{
  "best_metric": 1.3873900175094604,
  "best_model_checkpoint": "./outputs/checkpoint-300",
  "epoch": 1.6666666666666665,
  "eval_steps": 300,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 2.8496,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.0102999566398115e-05,
      "loss": 2.3809,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.771212547196624e-05,
      "loss": 2.3604,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.020599913279623e-05,
      "loss": 2.2425,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.989700043360187e-05,
      "loss": 2.0888,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.781512503836436e-05,
      "loss": 1.9669,
      "step": 6
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.450980400142567e-05,
      "loss": 1.8589,
      "step": 7
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.030899869919434e-05,
      "loss": 1.7722,
      "step": 8
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.542425094393248e-05,
      "loss": 1.6765,
      "step": 9
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.999999999999999e-05,
      "loss": 1.611,
      "step": 10
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00010413926851582249,
      "loss": 1.5547,
      "step": 11
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00010791812460476247,
      "loss": 1.5342,
      "step": 12
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00011139433523068365,
      "loss": 1.5394,
      "step": 13
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00011461280356782378,
      "loss": 1.5291,
      "step": 14
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00011760912590556812,
      "loss": 1.4864,
      "step": 15
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00012041199826559246,
      "loss": 1.4938,
      "step": 16
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001230448921378274,
      "loss": 1.4965,
      "step": 17
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00012552725051033058,
      "loss": 1.4751,
      "step": 18
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00012787536009528286,
      "loss": 1.4768,
      "step": 19
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001301029995663981,
      "loss": 1.4578,
      "step": 20
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001322219294733919,
      "loss": 1.4627,
      "step": 21
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00013424226808222061,
      "loss": 1.4535,
      "step": 22
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00013617278360175927,
      "loss": 1.451,
      "step": 23
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001380211241711606,
      "loss": 1.4446,
      "step": 24
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00013979400086720374,
      "loss": 1.4443,
      "step": 25
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00014149733479708177,
      "loss": 1.4401,
      "step": 26
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00014313637641589873,
      "loss": 1.4506,
      "step": 27
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001447158031342219,
      "loss": 1.4289,
      "step": 28
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001462397997898956,
      "loss": 1.433,
      "step": 29
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00014771212547196622,
      "loss": 1.4335,
      "step": 30
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00014913616938342725,
      "loss": 1.4263,
      "step": 31
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001505149978319906,
      "loss": 1.4278,
      "step": 32
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00015185139398778873,
      "loss": 1.4219,
      "step": 33
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001531478917042255,
      "loss": 1.4195,
      "step": 34
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00015440680443502754,
      "loss": 1.4314,
      "step": 35
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00015563025007672872,
      "loss": 1.4326,
      "step": 36
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001568201724066995,
      "loss": 1.4224,
      "step": 37
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000157978359661681,
      "loss": 1.4233,
      "step": 38
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001591064607026499,
      "loss": 1.417,
      "step": 39
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001602059991327962,
      "loss": 1.417,
      "step": 40
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00016127838567197352,
      "loss": 1.41,
      "step": 41
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00016232492903979004,
      "loss": 1.4319,
      "step": 42
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00016334684555795862,
      "loss": 1.4218,
      "step": 43
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00016434526764861872,
      "loss": 1.4196,
      "step": 44
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00016532125137753433,
      "loss": 1.4157,
      "step": 45
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001662757831681574,
      "loss": 1.4251,
      "step": 46
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001672097857935717,
      "loss": 1.4248,
      "step": 47
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001681241237375587,
      "loss": 1.4189,
      "step": 48
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00016901960800285134,
      "loss": 1.4165,
      "step": 49
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016989700043360185,
      "loss": 1.4167,
      "step": 50
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017075701760979362,
      "loss": 1.4146,
      "step": 51
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001716003343634799,
      "loss": 1.4133,
      "step": 52
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001724275869600789,
      "loss": 1.4074,
      "step": 53
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017323937598229684,
      "loss": 1.4164,
      "step": 54
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017403626894942436,
      "loss": 1.4178,
      "step": 55
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017481880270062004,
      "loss": 1.4239,
      "step": 56
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017558748556724914,
      "loss": 1.4074,
      "step": 57
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001763427993562937,
