": 1.475,
      "step": 410
    },
    {
      "epoch": 8.32,
      "learning_rate": 0.0001475765306122449,
      "loss": 1.5425,
      "step": 411
    },
    {
      "epoch": 8.34,
      "learning_rate": 0.00014744897959183674,
      "loss": 1.5407,
      "step": 412
    },
    {
      "epoch": 8.36,
      "learning_rate": 0.0001473214285714286,
      "loss": 1.5698,
      "step": 413
    },
    {
      "epoch": 8.38,
      "learning_rate": 0.0001471938775510204,
      "loss": 1.4282,
      "step": 414
    },
    {
      "epoch": 8.4,
      "learning_rate": 0.00014706632653061226,
      "loss": 1.5301,
      "step": 415
    },
    {
      "epoch": 8.42,
      "learning_rate": 0.0001469387755102041,
      "loss": 1.5083,
      "step": 416
    },
    {
      "epoch": 8.44,
      "learning_rate": 0.00014681122448979592,
      "loss": 1.5712,
      "step": 417
    },
    {
      "epoch": 8.46,
      "learning_rate": 0.00014668367346938775,
      "loss": 1.4363,
      "step": 418
    },
    {
      "epoch": 8.48,
      "learning_rate": 0.0001465561224489796,
      "loss": 1.4463,
      "step": 419
    },
    {
      "epoch": 8.5,
      "learning_rate": 0.00014642857142857141,
      "loss": 1.4738,
      "step": 420
    },
    {
      "epoch": 8.52,
      "learning_rate": 0.00014630102040816327,
      "loss": 1.5396,
      "step": 421
    },
    {
      "epoch": 8.54,
      "learning_rate": 0.0001461734693877551,
      "loss": 1.4384,
      "step": 422
    },
    {
      "epoch": 8.56,
      "learning_rate": 0.00014604591836734696,
      "loss": 1.5345,
      "step": 423
    },
    {
      "epoch": 8.58,
      "learning_rate": 0.0001459183673469388,
      "loss": 1.5355,
      "step": 424
    },
    {
      "epoch": 8.6,
      "learning_rate": 0.00014579081632653062,
      "loss": 1.5188,
      "step": 425
    },
    {
      "epoch": 8.62,
      "learning_rate": 0.00014566326530612245,
      "loss": 1.5575,
      "step": 426
    },
    {
      "epoch": 8.64,
      "learning_rate": 0.00014553571428571428,
      "loss": 1.5279,
      "step": 427
    },
    {
      "epoch": 8.66,
      "learning_rate": 0.00014540816326530614,
      "loss": 1.5484,
      "step": 428
    },
    {
      "epoch": 8.68,
      "learning_rate": 0.00014528061224489797,
      "loss": 1.4878,
      "step": 429
    },
    {
      "epoch": 8.7,
      "learning_rate": 0.0001451530612244898,
      "loss": 1.503,
      "step": 430
    },
    {
      "epoch": 8.72,
      "learning_rate": 0.00014502551020408163,
      "loss": 1.4723,
      "step": 431
    },
    {
      "epoch": 8.74,
      "learning_rate": 0.0001448979591836735,
      "loss": 1.5579,
      "step": 432
    },
    {
      "epoch": 8.76,
      "learning_rate": 0.0001447704081632653,
      "loss": 1.4789,
      "step": 433
    },
    {
      "epoch": 8.78,
      "learning_rate": 0.00014464285714285715,
      "loss": 1.5501,
      "step": 434
    },
    {
      "epoch": 8.8,
      "learning_rate": 0.00014451530612244899,
      "loss": 1.5204,
      "step": 435
    },
    {
      "epoch": 8.82,
      "learning_rate": 0.00014438775510204084,
      "loss": 1.5489,
      "step": 436
    },
    {
      "epoch": 8.84,
      "learning_rate": 0.00014426020408163265,
      "loss": 1.5464,
      "step": 437
    },
    {
      "epoch": 8.86,
      "learning_rate": 0.0001441326530612245,
      "loss": 1.5896,
      "step": 438
    },
    {
      "epoch": 8.88,
      "learning_rate": 0.00014400510204081634,
      "loss": 1.5465,
      "step": 439
    },
    {
      "epoch": 8.9,
      "learning_rate": 0.00014387755102040817,
      "loss": 1.5094,
      "step": 440
    },
    {
      "epoch": 8.92,
      "learning_rate": 0.00014375,
      "loss": 1.5144,
      "step": 441
    },
    {
      "epoch": 8.94,
      "learning_rate": 0.00014362244897959186,
      "loss": 1.4919,
      "step": 442
    },
    {
      "epoch": 8.96,
      "learning_rate": 0.00014349489795918366,
      "loss": 1.4702,
      "step": 443
    },
    {
      "epoch": 8.98,
      "learning_rate": 0.00014336734693877552,
      "loss": 1.4996,
      "step": 444
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.00014323979591836735,
      "loss": 1.5503,
      "step": 445
    },
    {
      "epoch": 9.02,
      "learning_rate": 0.00014311224489795918,
      "loss": 1.4125,
      "step": 446
    },
    {
      "epoch": 9.04,
      "learning_rate": 0.00014298469387755104,
      "loss": 1.4722,
      "step": 447
    },
    {
      "epoch": 9.06,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.5199,
      "step": 448
    },
    {
      "epoch": 9.09,
      "learning_rate": 0.0001427295918367347,
      "loss": 1.4571,
      "step": 449
    },
    {
      "epoch": 9.11,
      "learning_rate": 0.00014260204081632653,
      "loss": 1.4996,
      "step": 450
    },
    {
      "epoch": 9.13,
      "learning_rate": 0.0001424744897959184,
      "loss": 1.4092,
      "step": 451
    },
    {
      "epoch": 9.15,
      "learning_rate": 0.00014234693877551022,
      "loss": 1.4198,
      "step": 452
    },
    {
      "epoch": 9.17,
      "learning_rate": 0.00014221938775510205,
      "loss": 1.4916,
      "step": 453
    },
    {
      "epoch": 9.19,
      "learning_rate": 0.00014209183673469388,
      "loss": 1.5051,
      "step": 454
    },
    {
      "epoch": 9.21,
      "learning_rate": 0.00014196428571428574,
      "loss": 1.4321,
      "step": 455
    },
    {
      "epoch": 9.23,
      "learning_rate": 0.00014183673469387754,
      "loss": 1.4097,
      "step": 456
    },
    {
      "epoch": 9.25,
      "learning_rate": 0.0001417091836734694,
      "loss": 1.4853,
      "step": 457
    },
    {
      "epoch": 9.27,
      "learning_rate": 0.00014158163265306123,
      "loss": 1.4593,
      "step": 458
    },
    {
      "epoch": 9.29,
      "learning_rate": 0.00014145408163265306,
      "loss": 1.3729,
      "step": 459
    },
    {
      "epoch": 9.31,
      "learning_rate": 0.0001413265306122449,
      "loss": 1.4467,
      "step": 460
    },
    {
      "epoch": 9.33,
      "learning_rate": 0.00014119897959183675,
      "loss": 1.4467,
      "step": 461
    },
    {
      "epoch": 9.35,
      "learning_rate": 0.00014107142857142858,
      "loss": 1.4785,
      "step": 462
    },
    {
      "epoch": 9.37,
      "learning_rate": 0.0001409438775510204,
      "loss": 1.4089,
      "step": 463
    },
    {
      "epoch": 9.39,
      "learning_rate": 0.00014081632653061224,
      "loss": 1.5026,
      "step": 464
    },
    {
      "epoch": 9.41,
      "learning_rate": 0.0001406887755102041,
      "loss": 1.4857,
      "step": 465
    },
    {
      "epoch": 9.43,
      "learning_rate": 0.0001405612244897959,
      "loss": 1.3745,
      "step": 466
    },
    {
      "epoch": 9.45,
      "learning_rate": 0.00014043367346938776,
      "loss": 1.4733,
      "step": 467
    },
    {
      "epoch": 9.47,
      "learning_rate": 0.0001403061224489796,
      "loss": 1.5212,
      "step": 468
    },
    {
      "epoch": 9.49,
      "learning_rate": 0.00014017857142857142,
      "loss": 1.5398,
      "step": 469
    },
    {
      "epoch": 9.51,
      "learning_rate": 0.00014005102040816328,
      "loss": 1.478,
      "step": 470
    },
    {
      "epoch": 9.53,
      "learning_rate": 0.0001399234693877551,
      "loss": 1.496,
      "step": 471
    },
    {
      "epoch": 9.55,
      "learning_rate": 0.00013979591836734694,
