{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.3413,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2793,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0834,
      "step": 3
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.917,
      "step": 4
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.6094,
      "step": 5
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.2563,
      "step": 6
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.1912,
      "step": 7
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.0289,
      "step": 8
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.9676,
      "step": 9
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.9378,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.8781,
      "step": 11
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.8193,
      "step": 12
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.836,
      "step": 13
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7802,
      "step": 14
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.8298,
      "step": 15
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.713,
      "step": 16
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7249,
      "step": 17
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.6701,
      "step": 18
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.6247,
      "step": 19
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.584,
      "step": 20
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5329,
      "step": 21
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.6014,
      "step": 22
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.6378,
      "step": 23
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.5695,
      "step": 24
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.4947,
      "step": 25
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.5018,
      "step": 26
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.5127,
      "step": 27
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.4805,
      "step": 28
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.5404,
      "step": 29
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.5101,
      "step": 30
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.4084,
      "step": 31
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.8723,
      "step": 32
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.7323,
      "step": 33
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.7638,
      "step": 34
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.7656,
      "step": 35
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.7168,
      "step": 36
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.7287,
      "step": 37
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.6585,
      "step": 38
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.6802,
      "step": 39
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.6586,
      "step": 40
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.6798,
      "step": 41
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.604,
      "step": 42
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.5956,
      "step": 43
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.5964,
      "step": 44
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.5921,
      "step": 45
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.5801,
      "step": 46
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.5278,
      "step": 47
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.5501,
      "step": 48
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.5208,
      "step": 49
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.5353,
      "step": 50
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.4831,
      "step": 51
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.5108,
      "step": 52
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.4927,
      "step": 53
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.5039,
      "step": 54
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.4273,
      "step": 55
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.397,
      "step": 56
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.4147,
      "step": 57
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.4206,
      "step": 58
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.3996,
      "step": 59
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.3985,
      "step": 60
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.4251,
      "step": 61
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.3762,
      "step": 62
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.8826,
      "step": 63
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.7481,
      "step": 64
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.7089,
      "step": 65
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.7003,
      "step": 66
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.6645,
      "step": 67
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.6508,
      "step": 68
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.6183,
      "step": 69
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.6355,
      "step": 70
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.6137,
      "step": 71
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.5991,
      "step": 72
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.5746,
      "step": 73
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.5612,
      "step": 74
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.5754,
      "step": 75
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.5613,
      "step": 76
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.5478,
      "step": 77
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.5779,
      "step": 78
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.4949,
      "step": 79
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.5199,
      "step": 80
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 0.5102,
      "step": 81
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.503,
      "step": 82
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.4541,
      "step": 83
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.4918,
      "step": 84
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.4169,
      "step": 85
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.4295,
      "step": 86
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.4562,
      "step": 87
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.4317,
      "step": 88
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.4326,
      "step": 89
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.4192,
      "step": 90
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 0.3786,
      "step": 91
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.3615,
      "step": 92
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.4027,
      "step": 93
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.7332,
      "step": 94
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 0.7279,
      "step": 95
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.6832,
      "step": 96
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.6211,
      "step": 97
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.655,
      "step": 98
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.5706,
      "step": 99
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.646,
      "step": 100
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.5906,
      "step": 101
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.6442,
      "step": 102
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.5852,
      "step": 103
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.5407,
      "step": 104
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 0.5517,
      "step": 105
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.5054,
      "step": 106
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.5481,
      "step": 107
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.5696,
      "step": 108
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 0.5606,
      "step": 109
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.5186,
      "step": 110
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.4674,
      "step": 111
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.5036,
      "step": 112
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.4777,
      "step": 113
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 0.4872,
      "step": 114
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.4831,
      "step": 115
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.4348,
      "step": 116
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.4108,
      "step": 117
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.435,
      "step": 118
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 0.402,
      "step": 119
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.4152,
      "step": 120
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 0.4045,
      "step": 121
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.3942,
      "step": 122
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.3882,
      "step": 123
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.3794,
      "step": 124
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.5461,
      "step": 125
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 0.7042,
      "step": 126
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.5918,
      "step": 127
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.5802,
      "step": 128
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.604,
      "step": 129
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.5574,
      "step": 130
