{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4986817325800377,
  "eval_steps": 500,
  "global_step": 331,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.8905,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 2.1656,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.3249,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.9685,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015,
      "loss": 2.1294,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.8817,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00020999999999999998,
      "loss": 2.2963,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.9336,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00027,
      "loss": 2.0421,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 2.0513,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 2.1697,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 2.0023,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 2.0504,
      "step": 13
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 2.0074,
      "step": 14
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 2.002,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 2.0578,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 2.0869,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 2.1063,
      "step": 18
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 2.1839,
      "step": 19
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 2.0949,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.9404,
      "step": 21
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 2.0324,
      "step": 22
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 2.0512,
      "step": 23
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 2.1104,
      "step": 24
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 2.1898,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9796,
      "step": 26
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 2.0646,
      "step": 27
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9569,
      "step": 28
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.9712,
      "step": 29
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 2.0377,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 2.0644,
      "step": 31
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 2.0759,
      "step": 32
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 2.1904,
      "step": 33
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 2.0916,
      "step": 34
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.9401,
      "step": 35
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 2.0835,
      "step": 36
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.9561,
      "step": 37
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.9928,
      "step": 38
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 2.0915,
      "step": 39
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.9851,
      "step": 40
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 2.0892,
      "step": 41
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 2.0994,
      "step": 42
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.9865,
      "step": 43
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 2.2139,
      "step": 44
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 2.0593,
      "step": 45
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.8464,
      "step": 46
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 2.2206,
      "step": 47
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 2.0361,
      "step": 48
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 2.0758,
      "step": 49
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 2.0945,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 2.0155,
      "step": 51
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 2.0336,
      "step": 52
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 2.127,
      "step": 53
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 2.0667,
      "step": 54
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 2.1709,
      "step": 55
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 2.4412,
      "step": 56
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.9267,
      "step": 57
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.9786,
      "step": 58
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 2.0349,
      "step": 59
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 2.0223,
      "step": 60
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 2.1529,
      "step": 61
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.9149,
      "step": 62
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 2.3504,
      "step": 63
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 2.0441,
      "step": 64
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 2.007,
      "step": 65
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 2.0004,
      "step": 66
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 2.0794,
      "step": 67
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 2.0036,
      "step": 68
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 2.0511,
      "step": 69
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.928,
      "step": 70
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 2.3278,
      "step": 71
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 2.0023,
      "step": 72
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 2.3091,
      "step": 73
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 2.1404,
      "step": 74
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.9227,
      "step": 75
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.7812,
      "step": 76
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 2.107,
      "step": 77
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 2.1513,
      "step": 78
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 2.0299,
      "step": 79
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 2.0269,
      "step": 80
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 1.9991,
      "step": 81
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 2.0781,
      "step": 82
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 1.9091,
      "step": 83
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 2.1204,
      "step": 84
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 2.0487,
      "step": 85
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 2.0451,
      "step": 86
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 2.3471,
      "step": 87
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 2.0368,
      "step": 88
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 2.2143,
      "step": 89
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 2.2364,
      "step": 90
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.9512,
      "step": 91
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 2.0817,
      "step": 92
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 2.082,
      "step": 93
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 2.2095,
      "step": 94
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 2.2195,
      "step": 95
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.9682,
      "step": 96
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 2.1033,
      "step": 97
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 1.9134,
      "step": 98
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 2.0129,
      "step": 99
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 1.9787,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 2.1464,
      "step": 101
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 2.1134,
      "step": 102
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 2.2134,
      "step": 103
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 2.0798,
      "step": 104
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.9768,
      "step": 105
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.9717,
      "step": 106
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 2.2062,
      "step": 107
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 2.1276,
      "step": 108
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 1.8273,
      "step": 109
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 2.0189,
      "step": 110
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 2.3743,
      "step": 111
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 2.0398,
      "step": 112
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.9905,
      "step": 113