      "loss": 1.4837,
      "step": 472
    },
    {
      "epoch": 9.57,
      "learning_rate": 0.00013966836734693878,
      "loss": 1.4724,
      "step": 473
    },
    {
      "epoch": 9.59,
      "learning_rate": 0.00013954081632653063,
      "loss": 1.4828,
      "step": 474
    },
    {
      "epoch": 9.61,
      "learning_rate": 0.00013941326530612246,
      "loss": 1.5012,
      "step": 475
    },
    {
      "epoch": 9.63,
      "learning_rate": 0.0001392857142857143,
      "loss": 1.4879,
      "step": 476
    },
    {
      "epoch": 9.65,
      "learning_rate": 0.00013915816326530613,
      "loss": 1.4196,
      "step": 477
    },
    {
      "epoch": 9.67,
      "learning_rate": 0.00013903061224489798,
      "loss": 1.4915,
      "step": 478
    },
    {
      "epoch": 9.69,
      "learning_rate": 0.0001389030612244898,
      "loss": 1.3878,
      "step": 479
    },
    {
      "epoch": 9.71,
      "learning_rate": 0.00013877551020408165,
      "loss": 1.466,
      "step": 480
    },
    {
      "epoch": 9.73,
      "learning_rate": 0.00013864795918367348,
      "loss": 1.4582,
      "step": 481
    },
    {
      "epoch": 9.75,
      "learning_rate": 0.0001385204081632653,
      "loss": 1.533,
      "step": 482
    },
    {
      "epoch": 9.77,
      "learning_rate": 0.00013839285714285714,
      "loss": 1.4697,
      "step": 483
    },
    {
      "epoch": 9.79,
      "learning_rate": 0.000138265306122449,
      "loss": 1.3989,
      "step": 484
    },
    {
      "epoch": 9.81,
      "learning_rate": 0.00013813775510204083,
      "loss": 1.4361,
      "step": 485
    },
    {
      "epoch": 9.83,
      "learning_rate": 0.00013801020408163266,
      "loss": 1.5271,
      "step": 486
    },
    {
      "epoch": 9.85,
      "learning_rate": 0.0001378826530612245,
      "loss": 1.4905,
      "step": 487
    },
    {
      "epoch": 9.87,
      "learning_rate": 0.00013775510204081635,
      "loss": 1.4757,
      "step": 488
    },
    {
      "epoch": 9.89,
      "learning_rate": 0.00013762755102040815,
      "loss": 1.5485,
      "step": 489
    },
    {
      "epoch": 9.91,
      "learning_rate": 0.0001375,
      "loss": 1.4783,
      "step": 490
    },
    {
      "epoch": 9.93,
      "learning_rate": 0.00013737244897959184,
      "loss": 1.4849,
      "step": 491
    },
    {
      "epoch": 9.96,
      "learning_rate": 0.00013724489795918367,
      "loss": 1.5382,
      "step": 492
    },
    {
      "epoch": 9.98,
      "learning_rate": 0.00013711734693877553,
      "loss": 1.4902,
      "step": 493
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.00013698979591836736,
      "loss": 1.4865,
      "step": 494
    },
    {
      "epoch": 10.02,
      "learning_rate": 0.0001368622448979592,
      "loss": 1.4436,
      "step": 495
    },
    {
      "epoch": 10.04,
      "learning_rate": 0.00013673469387755102,
      "loss": 1.408,
      "step": 496
    },
    {
      "epoch": 10.06,
      "learning_rate": 0.00013660714285714288,
      "loss": 1.4764,
      "step": 497
    },
    {
      "epoch": 10.08,
      "learning_rate": 0.0001364795918367347,
      "loss": 1.4646,
      "step": 498
    },
    {
      "epoch": 10.1,
      "learning_rate": 0.00013635204081632654,
      "loss": 1.406,
      "step": 499
    },
    {
      "epoch": 10.12,
      "learning_rate": 0.00013622448979591837,
      "loss": 1.4785,
      "step": 500
    },
    {
      "epoch": 10.14,
      "learning_rate": 0.00013609693877551023,
      "loss": 1.4117,
      "step": 501
    },
    {
      "epoch": 10.16,
      "learning_rate": 0.00013596938775510203,
      "loss": 1.4108,
      "step": 502
    },
    {
      "epoch": 10.18,
      "learning_rate": 0.0001358418367346939,
      "loss": 1.4155,
      "step": 503
    },
    {
      "epoch": 10.2,
      "learning_rate": 0.00013571428571428572,
      "loss": 1.4021,
      "step": 504
    },
    {
      "epoch": 10.22,
      "learning_rate": 0.00013558673469387755,
      "loss": 1.411,
      "step": 505
    },
    {
      "epoch": 10.24,
      "learning_rate": 0.00013545918367346938,
      "loss": 1.3851,
      "step": 506
    },
    {
      "epoch": 10.26,
      "learning_rate": 0.00013533163265306124,
      "loss": 1.387,
      "step": 507
    },
    {
      "epoch": 10.28,
      "learning_rate": 0.00013520408163265305,
      "loss": 1.4163,
      "step": 508
    },
    {
      "epoch": 10.3,
      "learning_rate": 0.0001350765306122449,
      "loss": 1.3343,
      "step": 509
    },
    {
      "epoch": 10.32,
      "learning_rate": 0.00013494897959183673,
      "loss": 1.4811,
      "step": 510
    },
    {
      "epoch": 10.34,
      "learning_rate": 0.0001348214285714286,
      "loss": 1.4086,
      "step": 511
    },
    {
      "epoch": 10.36,
      "learning_rate": 0.0001346938775510204,
      "loss": 1.3879,
      "step": 512
    },
    {
      "epoch": 10.38,
      "learning_rate": 0.00013456632653061225,
      "loss": 1.4204,
      "step": 513
    },
    {
      "epoch": 10.4,
      "learning_rate": 0.00013443877551020408,
      "loss": 1.4158,
      "step": 514
    },
    {
      "epoch": 10.42,
      "learning_rate": 0.00013431122448979592,
      "loss": 1.4521,
      "step": 515
    },
    {
      "epoch": 10.44,
      "learning_rate": 0.00013418367346938777,
      "loss": 1.4196,
      "step": 516
    },
    {
      "epoch": 10.46,
      "learning_rate": 0.0001340561224489796,
      "loss": 1.4361,
      "step": 517
    },
    {
      "epoch": 10.48,
      "learning_rate": 0.00013392857142857144,
      "loss": 1.4482,
      "step": 518
    },
    {
      "epoch": 10.5,
      "learning_rate": 0.00013380102040816327,
      "loss": 1.4801,
      "step": 519
    },
    {
      "epoch": 10.52,
      "learning_rate": 0.00013367346938775512,
      "loss": 1.4556,
      "step": 520
    },
    {
      "epoch": 10.54,
      "learning_rate": 0.00013354591836734695,
      "loss": 1.3902,
      "step": 521
    },
    {
      "epoch": 10.56,
      "learning_rate": 0.00013341836734693879,
      "loss": 1.4269,
      "step": 522
    },
    {
      "epoch": 10.58,
      "learning_rate": 0.00013329081632653062,
      "loss": 1.4899,
      "step": 523
    },
    {
      "epoch": 10.6,
      "learning_rate": 0.00013316326530612247,
      "loss": 1.3952,
      "step": 524
    },
    {
      "epoch": 10.62,
      "learning_rate": 0.00013303571428571428,
      "loss": 1.4116,
      "step": 525
    },
    {
      "epoch": 10.64,
      "learning_rate": 0.00013290816326530614,
      "loss": 1.4583,
      "step": 526
    },
    {
      "epoch": 10.66,
      "learning_rate": 0.00013278061224489797,
      "loss": 1.4466,
      "step": 527
    },
    {
      "epoch": 10.68,
      "learning_rate": 0.0001326530612244898,
      "loss": 1.4242,
      "step": 528
    },
    {
      "epoch": 10.7,
      "learning_rate": 0.00013252551020408163,
      "loss": 1.3717,
      "step": 529
    },
    {
      "epoch": 10.72,
      "learning_rate": 0.0001323979591836735,
      "loss": 1.4583,
      "step": 530
    },
    {
      "epoch": 10.74,
      "learning_rate": 0.0001322704081632653,
      "loss": 1.4185,
      "step": 531
    },
    {
      "epoch": 10.76,
      "learning_rate": 0.00013214285714285715,
      "loss": 1.4287,
      "step": 532
    },
    {
      "epoch": 10.78,
      "learning_rate": 0.00013201530612244898,
      "loss": 1.4385,
      "step": 533
    },
    {
      "epoch": 10.8,