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 0.5743,
      "step": 131
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.5219,
      "step": 132
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.5178,
      "step": 133
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.5274,
      "step": 134
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.5128,
      "step": 135
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 0.4669,
      "step": 136
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.4696,
      "step": 137
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.4777,
      "step": 138
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.4399,
      "step": 139
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.4366,
      "step": 140
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.4878,
      "step": 141
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.3947,
      "step": 142
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.4458,
      "step": 143
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 0.4203,
      "step": 144
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.3752,
      "step": 145
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 0.3982,
      "step": 146
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.3519,
      "step": 147
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.3803,
      "step": 148
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 0.3584,
      "step": 149
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.3718,
      "step": 150
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 0.3447,
      "step": 151
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.348,
      "step": 152
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.3406,
      "step": 153
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.3659,
      "step": 154
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.3168,
      "step": 155
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.3055,
      "step": 156
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 0.7133,
      "step": 157
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 0.606,
      "step": 158
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 0.634,
      "step": 159
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 0.5842,
      "step": 160
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 0.5264,
      "step": 161
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.5321,
      "step": 162
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.5523,
      "step": 163
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 0.5155,
      "step": 164
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 0.5224,
      "step": 165
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.5018,
      "step": 166
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 0.4764,
      "step": 167
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 0.4888,
      "step": 168
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 0.4782,
      "step": 169
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 0.458,
      "step": 170
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 0.4754,
      "step": 171
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 0.4593,
      "step": 172
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 0.439,
      "step": 173
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 0.3804,
      "step": 174
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 0.4475,
      "step": 175
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 0.4229,
      "step": 176
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 0.4287,
      "step": 177
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 0.4237,
      "step": 178
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 0.3782,
      "step": 179
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 0.3502,
      "step": 180
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 0.3548,
      "step": 181
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 0.3341,
      "step": 182
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 0.3555,
      "step": 183
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 0.3561,
      "step": 184
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 0.3959,
      "step": 185
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 0.3096,
      "step": 186
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 0.3555,
      "step": 187
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 0.653,
      "step": 188
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 0.6019,
      "step": 189
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 0.6169,
      "step": 190
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 0.5261,
      "step": 191
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 0.5481,
      "step": 192
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 0.5701,
      "step": 193
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 0.5061,
      "step": 194
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 0.5073,
      "step": 195
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 0.5146,
      "step": 196
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 0.541,
      "step": 197
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 0.5036,
      "step": 198
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 0.4441,
      "step": 199
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 0.4536,
      "step": 200
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 0.4501,
      "step": 201
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 0.4893,
      "step": 202
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 0.4231,
      "step": 203
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 0.446,
      "step": 204
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 0.4262,
      "step": 205
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 0.4258,
      "step": 206
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 0.4337,
      "step": 207
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 0.3736,
      "step": 208
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 0.4079,
      "step": 209
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 0.3848,
      "step": 210
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 0.4034,
      "step": 211
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 0.3581,
      "step": 212
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 0.3691,
      "step": 213
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 0.3856,
      "step": 214
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0002,
      "loss": 0.3688,
      "step": 215
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 0.3378,
      "step": 216
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 0.3663,
      "step": 217
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 0.3173,
      "step": 218
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 0.6313,
      "step": 219
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 0.5564,
      "step": 220
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 0.5533,
      "step": 221
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 0.5213,
      "step": 222
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 0.5716,
      "step": 223
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 0.5287,
      "step": 224
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0002,
      "loss": 0.5217,
      "step": 225
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 0.5664,
      "step": 226
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 0.5245,
      "step": 227
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 0.4929,
      "step": 228
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0002,
      "loss": 0.4806,
      "step": 229
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002,
      "loss": 0.4499,
      "step": 230
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 0.4791,
      "step": 231
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 0.4916,
      "step": 232
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 0.5022,
      "step": 233
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 0.4708,
      "step": 234
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002,
      "loss": 0.4333,
      "step": 235
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 0.4246,
      "step": 236
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002,
      "loss": 0.4481,
      "step": 237
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002,
      "loss": 0.4252,
      "step": 238
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 0.4242,
      "step": 239
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002,
      "loss": 0.4012,
      "step": 240
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 0.3669,
      "step": 241
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0002,
      "loss": 0.3521,
      "step": 242
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0002,
      "loss": 0.366,
      "step": 243
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002,
      "loss": 0.3356,
      "step": 244
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 0.3463,
      "step": 245
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 0.3673,
      "step": 246
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002,
      "loss": 0.3366,
      "step": 247
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002,
      "loss": 0.3254,
      "step": 248
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0002,
      "loss": 0.3334,
      "step": 249
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 0.4874,
      "step": 250
    }
  ],
  "logging_steps": 1,
  "max_steps": 250,
  "num_train_epochs": 2,
  "save_steps": 25,
  "total_flos": 3.2208467410059264e+16,
  "trial_name": null,
  "trial_params": null
}