{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "global_step": 216,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 2.0595,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.124143742160444e-06,
      "loss": 1.5809,
      "step": 2
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.1291500681071595e-05,
      "loss": 1.5621,
      "step": 3
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.4248287484320888e-05,
      "loss": 1.2263,
      "step": 4
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.6541749506938325e-05,
      "loss": 0.87,
      "step": 5
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.8415644423232037e-05,
      "loss": 0.8188,
      "step": 6
    },
    {
      "epoch": 0.13,
      "learning_rate": 2e-05,
      "loss": 0.7566,
      "step": 7
    },
    {
      "epoch": 0.15,
      "learning_rate": 2e-05,
      "loss": 0.7719,
      "step": 8
    },
    {
      "epoch": 0.17,
      "learning_rate": 2e-05,
      "loss": 0.7064,
      "step": 9
    },
    {
      "epoch": 0.19,
      "learning_rate": 2e-05,
      "loss": 0.6295,
      "step": 10
    },
    {
      "epoch": 0.2,
      "learning_rate": 2e-05,
      "loss": 0.6276,
      "step": 11
    },
    {
      "epoch": 0.22,
      "learning_rate": 2e-05,
      "loss": 0.5933,
      "step": 12
    },
    {
      "epoch": 0.24,
      "learning_rate": 2e-05,
      "loss": 0.5395,
      "step": 13
    },
    {
      "epoch": 0.26,
      "learning_rate": 2e-05,
      "loss": 0.5074,
      "step": 14
    },
    {
      "epoch": 0.28,
      "learning_rate": 2e-05,
      "loss": 0.4968,
      "step": 15
    },
    {
      "epoch": 0.3,
      "learning_rate": 2e-05,
      "loss": 0.4922,
      "step": 16
    },
    {
      "epoch": 0.31,
      "learning_rate": 2e-05,
      "loss": 0.4973,
      "step": 17
    },
    {
      "epoch": 0.33,
      "learning_rate": 2e-05,
      "loss": 0.4864,
      "step": 18
    },
    {
      "epoch": 0.35,
      "learning_rate": 2e-05,
      "loss": 0.4994,
      "step": 19
    },
    {
      "epoch": 0.37,
      "learning_rate": 2e-05,
      "loss": 0.4599,
      "step": 20
    },
    {
      "epoch": 0.39,
      "learning_rate": 2e-05,
      "loss": 0.4907,
      "step": 21
    },
    {
      "epoch": 0.41,
      "learning_rate": 2e-05,
      "loss": 0.4957,
      "step": 22
    },
    {
      "epoch": 0.43,
      "learning_rate": 2e-05,
      "loss": 0.48,
      "step": 23
    },
    {
      "epoch": 0.44,
      "learning_rate": 2e-05,
      "loss": 0.4951,
      "step": 24
    },
    {
      "epoch": 0.46,
      "learning_rate": 2e-05,
      "loss": 0.4908,
      "step": 25
    },
    {
      "epoch": 0.48,
      "learning_rate": 2e-05,
      "loss": 0.5022,
      "step": 26
    },
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 0.4563,
      "step": 27
    },
    {
      "epoch": 0.52,
      "learning_rate": 2e-05,
      "loss": 0.4314,
      "step": 28
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 0.4315,
      "step": 29
    },
    {
      "epoch": 0.56,
      "learning_rate": 2e-05,
      "loss": 0.4862,
      "step": 30
    },
    {
      "epoch": 0.57,
      "learning_rate": 2e-05,
      "loss": 0.4721,
      "step": 31