      "learning_rate": 0.00013188775510204084,
      "loss": 1.453,
      "step": 534
    },
    {
      "epoch": 10.83,
      "learning_rate": 0.00013176020408163264,
      "loss": 1.4161,
      "step": 535
    },
    {
      "epoch": 10.85,
      "learning_rate": 0.0001316326530612245,
      "loss": 1.457,
      "step": 536
    },
    {
      "epoch": 10.87,
      "learning_rate": 0.00013150510204081633,
      "loss": 1.4367,
      "step": 537
    },
    {
      "epoch": 10.89,
      "learning_rate": 0.00013137755102040816,
      "loss": 1.4256,
      "step": 538
    },
    {
      "epoch": 10.91,
      "learning_rate": 0.00013125000000000002,
      "loss": 1.424,
      "step": 539
    },
    {
      "epoch": 10.93,
      "learning_rate": 0.00013112244897959185,
      "loss": 1.3923,
      "step": 540
    },
    {
      "epoch": 10.95,
      "learning_rate": 0.00013099489795918368,
      "loss": 1.4225,
      "step": 541
    },
    {
      "epoch": 10.97,
      "learning_rate": 0.0001308673469387755,
      "loss": 1.3969,
      "step": 542
    },
    {
      "epoch": 10.99,
      "learning_rate": 0.00013073979591836737,
      "loss": 1.4446,
      "step": 543
    },
    {
      "epoch": 11.01,
      "learning_rate": 0.00013061224489795917,
      "loss": 1.4375,
      "step": 544
    },
    {
      "epoch": 11.03,
      "learning_rate": 0.00013048469387755103,
      "loss": 1.4064,
      "step": 545
    },
    {
      "epoch": 11.05,
      "learning_rate": 0.00013035714285714286,
      "loss": 1.3454,
      "step": 546
    },
    {
      "epoch": 11.07,
      "learning_rate": 0.00013022959183673472,
      "loss": 1.3234,
      "step": 547
    },
    {
      "epoch": 11.09,
      "learning_rate": 0.00013010204081632652,
      "loss": 1.3759,
      "step": 548
    },
    {
      "epoch": 11.11,
      "learning_rate": 0.00012997448979591838,
      "loss": 1.4221,
      "step": 549
    },
    {
      "epoch": 11.13,
      "learning_rate": 0.0001298469387755102,
      "loss": 1.4261,
      "step": 550
    },
    {
      "epoch": 11.15,
      "learning_rate": 0.00012971938775510204,
      "loss": 1.3341,
      "step": 551
    },
    {
      "epoch": 11.17,
      "learning_rate": 0.00012959183673469387,
      "loss": 1.3994,
      "step": 552
    },
    {
      "epoch": 11.19,
      "learning_rate": 0.00012946428571428573,
      "loss": 1.3894,
      "step": 553
    },
    {
      "epoch": 11.21,
      "learning_rate": 0.00012933673469387754,
      "loss": 1.3585,
      "step": 554
    },
    {
      "epoch": 11.23,
      "learning_rate": 0.0001292091836734694,
      "loss": 1.3763,
      "step": 555
    },
    {
      "epoch": 11.25,
      "learning_rate": 0.00012908163265306123,
      "loss": 1.3623,
      "step": 556
    },
    {
      "epoch": 11.27,
      "learning_rate": 0.00012895408163265306,
      "loss": 1.3907,
      "step": 557
    },
    {
      "epoch": 11.29,
      "learning_rate": 0.0001288265306122449,
      "loss": 1.3807,
      "step": 558
    },
    {
      "epoch": 11.31,
      "learning_rate": 0.00012869897959183674,
      "loss": 1.4045,
      "step": 559
    },
    {
      "epoch": 11.33,
      "learning_rate": 0.00012857142857142858,
      "loss": 1.4038,
      "step": 560
    },
    {
      "epoch": 11.35,
      "learning_rate": 0.0001284438775510204,
      "loss": 1.3466,
      "step": 561
    },
    {
      "epoch": 11.37,
      "learning_rate": 0.00012831632653061226,
      "loss": 1.3449,
      "step": 562
    },
    {
      "epoch": 11.39,
      "learning_rate": 0.0001281887755102041,
      "loss": 1.3866,
      "step": 563
    },
    {
      "epoch": 11.41,
      "learning_rate": 0.00012806122448979593,
      "loss": 1.3106,
      "step": 564
    },
    {
      "epoch": 11.43,
      "learning_rate": 0.00012793367346938776,
      "loss": 1.4414,
      "step": 565
    },
    {
      "epoch": 11.45,
      "learning_rate": 0.00012780612244897962,
      "loss": 1.3737,
      "step": 566
    },
    {
      "epoch": 11.47,
      "learning_rate": 0.00012767857142857142,
      "loss": 1.4053,
      "step": 567
    },
    {
      "epoch": 11.49,
      "learning_rate": 0.00012755102040816328,
      "loss": 1.4561,
      "step": 568
    },
    {
      "epoch": 11.51,
      "learning_rate": 0.0001274234693877551,
      "loss": 1.3684,
      "step": 569
    },
    {
      "epoch": 11.53,
      "learning_rate": 0.00012729591836734697,
      "loss": 1.3117,
      "step": 570
    },
    {
      "epoch": 11.55,
      "learning_rate": 0.00012716836734693877,
      "loss": 1.3474,
      "step": 571
    },
    {
      "epoch": 11.57,
      "learning_rate": 0.00012704081632653063,
      "loss": 1.3804,
      "step": 572
    },
    {
      "epoch": 11.59,
      "learning_rate": 0.00012691326530612246,
      "loss": 1.3656,
      "step": 573
    },
    {
      "epoch": 11.61,
      "learning_rate": 0.0001267857142857143,
      "loss": 1.3133,
      "step": 574
    },
    {
      "epoch": 11.63,
      "learning_rate": 0.00012665816326530612,
      "loss": 1.4077,
      "step": 575
    },
    {
      "epoch": 11.65,
      "learning_rate": 0.00012653061224489798,
      "loss": 1.4087,
      "step": 576
    },
    {
      "epoch": 11.67,
      "learning_rate": 0.00012640306122448978,
      "loss": 1.3524,
      "step": 577
    },
    {
      "epoch": 11.7,
      "learning_rate": 0.00012627551020408164,
      "loss": 1.3481,
      "step": 578
    },
    {
      "epoch": 11.72,
      "learning_rate": 0.00012614795918367347,
      "loss": 1.4497,
      "step": 579
    },
    {
      "epoch": 11.74,
      "learning_rate": 0.0001260204081632653,
      "loss": 1.3866,
      "step": 580
    },
    {
      "epoch": 11.76,
      "learning_rate": 0.00012589285714285713,
      "loss": 1.42,
      "step": 581
    },
    {
      "epoch": 11.78,
      "learning_rate": 0.000125765306122449,
      "loss": 1.3562,
      "step": 582
    },
    {
      "epoch": 11.8,
      "learning_rate": 0.00012563775510204082,
      "loss": 1.3249,
      "step": 583
    },
    {
      "epoch": 11.82,
      "learning_rate": 0.00012551020408163265,
      "loss": 1.4277,
      "step": 584
    },
    {
      "epoch": 11.84,
      "learning_rate": 0.0001253826530612245,
      "loss": 1.3734,
      "step": 585
    },
    {
      "epoch": 11.86,
      "learning_rate": 0.00012525510204081634,
      "loss": 1.3765,
      "step": 586
    },
    {
      "epoch": 11.88,
      "learning_rate": 0.00012512755102040817,
      "loss": 1.4153,
      "step": 587
    },
    {
      "epoch": 11.9,
      "learning_rate": 0.000125,
      "loss": 1.3847,
      "step": 588
    },
    {
      "epoch": 11.92,
      "learning_rate": 0.00012487244897959186,
      "loss": 1.3824,
      "step": 589
    },
    {
      "epoch": 11.94,
      "learning_rate": 0.00012474489795918366,
      "loss": 1.3938,
      "step": 590
    },
    {
      "epoch": 11.96,
      "learning_rate": 0.00012461734693877552,
      "loss": 1.4143,
      "step": 591
    },
    {
      "epoch": 11.98,
      "learning_rate": 0.00012448979591836735,
      "loss": 1.3794,
      "step": 592
    },
    {
      "epoch": 12.0,
      "learning_rate": 0.00012436224489795918,
      "loss": 1.3755,
      "step": 593
    },
    {
      "epoch": 12.02,
      "learning_rate": 0.00012423469387755101,
      "loss": 1.3736,
      "step": 594
    },
    {
      "epoch": 12.04,
