{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.3015,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.4281,
      "step": 2
    },
    {
      "epoch": 0.03,
      "learning_rate": 3e-06,
      "loss": 1.4498,
      "step": 3
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.3943,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-06,
      "loss": 1.455,
      "step": 5
    },
    {
      "epoch": 0.07,
      "learning_rate": 6e-06,
      "loss": 1.4377,
      "step": 6
    },
    {
      "epoch": 0.08,
      "learning_rate": 7e-06,
      "loss": 1.5221,
      "step": 7
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.4089,
      "step": 8
    },
    {
      "epoch": 0.1,
      "learning_rate": 9e-06,
      "loss": 1.4574,
      "step": 9
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 1.3287,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.4322,
      "step": 11
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.2e-05,
      "loss": 1.4901,
      "step": 12
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.3765,
      "step": 13
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.4e-05,
      "loss": 1.4277,
      "step": 14
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.4893,
      "step": 15
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.2648,
      "step": 16
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.7e-05,
      "loss": 1.4851,
      "step": 17
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8e-05,
      "loss": 1.3235,
      "step": 18
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9e-05,
      "loss": 1.3674,
      "step": 19
    },
    {
      "epoch": 0.22,
      "learning_rate": 2e-05,
      "loss": 1.3619,
      "step": 20
    },
    {
      "epoch": 0.23,
      "learning_rate": 2e-05,
      "loss": 1.3814,
      "step": 21
    },
    {
      "epoch": 0.24,
      "learning_rate": 2e-05,
      "loss": 1.3902,
      "step": 22
    },
    {
      "epoch": 0.26,
      "learning_rate": 2e-05,
      "loss": 1.4724,
      "step": 23
    },
    {
      "epoch": 0.27,
      "learning_rate": 2e-05,
      "loss": 1.4082,
      "step": 24
    },
    {
      "epoch": 0.28,
      "learning_rate": 2e-05,
      "loss": 1.4753,
      "step": 25
    },
    {
      "epoch": 0.29,
      "learning_rate": 2e-05,
      "loss": 1.3142,
      "step": 26
    },
    {
      "epoch": 0.3,
      "learning_rate": 2e-05,
      "loss": 1.3124,
      "step": 27
    },
    {
      "epoch": 0.31,
      "learning_rate": 2e-05,
      "loss": 1.3489,
      "step": 28
    },
    {
      "epoch": 0.32,
      "learning_rate": 2e-05,
      "loss": 1.3424,
      "step": 29
    },
    {
      "epoch": 0.33,
      "learning_rate": 2e-05,
      "loss": 1.4087,
      "step": 30
    },
    {
      "epoch": 0.34,
      "learning_rate": 2e-05,
      "loss": 1.4061,
      "step": 31
    },
    {
      "epoch": 0.36,
      "learning_rate": 2e-05,
      "loss": 1.4727,
      "step": 32
    },
    {
      "epoch": 0.37,
      "learning_rate": 2e-05,
      "loss": 1.3032,
      "step": 33
    },
    {
      "epoch": 0.38,
      "learning_rate": 2e-05,
      "loss": 1.3527,
      "step": 34
    },
    {
      "epoch": 0.39,
      "learning_rate": 2e-05,
      "loss": 1.4014,
      "step": 35
    },
    {
      "epoch": 0.4,
      "learning_rate": 2e-05,
      "loss": 1.3887,
      "step": 36
    },
    {
      "epoch": 0.41,
      "learning_rate": 2e-05,
      "loss": 1.3897,
      "step": 37
    },
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 1.3574,
      "step": 38
    },
    {
      "epoch": 0.43,
      "learning_rate": 2e-05,
      "loss": 1.4434,
      "step": 39
    },
    {
      "epoch": 0.44,
      "learning_rate": 2e-05,
      "loss": 1.2705,
      "step": 40
    },
    {
      "epoch": 0.46,
      "learning_rate": 2e-05,
      "loss": 1.4504,
      "step": 41
    },
    {
      "epoch": 0.47,
      "learning_rate": 2e-05,
      "loss": 1.5292,
      "step": 42
    },
    {
      "epoch": 0.48,
      "learning_rate": 2e-05,
      "loss": 1.3911,
      "step": 43
    },
    {
      "epoch": 0.49,
      "learning_rate": 2e-05,
      "loss": 1.2904,
      "step": 44
    },
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 1.3152,
      "step": 45
    },
    {
      "epoch": 0.51,
      "learning_rate": 2e-05,
      "loss": 1.2907,
      "step": 46
    },
    {
      "epoch": 0.52,
      "learning_rate": 2e-05,
      "loss": 1.3705,
      "step": 47
    },
    {
      "epoch": 0.53,
      "learning_rate": 2e-05,
      "loss": 1.3643,
      "step": 48
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 1.4056,
      "step": 49
    },
    {
      "epoch": 0.56,
      "learning_rate": 2e-05,
      "loss": 1.502,
      "step": 50
    },
    {
      "epoch": 0.57,
      "learning_rate": 2e-05,
      "loss": 1.4266,
      "step": 51
    },
    {
      "epoch": 0.58,
      "learning_rate": 2e-05,
      "loss": 1.3296,
      "step": 52
    },
    {
      "epoch": 0.59,
      "learning_rate": 2e-05,
      "loss": 1.3355,
      "step": 53
    },
    {
      "epoch": 0.6,
      "learning_rate": 2e-05,
      "loss": 1.3942,
      "step": 54
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 1.3474,
      "step": 55
    },
    {
      "epoch": 0.62,
      "learning_rate": 2e-05,
      "loss": 1.3985,
      "step": 56
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 1.4883,
      "step": 57
    },
    {
      "epoch": 0.64,
      "learning_rate": 2e-05,
      "loss": 1.1958,
      "step": 58
    },
    {
      "epoch": 0.66,
      "learning_rate": 2e-05,
      "loss": 1.5296,
      "step": 59
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 1.3338,
      "step": 60
    },
    {
      "epoch": 0.68,
      "learning_rate": 2e-05,
      "loss": 1.2165,