    },
    {
      "epoch": 0.59,
      "learning_rate": 2e-05,
      "loss": 0.4564,
      "step": 32
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 0.4978,
      "step": 33
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 0.4627,
      "step": 34
    },
    {
      "epoch": 0.65,
      "learning_rate": 2e-05,
      "loss": 0.4774,
      "step": 35
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 0.436,
      "step": 36
    },
    {
      "epoch": 0.69,
      "learning_rate": 2e-05,
      "loss": 0.4408,
      "step": 37
    },
    {
      "epoch": 0.7,
      "learning_rate": 2e-05,
      "loss": 0.5087,
      "step": 38
    },
    {
      "epoch": 0.72,
      "learning_rate": 2e-05,
      "loss": 0.4735,
      "step": 39
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 0.4658,
      "step": 40
    },
    {
      "epoch": 0.76,
      "learning_rate": 2e-05,
      "loss": 0.4921,
      "step": 41
    },
    {
      "epoch": 0.78,
      "learning_rate": 2e-05,
      "loss": 0.4609,
      "step": 42
    },
    {
      "epoch": 0.8,
      "learning_rate": 2e-05,
      "loss": 0.4791,
      "step": 43
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 0.4988,
      "step": 44
    },
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 0.5128,
      "step": 45
    },
    {
      "epoch": 0.85,
      "learning_rate": 2e-05,
      "loss": 0.4588,
      "step": 46
    },
    {
      "epoch": 0.87,
      "learning_rate": 2e-05,
      "loss": 0.4214,
      "step": 47
    },
    {
      "epoch": 0.89,
      "learning_rate": 2e-05,
      "loss": 0.44,
      "step": 48
    },
    {
      "epoch": 0.91,
      "learning_rate": 2e-05,
      "loss": 0.4528,
      "step": 49
    },
    {
      "epoch": 0.93,
      "learning_rate": 2e-05,
      "loss": 0.4593,
      "step": 50
    },
    {
      "epoch": 0.94,
      "learning_rate": 2e-05,
      "loss": 0.4759,
      "step": 51
    },
    {
      "epoch": 0.96,
      "learning_rate": 2e-05,
      "loss": 0.4554,
      "step": 52
    },
    {
      "epoch": 0.98,
      "learning_rate": 2e-05,
      "loss": 0.4535,
      "step": 53
    },
    {
      "epoch": 1.0,
      "learning_rate": 2e-05,
      "loss": 0.474,
      "step": 54
    },
    {
      "epoch": 1.02,
      "learning_rate": 2e-05,
      "loss": 0.4714,
      "step": 55
    },
    {
      "epoch": 1.04,
      "learning_rate": 2e-05,
      "loss": 0.4581,
      "step": 56
    },
    {
      "epoch": 1.06,
      "learning_rate": 2e-05,
      "loss": 0.4388,
      "step": 57
    },
    {
      "epoch": 1.07,
      "learning_rate": 2e-05,
      "loss": 0.459,
      "step": 58
    },
    {
      "epoch": 1.09,
      "learning_rate": 2e-05,
      "loss": 0.4464,
      "step": 59
    },
    {
      "epoch": 1.11,
      "learning_rate": 2e-05,
      "loss": 0.4432,
      "step": 60
    },
    {
      "epoch": 1.13,
      "learning_rate": 2e-05,
      "loss": 0.439,
      "step": 61
    },
    {
      "epoch": 1.15,
      "learning_rate": 2e-05,
      "loss": 0.4096,
      "step": 62
    },
    {
      "epoch": 1.17,
      "learning_rate": 2e-05,
      "loss": 0.4271,
      "step": 63
    },
    {
      "epoch": 1.19,
      "learning_rate": 2e-05,
      "loss": 0.4565,
