{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06,
  "eval_steps": 1000,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 2.5395,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 8e-05,
      "loss": 2.2227,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012,
      "loss": 2.0058,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016,
      "loss": 2.186,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.0344,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019862068965517243,
      "loss": 2.5634,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019724137931034484,
      "loss": 2.8602,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019586206896551723,
      "loss": 2.0045,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019448275862068965,
      "loss": 2.3942,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001931034482758621,
      "loss": 2.3819,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001917241379310345,
      "loss": 2.1668,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001903448275862069,
      "loss": 2.487,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018896551724137932,
      "loss": 2.2638,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018758620689655173,
      "loss": 2.0681,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018620689655172415,
      "loss": 2.1391,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018482758620689654,
      "loss": 1.9643,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018344827586206896,
      "loss": 2.4113,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001820689655172414,
      "loss": 2.8991,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018068965517241382,
      "loss": 1.8999,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001793103448275862,
      "loss": 2.5225,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017793103448275862,
      "loss": 2.5132,
      "step": 21
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017655172413793104,
      "loss": 2.2057,
      "step": 22
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017517241379310346,
      "loss": 1.8064,
      "step": 23
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017379310344827587,
      "loss": 2.4351,
      "step": 24
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017241379310344826,
      "loss": 1.973,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001710344827586207,
      "loss": 2.4166,
      "step": 26
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016965517241379312,
      "loss": 1.7906,
      "step": 27
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016827586206896554,
      "loss": 1.9014,
      "step": 28
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016689655172413793,
      "loss": 1.9858,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016551724137931035,
      "loss": 1.8535,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016413793103448276,
      "loss": 1.9679,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016275862068965518,
      "loss": 1.7981,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001613793103448276,
      "loss": 2.6577,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016,
      "loss": 2.0167,
      "step": 34
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015862068965517243,
      "loss": 2.1755,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015724137931034485,
      "loss": 2.0749,
      "step": 36
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015586206896551724,
      "loss": 2.1446,
      "step": 37
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015448275862068965,
      "loss": 2.1946,
      "step": 38
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015310344827586207,
      "loss": 2.5521,
      "step": 39
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015172413793103449,
      "loss": 1.8626,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001503448275862069,
      "loss": 1.802,
      "step": 41
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014896551724137932,
      "loss": 2.3631,
      "step": 42
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014758620689655174,
      "loss": 2.3524,
      "step": 43
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014620689655172415,
      "loss": 1.9224,
      "step": 44
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014482758620689657,
      "loss": 2.1055,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014344827586206896,
      "loss": 1.805,
      "step": 46
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014206896551724138,
      "loss": 2.3304,
      "step": 47
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001406896551724138,
      "loss": 1.9121,
      "step": 48
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001393103448275862,
      "loss": 2.1669,
      "step": 49
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013793103448275863,
      "loss": 1.7105,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013655172413793104,
      "loss": 2.1727,
      "step": 51
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013517241379310346,
      "loss": 2.0495,
      "step": 52
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013379310344827588,
      "loss": 1.9103,
      "step": 53
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001324137931034483,
      "loss": 1.8553,
      "step": 54
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013103448275862068,
      "loss": 1.8783,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001296551724137931,
      "loss": 2.3317,
      "step": 56
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012827586206896552,
      "loss": 2.0937,
      "step": 57
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012689655172413793,
      "loss": 1.8499,
      "step": 58
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012551724137931035,
      "loss": 2.2077,
      "step": 59
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012413793103448277,
      "loss": 2.0938,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012275862068965518,
      "loss": 2.1248,
      "step": 61
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012137931034482759,
      "loss": 2.088,
      "step": 62
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00012,
      "loss": 1.8202,
      "step": 63
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001186206896551724,
      "loss": 1.7176,
      "step": 64
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011724137931034482,
      "loss": 1.6984,
      "step": 65
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011586206896551725,
      "loss": 2.5114,
      "step": 66
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011448275862068967,
      "loss": 2.0009,
      "step": 67
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011310344827586207,
      "loss": 1.8106,
      "step": 68
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011172413793103449,
      "loss": 2.0636,
      "step": 69
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001103448275862069,
      "loss": 1.973,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00010896551724137931,
      "loss": 2.5624,
      "step": 71
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00010758620689655173,
      "loss": 2.3377,
      "step": 72
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00010620689655172413,
      "loss": 1.7512,
      "step": 73
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00010482758620689656,
      "loss": 1.8202,
      "step": 74
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00010344827586206898,
      "loss": 1.8357,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001020689655172414,
      "loss": 2.2172,
      "step": 76
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001006896551724138,
      "loss": 2.1916,
      "step": 77
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.931034482758621e-05,
      "loss": 1.7556,
      "step": 78
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.793103448275862e-05,
      "loss": 1.8581,