      "step": 61
    },
    {
      "epoch": 0.69,
      "learning_rate": 2e-05,
      "loss": 1.3481,
      "step": 62
    },
    {
      "epoch": 0.7,
      "learning_rate": 2e-05,
      "loss": 1.3667,
      "step": 63
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 1.3844,
      "step": 64
    },
    {
      "epoch": 0.72,
      "learning_rate": 2e-05,
      "loss": 1.3475,
      "step": 65
    },
    {
      "epoch": 0.73,
      "learning_rate": 2e-05,
      "loss": 1.3695,
      "step": 66
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 1.212,
      "step": 67
    },
    {
      "epoch": 0.76,
      "learning_rate": 2e-05,
      "loss": 1.2033,
      "step": 68
    },
    {
      "epoch": 0.77,
      "learning_rate": 2e-05,
      "loss": 1.3812,
      "step": 69
    },
    {
      "epoch": 0.78,
      "learning_rate": 2e-05,
      "loss": 1.5949,
      "step": 70
    },
    {
      "epoch": 0.79,
      "learning_rate": 2e-05,
      "loss": 1.3994,
      "step": 71
    },
    {
      "epoch": 0.8,
      "learning_rate": 2e-05,
      "loss": 1.3861,
      "step": 72
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 1.2532,
      "step": 73
    },
    {
      "epoch": 0.82,
      "learning_rate": 2e-05,
      "loss": 1.3334,
      "step": 74
    },
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 1.3905,
      "step": 75
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "loss": 1.2549,
      "step": 76
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 1.3188,
      "step": 77
    },
    {
      "epoch": 0.87,
      "learning_rate": 2e-05,
      "loss": 1.2879,
      "step": 78
    },
    {
      "epoch": 0.88,
      "learning_rate": 2e-05,
      "loss": 1.3814,
      "step": 79
    },
    {
      "epoch": 0.89,
      "learning_rate": 2e-05,
      "loss": 1.4786,
      "step": 80
    },
    {
      "epoch": 0.9,
      "learning_rate": 2e-05,
      "loss": 1.2379,
      "step": 81
    },
    {
      "epoch": 0.91,
      "learning_rate": 2e-05,
      "loss": 1.2746,
      "step": 82
    },
    {
      "epoch": 0.92,
      "learning_rate": 2e-05,
      "loss": 1.341,
      "step": 83
    },
    {
      "epoch": 0.93,
      "learning_rate": 2e-05,
      "loss": 1.4664,
      "step": 84
    },
    {
      "epoch": 0.94,
      "learning_rate": 2e-05,
      "loss": 1.2359,
      "step": 85
    },
    {
      "epoch": 0.96,
      "learning_rate": 2e-05,
      "loss": 1.3863,
      "step": 86
    },
    {
      "epoch": 0.97,
      "learning_rate": 2e-05,
      "loss": 1.3409,
      "step": 87
    },
    {
      "epoch": 0.98,
      "learning_rate": 2e-05,
      "loss": 1.261,
      "step": 88
    },
    {
      "epoch": 0.99,
      "learning_rate": 2e-05,
      "loss": 1.4486,
      "step": 89
    },
    {
      "epoch": 1.0,
      "learning_rate": 2e-05,
      "loss": 1.3002,
      "step": 90
    },
    {
      "epoch": 1.01,
      "learning_rate": 2e-05,
      "loss": 1.3119,
      "step": 91
    },
    {
      "epoch": 1.02,
      "learning_rate": 2e-05,
      "loss": 1.3295,
      "step": 92
    },
    {
      "epoch": 1.03,
      "learning_rate": 2e-05,
      "loss": 1.3181,
      "step": 93
    },
    {
      "epoch": 1.04,
      "learning_rate": 2e-05,
      "loss": 1.2759,
      "step": 94
    },
    {
      "epoch": 1.06,
      "learning_rate": 2e-05,
      "loss": 1.309,
      "step": 95
    },
    {
      "epoch": 1.07,
      "learning_rate": 2e-05,
      "loss": 1.3587,
      "step": 96
    },
    {
      "epoch": 1.08,
      "learning_rate": 2e-05,
      "loss": 1.2882,
      "step": 97
    },
    {
      "epoch": 1.09,
      "learning_rate": 2e-05,
      "loss": 1.4208,
      "step": 98
    },
    {
      "epoch": 1.1,
      "learning_rate": 2e-05,
      "loss": 1.139,
      "step": 99
    },
    {
      "epoch": 1.11,
      "learning_rate": 2e-05,
      "loss": 1.1894,
      "step": 100
    },
    {
      "epoch": 1.12,
      "learning_rate": 2e-05,
      "loss": 1.3628,
      "step": 101
    },
    {
      "epoch": 1.13,
      "learning_rate": 2e-05,
      "loss": 1.27,
      "step": 102
    },
    {
      "epoch": 1.14,
      "learning_rate": 2e-05,
      "loss": 1.2595,
      "step": 103
    },
    {
      "epoch": 1.16,
      "learning_rate": 2e-05,
      "loss": 1.33,
      "step": 104
    },
    {
      "epoch": 1.17,
      "learning_rate": 2e-05,
      "loss": 1.4013,
      "step": 105
    },
    {
      "epoch": 1.18,
      "learning_rate": 2e-05,
      "loss": 1.1994,
      "step": 106
    },
    {
      "epoch": 1.19,
      "learning_rate": 2e-05,
      "loss": 1.3142,
      "step": 107
    },
    {
      "epoch": 1.2,
      "learning_rate": 2e-05,
      "loss": 1.4185,
      "step": 108
    },
    {
      "epoch": 1.21,
      "learning_rate": 2e-05,
      "loss": 1.2608,
      "step": 109
    },
    {
      "epoch": 1.22,
      "learning_rate": 2e-05,
      "loss": 1.3811,
      "step": 110
    },
    {
      "epoch": 1.23,
      "learning_rate": 2e-05,
      "loss": 1.3882,
      "step": 111
    },
    {
      "epoch": 1.24,
      "learning_rate": 2e-05,
      "loss": 1.2802,
      "step": 112
    },
    {
      "epoch": 1.26,
      "learning_rate": 2e-05,
      "loss": 1.1823,
      "step": 113
    },
    {
      "epoch": 1.27,
      "learning_rate": 2e-05,
      "loss": 1.2833,
      "step": 114
    },
    {
      "epoch": 1.28,
      "learning_rate": 2e-05,
      "loss": 1.4519,
      "step": 115
    },
    {
      "epoch": 1.29,
      "learning_rate": 2e-05,
      "loss": 1.2855,
      "step": 116
    },
    {
      "epoch": 1.3,
      "learning_rate": 2e-05,
      "loss": 1.2367,
      "step": 117
    },
    {
      "epoch": 1.31,
      "learning_rate": 2e-05,
      "loss": 1.3691,
      "step": 118
    },
    {
      "epoch": 1.32,