      "step": 64
    },
    {
      "epoch": 1.2,
      "learning_rate": 2e-05,
      "loss": 0.4329,
      "step": 65
    },
    {
      "epoch": 1.22,
      "learning_rate": 2e-05,
      "loss": 0.4469,
      "step": 66
    },
    {
      "epoch": 1.24,
      "learning_rate": 2e-05,
      "loss": 0.4196,
      "step": 67
    },
    {
      "epoch": 1.26,
      "learning_rate": 2e-05,
      "loss": 0.4281,
      "step": 68
    },
    {
      "epoch": 1.28,
      "learning_rate": 2e-05,
      "loss": 0.3993,
      "step": 69
    },
    {
      "epoch": 1.3,
      "learning_rate": 2e-05,
      "loss": 0.389,
      "step": 70
    },
    {
      "epoch": 1.31,
      "learning_rate": 2e-05,
      "loss": 0.4431,
      "step": 71
    },
    {
      "epoch": 1.33,
      "learning_rate": 2e-05,
      "loss": 0.4597,
      "step": 72
    },
    {
      "epoch": 1.35,
      "learning_rate": 2e-05,
      "loss": 0.462,
      "step": 73
    },
    {
      "epoch": 1.37,
      "learning_rate": 2e-05,
      "loss": 0.4576,
      "step": 74
    },
    {
      "epoch": 1.39,
      "learning_rate": 2e-05,
      "loss": 0.463,
      "step": 75
    },
    {
      "epoch": 1.41,
      "learning_rate": 2e-05,
      "loss": 0.4565,
      "step": 76
    },
    {
      "epoch": 1.43,
      "learning_rate": 2e-05,
      "loss": 0.4043,
      "step": 77
    },
    {
      "epoch": 1.44,
      "learning_rate": 2e-05,
      "loss": 0.464,
      "step": 78
    },
    {
      "epoch": 1.46,
      "learning_rate": 2e-05,
      "loss": 0.4279,
      "step": 79
    },
    {
      "epoch": 1.48,
      "learning_rate": 2e-05,
      "loss": 0.4119,
      "step": 80
    },
    {
      "epoch": 1.5,
      "learning_rate": 2e-05,
      "loss": 0.4033,
      "step": 81
    },
    {
      "epoch": 1.52,
      "learning_rate": 2e-05,
      "loss": 0.4212,
      "step": 82
    },
    {
      "epoch": 1.54,
      "learning_rate": 2e-05,
      "loss": 0.456,
      "step": 83
    },
    {
      "epoch": 1.56,
      "learning_rate": 2e-05,
      "loss": 0.4352,
      "step": 84
    },
    {
      "epoch": 1.57,
      "learning_rate": 2e-05,
      "loss": 0.4276,
      "step": 85
    },
    {
      "epoch": 1.59,
      "learning_rate": 2e-05,
      "loss": 0.407,
      "step": 86
    },
    {
      "epoch": 1.61,
      "learning_rate": 2e-05,
      "loss": 0.4177,
      "step": 87
    },
    {
      "epoch": 1.63,
      "learning_rate": 2e-05,
      "loss": 0.4293,
      "step": 88
    },
    {
      "epoch": 1.65,
      "learning_rate": 2e-05,
      "loss": 0.4414,
      "step": 89
    },
    {
      "epoch": 1.67,
      "learning_rate": 2e-05,
      "loss": 0.4024,
      "step": 90
    },
    {
      "epoch": 1.69,
      "learning_rate": 2e-05,
      "loss": 0.4743,
      "step": 91
    },
    {
      "epoch": 1.7,
      "learning_rate": 2e-05,
      "loss": 0.4629,
      "step": 92
    },
    {
      "epoch": 1.72,
      "learning_rate": 2e-05,
      "loss": 0.4728,
      "step": 93
    },
    {
      "epoch": 1.74,
      "learning_rate": 2e-05,
      "loss": 0.4079,
      "step": 94
    },
    {
      "epoch": 1.76,
      "learning_rate": 2e-05,
      "loss": 0.4461,
      "step": 95
    },
    {