      "learning_rate": 0.00012410714285714287,
      "loss": 1.2957,
      "step": 595
    },
    {
      "epoch": 12.06,
      "learning_rate": 0.0001239795918367347,
      "loss": 1.2996,
      "step": 596
    },
    {
      "epoch": 12.08,
      "learning_rate": 0.00012385204081632653,
      "loss": 1.3648,
      "step": 597
    },
    {
      "epoch": 12.1,
      "learning_rate": 0.00012372448979591837,
      "loss": 1.3031,
      "step": 598
    },
    {
      "epoch": 12.12,
      "learning_rate": 0.00012359693877551022,
      "loss": 1.2933,
      "step": 599
    },
    {
      "epoch": 12.14,
      "learning_rate": 0.00012346938775510203,
      "loss": 1.322,
      "step": 600
    },
    {
      "epoch": 12.16,
      "learning_rate": 0.00012334183673469389,
      "loss": 1.3123,
      "step": 601
    },
    {
      "epoch": 12.18,
      "learning_rate": 0.00012321428571428572,
      "loss": 1.3187,
      "step": 602
    },
    {
      "epoch": 12.2,
      "learning_rate": 0.00012308673469387755,
      "loss": 1.3353,
      "step": 603
    },
    {
      "epoch": 12.22,
      "learning_rate": 0.0001229591836734694,
      "loss": 1.3221,
      "step": 604
    },
    {
      "epoch": 12.24,
      "learning_rate": 0.00012283163265306124,
      "loss": 1.3458,
      "step": 605
    },
    {
      "epoch": 12.26,
      "learning_rate": 0.00012270408163265307,
      "loss": 1.275,
      "step": 606
    },
    {
      "epoch": 12.28,
      "learning_rate": 0.0001225765306122449,
      "loss": 1.3455,
      "step": 607
    },
    {
      "epoch": 12.3,
      "learning_rate": 0.00012244897959183676,
      "loss": 1.2769,
      "step": 608
    },
    {
      "epoch": 12.32,
      "learning_rate": 0.00012232142857142859,
      "loss": 1.3201,
      "step": 609
    },
    {
      "epoch": 12.34,
      "learning_rate": 0.00012219387755102042,
      "loss": 1.3073,
      "step": 610
    },
    {
      "epoch": 12.36,
      "learning_rate": 0.00012206632653061225,
      "loss": 1.3103,
      "step": 611
    },
    {
      "epoch": 12.38,
      "learning_rate": 0.00012193877551020409,
      "loss": 1.4437,
      "step": 612
    },
    {
      "epoch": 12.4,
      "learning_rate": 0.00012181122448979591,
      "loss": 1.3086,
      "step": 613
    },
    {
      "epoch": 12.42,
      "learning_rate": 0.00012168367346938775,
      "loss": 1.3867,
      "step": 614
    },
    {
      "epoch": 12.44,
      "learning_rate": 0.0001215561224489796,
      "loss": 1.2565,
      "step": 615
    },
    {
      "epoch": 12.46,
      "learning_rate": 0.00012142857142857143,
      "loss": 1.335,
      "step": 616
    },
    {
      "epoch": 12.48,
      "learning_rate": 0.00012130102040816327,
      "loss": 1.3423,
      "step": 617
    },
    {
      "epoch": 12.5,
      "learning_rate": 0.00012117346938775512,
      "loss": 1.3433,
      "step": 618
    },
    {
      "epoch": 12.52,
      "learning_rate": 0.00012104591836734695,
      "loss": 1.3387,
      "step": 619
    },
    {
      "epoch": 12.55,
      "learning_rate": 0.00012091836734693878,
      "loss": 1.3923,
      "step": 620
    },
    {
      "epoch": 12.57,
      "learning_rate": 0.00012079081632653062,
      "loss": 1.3774,
      "step": 621
    },
    {
      "epoch": 12.59,
      "learning_rate": 0.00012066326530612247,
      "loss": 1.3203,
      "step": 622
    },
    {
      "epoch": 12.61,
      "learning_rate": 0.00012053571428571429,
      "loss": 1.2924,
      "step": 623
    },
    {
      "epoch": 12.63,
      "learning_rate": 0.00012040816326530613,
      "loss": 1.3292,
      "step": 624
    },
    {
      "epoch": 12.65,
      "learning_rate": 0.00012028061224489798,
      "loss": 1.3161,
      "step": 625
    },
    {
      "epoch": 12.67,
      "learning_rate": 0.00012015306122448979,
      "loss": 1.352,
      "step": 626
    },
    {
      "epoch": 12.69,
      "learning_rate": 0.00012002551020408164,
      "loss": 1.3577,
      "step": 627
    },
    {
      "epoch": 12.71,
      "learning_rate": 0.00011989795918367348,
      "loss": 1.3575,
      "step": 628
    },
    {
      "epoch": 12.73,
      "learning_rate": 0.0001197704081632653,
      "loss": 1.3727,
      "step": 629
    },
    {
      "epoch": 12.75,
      "learning_rate": 0.00011964285714285714,
      "loss": 1.3312,
      "step": 630
    },
    {
      "epoch": 12.77,
      "learning_rate": 0.00011951530612244899,
      "loss": 1.3378,
      "step": 631
    },
    {
      "epoch": 12.79,
      "learning_rate": 0.00011938775510204083,
      "loss": 1.295,
      "step": 632
    },
    {
      "epoch": 12.81,
      "learning_rate": 0.00011926020408163265,
      "loss": 1.3447,
      "step": 633
    },
    {
      "epoch": 12.83,
      "learning_rate": 0.0001191326530612245,
      "loss": 1.3835,
      "step": 634
    },
    {
      "epoch": 12.85,
      "learning_rate": 0.00011900510204081634,
      "loss": 1.3222,
      "step": 635
    },
    {
      "epoch": 12.87,
      "learning_rate": 0.00011887755102040817,
      "loss": 1.2851,
      "step": 636
    },
    {
      "epoch": 12.89,
      "learning_rate": 0.00011875,
      "loss": 1.2723,
      "step": 637
    },
    {
      "epoch": 12.91,
      "learning_rate": 0.00011862244897959184,
      "loss": 1.3924,
      "step": 638
    },
    {
      "epoch": 12.93,
      "learning_rate": 0.00011849489795918368,
      "loss": 1.4625,
      "step": 639
    },
    {
      "epoch": 12.95,
      "learning_rate": 0.00011836734693877552,
      "loss": 1.3245,
      "step": 640
    },
    {
      "epoch": 12.97,
      "learning_rate": 0.00011823979591836736,
      "loss": 1.4042,
      "step": 641
    },
    {
      "epoch": 12.99,
      "learning_rate": 0.00011811224489795918,
      "loss": 1.3761,
      "step": 642
    },
    {
      "epoch": 13.01,
      "learning_rate": 0.00011798469387755103,
      "loss": 1.3376,
      "step": 643
    },
    {
      "epoch": 13.03,
      "learning_rate": 0.00011785714285714287,
      "loss": 1.2174,
      "step": 644
    },
    {
      "epoch": 13.05,
      "learning_rate": 0.00011772959183673471,
      "loss": 1.3602,
      "step": 645
    },
    {
      "epoch": 13.07,
      "learning_rate": 0.00011760204081632653,
      "loss": 1.3002,
      "step": 646
    },
    {
      "epoch": 13.09,
      "learning_rate": 0.00011747448979591838,
      "loss": 1.2262,
      "step": 647
    },
    {
      "epoch": 13.11,
      "learning_rate": 0.00011734693877551022,
      "loss": 1.3048,
      "step": 648
    },
    {
      "epoch": 13.13,
      "learning_rate": 0.00011721938775510204,
      "loss": 1.2231,
      "step": 649
    },
    {
      "epoch": 13.15,
      "learning_rate": 0.00011709183673469388,
      "loss": 1.2996,
      "step": 650
    },
    {
      "epoch": 13.17,
      "learning_rate": 0.00011696428571428573,
      "loss": 1.2708,
      "step": 651
    },
    {
      "epoch": 13.19,
      "learning_rate": 0.00011683673469387754,
      "loss": 1.2776,
      "step": 652
    },
    {
      "epoch": 13.21,
      "learning_rate": 0.00011670918367346939,
      "loss": 1.248,
      "step": 653
    },
    {
      "epoch": 13.23,
      "learning_rate": 0.00011658163265306123,
      "loss": 1.2582,
      "step": 654
    },
    {
      "epoch": 13.25,
      "learning_rate": 0.00011645408163265305,
      "loss": 1.3011,
      "step": 655
    },
    {
      "epoch": 13.27,
      "learning_rate": 0.0001163265306122449,