      "loss": 1.4118,
      "step": 58
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001770852011642144,
      "loss": 1.4088,
      "step": 59
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017781512503836432,
      "loss": 1.4211,
      "step": 60
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00017853298350107669,
      "loss": 1.4019,
      "step": 61
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00017923916894982539,
      "loss": 1.4284,
      "step": 62
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00017993405494535816,
      "loss": 1.4092,
      "step": 63
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018061799739838867,
      "loss": 1.415,
      "step": 64
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018129133566428552,
      "loss": 1.4249,
      "step": 65
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00018195439355418684,
      "loss": 1.4114,
      "step": 66
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001826074802700826,
      "loss": 1.4209,
      "step": 67
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018325089127062364,
      "loss": 1.4141,
      "step": 68
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018388490907372552,
      "loss": 1.4092,
      "step": 69
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00018450980400142568,
      "loss": 1.4177,
      "step": 70
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00018512583487190751,
      "loss": 1.4134,
      "step": 71
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00018573324964312683,
      "loss": 1.4015,
      "step": 72
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018633228601204555,
      "loss": 1.4165,
      "step": 73
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001869231719730976,
      "loss": 1.4043,
      "step": 74
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00018750612633916996,
      "loss": 1.4045,
      "step": 75
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00018808135922807913,
      "loss": 1.4063,
      "step": 76
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00018864907251724816,
      "loss": 1.4057,
      "step": 77
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00018920946026904802,
      "loss": 1.4009,
      "step": 78
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00018976270912904412,
      "loss": 1.4017,
      "step": 79
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019030899869919432,
      "loss": 1.4172,
      "step": 80
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019084850188786495,
      "loss": 1.4061,
      "step": 81
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019138138523837166,
      "loss": 1.4047,
      "step": 82
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019190780923760738,
      "loss": 1.408,
      "step": 83
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019242792860618813,
      "loss": 1.4054,
      "step": 84
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019294189257142928,
      "loss": 1.399,
      "step": 85
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019344984512435672,
      "loss": 1.4015,
      "step": 86
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019395192526186183,
      "loss": 1.4108,
      "step": 87
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019444826721501686,
      "loss": 1.407,
      "step": 88
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019493900066449123,
      "loss": 1.4018,
      "step": 89
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019542425094393247,
      "loss": 1.4013,
      "step": 90
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019590413923210932,
      "loss": 1.4123,
      "step": 91
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001963787827345555,
      "loss": 1.4064,
      "step": 92
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001968482948553935,
      "loss": 1.4009,
      "step": 93
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019731278535996984,
      "loss": 1.4046,
      "step": 94
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019777236052888474,
      "loss": 1.4029,
      "step": 95
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019822712330395682,
      "loss": 1.4063,
      "step": 96
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019867717342662446,
      "loss": 1.3971,
      "step": 97
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019912260756924948,
      "loss": 1.3985,
      "step": 98
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019956351945975496,
      "loss": 1.402,
      "step": 99
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019999999999999998,
      "loss": 1.4014,
      "step": 100
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.3979,
      "step": 101
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019975,
      "loss": 1.4003,
      "step": 102
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019950000000000002,
      "loss": 1.3969,
      "step": 103
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019925,
      "loss": 1.4054,
      "step": 104
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000199,
      "loss": 1.3978,
      "step": 105
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019875,
      "loss": 1.3996,
      "step": 106
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019850000000000003,
      "loss": 1.3895,
      "step": 107
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019825,
      "loss": 1.3965,
      "step": 108
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.4077,
      "step": 109
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019775,
      "loss": 1.3999,
      "step": 110
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019750000000000003,
      "loss": 1.3975,
      "step": 111
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019725,
      "loss": 1.3985,
      "step": 112
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019700000000000002,
      "loss": 1.3939,
      "step": 113
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019675,
      "loss": 1.4033,
      "step": 114
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001965,
      "loss": 1.4035,
      "step": 115
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019625,
      "loss": 1.3979,
      "step": 116
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000196,
      "loss": 1.4002,
      "step": 117