      "learning_rate": 2e-05,
      "loss": 1.2726,
      "step": 119
    },
    {
      "epoch": 1.33,
      "learning_rate": 2e-05,
      "loss": 1.2895,
      "step": 120
    },
    {
      "epoch": 1.34,
      "learning_rate": 2e-05,
      "loss": 1.3119,
      "step": 121
    },
    {
      "epoch": 1.36,
      "learning_rate": 2e-05,
      "loss": 1.279,
      "step": 122
    },
    {
      "epoch": 1.37,
      "learning_rate": 2e-05,
      "loss": 1.2333,
      "step": 123
    },
    {
      "epoch": 1.38,
      "learning_rate": 2e-05,
      "loss": 1.2206,
      "step": 124
    },
    {
      "epoch": 1.39,
      "learning_rate": 2e-05,
      "loss": 1.3423,
      "step": 125
    },
    {
      "epoch": 1.4,
      "learning_rate": 2e-05,
      "loss": 1.2588,
      "step": 126
    },
    {
      "epoch": 1.41,
      "learning_rate": 2e-05,
      "loss": 1.1811,
      "step": 127
    },
    {
      "epoch": 1.42,
      "learning_rate": 2e-05,
      "loss": 1.3719,
      "step": 128
    },
    {
      "epoch": 1.43,
      "learning_rate": 2e-05,
      "loss": 1.4495,
      "step": 129
    },
    {
      "epoch": 1.44,
      "learning_rate": 2e-05,
      "loss": 1.4182,
      "step": 130
    },
    {
      "epoch": 1.46,
      "learning_rate": 2e-05,
      "loss": 1.3553,
      "step": 131
    },
    {
      "epoch": 1.47,
      "learning_rate": 2e-05,
      "loss": 1.3562,
      "step": 132
    },
    {
      "epoch": 1.48,
      "learning_rate": 2e-05,
      "loss": 1.2997,
      "step": 133
    },
    {
      "epoch": 1.49,
      "learning_rate": 2e-05,
      "loss": 1.2518,
      "step": 134
    },
    {
      "epoch": 1.5,
      "learning_rate": 2e-05,
      "loss": 1.3145,
      "step": 135
    },
    {
      "epoch": 1.51,
      "learning_rate": 2e-05,
      "loss": 1.3927,
      "step": 136
    },
    {
      "epoch": 1.52,
      "learning_rate": 2e-05,
      "loss": 1.4503,
      "step": 137
    },
    {
      "epoch": 1.53,
      "learning_rate": 2e-05,
      "loss": 1.4147,
      "step": 138
    },
    {
      "epoch": 1.54,
      "learning_rate": 2e-05,
      "loss": 1.2696,
      "step": 139
    },
    {
      "epoch": 1.56,
      "learning_rate": 2e-05,
      "loss": 1.2751,
      "step": 140
    },
    {
      "epoch": 1.57,
      "learning_rate": 2e-05,
      "loss": 1.303,
      "step": 141
    },
    {
      "epoch": 1.58,
      "learning_rate": 2e-05,
      "loss": 1.295,
      "step": 142
    },
    {
      "epoch": 1.59,
      "learning_rate": 2e-05,
      "loss": 1.3347,
      "step": 143
    },
    {
      "epoch": 1.6,
      "learning_rate": 2e-05,
      "loss": 1.3195,
      "step": 144
    },
    {
      "epoch": 1.61,
      "learning_rate": 2e-05,
      "loss": 1.2815,
      "step": 145
    },
    {
      "epoch": 1.62,
      "learning_rate": 2e-05,
      "loss": 1.3128,
      "step": 146
    },
    {
      "epoch": 1.63,
      "learning_rate": 2e-05,
      "loss": 1.1768,
      "step": 147
    },
    {
      "epoch": 1.64,
      "learning_rate": 2e-05,
      "loss": 1.3368,
      "step": 148
    },
    {
      "epoch": 1.66,
      "learning_rate": 2e-05,
      "loss": 1.3746,
      "step": 149
    },
    {
      "epoch": 1.67,
      "learning_rate": 2e-05,
      "loss": 1.3906,
      "step": 150
    },
    {
      "epoch": 1.68,
      "learning_rate": 2e-05,
      "loss": 1.321,
      "step": 151
    },
    {
      "epoch": 1.69,
      "learning_rate": 2e-05,
      "loss": 1.2435,
      "step": 152
    },
    {
      "epoch": 1.7,
      "learning_rate": 2e-05,
      "loss": 1.3075,
      "step": 153
    },
    {
      "epoch": 1.71,
      "learning_rate": 2e-05,
      "loss": 1.3707,
      "step": 154
    },
    {
      "epoch": 1.72,
      "learning_rate": 2e-05,
      "loss": 1.3653,
      "step": 155
    },
    {
      "epoch": 1.73,
      "learning_rate": 2e-05,
      "loss": 1.3269,
      "step": 156
    },
    {
      "epoch": 1.74,
      "learning_rate": 2e-05,
      "loss": 1.2515,
      "step": 157
    },
    {
      "epoch": 1.76,
      "learning_rate": 2e-05,
      "loss": 1.3876,
      "step": 158
    },
    {
      "epoch": 1.77,
      "learning_rate": 2e-05,
      "loss": 1.1814,
      "step": 159
    },
    {
      "epoch": 1.78,
      "learning_rate": 2e-05,
      "loss": 1.3542,
      "step": 160
    },
    {
      "epoch": 1.79,
      "learning_rate": 2e-05,
      "loss": 1.2409,
      "step": 161
    },
    {
      "epoch": 1.8,
      "learning_rate": 2e-05,
      "loss": 1.4083,
      "step": 162
    },
    {
      "epoch": 1.81,
      "learning_rate": 2e-05,
      "loss": 1.3068,
      "step": 163
    },
    {
      "epoch": 1.82,
      "learning_rate": 2e-05,
      "loss": 1.3397,
      "step": 164
    },
    {
      "epoch": 1.83,
      "learning_rate": 2e-05,
      "loss": 1.3989,
      "step": 165
    },
    {
      "epoch": 1.84,
      "learning_rate": 2e-05,
      "loss": 1.1801,
      "step": 166
    },
    {
      "epoch": 1.86,
      "learning_rate": 2e-05,
      "loss": 1.231,
      "step": 167
    },
    {
      "epoch": 1.87,
      "learning_rate": 2e-05,
      "loss": 1.2747,
      "step": 168
    },
    {
      "epoch": 1.88,
      "learning_rate": 2e-05,
      "loss": 1.3697,
      "step": 169
    },
    {
      "epoch": 1.89,
      "learning_rate": 2e-05,
      "loss": 1.1737,
      "step": 170
    },
    {
      "epoch": 1.9,
      "learning_rate": 2e-05,
      "loss": 1.4005,
      "step": 171
    },
    {
      "epoch": 1.91,
      "learning_rate": 2e-05,
      "loss": 1.3068,
      "step": 172
    },
    {
      "epoch": 1.92,
      "learning_rate": 2e-05,
      "loss": 1.314,
      "step": 173
    },
    {
      "epoch": 1.93,
      "learning_rate": 2e-05,
      "loss": 1.2888,
      "step": 174
    },
    {
      "epoch": 1.94,