      "loss": 1.2969,
      "step": 656
    },
    {
      "epoch": 13.29,
      "learning_rate": 0.00011619897959183674,
      "loss": 1.2454,
      "step": 657
    },
    {
      "epoch": 13.31,
      "learning_rate": 0.00011607142857142858,
      "loss": 1.1914,
      "step": 658
    },
    {
      "epoch": 13.33,
      "learning_rate": 0.00011594387755102041,
      "loss": 1.34,
      "step": 659
    },
    {
      "epoch": 13.35,
      "learning_rate": 0.00011581632653061225,
      "loss": 1.2828,
      "step": 660
    },
    {
      "epoch": 13.37,
      "learning_rate": 0.00011568877551020409,
      "loss": 1.2962,
      "step": 661
    },
    {
      "epoch": 13.39,
      "learning_rate": 0.00011556122448979592,
      "loss": 1.3334,
      "step": 662
    },
    {
      "epoch": 13.42,
      "learning_rate": 0.00011543367346938776,
      "loss": 1.2832,
      "step": 663
    },
    {
      "epoch": 13.44,
      "learning_rate": 0.00011530612244897961,
      "loss": 1.3012,
      "step": 664
    },
    {
      "epoch": 13.46,
      "learning_rate": 0.00011517857142857143,
      "loss": 1.2857,
      "step": 665
    },
    {
      "epoch": 13.48,
      "learning_rate": 0.00011505102040816327,
      "loss": 1.2855,
      "step": 666
    },
    {
      "epoch": 13.5,
      "learning_rate": 0.00011492346938775512,
      "loss": 1.3077,
      "step": 667
    },
    {
      "epoch": 13.52,
      "learning_rate": 0.00011479591836734696,
      "loss": 1.3139,
      "step": 668
    },
    {
      "epoch": 13.54,
      "learning_rate": 0.00011466836734693878,
      "loss": 1.3138,
      "step": 669
    },
    {
      "epoch": 13.56,
      "learning_rate": 0.00011454081632653062,
      "loss": 1.2808,
      "step": 670
    },
    {
      "epoch": 13.58,
      "learning_rate": 0.00011441326530612247,
      "loss": 1.2492,
      "step": 671
    },
    {
      "epoch": 13.6,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.2027,
      "step": 672
    },
    {
      "epoch": 13.62,
      "learning_rate": 0.00011415816326530613,
      "loss": 1.33,
      "step": 673
    },
    {
      "epoch": 13.64,
      "learning_rate": 0.00011403061224489797,
      "loss": 1.3112,
      "step": 674
    },
    {
      "epoch": 13.66,
      "learning_rate": 0.00011390306122448979,
      "loss": 1.2772,
      "step": 675
    },
    {
      "epoch": 13.68,
      "learning_rate": 0.00011377551020408163,
      "loss": 1.2701,
      "step": 676
    },
    {
      "epoch": 13.7,
      "learning_rate": 0.00011364795918367348,
      "loss": 1.1973,
      "step": 677
    },
    {
      "epoch": 13.72,
      "learning_rate": 0.0001135204081632653,
      "loss": 1.3124,
      "step": 678
    },
    {
      "epoch": 13.74,
      "learning_rate": 0.00011339285714285714,
      "loss": 1.3085,
      "step": 679
    },
    {
      "epoch": 13.76,
      "learning_rate": 0.00011326530612244898,
      "loss": 1.3457,
      "step": 680
    },
    {
      "epoch": 13.78,
      "learning_rate": 0.00011313775510204083,
      "loss": 1.3338,
      "step": 681
    },
    {
      "epoch": 13.8,
      "learning_rate": 0.00011301020408163266,
      "loss": 1.2753,
      "step": 682
    },
    {
      "epoch": 13.82,
      "learning_rate": 0.00011288265306122449,
      "loss": 1.2786,
      "step": 683
    },
    {
      "epoch": 13.84,
      "learning_rate": 0.00011275510204081634,
      "loss": 1.2584,
      "step": 684
    },
    {
      "epoch": 13.86,
      "learning_rate": 0.00011262755102040817,
      "loss": 1.2779,
      "step": 685
    },
    {
      "epoch": 13.88,
      "learning_rate": 0.00011250000000000001,
      "loss": 1.3502,
      "step": 686
    },
    {
      "epoch": 13.9,
      "learning_rate": 0.00011237244897959185,
      "loss": 1.3251,
      "step": 687
    },
    {
      "epoch": 13.92,
      "learning_rate": 0.00011224489795918367,
      "loss": 1.273,
      "step": 688
    },
    {
      "epoch": 13.94,
      "learning_rate": 0.00011211734693877552,
      "loss": 1.3341,
      "step": 689
    },
    {
      "epoch": 13.96,
      "learning_rate": 0.00011198979591836736,
      "loss": 1.2654,
      "step": 690
    },
    {
      "epoch": 13.98,
      "learning_rate": 0.00011186224489795918,
      "loss": 1.3333,
      "step": 691
    },
    {
      "epoch": 14.0,
      "learning_rate": 0.00011173469387755102,
      "loss": 1.3246,
      "step": 692
    },
    {
      "epoch": 14.02,
      "learning_rate": 0.00011160714285714287,
      "loss": 1.2547,
      "step": 693
    },
    {
      "epoch": 14.04,
      "learning_rate": 0.00011147959183673471,
      "loss": 1.208,
      "step": 694
    },
    {
      "epoch": 14.06,
      "learning_rate": 0.00011135204081632653,
      "loss": 1.223,
      "step": 695
    },
    {
      "epoch": 14.08,
      "learning_rate": 0.00011122448979591837,
      "loss": 1.2483,
      "step": 696
    },
    {
      "epoch": 14.1,
      "learning_rate": 0.00011109693877551022,
      "loss": 1.2823,
      "step": 697
    },
    {
      "epoch": 14.12,
      "learning_rate": 0.00011096938775510204,
      "loss": 1.2013,
      "step": 698
    },
    {
      "epoch": 14.14,
      "learning_rate": 0.00011084183673469388,
      "loss": 1.1883,
      "step": 699
    },
    {
      "epoch": 14.16,
      "learning_rate": 0.00011071428571428572,
      "loss": 1.2364,
      "step": 700
    },
    {
      "epoch": 14.18,
      "learning_rate": 0.00011058673469387754,
      "loss": 1.2069,
      "step": 701
    },
    {
      "epoch": 14.2,
      "learning_rate": 0.00011045918367346939,
      "loss": 1.1968,
      "step": 702
    },
    {
      "epoch": 14.22,
      "learning_rate": 0.00011033163265306123,
      "loss": 1.2236,
      "step": 703
    },
    {
      "epoch": 14.24,
      "learning_rate": 0.00011020408163265306,
      "loss": 1.1942,
      "step": 704
    },
    {
      "epoch": 14.26,
      "learning_rate": 0.0001100765306122449,
      "loss": 1.2561,
      "step": 705
    },
    {
      "epoch": 14.29,
      "learning_rate": 0.00010994897959183674,
      "loss": 1.1839,
      "step": 706
    },
    {
      "epoch": 14.31,
      "learning_rate": 0.00010982142857142858,
      "loss": 1.2128,
      "step": 707
    },
    {
      "epoch": 14.33,
      "learning_rate": 0.00010969387755102041,
      "loss": 1.3086,
      "step": 708
    },
    {
      "epoch": 14.35,
      "learning_rate": 0.00010956632653061226,
      "loss": 1.2379,
      "step": 709
    },
    {
      "epoch": 14.37,
      "learning_rate": 0.0001094387755102041,
      "loss": 1.176,
      "step": 710
    },
    {
      "epoch": 14.39,
      "learning_rate": 0.00010931122448979592,
      "loss": 1.2105,
      "step": 711
    },
    {
      "epoch": 14.41,
      "learning_rate": 0.00010918367346938776,
      "loss": 1.2149,
      "step": 712
    },
    {
      "epoch": 14.43,
      "learning_rate": 0.0001090561224489796,
      "loss": 1.2392,
      "step": 713
    },
    {
      "epoch": 14.45,
      "learning_rate": 0.00010892857142857142,
      "loss": 1.2471,
      "step": 714
    },
    {
      "epoch": 14.47,
      "learning_rate": 0.00010880102040816327,
      "loss": 1.2561,
      "step": 715
    },
    {
      "epoch": 14.49,
      "learning_rate": 0.00010867346938775511,
      "loss": 1.2179,
      "step": 716
    },
    {
      "epoch": 14.51,
      "learning_rate": 0.00010854591836734696,
      "loss": 1.2459,