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019575000000000001,
      "loss": 1.3949,
      "step": 118
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001955,
      "loss": 1.3906,
      "step": 119
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019525,
      "loss": 1.4039,
      "step": 120
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000195,
      "loss": 1.4,
      "step": 121
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019475000000000002,
      "loss": 1.3961,
      "step": 122
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001945,
      "loss": 1.3997,
      "step": 123
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019425,
      "loss": 1.414,
      "step": 124
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000194,
      "loss": 1.3942,
      "step": 125
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019375000000000002,
      "loss": 1.406,
      "step": 126
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019350000000000001,
      "loss": 1.4017,
      "step": 127
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019325,
      "loss": 1.3917,
      "step": 128
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000193,
      "loss": 1.3945,
      "step": 129
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019275,
      "loss": 1.3966,
      "step": 130
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019250000000000002,
      "loss": 1.3942,
      "step": 131
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019225,
      "loss": 1.3968,
      "step": 132
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.000192,
      "loss": 1.3921,
      "step": 133
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019175,
      "loss": 1.3931,
      "step": 134
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019150000000000002,
      "loss": 1.3917,
      "step": 135
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019125000000000001,
      "loss": 1.4025,
      "step": 136
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000191,
      "loss": 1.3997,
      "step": 137
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019075,
      "loss": 1.4027,
      "step": 138
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019050000000000002,
      "loss": 1.4068,
      "step": 139
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019025000000000002,
      "loss": 1.4075,
      "step": 140
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019,
      "loss": 1.3986,
      "step": 141
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00018975,
      "loss": 1.3996,
      "step": 142
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001895,
      "loss": 1.3973,
      "step": 143
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00018925000000000002,
      "loss": 1.4034,
      "step": 144
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018899999999999999,
      "loss": 1.4142,
      "step": 145
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018875,
      "loss": 1.3989,
      "step": 146
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001885,
      "loss": 1.3939,
      "step": 147
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00018825000000000002,
      "loss": 1.3948,
      "step": 148
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000188,
      "loss": 1.3951,
      "step": 149
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00018775,
      "loss": 1.3982,
      "step": 150
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001875,
      "loss": 1.3982,
      "step": 151
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00018725000000000002,
      "loss": 1.404,
      "step": 152
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018700000000000002,
      "loss": 1.3949,
      "step": 153
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018675,
      "loss": 1.3955,
      "step": 154
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001865,
      "loss": 1.3873,
      "step": 155
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018625,
      "loss": 1.3995,
      "step": 156
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018600000000000002,
      "loss": 1.389,
      "step": 157
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018575,
      "loss": 1.3944,
      "step": 158
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001855,
      "loss": 1.389,
      "step": 159
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018525,
      "loss": 1.4016,
      "step": 160
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018500000000000002,
      "loss": 1.3953,
      "step": 161
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018475,
      "loss": 1.4005,
      "step": 162
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001845,
      "loss": 1.3977,
      "step": 163
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018425,
      "loss": 1.3914,
      "step": 164
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.391,
      "step": 165
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018375,
      "loss": 1.4055,
      "step": 166
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018350000000000002,
      "loss": 1.3956,
      "step": 167
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018325,
      "loss": 1.3845,
      "step": 168
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.000183,
      "loss": 1.3882,
      "step": 169
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018275,
      "loss": 1.3891,
      "step": 170
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001825,
      "loss": 1.3868,
      "step": 171
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018225,
      "loss": 1.3909,
      "step": 172
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000182,
      "loss": 1.392,
      "step": 173
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018175,
      "loss": 1.3919,
      "step": 174
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001815,
      "loss": 1.3952,
      "step": 175
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018125000000000001,
      "loss": 1.3903,
      "step": 176
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000181,
      "loss": 1.4049,
      "step": 177
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018075000000000003,
      "loss": 1.3926,
      "step": 178
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001805,
      "loss": 1.3918,
      "step": 179
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00018025000000000002,