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 2.0883,
      "step": 114
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 2.1952,
      "step": 115
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 2.1037,
      "step": 116
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 1.9426,
      "step": 117
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 1.9381,
      "step": 118
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 2.1171,
      "step": 119
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 1.9546,
      "step": 120
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 2.1014,
      "step": 121
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 2.1496,
      "step": 122
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.9256,
      "step": 123
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 2.0874,
      "step": 124
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.9993,
      "step": 125
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 1.7879,
      "step": 126
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 2.0628,
      "step": 127
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 2.2478,
      "step": 128
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 2.0526,
      "step": 129
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.9074,
      "step": 130
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.9984,
      "step": 131
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 1.8438,
      "step": 132
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 2.4196,
      "step": 133
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 2.0999,
      "step": 134
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 2.0693,
      "step": 135
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 2.1701,
      "step": 136
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 2.1491,
      "step": 137
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 2.1771,
      "step": 138
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 1.9413,
      "step": 139
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 2.0578,
      "step": 140
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 2.0194,
      "step": 141
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 2.0705,
      "step": 142
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 2.1,
      "step": 143
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 2.0259,
      "step": 144
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 2.1556,
      "step": 145
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 2.1039,
      "step": 146
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 1.9508,
      "step": 147
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 2.0704,
      "step": 148
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 1.9881,
      "step": 149
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 1.9417,
      "step": 150
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 1.9987,
      "step": 151
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 2.1971,
      "step": 152
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 2.0704,
      "step": 153
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 2.0985,
      "step": 154
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 2.0246,
      "step": 155
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 2.0278,
      "step": 156
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 2.0568,
      "step": 157
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 1.9288,
      "step": 158
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 1.9184,
      "step": 159
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 2.103,
      "step": 160
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 2.3037,
      "step": 161
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 1.9698,
      "step": 162
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.9212,
      "step": 163
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 2.2849,
      "step": 164
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.9339,
      "step": 165
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.822,
      "step": 166
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 2.1275,
      "step": 167
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 2.1951,
      "step": 168
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 1.8187,
      "step": 169
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.7058,
      "step": 170
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 2.1556,
      "step": 171
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 2.292,
      "step": 172
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.936,
      "step": 173
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 2.1493,
      "step": 174
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 1.9358,
      "step": 175
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.9508,
      "step": 176
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.9643,
      "step": 177
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 2.04,
      "step": 178
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 2.006,
      "step": 179
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 2.094,
      "step": 180
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 1.8666,
      "step": 181
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 2.0238,
      "step": 182
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 1.8641,
      "step": 183
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 1.8903,
      "step": 184
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 2.3543,
      "step": 185
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 1.976,
      "step": 186
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 2.1613,
      "step": 187
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 2.08,
      "step": 188
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 2.1041,
      "step": 189
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 2.2185,
      "step": 190
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 2.0194,
      "step": 191
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 2.0477,
      "step": 192
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 2.0584,
      "step": 193
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 1.9977,
      "step": 194
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 1.9739,
      "step": 195
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 2.0756,
      "step": 196
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.8116,
      "step": 197
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 2.1163,
      "step": 198
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.9504,
      "step": 199
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.7949,
      "step": 200
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 1.8974,
      "step": 201
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 2.1663,
      "step": 202
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 2.0203,
      "step": 203
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.8607,
      "step": 204
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 2.0307,
      "step": 205
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.8939,
      "step": 206
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 2.0563,
      "step": 207
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.849,
      "step": 208
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 2.1393,
      "step": 209
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.9289,
      "step": 210
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.9012,
      "step": 211
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 2.0093,
      "step": 212
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 1.9948,
      "step": 213
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 2.1939,
      "step": 214
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 2.1544,
      "step": 215
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 2.069,
      "step": 216
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 2.0003,
      "step": 217
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 2.0891,
      "step": 218
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.9638,
      "step": 219
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.862,
      "step": 220
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 1.8535,
      "step": 221
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 2.0076,
      "step": 222
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 2.2361,
      "step": 223