      "learning_rate": 2e-05,
      "loss": 1.4259,
      "step": 175
    },
    {
      "epoch": 1.96,
      "learning_rate": 2e-05,
      "loss": 1.346,
      "step": 176
    },
    {
      "epoch": 1.97,
      "learning_rate": 2e-05,
      "loss": 1.1118,
      "step": 177
    },
    {
      "epoch": 1.98,
      "learning_rate": 2e-05,
      "loss": 1.3533,
      "step": 178
    },
    {
      "epoch": 1.99,
      "learning_rate": 2e-05,
      "loss": 1.2803,
      "step": 179
    },
    {
      "epoch": 2.0,
      "learning_rate": 2e-05,
      "loss": 1.2263,
      "step": 180
    },
    {
      "epoch": 2.01,
      "learning_rate": 2e-05,
      "loss": 1.211,
      "step": 181
    },
    {
      "epoch": 2.02,
      "learning_rate": 2e-05,
      "loss": 1.3963,
      "step": 182
    },
    {
      "epoch": 2.03,
      "learning_rate": 2e-05,
      "loss": 1.3386,
      "step": 183
    },
    {
      "epoch": 2.04,
      "learning_rate": 2e-05,
      "loss": 1.2399,
      "step": 184
    },
    {
      "epoch": 2.06,
      "learning_rate": 2e-05,
      "loss": 1.2932,
      "step": 185
    },
    {
      "epoch": 2.07,
      "learning_rate": 2e-05,
      "loss": 1.3952,
      "step": 186
    },
    {
      "epoch": 2.08,
      "learning_rate": 2e-05,
      "loss": 1.3003,
      "step": 187
    },
    {
      "epoch": 2.09,
      "learning_rate": 2e-05,
      "loss": 1.2899,
      "step": 188
    },
    {
      "epoch": 2.1,
      "learning_rate": 2e-05,
      "loss": 1.363,
      "step": 189
    },
    {
      "epoch": 2.11,
      "learning_rate": 2e-05,
      "loss": 1.2344,
      "step": 190
    },
    {
      "epoch": 2.12,
      "learning_rate": 2e-05,
      "loss": 1.1305,
      "step": 191
    },
    {
      "epoch": 2.13,
      "learning_rate": 2e-05,
      "loss": 1.186,
      "step": 192
    },
    {
      "epoch": 2.14,
      "learning_rate": 2e-05,
      "loss": 1.2804,
      "step": 193
    },
    {
      "epoch": 2.16,
      "learning_rate": 2e-05,
      "loss": 1.1893,
      "step": 194
    },
    {
      "epoch": 2.17,
      "learning_rate": 2e-05,
      "loss": 1.2607,
      "step": 195
    },
    {
      "epoch": 2.18,
      "learning_rate": 2e-05,
      "loss": 1.2015,
      "step": 196
    },
    {
      "epoch": 2.19,
      "learning_rate": 2e-05,
      "loss": 1.3948,
      "step": 197
    },
    {
      "epoch": 2.2,
      "learning_rate": 2e-05,
      "loss": 1.2904,
      "step": 198
    },
    {
      "epoch": 2.21,
      "learning_rate": 2e-05,
      "loss": 1.4623,
      "step": 199
    },
    {
      "epoch": 2.22,
      "learning_rate": 2e-05,
      "loss": 1.3776,
      "step": 200
    },
    {
      "epoch": 2.23,
      "learning_rate": 2e-05,
      "loss": 1.2358,
      "step": 201
    },
    {
      "epoch": 2.24,
      "learning_rate": 2e-05,
      "loss": 1.2964,
      "step": 202
    },
    {
      "epoch": 2.26,
      "learning_rate": 2e-05,
      "loss": 1.095,
      "step": 203
    },
    {
      "epoch": 2.27,
      "learning_rate": 2e-05,
      "loss": 1.3107,
      "step": 204
    },
    {
      "epoch": 2.28,
      "learning_rate": 2e-05,
      "loss": 1.1573,
      "step": 205
    },
    {
      "epoch": 2.29,
      "learning_rate": 2e-05,
      "loss": 1.2963,
      "step": 206
    },
    {
      "epoch": 2.3,
      "learning_rate": 2e-05,
      "loss": 1.212,
      "step": 207
    },
    {
      "epoch": 2.31,
      "learning_rate": 2e-05,
      "loss": 1.3345,
      "step": 208
    },
    {
      "epoch": 2.32,
      "learning_rate": 2e-05,
      "loss": 1.5012,
      "step": 209
    },
    {
      "epoch": 2.33,
      "learning_rate": 2e-05,
      "loss": 1.2649,
      "step": 210
    },
    {
      "epoch": 2.34,
      "learning_rate": 2e-05,
      "loss": 1.1612,
      "step": 211
    },
    {
      "epoch": 2.36,
      "learning_rate": 2e-05,
      "loss": 1.2271,
      "step": 212
    },
    {
      "epoch": 2.37,
      "learning_rate": 2e-05,
      "loss": 1.3223,
      "step": 213
    },
    {
      "epoch": 2.38,
      "learning_rate": 2e-05,
      "loss": 1.343,
      "step": 214
    },
    {
      "epoch": 2.39,
      "learning_rate": 2e-05,
      "loss": 1.3141,
      "step": 215
    },
    {
      "epoch": 2.4,
      "learning_rate": 2e-05,
      "loss": 1.3062,
      "step": 216
    },
    {
      "epoch": 2.41,
      "learning_rate": 2e-05,
      "loss": 1.3975,
      "step": 217
    },
    {
      "epoch": 2.42,
      "learning_rate": 2e-05,
      "loss": 1.1237,
      "step": 218
    },
    {
      "epoch": 2.43,
      "learning_rate": 2e-05,
      "loss": 1.2495,
      "step": 219
    },
    {
      "epoch": 2.44,
      "learning_rate": 2e-05,
      "loss": 1.419,
      "step": 220
    },
    {
      "epoch": 2.46,
      "learning_rate": 2e-05,
      "loss": 1.2452,
      "step": 221
    },
    {
      "epoch": 2.47,
      "learning_rate": 2e-05,
      "loss": 1.4173,
      "step": 222
    },
    {
      "epoch": 2.48,
      "learning_rate": 2e-05,
      "loss": 1.4226,
      "step": 223
    },
    {
      "epoch": 2.49,
      "learning_rate": 2e-05,
      "loss": 1.303,
      "step": 224
    },
    {
      "epoch": 2.5,
      "learning_rate": 2e-05,
      "loss": 1.3202,
      "step": 225
    },
    {
      "epoch": 2.51,
      "learning_rate": 2e-05,
      "loss": 1.3554,
      "step": 226
    },
    {
      "epoch": 2.52,
      "learning_rate": 2e-05,
      "loss": 1.1988,
      "step": 227
    },
    {
      "epoch": 2.53,
      "learning_rate": 2e-05,
      "loss": 1.2966,
      "step": 228
    },
    {
      "epoch": 2.54,
      "learning_rate": 2e-05,
      "loss": 1.1834,
      "step": 229
    },
    {
      "epoch": 2.56,
      "learning_rate": 2e-05,
      "loss": 1.204,
      "step": 230
    },
    {