      "loss": 1.4015,
      "step": 180
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00018,
      "loss": 1.3907,
      "step": 181
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00017975,
      "loss": 1.3876,
      "step": 182
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001795,
      "loss": 1.3907,
      "step": 183
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00017925000000000002,
      "loss": 1.3936,
      "step": 184
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00017900000000000001,
      "loss": 1.3907,
      "step": 185
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00017875,
      "loss": 1.4007,
      "step": 186
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001785,
      "loss": 1.3944,
      "step": 187
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00017825,
      "loss": 1.3884,
      "step": 188
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.3892,
      "step": 189
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00017775,
      "loss": 1.3897,
      "step": 190
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001775,
      "loss": 1.3958,
      "step": 191
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00017725,
      "loss": 1.3904,
      "step": 192
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00017700000000000002,
      "loss": 1.3907,
      "step": 193
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00017675000000000001,
      "loss": 1.395,
      "step": 194
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001765,
      "loss": 1.3898,
      "step": 195
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00017625,
      "loss": 1.3949,
      "step": 196
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.3917,
      "step": 197
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00017575000000000002,
      "loss": 1.3944,
      "step": 198
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001755,
      "loss": 1.3873,
      "step": 199
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00017525,
      "loss": 1.389,
      "step": 200
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.000175,
      "loss": 1.3887,
      "step": 201
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00017475000000000002,
      "loss": 1.3971,
      "step": 202
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001745,
      "loss": 1.3831,
      "step": 203
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00017425,
      "loss": 1.3864,
      "step": 204
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.000174,
      "loss": 1.3874,
      "step": 205
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00017375000000000002,
      "loss": 1.3887,
      "step": 206
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00017350000000000002,
      "loss": 1.3884,
      "step": 207
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00017325,
      "loss": 1.3909,
      "step": 208
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.000173,
      "loss": 1.392,
      "step": 209
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00017275000000000002,
      "loss": 1.3925,
      "step": 210
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00017250000000000002,
      "loss": 1.3947,
      "step": 211
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00017225,
      "loss": 1.3922,
      "step": 212
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.000172,
      "loss": 1.3901,
      "step": 213
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017175,
      "loss": 1.3882,
      "step": 214
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017150000000000002,
      "loss": 1.3886,
      "step": 215
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00017125,
      "loss": 1.3953,
      "step": 216
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.000171,
      "loss": 1.3935,
      "step": 217
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017075,
      "loss": 1.3845,
      "step": 218
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00017050000000000002,
      "loss": 1.3986,
      "step": 219
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00017025,
      "loss": 1.3949,
      "step": 220
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017,
      "loss": 1.3914,
      "step": 221
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00016975,
      "loss": 1.3975,
      "step": 222
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00016950000000000003,
      "loss": 1.3911,
      "step": 223
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00016925,
      "loss": 1.3945,
      "step": 224
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00016900000000000002,
      "loss": 1.394,
      "step": 225
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00016875,
      "loss": 1.385,
      "step": 226
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001685,
      "loss": 1.3867,
      "step": 227
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00016825000000000002,
      "loss": 1.3976,
      "step": 228
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.000168,
      "loss": 1.392,
      "step": 229
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00016775,
      "loss": 1.3883,
      "step": 230
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001675,
      "loss": 1.3884,
      "step": 231
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00016725000000000003,
      "loss": 1.3893,
      "step": 232
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.000167,
      "loss": 1.3888,
      "step": 233
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00016675000000000001,
      "loss": 1.3886,
      "step": 234
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001665,
      "loss": 1.385,
      "step": 235
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00016625000000000003,
      "loss": 1.3939,
      "step": 236
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.000166,
      "loss": 1.3952,
      "step": 237
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00016575000000000002,
      "loss": 1.3913,
      "step": 238
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001655,
      "loss": 1.3863,
      "step": 239
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00016525,
      "loss": 1.3908,
      "step": 240
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.000165,
      "loss": 1.3864,
      "step": 241