      "epoch": 1.78,
      "learning_rate": 2e-05,
      "loss": 0.3941,
      "step": 96
    },
    {
      "epoch": 1.8,
      "learning_rate": 2e-05,
      "loss": 0.465,
      "step": 97
    },
    {
      "epoch": 1.81,
      "learning_rate": 2e-05,
      "loss": 0.4543,
      "step": 98
    },
    {
      "epoch": 1.83,
      "learning_rate": 2e-05,
      "loss": 0.436,
      "step": 99
    },
    {
      "epoch": 1.85,
      "learning_rate": 2e-05,
      "loss": 0.4239,
      "step": 100
    },
    {
      "epoch": 1.87,
      "learning_rate": 2e-05,
      "loss": 0.4196,
      "step": 101
    },
    {
      "epoch": 1.89,
      "learning_rate": 2e-05,
      "loss": 0.4159,
      "step": 102
    },
    {
      "epoch": 1.91,
      "learning_rate": 2e-05,
      "loss": 0.4132,
      "step": 103
    },
    {
      "epoch": 1.93,
      "learning_rate": 2e-05,
      "loss": 0.4218,
      "step": 104
    },
    {
      "epoch": 1.94,
      "learning_rate": 2e-05,
      "loss": 0.385,
      "step": 105
    },
    {
      "epoch": 1.96,
      "learning_rate": 2e-05,
      "loss": 0.4221,
      "step": 106
    },
    {
      "epoch": 1.98,
      "learning_rate": 2e-05,
      "loss": 0.4218,
      "step": 107
    },
    {
      "epoch": 2.0,
      "learning_rate": 2e-05,
      "loss": 0.4493,
      "step": 108
    },
    {
      "epoch": 2.02,
      "learning_rate": 2e-05,
      "loss": 0.4292,
      "step": 109
    },
    {
      "epoch": 2.04,
      "learning_rate": 2e-05,
      "loss": 0.4335,
      "step": 110
    },
    {
      "epoch": 2.06,
      "learning_rate": 2e-05,
      "loss": 0.4134,
      "step": 111
    },
    {
      "epoch": 2.07,
      "learning_rate": 2e-05,
      "loss": 0.4186,
      "step": 112
    },
    {
      "epoch": 2.09,
      "learning_rate": 2e-05,
      "loss": 0.3658,
      "step": 113
    },
    {
      "epoch": 2.11,
      "learning_rate": 2e-05,
      "loss": 0.4121,
      "step": 114
    },
    {
      "epoch": 2.13,
      "learning_rate": 2e-05,
      "loss": 0.4266,
      "step": 115
    },
    {
      "epoch": 2.15,
      "learning_rate": 2e-05,
      "loss": 0.3959,
      "step": 116
    },
    {
      "epoch": 2.17,
      "learning_rate": 2e-05,
      "loss": 0.385,
      "step": 117
    },
    {
      "epoch": 2.19,
      "learning_rate": 2e-05,
      "loss": 0.3935,
      "step": 118
    },
    {
      "epoch": 2.2,
      "learning_rate": 2e-05,
      "loss": 0.3807,
      "step": 119
    },
    {
      "epoch": 2.22,
      "learning_rate": 2e-05,
      "loss": 0.3905,
      "step": 120
    },
    {
      "epoch": 2.24,
      "learning_rate": 2e-05,
      "loss": 0.4031,
      "step": 121
    },
    {
      "epoch": 2.26,
      "learning_rate": 2e-05,
      "loss": 0.3834,
      "step": 122
    },
    {
      "epoch": 2.28,
      "learning_rate": 2e-05,
      "loss": 0.4176,
      "step": 123
    },
    {
      "epoch": 2.3,
      "learning_rate": 2e-05,
      "loss": 0.4219,
      "step": 124
    },
    {
      "epoch": 2.31,
      "learning_rate": 2e-05,
      "loss": 0.4241,
      "step": 125
    },
    {
      "epoch": 2.33,
      "learning_rate": 2e-05,
      "loss": 0.4152,
      "step": 126
    },
    {
      "epoch": 2.35,