      "epoch": 2.57,
      "learning_rate": 2e-05,
      "loss": 1.2432,
      "step": 231
    },
    {
      "epoch": 2.58,
      "learning_rate": 2e-05,
      "loss": 1.2509,
      "step": 232
    },
    {
      "epoch": 2.59,
      "learning_rate": 2e-05,
      "loss": 1.2474,
      "step": 233
    },
    {
      "epoch": 2.6,
      "learning_rate": 2e-05,
      "loss": 1.2901,
      "step": 234
    },
    {
      "epoch": 2.61,
      "learning_rate": 2e-05,
      "loss": 1.2185,
      "step": 235
    },
    {
      "epoch": 2.62,
      "learning_rate": 2e-05,
      "loss": 1.1084,
      "step": 236
    },
    {
      "epoch": 2.63,
      "learning_rate": 2e-05,
      "loss": 1.4245,
      "step": 237
    },
    {
      "epoch": 2.64,
      "learning_rate": 2e-05,
      "loss": 1.2993,
      "step": 238
    },
    {
      "epoch": 2.66,
      "learning_rate": 2e-05,
      "loss": 1.313,
      "step": 239
    },
    {
      "epoch": 2.67,
      "learning_rate": 2e-05,
      "loss": 1.3624,
      "step": 240
    },
    {
      "epoch": 2.68,
      "learning_rate": 2e-05,
      "loss": 1.1682,
      "step": 241
    },
    {
      "epoch": 2.69,
      "learning_rate": 2e-05,
      "loss": 1.2933,
      "step": 242
    },
    {
      "epoch": 2.7,
      "learning_rate": 2e-05,
      "loss": 1.243,
      "step": 243
    },
    {
      "epoch": 2.71,
      "learning_rate": 2e-05,
      "loss": 1.1929,
      "step": 244
    },
    {
      "epoch": 2.72,
      "learning_rate": 2e-05,
      "loss": 1.3383,
      "step": 245
    },
    {
      "epoch": 2.73,
      "learning_rate": 2e-05,
      "loss": 1.1987,
      "step": 246
    },
    {
      "epoch": 2.74,
      "learning_rate": 2e-05,
      "loss": 1.2616,
      "step": 247
    },
    {
      "epoch": 2.76,
      "learning_rate": 2e-05,
      "loss": 1.2453,
      "step": 248
    },
    {
      "epoch": 2.77,
      "learning_rate": 2e-05,
      "loss": 1.2939,
      "step": 249
    },
    {
      "epoch": 2.78,
      "learning_rate": 2e-05,
      "loss": 1.2291,
      "step": 250
    },
    {
      "epoch": 2.79,
      "learning_rate": 2e-05,
      "loss": 1.223,
      "step": 251
    },
    {
      "epoch": 2.8,
      "learning_rate": 2e-05,
      "loss": 1.2218,
      "step": 252
    },
    {
      "epoch": 2.81,
      "learning_rate": 2e-05,
      "loss": 1.325,
      "step": 253
    },
    {
      "epoch": 2.82,
      "learning_rate": 2e-05,
      "loss": 1.1948,
      "step": 254
    },
    {
      "epoch": 2.83,
      "learning_rate": 2e-05,
      "loss": 1.3043,
      "step": 255
    },
    {
      "epoch": 2.84,
      "learning_rate": 2e-05,
      "loss": 1.2954,
      "step": 256
    },
    {
      "epoch": 2.86,
      "learning_rate": 2e-05,
      "loss": 1.2569,
      "step": 257
    },
    {
      "epoch": 2.87,
      "learning_rate": 2e-05,
      "loss": 1.3089,
      "step": 258
    },
    {
      "epoch": 2.88,
      "learning_rate": 2e-05,
      "loss": 1.2996,
      "step": 259
    },
    {
      "epoch": 2.89,
      "learning_rate": 2e-05,
      "loss": 1.299,
      "step": 260
    },
    {
      "epoch": 2.9,
      "learning_rate": 2e-05,
      "loss": 1.2845,
      "step": 261
    },
    {
      "epoch": 2.91,
      "learning_rate": 2e-05,
      "loss": 1.1922,
      "step": 262
    },
    {
      "epoch": 2.92,
      "learning_rate": 2e-05,
      "loss": 1.1089,
      "step": 263
    },
    {
      "epoch": 2.93,
      "learning_rate": 2e-05,
      "loss": 1.2926,
      "step": 264
    },
    {
      "epoch": 2.94,
      "learning_rate": 2e-05,
      "loss": 1.2205,
      "step": 265
    },
    {
      "epoch": 2.96,
      "learning_rate": 2e-05,
      "loss": 1.2509,
      "step": 266
    },
    {
      "epoch": 2.97,
      "learning_rate": 2e-05,
      "loss": 1.3576,
      "step": 267
    },
    {
      "epoch": 2.98,
      "learning_rate": 2e-05,
      "loss": 1.3584,
      "step": 268
    },
    {
      "epoch": 2.99,
      "learning_rate": 2e-05,
      "loss": 1.2712,
      "step": 269
    },
    {
      "epoch": 3.0,
      "learning_rate": 2e-05,
      "loss": 1.3389,
      "step": 270
    },
    {
      "epoch": 3.01,
      "learning_rate": 2e-05,
      "loss": 1.217,
      "step": 271
    },
    {
      "epoch": 3.02,
      "learning_rate": 2e-05,
      "loss": 1.2596,
      "step": 272
    },
    {
      "epoch": 3.03,
      "learning_rate": 2e-05,
      "loss": 1.2238,
      "step": 273
    },
    {
      "epoch": 3.04,
      "learning_rate": 2e-05,
      "loss": 1.1841,
      "step": 274
    },
    {
      "epoch": 3.06,
      "learning_rate": 2e-05,
      "loss": 1.3192,
      "step": 275
    },
    {
      "epoch": 3.07,
      "learning_rate": 2e-05,
      "loss": 1.3277,
      "step": 276
    },
    {
      "epoch": 3.08,
      "learning_rate": 2e-05,
      "loss": 1.3483,
      "step": 277
    },
    {
      "epoch": 3.09,
      "learning_rate": 2e-05,
      "loss": 1.2256,
      "step": 278
    },
    {
      "epoch": 3.1,
      "learning_rate": 2e-05,
      "loss": 1.1878,
      "step": 279
    },
    {
      "epoch": 3.11,
      "learning_rate": 2e-05,
      "loss": 1.2736,
      "step": 280
    },
    {
      "epoch": 3.12,
      "learning_rate": 2e-05,
      "loss": 1.2108,
      "step": 281
    },
    {
      "epoch": 3.13,
      "learning_rate": 2e-05,
      "loss": 1.1168,
      "step": 282
    },
    {
      "epoch": 3.14,
      "learning_rate": 2e-05,
      "loss": 1.2841,
      "step": 283
    },
    {
      "epoch": 3.16,
      "learning_rate": 2e-05,
      "loss": 1.215,
      "step": 284
    },
    {
      "epoch": 3.17,
      "learning_rate": 2e-05,
      "loss": 1.1552,
      "step": 285
    },
    {
      "epoch": 3.18,
      "learning_rate": 2e-05,
      "loss": 1.2161,
      "step": 286
    },
    {