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 1.8635,
      "step": 224
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 2.1778,
      "step": 225
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 1.9204,
      "step": 226
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 1.9226,
      "step": 227
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 2.0887,
      "step": 228
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 2.0246,
      "step": 229
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 2.1383,
      "step": 230
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.9935,
      "step": 231
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.918,
      "step": 232
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 2.127,
      "step": 233
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.5184,
      "step": 234
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 1.6256,
      "step": 235
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 2.0977,
      "step": 236
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.9014,
      "step": 237
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 2.176,
      "step": 238
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.9032,
      "step": 239
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 2.145,
      "step": 240
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 2.1025,
      "step": 241
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 1.8974,
      "step": 242
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 1.7994,
      "step": 243
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 2.108,
      "step": 244
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 1.9332,
      "step": 245
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 2.0835,
      "step": 246
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 1.9987,
      "step": 247
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 2.1745,
      "step": 248
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.9741,
      "step": 249
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.8604,
      "step": 250
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.96,
      "step": 251
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 2.0263,
      "step": 252
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 1.514,
      "step": 253
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 2.2639,
      "step": 254
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 2.1194,
      "step": 255
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.9833,
      "step": 256
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.918,
      "step": 257
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.8254,
      "step": 258
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 2.4053,
      "step": 259
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 1.7951,
      "step": 260
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 2.013,
      "step": 261
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 2.1676,
      "step": 262
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 2.0155,
      "step": 263
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 1.9095,
      "step": 264
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 1.9232,
      "step": 265
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 2.0527,
      "step": 266
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 1.9979,
      "step": 267
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 2.0832,
      "step": 268
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.6021,
      "step": 269
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.8084,
      "step": 270
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 2.0317,
      "step": 271
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 1.6905,
      "step": 272
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 2.06,
      "step": 273
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 2.0294,
      "step": 274
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 2.1131,
      "step": 275
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.9358,
      "step": 276
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 2.0318,
      "step": 277
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.919,
      "step": 278
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.9638,
      "step": 279
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 1.9176,
      "step": 280
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 2.1244,
      "step": 281
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 2.2036,
      "step": 282
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.668,
      "step": 283
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.8759,
      "step": 284
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.8572,
      "step": 285
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.7817,
      "step": 286
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 1.9717,
      "step": 287
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 2.0483,
      "step": 288
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.8529,
      "step": 289
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.9906,
      "step": 290
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 1.9142,
      "step": 291
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 2.2337,
      "step": 292
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 2.0235,
      "step": 293
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 2.1023,
      "step": 294
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 2.3761,
      "step": 295
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 2.0978,
      "step": 296
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.9255,
      "step": 297
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 2.0125,
      "step": 298
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.6572,
      "step": 299
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.9519,
      "step": 300
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.9269,
      "step": 301
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 1.969,
      "step": 302
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 1.9098,
      "step": 303
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 1.6767,
      "step": 304
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 2.0155,
      "step": 305
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 2.1757,
      "step": 306
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 2.1494,
      "step": 307
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 1.9646,
      "step": 308
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 2.0318,
      "step": 309
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 2.0938,
      "step": 310
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.9784,
      "step": 311
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.8806,
      "step": 312
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 2.1179,
      "step": 313
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 2.0675,
      "step": 314
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 1.5312,
      "step": 315
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 2.187,
      "step": 316
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 1.8088,
      "step": 317
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 1.9437,
      "step": 318
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 2.0473,
      "step": 319
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 2.288,
      "step": 320
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 2.0301,
      "step": 321
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 1.8678,
      "step": 322
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 2.0297,
      "step": 323
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 2.102,
      "step": 324
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 2.0993,
      "step": 325
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 1.8891,
      "step": 326
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 1.9021,
      "step": 327
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 2.0166,
      "step": 328
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 1.5827,
      "step": 329
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 2.1066,
      "step": 330
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 1.7016,
      "step": 331
    }
  ],
  "logging_steps": 1,
  "max_steps": 663,
  "num_train_epochs": 1,
  "save_steps": 331,
  "total_flos": 2.5320739618317926e+17,
  "trial_name": null,
  "trial_params": null
}