      "learning_rate": 2e-05,
      "loss": 0.4085,
      "step": 127
    },
    {
      "epoch": 2.37,
      "learning_rate": 2e-05,
      "loss": 0.416,
      "step": 128
    },
    {
      "epoch": 2.39,
      "learning_rate": 2e-05,
      "loss": 0.3932,
      "step": 129
    },
    {
      "epoch": 2.41,
      "learning_rate": 2e-05,
      "loss": 0.3904,
      "step": 130
    },
    {
      "epoch": 2.43,
      "learning_rate": 2e-05,
      "loss": 0.4162,
      "step": 131
    },
    {
      "epoch": 2.44,
      "learning_rate": 2e-05,
      "loss": 0.3977,
      "step": 132
    },
    {
      "epoch": 2.46,
      "learning_rate": 2e-05,
      "loss": 0.4314,
      "step": 133
    },
    {
      "epoch": 2.48,
      "learning_rate": 2e-05,
      "loss": 0.401,
      "step": 134
    },
    {
      "epoch": 2.5,
      "learning_rate": 2e-05,
      "loss": 0.4034,
      "step": 135
    },
    {
      "epoch": 2.52,
      "learning_rate": 2e-05,
      "loss": 0.4091,
      "step": 136
    },
    {
      "epoch": 2.54,
      "learning_rate": 2e-05,
      "loss": 0.4292,
      "step": 137
    },
    {
      "epoch": 2.56,
      "learning_rate": 2e-05,
      "loss": 0.453,
      "step": 138
    },
    {
      "epoch": 2.57,
      "learning_rate": 2e-05,
      "loss": 0.4213,
      "step": 139
    },
    {
      "epoch": 2.59,
      "learning_rate": 2e-05,
      "loss": 0.4352,
      "step": 140
    },
    {
      "epoch": 2.61,
      "learning_rate": 2e-05,
      "loss": 0.4154,
      "step": 141
    },
    {
      "epoch": 2.63,
      "learning_rate": 2e-05,
      "loss": 0.4237,
      "step": 142
    },
    {
      "epoch": 2.65,
      "learning_rate": 2e-05,
      "loss": 0.4116,
      "step": 143
    },
    {
      "epoch": 2.67,
      "learning_rate": 2e-05,
      "loss": 0.4038,
      "step": 144
    },
    {
      "epoch": 2.69,
      "learning_rate": 2e-05,
      "loss": 0.4014,
      "step": 145
    },
    {
      "epoch": 2.7,
      "learning_rate": 2e-05,
      "loss": 0.4252,
      "step": 146
    },
    {
      "epoch": 2.72,
      "learning_rate": 2e-05,
      "loss": 0.3945,
      "step": 147
    },
    {
      "epoch": 2.74,
      "learning_rate": 2e-05,
      "loss": 0.4337,
      "step": 148
    },
    {
      "epoch": 2.76,
      "learning_rate": 2e-05,
      "loss": 0.4137,
      "step": 149
    },
    {
      "epoch": 2.78,
      "learning_rate": 2e-05,
      "loss": 0.4059,
      "step": 150
    },
    {
      "epoch": 2.8,
      "learning_rate": 2e-05,
      "loss": 0.4198,
      "step": 151
    },
    {
      "epoch": 2.81,
      "learning_rate": 2e-05,
      "loss": 0.3999,
      "step": 152
    },
    {
      "epoch": 2.83,
      "learning_rate": 2e-05,
      "loss": 0.4217,
      "step": 153
    },
    {
      "epoch": 2.85,
      "learning_rate": 2e-05,
      "loss": 0.4317,
      "step": 154
    },
    {
      "epoch": 2.87,
      "learning_rate": 2e-05,
      "loss": 0.4213,
      "step": 155
    },
    {
      "epoch": 2.89,
      "learning_rate": 2e-05,
      "loss": 0.3998,
      "step": 156
    },
    {
      "epoch": 2.91,
      "learning_rate": 2e-05,
      "loss": 0.4306,
      "step": 157
    },
    {
      "epoch": 2.93,