      "epoch": 3.19,
      "learning_rate": 2e-05,
      "loss": 1.3477,
      "step": 287
    },
    {
      "epoch": 3.2,
      "learning_rate": 2e-05,
      "loss": 1.2334,
      "step": 288
    },
    {
      "epoch": 3.21,
      "learning_rate": 2e-05,
      "loss": 1.3001,
      "step": 289
    },
    {
      "epoch": 3.22,
      "learning_rate": 2e-05,
      "loss": 1.0189,
      "step": 290
    },
    {
      "epoch": 3.23,
      "learning_rate": 2e-05,
      "loss": 1.254,
      "step": 291
    },
    {
      "epoch": 3.24,
      "learning_rate": 2e-05,
      "loss": 1.0806,
      "step": 292
    },
    {
      "epoch": 3.26,
      "learning_rate": 2e-05,
      "loss": 1.3138,
      "step": 293
    },
    {
      "epoch": 3.27,
      "learning_rate": 2e-05,
      "loss": 1.2069,
      "step": 294
    },
    {
      "epoch": 3.28,
      "learning_rate": 2e-05,
      "loss": 1.2564,
      "step": 295
    },
    {
      "epoch": 3.29,
      "learning_rate": 2e-05,
      "loss": 1.2159,
      "step": 296
    },
    {
      "epoch": 3.3,
      "learning_rate": 2e-05,
      "loss": 1.035,
      "step": 297
    },
    {
      "epoch": 3.31,
      "learning_rate": 2e-05,
      "loss": 1.3348,
      "step": 298
    },
    {
      "epoch": 3.32,
      "learning_rate": 2e-05,
      "loss": 1.1858,
      "step": 299
    },
    {
      "epoch": 3.33,
      "learning_rate": 2e-05,
      "loss": 1.2503,
      "step": 300
    },
    {
      "epoch": 3.34,
      "learning_rate": 2e-05,
      "loss": 1.2748,
      "step": 301
    },
    {
      "epoch": 3.36,
      "learning_rate": 2e-05,
      "loss": 1.2131,
      "step": 302
    },
    {
      "epoch": 3.37,
      "learning_rate": 2e-05,
      "loss": 1.2046,
      "step": 303
    },
    {
      "epoch": 3.38,
      "learning_rate": 2e-05,
      "loss": 1.2716,
      "step": 304
    },
    {
      "epoch": 3.39,
      "learning_rate": 2e-05,
      "loss": 1.3449,
      "step": 305
    },
    {
      "epoch": 3.4,
      "learning_rate": 2e-05,
      "loss": 1.1789,
      "step": 306
    },
    {
      "epoch": 3.41,
      "learning_rate": 2e-05,
      "loss": 1.2985,
      "step": 307
    },
    {
      "epoch": 3.42,
      "learning_rate": 2e-05,
      "loss": 1.2788,
      "step": 308
    },
    {
      "epoch": 3.43,
      "learning_rate": 2e-05,
      "loss": 1.2677,
      "step": 309
    },
    {
      "epoch": 3.44,
      "learning_rate": 2e-05,
      "loss": 1.2218,
      "step": 310
    },
    {
      "epoch": 3.46,
      "learning_rate": 2e-05,
      "loss": 1.271,
      "step": 311
    },
    {
      "epoch": 3.47,
      "learning_rate": 2e-05,
      "loss": 1.2715,
      "step": 312
    },
    {
      "epoch": 3.48,
      "learning_rate": 2e-05,
      "loss": 1.2005,
      "step": 313
    },
    {
      "epoch": 3.49,
      "learning_rate": 2e-05,
      "loss": 1.1717,
      "step": 314
    },
    {
      "epoch": 3.5,
      "learning_rate": 2e-05,
      "loss": 1.3096,
      "step": 315
    },
    {
      "epoch": 3.51,
      "learning_rate": 2e-05,
      "loss": 1.3051,
      "step": 316
    },
    {
      "epoch": 3.52,
      "learning_rate": 2e-05,
      "loss": 1.1878,
      "step": 317
    },
    {
      "epoch": 3.53,
      "learning_rate": 2e-05,
      "loss": 1.2418,
      "step": 318
    },
    {
      "epoch": 3.54,
      "learning_rate": 2e-05,
      "loss": 1.3962,
      "step": 319
    },
    {
      "epoch": 3.56,
      "learning_rate": 2e-05,
      "loss": 1.299,
      "step": 320
    },
    {
      "epoch": 3.57,
      "learning_rate": 2e-05,
      "loss": 1.3695,
      "step": 321
    },
    {
      "epoch": 3.58,
      "learning_rate": 2e-05,
      "loss": 1.1061,
      "step": 322
    },
    {
      "epoch": 3.59,
      "learning_rate": 2e-05,
      "loss": 1.2401,
      "step": 323
    },
    {
      "epoch": 3.6,
      "learning_rate": 2e-05,
      "loss": 1.3242,
      "step": 324
    },
    {
      "epoch": 3.61,
      "learning_rate": 2e-05,
      "loss": 1.2457,
      "step": 325
    },
    {
      "epoch": 3.62,
      "learning_rate": 2e-05,
      "loss": 1.2978,
      "step": 326
    },
    {
      "epoch": 3.63,
      "learning_rate": 2e-05,
      "loss": 1.3897,
      "step": 327
    },
    {
      "epoch": 3.64,
      "learning_rate": 2e-05,
      "loss": 1.2661,
      "step": 328
    },
    {
      "epoch": 3.66,
      "learning_rate": 2e-05,
      "loss": 1.2118,
      "step": 329
    },
    {
      "epoch": 3.67,
      "learning_rate": 2e-05,
      "loss": 1.1694,
      "step": 330
    },
    {
      "epoch": 3.68,
      "learning_rate": 2e-05,
      "loss": 1.3988,
      "step": 331
    },
    {
      "epoch": 3.69,
      "learning_rate": 2e-05,
      "loss": 1.2731,
      "step": 332
    },
    {
      "epoch": 3.7,
      "learning_rate": 2e-05,
      "loss": 1.2065,
      "step": 333
    },
    {
      "epoch": 3.71,
      "learning_rate": 2e-05,
      "loss": 1.2534,
      "step": 334
    },
    {
      "epoch": 3.72,
      "learning_rate": 2e-05,
      "loss": 1.27,
      "step": 335
    },
    {
      "epoch": 3.73,
      "learning_rate": 2e-05,
      "loss": 1.2694,
      "step": 336
    },
    {
      "epoch": 3.74,
      "learning_rate": 2e-05,
      "loss": 1.3454,
      "step": 337
    },
    {
      "epoch": 3.76,
      "learning_rate": 2e-05,
      "loss": 1.2267,
      "step": 338
    },
    {
      "epoch": 3.77,
      "learning_rate": 2e-05,
      "loss": 1.218,
      "step": 339
    },
    {
      "epoch": 3.78,
      "learning_rate": 2e-05,
      "loss": 1.2273,
      "step": 340
    },
    {
      "epoch": 3.79,
      "learning_rate": 2e-05,
      "loss": 1.2489,
      "step": 341
    },
    {
      "epoch": 3.8,
      "learning_rate": 2e-05,
      "loss": 1.2881,
      "step": 342
    },
    {