      "step": 717
    },
    {
      "epoch": 14.53,
      "learning_rate": 0.00010841836734693877,
      "loss": 1.2933,
      "step": 718
    },
    {
      "epoch": 14.55,
      "learning_rate": 0.00010829081632653062,
      "loss": 1.2862,
      "step": 719
    },
    {
      "epoch": 14.57,
      "learning_rate": 0.00010816326530612246,
      "loss": 1.2976,
      "step": 720
    },
    {
      "epoch": 14.59,
      "learning_rate": 0.00010803571428571428,
      "loss": 1.231,
      "step": 721
    },
    {
      "epoch": 14.61,
      "learning_rate": 0.00010790816326530613,
      "loss": 1.2464,
      "step": 722
    },
    {
      "epoch": 14.63,
      "learning_rate": 0.00010778061224489797,
      "loss": 1.2181,
      "step": 723
    },
    {
      "epoch": 14.65,
      "learning_rate": 0.00010765306122448979,
      "loss": 1.3307,
      "step": 724
    },
    {
      "epoch": 14.67,
      "learning_rate": 0.00010752551020408163,
      "loss": 1.1723,
      "step": 725
    },
    {
      "epoch": 14.69,
      "learning_rate": 0.00010739795918367348,
      "loss": 1.1528,
      "step": 726
    },
    {
      "epoch": 14.71,
      "learning_rate": 0.0001072704081632653,
      "loss": 1.215,
      "step": 727
    },
    {
      "epoch": 14.73,
      "learning_rate": 0.00010714285714285715,
      "loss": 1.2624,
      "step": 728
    },
    {
      "epoch": 14.75,
      "learning_rate": 0.00010701530612244898,
      "loss": 1.3117,
      "step": 729
    },
    {
      "epoch": 14.77,
      "learning_rate": 0.00010688775510204083,
      "loss": 1.2572,
      "step": 730
    },
    {
      "epoch": 14.79,
      "learning_rate": 0.00010676020408163266,
      "loss": 1.222,
      "step": 731
    },
    {
      "epoch": 14.81,
      "learning_rate": 0.0001066326530612245,
      "loss": 1.2881,
      "step": 732
    },
    {
      "epoch": 14.83,
      "learning_rate": 0.00010650510204081635,
      "loss": 1.2676,
      "step": 733
    },
    {
      "epoch": 14.85,
      "learning_rate": 0.00010637755102040816,
      "loss": 1.2734,
      "step": 734
    },
    {
      "epoch": 14.87,
      "learning_rate": 0.00010625000000000001,
      "loss": 1.2885,
      "step": 735
    },
    {
      "epoch": 14.89,
      "learning_rate": 0.00010612244897959185,
      "loss": 1.2764,
      "step": 736
    },
    {
      "epoch": 14.91,
      "learning_rate": 0.00010599489795918367,
      "loss": 1.3267,
      "step": 737
    },
    {
      "epoch": 14.93,
      "learning_rate": 0.00010586734693877551,
      "loss": 1.2445,
      "step": 738
    },
    {
      "epoch": 14.95,
      "learning_rate": 0.00010573979591836736,
      "loss": 1.3359,
      "step": 739
    },
    {
      "epoch": 14.97,
      "learning_rate": 0.00010561224489795918,
      "loss": 1.2508,
      "step": 740
    },
    {
      "epoch": 14.99,
      "learning_rate": 0.00010548469387755102,
      "loss": 1.2227,
      "step": 741
    },
    {
      "epoch": 15.01,
      "learning_rate": 0.00010535714285714286,
      "loss": 1.1889,
      "step": 742
    },
    {
      "epoch": 15.03,
      "learning_rate": 0.00010522959183673471,
      "loss": 1.1919,
      "step": 743
    },
    {
      "epoch": 15.05,
      "learning_rate": 0.00010510204081632653,
      "loss": 1.2383,
      "step": 744
    },
    {
      "epoch": 15.07,
      "learning_rate": 0.00010497448979591837,
      "loss": 1.2401,
      "step": 745
    },
    {
      "epoch": 15.09,
      "learning_rate": 0.00010484693877551021,
      "loss": 1.2015,
      "step": 746
    },
    {
      "epoch": 15.11,
      "learning_rate": 0.00010471938775510203,
      "loss": 1.1509,
      "step": 747
    },
    {
      "epoch": 15.13,
      "learning_rate": 0.00010459183673469388,
      "loss": 1.1878,
      "step": 748
    },
    {
      "epoch": 15.16,
      "learning_rate": 0.00010446428571428572,
      "loss": 1.1706,
      "step": 749
    },
    {
      "epoch": 15.18,
      "learning_rate": 0.00010433673469387755,
      "loss": 1.1285,
      "step": 750
    },
    {
      "epoch": 15.2,
      "learning_rate": 0.0001042091836734694,
      "loss": 1.1608,
      "step": 751
    },
    {
      "epoch": 15.22,
      "learning_rate": 0.00010408163265306123,
      "loss": 1.1178,
      "step": 752
    },
    {
      "epoch": 15.24,
      "learning_rate": 0.00010395408163265306,
      "loss": 1.1293,
      "step": 753
    },
    {
      "epoch": 15.26,
      "learning_rate": 0.0001038265306122449,
      "loss": 1.2306,
      "step": 754
    },
    {
      "epoch": 15.28,
      "learning_rate": 0.00010369897959183675,
      "loss": 1.1541,
      "step": 755
    },
    {
      "epoch": 15.3,
      "learning_rate": 0.00010357142857142859,
      "loss": 1.1702,
      "step": 756
    },
    {
      "epoch": 15.32,
      "learning_rate": 0.00010344387755102041,
      "loss": 1.2119,
      "step": 757
    },
    {
      "epoch": 15.34,
      "learning_rate": 0.00010331632653061225,
      "loss": 1.2239,
      "step": 758
    },
    {
      "epoch": 15.36,
      "learning_rate": 0.0001031887755102041,
      "loss": 1.2019,
      "step": 759
    },
    {
      "epoch": 15.38,
      "learning_rate": 0.00010306122448979591,
      "loss": 1.2197,
      "step": 760
    },
    {
      "epoch": 15.4,
      "learning_rate": 0.00010293367346938776,
      "loss": 1.1769,
      "step": 761
    },
    {
      "epoch": 15.42,
      "learning_rate": 0.0001028061224489796,
      "loss": 1.1907,
      "step": 762
    },
    {
      "epoch": 15.44,
      "learning_rate": 0.00010267857142857142,
      "loss": 1.2089,
      "step": 763
    },
    {
      "epoch": 15.46,
      "learning_rate": 0.00010255102040816327,
      "loss": 1.1335,
      "step": 764
    },
    {
      "epoch": 15.48,
      "learning_rate": 0.00010242346938775511,
      "loss": 1.1633,
      "step": 765
    },
    {
      "epoch": 15.5,
      "learning_rate": 0.00010229591836734695,
      "loss": 1.1578,
      "step": 766
    },
    {
      "epoch": 15.52,
      "learning_rate": 0.00010216836734693877,
      "loss": 1.2236,
      "step": 767
    },
    {
      "epoch": 15.54,
      "learning_rate": 0.00010204081632653062,
      "loss": 1.1941,
      "step": 768
    },
    {
      "epoch": 15.56,
      "learning_rate": 0.00010191326530612246,
      "loss": 1.2666,
      "step": 769
    },
    {
      "epoch": 15.58,
      "learning_rate": 0.00010178571428571428,
      "loss": 1.1232,
      "step": 770
    },
    {
      "epoch": 15.6,
      "learning_rate": 0.00010165816326530612,
      "loss": 1.2242,
      "step": 771
    },
    {
      "epoch": 15.62,
      "learning_rate": 0.00010153061224489797,
      "loss": 1.1852,
      "step": 772
    },
    {
      "epoch": 15.64,
      "learning_rate": 0.0001014030612244898,
      "loss": 1.2626,
      "step": 773
    },
    {
      "epoch": 15.66,
      "learning_rate": 0.00010127551020408164,
      "loss": 1.1873,
      "step": 774
    },
    {
      "epoch": 15.68,
      "learning_rate": 0.00010114795918367349,
      "loss": 1.3005,
      "step": 775
    },
    {
      "epoch": 15.7,
      "learning_rate": 0.0001010204081632653,
      "loss": 1.1904,
      "step": 776
    },
    {
      "epoch": 15.72,
      "learning_rate": 0.00010089285714285715,
      "loss": 1.2927,
      "step": 777
    },
    {
      "epoch": 15.74,
      "learning_rate": 0.00010076530612244899,
      "loss": 1.179,
      "step": 778