      "step": 79
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.655172413793105e-05,
      "loss": 2.0288,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.517241379310345e-05,
      "loss": 1.8501,
      "step": 81
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.379310344827587e-05,
      "loss": 2.0251,
      "step": 82
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.241379310344827e-05,
      "loss": 1.7272,
      "step": 83
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.10344827586207e-05,
      "loss": 2.3454,
      "step": 84
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.96551724137931e-05,
      "loss": 2.0192,
      "step": 85
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.827586206896552e-05,
      "loss": 2.1827,
      "step": 86
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.689655172413794e-05,
      "loss": 1.9185,
      "step": 87
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.551724137931035e-05,
      "loss": 2.2224,
      "step": 88
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.413793103448277e-05,
      "loss": 2.1385,
      "step": 89
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.275862068965517e-05,
      "loss": 2.1765,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.137931034482759e-05,
      "loss": 2.2526,
      "step": 91
    },
    {
      "epoch": 0.04,
      "learning_rate": 8e-05,
      "loss": 1.3835,
      "step": 92
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.862068965517242e-05,
      "loss": 2.0079,
      "step": 93
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.724137931034483e-05,
      "loss": 2.5927,
      "step": 94
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.586206896551724e-05,
      "loss": 1.7471,
      "step": 95
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.448275862068966e-05,
      "loss": 1.8743,
      "step": 96
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.310344827586208e-05,
      "loss": 2.0863,
      "step": 97
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.172413793103448e-05,
      "loss": 1.9628,
      "step": 98
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.03448275862069e-05,
      "loss": 2.1242,
      "step": 99
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.896551724137931e-05,
      "loss": 1.9601,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.758620689655173e-05,
      "loss": 1.8597,
      "step": 101
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.620689655172415e-05,
      "loss": 1.94,
      "step": 102
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.482758620689655e-05,
      "loss": 2.1304,
      "step": 103
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.344827586206897e-05,
      "loss": 2.1898,
      "step": 104
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.206896551724138e-05,
      "loss": 2.2578,
      "step": 105
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.068965517241379e-05,
      "loss": 1.822,
      "step": 106
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.93103448275862e-05,
      "loss": 1.923,
      "step": 107
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.7931034482758627e-05,
      "loss": 1.7571,
      "step": 108
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.6551724137931037e-05,
      "loss": 2.0625,
      "step": 109
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.517241379310345e-05,
      "loss": 1.8541,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.379310344827586e-05,
      "loss": 1.9109,
      "step": 111
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.241379310344828e-05,
      "loss": 2.0033,
      "step": 112
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.10344827586207e-05,
      "loss": 2.3862,
      "step": 113
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9655172413793107e-05,
      "loss": 2.0193,
      "step": 114
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.827586206896552e-05,
      "loss": 2.2845,
      "step": 115
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.689655172413793e-05,
      "loss": 2.1102,
      "step": 116
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.551724137931035e-05,
      "loss": 2.0114,
      "step": 117
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.413793103448276e-05,
      "loss": 2.0468,
      "step": 118
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.275862068965518e-05,
      "loss": 1.9579,
      "step": 119
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.1379310344827587e-05,
      "loss": 1.765,
      "step": 120
    },
    {
      "epoch": 0.05,
      "learning_rate": 4e-05,
      "loss": 1.8117,
      "step": 121
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.862068965517241e-05,
      "loss": 2.1734,
      "step": 122
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.724137931034483e-05,
      "loss": 1.7121,
      "step": 123
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.586206896551724e-05,
      "loss": 1.9704,
      "step": 124
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.4482758620689657e-05,
      "loss": 2.1059,
      "step": 125
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.310344827586207e-05,
      "loss": 2.0225,
      "step": 126
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.172413793103448e-05,
      "loss": 2.1301,
      "step": 127
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.0344827586206897e-05,
      "loss": 1.5007,
      "step": 128
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.8965517241379313e-05,
      "loss": 2.1499,
      "step": 129
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.7586206896551727e-05,
      "loss": 2.6004,
      "step": 130
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.620689655172414e-05,
      "loss": 2.0711,
      "step": 131
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.4827586206896553e-05,
      "loss": 1.3493,
      "step": 132
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.3448275862068967e-05,
      "loss": 1.5959,
      "step": 133
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.206896551724138e-05,
      "loss": 1.8896,
      "step": 134
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.0689655172413793e-05,
      "loss": 2.2874,
      "step": 135
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9310344827586207e-05,
      "loss": 2.1101,
      "step": 136
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.793103448275862e-05,
      "loss": 1.9485,
      "step": 137
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.6551724137931037e-05,
      "loss": 1.7614,
      "step": 138
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.5172413793103448e-05,
      "loss": 2.0501,
      "step": 139
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.3793103448275863e-05,
      "loss": 2.1258,
      "step": 140
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.2413793103448277e-05,
      "loss": 1.9039,
      "step": 141
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.103448275862069e-05,
      "loss": 1.8506,
      "step": 142
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.655172413793103e-06,
      "loss": 1.7843,
      "step": 143
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.275862068965518e-06,
      "loss": 1.9734,
      "step": 144
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.896551724137932e-06,
      "loss": 2.0637,
      "step": 145
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.517241379310345e-06,
      "loss": 1.9301,
      "step": 146
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.137931034482759e-06,
      "loss": 1.9931,
      "step": 147
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.7586206896551725e-06,
      "loss": 1.9537,
      "step": 148
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.3793103448275862e-06,
      "loss": 2.0301,
      "step": 149
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0,
      "loss": 1.7689,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 8076780710022144.0,
  "trial_name": null,
  "trial_params": null
}