      "epoch": 3.81,
      "learning_rate": 2e-05,
      "loss": 1.2662,
      "step": 343
    },
    {
      "epoch": 3.82,
      "learning_rate": 2e-05,
      "loss": 1.2939,
      "step": 344
    },
    {
      "epoch": 3.83,
      "learning_rate": 2e-05,
      "loss": 1.2775,
      "step": 345
    },
    {
      "epoch": 3.84,
      "learning_rate": 2e-05,
      "loss": 1.2644,
      "step": 346
    },
    {
      "epoch": 3.86,
      "learning_rate": 2e-05,
      "loss": 1.2018,
      "step": 347
    },
    {
      "epoch": 3.87,
      "learning_rate": 2e-05,
      "loss": 1.2024,
      "step": 348
    },
    {
      "epoch": 3.88,
      "learning_rate": 2e-05,
      "loss": 1.1545,
      "step": 349
    },
    {
      "epoch": 3.89,
      "learning_rate": 2e-05,
      "loss": 1.2889,
      "step": 350
    },
    {
      "epoch": 3.9,
      "learning_rate": 2e-05,
      "loss": 1.325,
      "step": 351
    },
    {
      "epoch": 3.91,
      "learning_rate": 2e-05,
      "loss": 1.2361,
      "step": 352
    },
    {
      "epoch": 3.92,
      "learning_rate": 2e-05,
      "loss": 1.1623,
      "step": 353
    },
    {
      "epoch": 3.93,
      "learning_rate": 2e-05,
      "loss": 1.2293,
      "step": 354
    },
    {
      "epoch": 3.94,
      "learning_rate": 2e-05,
      "loss": 1.2276,
      "step": 355
    },
    {
      "epoch": 3.96,
      "learning_rate": 2e-05,
      "loss": 1.3927,
      "step": 356
    },
    {
      "epoch": 3.97,
      "learning_rate": 2e-05,
      "loss": 1.2086,
      "step": 357
    },
    {
      "epoch": 3.98,
      "learning_rate": 2e-05,
      "loss": 1.2342,
      "step": 358
    },
    {
      "epoch": 3.99,
      "learning_rate": 2e-05,
      "loss": 1.3277,
      "step": 359
    },
    {
      "epoch": 4.0,
      "learning_rate": 2e-05,
      "loss": 1.095,
      "step": 360
    },
    {
      "epoch": 4.01,
      "learning_rate": 2e-05,
      "loss": 1.2089,
      "step": 361
    },
    {
      "epoch": 4.02,
      "learning_rate": 2e-05,
      "loss": 1.1913,
      "step": 362
    },
    {
      "epoch": 4.03,
      "learning_rate": 2e-05,
      "loss": 1.2266,
      "step": 363
    },
    {
      "epoch": 4.04,
      "learning_rate": 2e-05,
      "loss": 1.2277,
      "step": 364
    },
    {
      "epoch": 4.06,
      "learning_rate": 2e-05,
      "loss": 1.1979,
      "step": 365
    },
    {
      "epoch": 4.07,
      "learning_rate": 2e-05,
      "loss": 1.0823,
      "step": 366
    },
    {
      "epoch": 4.08,
      "learning_rate": 2e-05,
      "loss": 1.154,
      "step": 367
    },
    {
      "epoch": 4.09,
      "learning_rate": 2e-05,
      "loss": 1.0512,
      "step": 368
    },
    {
      "epoch": 4.1,
      "learning_rate": 2e-05,
      "loss": 1.2045,
      "step": 369
    },
    {
      "epoch": 4.11,
      "learning_rate": 2e-05,
      "loss": 1.014,
      "step": 370
    },
    {
      "epoch": 4.12,
      "learning_rate": 2e-05,
      "loss": 1.3316,
      "step": 371
    },
    {
      "epoch": 4.13,
      "learning_rate": 2e-05,
      "loss": 1.203,
      "step": 372
    },
    {
      "epoch": 4.14,
      "learning_rate": 2e-05,
      "loss": 1.12,
      "step": 373
    },
    {
      "epoch": 4.16,
      "learning_rate": 2e-05,
      "loss": 1.1264,
      "step": 374
    },
    {
      "epoch": 4.17,
      "learning_rate": 2e-05,
      "loss": 1.1057,
      "step": 375
    },
    {
      "epoch": 4.18,
      "learning_rate": 2e-05,
      "loss": 1.2399,
      "step": 376
    },
    {
      "epoch": 4.19,
      "learning_rate": 2e-05,
      "loss": 1.1301,
      "step": 377
    },
    {
      "epoch": 4.2,
      "learning_rate": 2e-05,
      "loss": 1.3355,
      "step": 378
    },
    {
      "epoch": 4.21,
      "learning_rate": 2e-05,
      "loss": 1.1899,
      "step": 379
    },
    {
      "epoch": 4.22,
      "learning_rate": 2e-05,
      "loss": 1.2065,
      "step": 380
    },
    {
      "epoch": 4.23,
      "learning_rate": 2e-05,
      "loss": 1.136,
      "step": 381
    },
    {
      "epoch": 4.24,
      "learning_rate": 2e-05,
      "loss": 1.1253,
      "step": 382
    },
    {
      "epoch": 4.26,
      "learning_rate": 2e-05,
      "loss": 1.0939,
      "step": 383
    },
    {
      "epoch": 4.27,
      "learning_rate": 2e-05,
      "loss": 1.1914,
      "step": 384
    },
    {
      "epoch": 4.28,
      "learning_rate": 2e-05,
      "loss": 1.0254,
      "step": 385
    },
    {
      "epoch": 4.29,
      "learning_rate": 2e-05,
      "loss": 1.2813,
      "step": 386
    },
    {
      "epoch": 4.3,
      "learning_rate": 2e-05,
      "loss": 1.33,
      "step": 387
    },
    {
      "epoch": 4.31,
      "learning_rate": 2e-05,
      "loss": 1.2726,
      "step": 388
    },
    {
      "epoch": 4.32,
      "learning_rate": 2e-05,
      "loss": 1.285,
      "step": 389
    },
    {
      "epoch": 4.33,
      "learning_rate": 2e-05,
      "loss": 1.2668,
      "step": 390
    },
    {
      "epoch": 4.34,
      "learning_rate": 2e-05,
      "loss": 1.1492,
      "step": 391
    },
    {
      "epoch": 4.36,
      "learning_rate": 2e-05,
      "loss": 1.3813,
      "step": 392
    },
    {
      "epoch": 4.37,
      "learning_rate": 2e-05,
      "loss": 1.2568,
      "step": 393
    },
    {
      "epoch": 4.38,
      "learning_rate": 2e-05,
      "loss": 1.2187,
      "step": 394
    },
    {
      "epoch": 4.39,
      "learning_rate": 2e-05,
      "loss": 1.2138,
      "step": 395
    },
    {
      "epoch": 4.4,
      "learning_rate": 2e-05,
      "loss": 1.1566,
      "step": 396
    },
    {
      "epoch": 4.41,
      "learning_rate": 2e-05,
      "loss": 1.1737,
      "step": 397
    },
    {
      "epoch": 4.42,
      "learning_rate": 2e-05,
      "loss": 1.0587,
      "step": 398
    },
    {