    },
    {
      "epoch": 15.76,
      "learning_rate": 0.00010063775510204084,
      "loss": 1.2027,
      "step": 779
    },
    {
      "epoch": 15.78,
      "learning_rate": 0.00010051020408163265,
      "loss": 1.2428,
      "step": 780
    },
    {
      "epoch": 15.8,
      "learning_rate": 0.0001003826530612245,
      "loss": 1.2324,
      "step": 781
    },
    {
      "epoch": 15.82,
      "learning_rate": 0.00010025510204081634,
      "loss": 1.1251,
      "step": 782
    },
    {
      "epoch": 15.84,
      "learning_rate": 0.00010012755102040816,
      "loss": 1.2405,
      "step": 783
    },
    {
      "epoch": 15.86,
      "learning_rate": 0.0001,
      "loss": 1.2005,
      "step": 784
    },
    {
      "epoch": 15.88,
      "learning_rate": 9.987244897959184e-05,
      "loss": 1.2259,
      "step": 785
    },
    {
      "epoch": 15.9,
      "learning_rate": 9.974489795918368e-05,
      "loss": 1.1576,
      "step": 786
    },
    {
      "epoch": 15.92,
      "learning_rate": 9.961734693877551e-05,
      "loss": 1.1834,
      "step": 787
    },
    {
      "epoch": 15.94,
      "learning_rate": 9.948979591836736e-05,
      "loss": 1.2396,
      "step": 788
    },
    {
      "epoch": 15.96,
      "learning_rate": 9.936224489795919e-05,
      "loss": 1.1865,
      "step": 789
    },
    {
      "epoch": 15.98,
      "learning_rate": 9.923469387755102e-05,
      "loss": 1.2356,
      "step": 790
    },
    {
      "epoch": 16.01,
      "learning_rate": 9.910714285714286e-05,
      "loss": 1.2639,
      "step": 791
    },
    {
      "epoch": 16.03,
      "learning_rate": 9.897959183673469e-05,
      "loss": 1.1216,
      "step": 792
    },
    {
      "epoch": 16.05,
      "learning_rate": 9.885204081632652e-05,
      "loss": 1.1051,
      "step": 793
    },
    {
      "epoch": 16.07,
      "learning_rate": 9.872448979591837e-05,
      "loss": 1.0864,
      "step": 794
    },
    {
      "epoch": 16.09,
      "learning_rate": 9.859693877551021e-05,
      "loss": 1.182,
      "step": 795
    },
    {
      "epoch": 16.11,
      "learning_rate": 9.846938775510204e-05,
      "loss": 1.1272,
      "step": 796
    },
    {
      "epoch": 16.13,
      "learning_rate": 9.834183673469389e-05,
      "loss": 1.1946,
      "step": 797
    },
    {
      "epoch": 16.15,
      "learning_rate": 9.821428571428572e-05,
      "loss": 1.0875,
      "step": 798
    },
    {
      "epoch": 16.17,
      "learning_rate": 9.808673469387756e-05,
      "loss": 1.1671,
      "step": 799
    },
    {
      "epoch": 16.19,
      "learning_rate": 9.79591836734694e-05,
      "loss": 1.1502,
      "step": 800
    },
    {
      "epoch": 16.21,
      "learning_rate": 9.783163265306124e-05,
      "loss": 1.19,
      "step": 801
    },
    {
      "epoch": 16.23,
      "learning_rate": 9.770408163265307e-05,
      "loss": 1.1258,
      "step": 802
    },
    {
      "epoch": 16.25,
      "learning_rate": 9.75765306122449e-05,
      "loss": 1.1765,
      "step": 803
    },
    {
      "epoch": 16.27,
      "learning_rate": 9.744897959183674e-05,
      "loss": 1.1217,
      "step": 804
    },
    {
      "epoch": 16.29,
      "learning_rate": 9.732142857142858e-05,
      "loss": 1.1293,
      "step": 805
    },
    {
      "epoch": 16.31,
      "learning_rate": 9.719387755102042e-05,
      "loss": 1.17,
      "step": 806
    },
    {
      "epoch": 16.33,
      "learning_rate": 9.706632653061225e-05,
      "loss": 1.17,
      "step": 807
    },
    {
      "epoch": 16.35,
      "learning_rate": 9.693877551020408e-05,
      "loss": 1.2004,
      "step": 808
    },
    {
      "epoch": 16.37,
      "learning_rate": 9.681122448979593e-05,
      "loss": 1.1648,
      "step": 809
    },
    {
      "epoch": 16.39,
      "learning_rate": 9.668367346938776e-05,
      "loss": 1.0688,
      "step": 810
    },
    {
      "epoch": 16.41,
      "learning_rate": 9.655612244897959e-05,
      "loss": 1.1607,
      "step": 811
    },
    {
      "epoch": 16.43,
      "learning_rate": 9.642857142857143e-05,
      "loss": 1.1298,
      "step": 812
    },
    {
      "epoch": 16.45,
      "learning_rate": 9.630102040816326e-05,
      "loss": 1.1064,
      "step": 813
    },
    {
      "epoch": 16.47,
      "learning_rate": 9.617346938775511e-05,
      "loss": 1.1472,
      "step": 814
    },
    {
      "epoch": 16.49,
      "learning_rate": 9.604591836734694e-05,
      "loss": 1.1577,
      "step": 815
    },
    {
      "epoch": 16.51,
      "learning_rate": 9.591836734693878e-05,
      "loss": 1.1436,
      "step": 816
    },
    {
      "epoch": 16.53,
      "learning_rate": 9.579081632653061e-05,
      "loss": 1.1657,
      "step": 817
    },
    {
      "epoch": 16.55,
      "learning_rate": 9.566326530612246e-05,
      "loss": 1.1147,
      "step": 818
    },
    {
      "epoch": 16.57,
      "learning_rate": 9.553571428571429e-05,
      "loss": 1.1839,
      "step": 819
    },
    {
      "epoch": 16.59,
      "learning_rate": 9.540816326530613e-05,
      "loss": 1.1298,
      "step": 820
    },
    {
      "epoch": 16.61,
      "learning_rate": 9.528061224489796e-05,
      "loss": 1.2141,
      "step": 821
    },
    {
      "epoch": 16.63,
      "learning_rate": 9.515306122448981e-05,
      "loss": 1.2045,
      "step": 822
    },
    {
      "epoch": 16.65,
      "learning_rate": 9.502551020408164e-05,
      "loss": 1.1791,
      "step": 823
    },
    {
      "epoch": 16.67,
      "learning_rate": 9.489795918367348e-05,
      "loss": 1.1137,
      "step": 824
    },
    {
      "epoch": 16.69,
      "learning_rate": 9.477040816326531e-05,
      "loss": 1.1312,
      "step": 825
    },
    {
      "epoch": 16.71,
      "learning_rate": 9.464285714285715e-05,
      "loss": 1.1102,
      "step": 826
    },
    {
      "epoch": 16.73,
      "learning_rate": 9.451530612244899e-05,
      "loss": 1.1865,
      "step": 827
    },
    {
      "epoch": 16.75,
      "learning_rate": 9.438775510204082e-05,
      "loss": 1.1232,
      "step": 828
    },
    {
      "epoch": 16.77,
      "learning_rate": 9.426020408163265e-05,
      "loss": 1.2068,
      "step": 829
    },
    {
      "epoch": 16.79,
      "learning_rate": 9.41326530612245e-05,
      "loss": 1.1864,
      "step": 830
    },
    {
      "epoch": 16.81,
      "learning_rate": 9.400510204081633e-05,
      "loss": 1.2195,
      "step": 831
    },
    {
      "epoch": 16.83,
      "learning_rate": 9.387755102040817e-05,
      "loss": 1.2063,
      "step": 832
    },
    {
      "epoch": 16.85,
      "learning_rate": 9.375e-05,
      "loss": 1.1455,
      "step": 833
    },
    {
      "epoch": 16.88,
      "learning_rate": 9.362244897959183e-05,
      "loss": 1.1819,
      "step": 834
    },
    {
      "epoch": 16.9,
      "learning_rate": 9.349489795918368e-05,
      "loss": 1.1887,
      "step": 835
    },
    {
      "epoch": 16.92,
      "learning_rate": 9.336734693877551e-05,
      "loss": 1.1557,
      "step": 836
    },
    {
      "epoch": 16.94,
      "learning_rate": 9.323979591836735e-05,
      "loss": 1.2094,
      "step": 837
    },
    {
      "epoch": 16.96,
      "learning_rate": 9.311224489795918e-05,
      "loss": 1.1512,
      "step": 838
    },
    {
      "epoch": 16.98,
      "learning_rate": 9.298469387755103e-05,
      "loss": 1.1463,
      "step": 839
    },
    {
      "epoch": 17.0,
      "learning_rate": 9.285714285714286e-05,