      "learning_rate": 2e-05,
      "loss": 0.4137,
      "step": 158
    },
    {
      "epoch": 2.94,
      "learning_rate": 2e-05,
      "loss": 0.4127,
      "step": 159
    },
    {
      "epoch": 2.96,
      "learning_rate": 2e-05,
      "loss": 0.3819,
      "step": 160
    },
    {
      "epoch": 2.98,
      "learning_rate": 2e-05,
      "loss": 0.3971,
      "step": 161
    },
    {
      "epoch": 3.0,
      "learning_rate": 2e-05,
      "loss": 0.3999,
      "step": 162
    },
    {
      "epoch": 3.02,
      "learning_rate": 2e-05,
      "loss": 0.3757,
      "step": 163
    },
    {
      "epoch": 3.04,
      "learning_rate": 2e-05,
      "loss": 0.3848,
      "step": 164
    },
    {
      "epoch": 3.06,
      "learning_rate": 2e-05,
      "loss": 0.3734,
      "step": 165
    },
    {
      "epoch": 3.07,
      "learning_rate": 2e-05,
      "loss": 0.3705,
      "step": 166
    },
    {
      "epoch": 3.09,
      "learning_rate": 2e-05,
      "loss": 0.408,
      "step": 167
    },
    {
      "epoch": 3.11,
      "learning_rate": 2e-05,
      "loss": 0.3969,
      "step": 168
    },
    {
      "epoch": 3.13,
      "learning_rate": 2e-05,
      "loss": 0.3869,
      "step": 169
    },
    {
      "epoch": 3.15,
      "learning_rate": 2e-05,
      "loss": 0.4048,
      "step": 170
    },
    {
      "epoch": 3.17,
      "learning_rate": 2e-05,
      "loss": 0.3801,
      "step": 171
    },
    {
      "epoch": 3.19,
      "learning_rate": 2e-05,
      "loss": 0.4112,
      "step": 172
    },
    {
      "epoch": 3.2,
      "learning_rate": 2e-05,
      "loss": 0.3849,
      "step": 173
    },
    {
      "epoch": 3.22,
      "learning_rate": 2e-05,
      "loss": 0.372,
      "step": 174
    },
    {
      "epoch": 3.24,
      "learning_rate": 2e-05,
      "loss": 0.3862,
      "step": 175
    },
    {
      "epoch": 3.26,
      "learning_rate": 2e-05,
      "loss": 0.4198,
      "step": 176
    },
    {
      "epoch": 3.28,
      "learning_rate": 2e-05,
      "loss": 0.4139,
      "step": 177
    },
    {
      "epoch": 3.3,
      "learning_rate": 2e-05,
      "loss": 0.4024,
      "step": 178
    },
    {
      "epoch": 3.31,
      "learning_rate": 2e-05,
      "loss": 0.3983,
      "step": 179
    },
    {
      "epoch": 3.33,
      "learning_rate": 2e-05,
      "loss": 0.3419,
      "step": 180
    },
    {
      "epoch": 3.35,
      "learning_rate": 2e-05,
      "loss": 0.3883,
      "step": 181
    },
    {
      "epoch": 3.37,
      "learning_rate": 2e-05,
      "loss": 0.3695,
      "step": 182
    },
    {
      "epoch": 3.39,
      "learning_rate": 2e-05,
      "loss": 0.3826,
      "step": 183
    },
    {
      "epoch": 3.41,
      "learning_rate": 2e-05,
      "loss": 0.3662,
      "step": 184
    },
    {
      "epoch": 3.43,
      "learning_rate": 2e-05,
      "loss": 0.3924,
      "step": 185
    },
    {
      "epoch": 3.44,
      "learning_rate": 2e-05,
      "loss": 0.4145,
      "step": 186
    },
    {
      "epoch": 3.46,
      "learning_rate": 2e-05,
      "loss": 0.4054,
      "step": 187
    },
    {
      "epoch": 3.48,
      "learning_rate": 2e-05,
      "loss": 0.4051,
      "step": 188
    },
    {
      "epoch": 3.5,
      "learning_rate": 2e-05,