      "epoch": 4.43,
      "learning_rate": 2e-05,
      "loss": 1.2795,
      "step": 399
    },
    {
      "epoch": 4.44,
      "learning_rate": 2e-05,
      "loss": 1.1618,
      "step": 400
    },
    {
      "epoch": 4.46,
      "learning_rate": 2e-05,
      "loss": 1.34,
      "step": 401
    },
    {
      "epoch": 4.47,
      "learning_rate": 2e-05,
      "loss": 1.209,
      "step": 402
    },
    {
      "epoch": 4.48,
      "learning_rate": 2e-05,
      "loss": 1.2528,
      "step": 403
    },
    {
      "epoch": 4.49,
      "learning_rate": 2e-05,
      "loss": 1.2385,
      "step": 404
    },
    {
      "epoch": 4.5,
      "learning_rate": 2e-05,
      "loss": 1.1926,
      "step": 405
    },
    {
      "epoch": 4.51,
      "learning_rate": 2e-05,
      "loss": 1.1949,
      "step": 406
    },
    {
      "epoch": 4.52,
      "learning_rate": 2e-05,
      "loss": 1.2489,
      "step": 407
    },
    {
      "epoch": 4.53,
      "learning_rate": 2e-05,
      "loss": 1.2361,
      "step": 408
    },
    {
      "epoch": 4.54,
      "learning_rate": 2e-05,
      "loss": 1.186,
      "step": 409
    },
    {
      "epoch": 4.56,
      "learning_rate": 2e-05,
      "loss": 1.2088,
      "step": 410
    },
    {
      "epoch": 4.57,
      "learning_rate": 2e-05,
      "loss": 1.2573,
      "step": 411
    },
    {
      "epoch": 4.58,
      "learning_rate": 2e-05,
      "loss": 1.3231,
      "step": 412
    },
    {
      "epoch": 4.59,
      "learning_rate": 2e-05,
      "loss": 1.1717,
      "step": 413
    },
    {
      "epoch": 4.6,
      "learning_rate": 2e-05,
      "loss": 1.2754,
      "step": 414
    },
    {
      "epoch": 4.61,
      "learning_rate": 2e-05,
      "loss": 1.1537,
      "step": 415
    },
    {
      "epoch": 4.62,
      "learning_rate": 2e-05,
      "loss": 1.3393,
      "step": 416
    },
    {
      "epoch": 4.63,
      "learning_rate": 2e-05,
      "loss": 1.3616,
      "step": 417
    },
    {
      "epoch": 4.64,
      "learning_rate": 2e-05,
      "loss": 1.2624,
      "step": 418
    },
    {
      "epoch": 4.66,
      "learning_rate": 2e-05,
      "loss": 1.3203,
      "step": 419
    },
    {
      "epoch": 4.67,
      "learning_rate": 2e-05,
      "loss": 1.1883,
      "step": 420
    },
    {
      "epoch": 4.68,
      "learning_rate": 2e-05,
      "loss": 1.1471,
      "step": 421
    },
    {
      "epoch": 4.69,
      "learning_rate": 2e-05,
      "loss": 1.2844,
      "step": 422
    },
    {
      "epoch": 4.7,
      "learning_rate": 2e-05,
      "loss": 1.1279,
      "step": 423
    },
    {
      "epoch": 4.71,
      "learning_rate": 2e-05,
      "loss": 1.1775,
      "step": 424
    },
    {
      "epoch": 4.72,
      "learning_rate": 2e-05,
      "loss": 1.172,
      "step": 425
    },
    {
      "epoch": 4.73,
      "learning_rate": 2e-05,
      "loss": 1.1898,
      "step": 426
    },
    {
      "epoch": 4.74,
      "learning_rate": 2e-05,
      "loss": 1.3115,
      "step": 427
    },
    {
      "epoch": 4.76,
      "learning_rate": 2e-05,
      "loss": 1.1819,
      "step": 428
    },
    {
      "epoch": 4.77,
      "learning_rate": 2e-05,
      "loss": 1.4133,
      "step": 429
    },
    {
      "epoch": 4.78,
      "learning_rate": 2e-05,
      "loss": 1.0906,
      "step": 430
    },
    {
      "epoch": 4.79,
      "learning_rate": 2e-05,
      "loss": 1.1073,
      "step": 431
    },
    {
      "epoch": 4.8,
      "learning_rate": 2e-05,
      "loss": 1.2781,
      "step": 432
    },
    {
      "epoch": 4.81,
      "learning_rate": 2e-05,
      "loss": 1.2681,
      "step": 433
    },
    {
      "epoch": 4.82,
      "learning_rate": 2e-05,
      "loss": 1.1153,
      "step": 434
    },
    {
      "epoch": 4.83,
      "learning_rate": 2e-05,
      "loss": 1.3497,
      "step": 435
    },
    {
      "epoch": 4.84,
      "learning_rate": 2e-05,
      "loss": 1.2134,
      "step": 436
    },
    {
      "epoch": 4.86,
      "learning_rate": 2e-05,
      "loss": 1.3535,
      "step": 437
    },
    {
      "epoch": 4.87,
      "learning_rate": 2e-05,
      "loss": 1.3021,
      "step": 438
    },
    {
      "epoch": 4.88,
      "learning_rate": 2e-05,
      "loss": 1.1148,
      "step": 439
    },
    {
      "epoch": 4.89,
      "learning_rate": 2e-05,
      "loss": 1.0422,
      "step": 440
    },
    {
      "epoch": 4.9,
      "learning_rate": 2e-05,
      "loss": 1.3359,
      "step": 441
    },
    {
      "epoch": 4.91,
      "learning_rate": 2e-05,
      "loss": 1.128,
      "step": 442
    },
    {
      "epoch": 4.92,
      "learning_rate": 2e-05,
      "loss": 1.2882,
      "step": 443
    },
    {
      "epoch": 4.93,
      "learning_rate": 2e-05,
      "loss": 1.2593,
      "step": 444
    },
    {
      "epoch": 4.94,
      "learning_rate": 2e-05,
      "loss": 1.2965,
      "step": 445
    },
    {
      "epoch": 4.96,
      "learning_rate": 2e-05,
      "loss": 1.2561,
      "step": 446
    },
    {
      "epoch": 4.97,
      "learning_rate": 2e-05,
      "loss": 1.195,
      "step": 447
    },
    {
      "epoch": 4.98,
      "learning_rate": 2e-05,
      "loss": 1.1439,
      "step": 448
    },
    {
      "epoch": 4.99,
      "learning_rate": 2e-05,
      "loss": 1.2452,
      "step": 449
    },
    {
      "epoch": 5.0,
      "learning_rate": 2e-05,
      "loss": 1.3703,
      "step": 450
    },
    {
      "epoch": 5.0,
      "step": 450,
      "total_flos": 1.347899379867648e+17,
      "train_loss": 1.2846886356671652,
      "train_runtime": 1802.7215,
      "train_samples_per_second": 1.997,
      "train_steps_per_second": 0.25
    }
  ],
  "logging_steps": 1,
  "max_steps": 450,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.347899379867648e+17,
  "trial_name": null,
  "trial_params": null
}