      "loss": 1.155,
      "step": 840
    },
    {
      "epoch": 17.02,
      "learning_rate": 9.27295918367347e-05,
      "loss": 1.1292,
      "step": 841
    },
    {
      "epoch": 17.04,
      "learning_rate": 9.260204081632653e-05,
      "loss": 1.0996,
      "step": 842
    },
    {
      "epoch": 17.06,
      "learning_rate": 9.247448979591838e-05,
      "loss": 1.0662,
      "step": 843
    },
    {
      "epoch": 17.08,
      "learning_rate": 9.234693877551021e-05,
      "loss": 1.0931,
      "step": 844
    },
    {
      "epoch": 17.1,
      "learning_rate": 9.221938775510205e-05,
      "loss": 1.0727,
      "step": 845
    },
    {
      "epoch": 17.12,
      "learning_rate": 9.209183673469388e-05,
      "loss": 1.1043,
      "step": 846
    },
    {
      "epoch": 17.14,
      "learning_rate": 9.196428571428572e-05,
      "loss": 1.0594,
      "step": 847
    },
    {
      "epoch": 17.16,
      "learning_rate": 9.183673469387756e-05,
      "loss": 1.0952,
      "step": 848
    },
    {
      "epoch": 17.18,
      "learning_rate": 9.170918367346939e-05,
      "loss": 1.0639,
      "step": 849
    },
    {
      "epoch": 17.2,
      "learning_rate": 9.158163265306124e-05,
      "loss": 1.132,
      "step": 850
    },
    {
      "epoch": 17.22,
      "learning_rate": 9.145408163265307e-05,
      "loss": 1.1083,
      "step": 851
    },
    {
      "epoch": 17.24,
      "learning_rate": 9.13265306122449e-05,
      "loss": 1.1282,
      "step": 852
    },
    {
      "epoch": 17.26,
      "learning_rate": 9.119897959183674e-05,
      "loss": 1.0474,
      "step": 853
    },
    {
      "epoch": 17.28,
      "learning_rate": 9.107142857142857e-05,
      "loss": 1.1138,
      "step": 854
    },
    {
      "epoch": 17.3,
      "learning_rate": 9.094387755102042e-05,
      "loss": 1.1025,
      "step": 855
    },
    {
      "epoch": 17.32,
      "learning_rate": 9.081632653061225e-05,
      "loss": 1.0968,
      "step": 856
    },
    {
      "epoch": 17.34,
      "learning_rate": 9.068877551020408e-05,
      "loss": 1.1683,
      "step": 857
    },
    {
      "epoch": 17.36,
      "learning_rate": 9.056122448979592e-05,
      "loss": 1.0975,
      "step": 858
    },
    {
      "epoch": 17.38,
      "learning_rate": 9.043367346938775e-05,
      "loss": 1.1274,
      "step": 859
    },
    {
      "epoch": 17.4,
      "learning_rate": 9.030612244897958e-05,
      "loss": 1.0916,
      "step": 860
    },
    {
      "epoch": 17.42,
      "learning_rate": 9.017857142857143e-05,
      "loss": 1.0912,
      "step": 861
    },
    {
      "epoch": 17.44,
      "learning_rate": 9.005102040816327e-05,
      "loss": 1.0875,
      "step": 862
    },
    {
      "epoch": 17.46,
      "learning_rate": 8.99234693877551e-05,
      "loss": 1.05,
      "step": 863
    },
    {
      "epoch": 17.48,
      "learning_rate": 8.979591836734695e-05,
      "loss": 1.1418,
      "step": 864
    },
    {
      "epoch": 17.5,
      "learning_rate": 8.966836734693878e-05,
      "loss": 1.0609,
      "step": 865
    },
    {
      "epoch": 17.52,
      "learning_rate": 8.954081632653062e-05,
      "loss": 1.1611,
      "step": 866
    },
    {
      "epoch": 17.54,
      "learning_rate": 8.941326530612245e-05,
      "loss": 1.1065,
      "step": 867
    },
    {
      "epoch": 17.56,
      "learning_rate": 8.92857142857143e-05,
      "loss": 1.1611,
      "step": 868
    },
    {
      "epoch": 17.58,
      "learning_rate": 8.915816326530613e-05,
      "loss": 1.1398,
      "step": 869
    },
    {
      "epoch": 17.6,
      "learning_rate": 8.903061224489796e-05,
      "loss": 1.1055,
      "step": 870
    },
    {
      "epoch": 17.62,
      "learning_rate": 8.89030612244898e-05,
      "loss": 1.1314,
      "step": 871
    },
    {
      "epoch": 17.64,
      "learning_rate": 8.877551020408164e-05,
      "loss": 1.1084,
      "step": 872
    },
    {
      "epoch": 17.66,
      "learning_rate": 8.864795918367348e-05,
      "loss": 1.1254,
      "step": 873
    },
    {
      "epoch": 17.68,
      "learning_rate": 8.852040816326531e-05,
      "loss": 1.142,
      "step": 874
    },
    {
      "epoch": 17.7,
      "learning_rate": 8.839285714285714e-05,
      "loss": 1.1371,
      "step": 875
    },
    {
      "epoch": 17.72,
      "learning_rate": 8.826530612244899e-05,
      "loss": 1.1092,
      "step": 876
    },
    {
      "epoch": 17.75,
      "learning_rate": 8.813775510204082e-05,
      "loss": 1.161,
      "step": 877
    },
    {
      "epoch": 17.77,
      "learning_rate": 8.801020408163265e-05,
      "loss": 1.1044,
      "step": 878
    },
    {
      "epoch": 17.79,
      "learning_rate": 8.788265306122449e-05,
      "loss": 1.117,
      "step": 879
    },
    {
      "epoch": 17.81,
      "learning_rate": 8.775510204081632e-05,
      "loss": 1.1262,
      "step": 880
    },
    {
      "epoch": 17.83,
      "learning_rate": 8.762755102040817e-05,
      "loss": 1.0829,
      "step": 881
    },
    {
      "epoch": 17.85,
      "learning_rate": 8.75e-05,
      "loss": 1.1393,
      "step": 882
    },
    {
      "epoch": 17.87,
      "learning_rate": 8.737244897959183e-05,
      "loss": 1.1781,
      "step": 883
    },
    {
      "epoch": 17.89,
      "learning_rate": 8.724489795918367e-05,
      "loss": 1.1582,
      "step": 884
    },
    {
      "epoch": 17.91,
      "learning_rate": 8.711734693877552e-05,
      "loss": 1.1469,
      "step": 885
    },
    {
      "epoch": 17.93,
      "learning_rate": 8.698979591836735e-05,
      "loss": 1.1494,
      "step": 886
    },
    {
      "epoch": 17.95,
      "learning_rate": 8.68622448979592e-05,
      "loss": 1.1251,
      "step": 887
    },
    {
      "epoch": 17.97,
      "learning_rate": 8.673469387755102e-05,
      "loss": 1.1624,
      "step": 888
    },
    {
      "epoch": 17.99,
      "learning_rate": 8.660714285714287e-05,
      "loss": 1.0842,
      "step": 889
    },
    {
      "epoch": 18.01,
      "learning_rate": 8.64795918367347e-05,
      "loss": 1.1944,
      "step": 890
    },
    {
      "epoch": 18.03,
      "learning_rate": 8.635204081632653e-05,
      "loss": 1.0642,
      "step": 891
    },
    {
      "epoch": 18.05,
      "learning_rate": 8.622448979591838e-05,
      "loss": 1.0459,
      "step": 892
    },
    {
      "epoch": 18.07,
      "learning_rate": 8.60969387755102e-05,
      "loss": 1.0941,
      "step": 893
    },
    {
      "epoch": 18.09,
      "learning_rate": 8.596938775510205e-05,
      "loss": 1.0457,
      "step": 894
    },
    {
      "epoch": 18.11,
      "learning_rate": 8.584183673469388e-05,
      "loss": 1.1033,
      "step": 895
    },
    {
      "epoch": 18.13,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.0756,
      "step": 896
    },
    {
      "epoch": 18.15,
      "learning_rate": 8.558673469387756e-05,
      "loss": 1.0615,
      "step": 897
    },
    {
      "epoch": 18.17,
      "learning_rate": 8.545918367346939e-05,
      "loss": 1.0828,
      "step": 898
    },
    {
      "epoch": 18.19,
      "learning_rate": 8.533163265306123e-05,
      "loss": 1.1158,
      "step": 899
    },
    {
      "epoch": 18.21,
      "learning_rate": 8.520408163265306e-05,
      "loss": 1.0133,
      "step": 900
    }
  ],
  "logging_steps": 1,
  "max_steps": 1568,
  "num_train_epochs": 32,
  "save_steps": 100,
  "total_flos": 1.3323843726343987e+18,
  "trial_name": null,
  "trial_params": null
}