      "loss": 0.3838,
      "step": 189
    },
    {
      "epoch": 3.52,
      "learning_rate": 2e-05,
      "loss": 0.427,
      "step": 190
    },
    {
      "epoch": 3.54,
      "learning_rate": 2e-05,
      "loss": 0.3733,
      "step": 191
    },
    {
      "epoch": 3.56,
      "learning_rate": 2e-05,
      "loss": 0.395,
      "step": 192
    },
    {
      "epoch": 3.57,
      "learning_rate": 2e-05,
      "loss": 0.4194,
      "step": 193
    },
    {
      "epoch": 3.59,
      "learning_rate": 2e-05,
      "loss": 0.4201,
      "step": 194
    },
    {
      "epoch": 3.61,
      "learning_rate": 2e-05,
      "loss": 0.4206,
      "step": 195
    },
    {
      "epoch": 3.63,
      "learning_rate": 2e-05,
      "loss": 0.41,
      "step": 196
    },
    {
      "epoch": 3.65,
      "learning_rate": 2e-05,
      "loss": 0.4171,
      "step": 197
    },
    {
      "epoch": 3.67,
      "learning_rate": 2e-05,
      "loss": 0.3895,
      "step": 198
    },
    {
      "epoch": 3.69,
      "learning_rate": 2e-05,
      "loss": 0.4068,
      "step": 199
    },
    {
      "epoch": 3.7,
      "learning_rate": 2e-05,
      "loss": 0.3993,
      "step": 200
    },
    {
      "epoch": 3.72,
      "learning_rate": 2e-05,
      "loss": 0.405,
      "step": 201
    },
    {
      "epoch": 3.74,
      "learning_rate": 2e-05,
      "loss": 0.4027,
      "step": 202
    },
    {
      "epoch": 3.76,
      "learning_rate": 2e-05,
      "loss": 0.4076,
      "step": 203
    },
    {
      "epoch": 3.78,
      "learning_rate": 2e-05,
      "loss": 0.3802,
      "step": 204
    },
    {
      "epoch": 3.8,
      "learning_rate": 2e-05,
      "loss": 0.4454,
      "step": 205
    },
    {
      "epoch": 3.81,
      "learning_rate": 2e-05,
      "loss": 0.3908,
      "step": 206
    },
    {
      "epoch": 3.83,
      "learning_rate": 2e-05,
      "loss": 0.4011,
      "step": 207
    },
    {
      "epoch": 3.85,
      "learning_rate": 2e-05,
      "loss": 0.3761,
      "step": 208
    },
    {
      "epoch": 3.87,
      "learning_rate": 2e-05,
      "loss": 0.4067,
      "step": 209
    },
    {
      "epoch": 3.89,
      "learning_rate": 2e-05,
      "loss": 0.3998,
      "step": 210
    },
    {
      "epoch": 3.91,
      "learning_rate": 2e-05,
      "loss": 0.4033,
      "step": 211
    },
    {
      "epoch": 3.93,
      "learning_rate": 2e-05,
      "loss": 0.4297,
      "step": 212
    },
    {
      "epoch": 3.94,
      "learning_rate": 2e-05,
      "loss": 0.4063,
      "step": 213
    },
    {
      "epoch": 3.96,
      "learning_rate": 2e-05,
      "loss": 0.3957,
      "step": 214
    },
    {
      "epoch": 3.98,
      "learning_rate": 2e-05,
      "loss": 0.4267,
      "step": 215
    },
    {
      "epoch": 4.0,
      "learning_rate": 2e-05,
      "loss": 0.4129,
      "step": 216
    },
    {
      "epoch": 4.0,
      "step": 216,
      "total_flos": 145703921123328.0,
      "train_loss": 0.45959411313136417,
      "train_runtime": 7059.0908,
      "train_samples_per_second": 1.953,
      "train_steps_per_second": 0.031
    }
  ],
  "max_steps": 216,
  "num_train_epochs": 4,
  "total_flos": 145703921123328.0,
  "trial_name": null,
  "trial_params": null
}