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00016475,
      "loss": 1.3878,
      "step": 242
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00016450000000000001,
      "loss": 1.3949,
      "step": 243
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00016425,
      "loss": 1.3902,
      "step": 244
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.000164,
      "loss": 1.3879,
      "step": 245
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00016375,
      "loss": 1.3876,
      "step": 246
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00016350000000000002,
      "loss": 1.3838,
      "step": 247
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00016325,
      "loss": 1.3934,
      "step": 248
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.000163,
      "loss": 1.3891,
      "step": 249
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016275,
      "loss": 1.3939,
      "step": 250
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016250000000000002,
      "loss": 1.3834,
      "step": 251
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00016225000000000001,
      "loss": 1.3885,
      "step": 252
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.000162,
      "loss": 1.3857,
      "step": 253
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016175,
      "loss": 1.389,
      "step": 254
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001615,
      "loss": 1.3825,
      "step": 255
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00016125000000000002,
      "loss": 1.3851,
      "step": 256
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.000161,
      "loss": 1.3811,
      "step": 257
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00016075,
      "loss": 1.3925,
      "step": 258
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001605,
      "loss": 1.3881,
      "step": 259
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016025000000000002,
      "loss": 1.3926,
      "step": 260
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00016,
      "loss": 1.3912,
      "step": 261
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00015975,
      "loss": 1.3906,
      "step": 262
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001595,
      "loss": 1.3881,
      "step": 263
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00015925000000000002,
      "loss": 1.3869,
      "step": 264
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00015900000000000002,
      "loss": 1.3915,
      "step": 265
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00015875,
      "loss": 1.3899,
      "step": 266
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001585,
      "loss": 1.387,
      "step": 267
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00015825,
      "loss": 1.3874,
      "step": 268
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.3911,
      "step": 269
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00015774999999999999,
      "loss": 1.3832,
      "step": 270
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001575,
      "loss": 1.3916,
      "step": 271
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00015725,
      "loss": 1.3882,
      "step": 272
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00015700000000000002,
      "loss": 1.3844,
      "step": 273
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00015675,
      "loss": 1.391,
      "step": 274
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001565,
      "loss": 1.3868,
      "step": 275
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00015625,
      "loss": 1.384,
      "step": 276
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.3825,
      "step": 277
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00015575000000000002,
      "loss": 1.3843,
      "step": 278
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001555,
      "loss": 1.3842,
      "step": 279
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00015525,
      "loss": 1.3806,
      "step": 280
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.000155,
      "loss": 1.382,
      "step": 281
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00015475000000000002,
      "loss": 1.3885,
      "step": 282
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0001545,
      "loss": 1.3863,
      "step": 283
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00015425,
      "loss": 1.3881,
      "step": 284
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.000154,
      "loss": 1.3901,
      "step": 285
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00015375000000000002,
      "loss": 1.3802,
      "step": 286
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001535,
      "loss": 1.3903,
      "step": 287
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00015325,
      "loss": 1.3905,
      "step": 288
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.000153,
      "loss": 1.3858,
      "step": 289
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00015275000000000003,
      "loss": 1.3914,
      "step": 290
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001525,
      "loss": 1.3874,
      "step": 291
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00015225000000000001,
      "loss": 1.3876,
      "step": 292
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.000152,
      "loss": 1.385,
      "step": 293
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00015175,
      "loss": 1.3858,
      "step": 294
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001515,
      "loss": 1.3849,
      "step": 295
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00015125,
      "loss": 1.39,
      "step": 296
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.000151,
      "loss": 1.3869,
      "step": 297
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00015075,
      "loss": 1.3896,
      "step": 298
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001505,
      "loss": 1.3926,
      "step": 299
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00015025,
      "loss": 1.3823,
      "step": 300
    },
    {
      "epoch": 1.67,
      "eval_loss": 1.3873900175094604,
      "eval_runtime": 1.5789,
      "eval_samples_per_second": 63.336,
      "eval_steps_per_second": 4.433,
      "step": 300
    }
  ],
  "logging_steps": 1,
  "max_steps": 900,
  "num_train_epochs": 5,
  "save_steps": 300,
  "total_flos": 6.755002364618342e+16,
  "trial_name": null,
  "trial_params": null
}