{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 4.0818,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 4.2333,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 6e-05,
      "loss": 4.1534,
      "step": 3
    },
    {
      "epoch": 0.03,
      "learning_rate": 8e-05,
      "loss": 3.8975,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 3.6751,
      "step": 5
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.931034482758621e-05,
      "loss": 3.628,
      "step": 6
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.862068965517242e-05,
      "loss": 2.9881,
      "step": 7
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.793103448275862e-05,
      "loss": 2.9728,
      "step": 8
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.724137931034482e-05,
      "loss": 2.8344,
      "step": 9
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.655172413793105e-05,
      "loss": 2.5139,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.586206896551725e-05,
      "loss": 2.6705,
      "step": 11
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.517241379310345e-05,
      "loss": 2.4531,
      "step": 12
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.448275862068966e-05,
      "loss": 2.2288,
      "step": 13
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.448275862068966e-05,
      "loss": 2.2861,
      "step": 14
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.379310344827587e-05,
      "loss": 2.1408,
      "step": 15
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.310344827586207e-05,
      "loss": 2.0435,
      "step": 16
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.241379310344827e-05,
      "loss": 2.2004,
      "step": 17
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.172413793103448e-05,
      "loss": 2.0824,
      "step": 18
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.10344827586207e-05,
      "loss": 1.9434,
      "step": 19
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.034482758620691e-05,
      "loss": 1.9493,
      "step": 20
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.96551724137931e-05,
      "loss": 1.7111,
      "step": 21
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.896551724137931e-05,
      "loss": 1.845,
      "step": 22
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.827586206896552e-05,
      "loss": 1.7654,
      "step": 23
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.758620689655173e-05,
      "loss": 1.8127,
      "step": 24
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.758620689655173e-05,
      "loss": 1.8127,
      "step": 25
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.689655172413794e-05,
      "loss": 2.0117,
      "step": 26
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.620689655172413e-05,
      "loss": 2.0344,
      "step": 27
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.551724137931035e-05,
      "loss": 2.1526,
      "step": 28
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.482758620689656e-05,
      "loss": 1.5487,
      "step": 29
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.413793103448277e-05,
      "loss": 1.9183,
      "step": 30
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.344827586206896e-05,
      "loss": 2.0809,
      "step": 31
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.275862068965517e-05,
      "loss": 1.9258,
      "step": 32
    },
    {
      "epoch": 0.22,
      "learning_rate": 8.206896551724138e-05,
      "loss": 1.8828,
      "step": 33
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.137931034482759e-05,
      "loss": 1.8153,
      "step": 34
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.06896551724138e-05,
      "loss": 1.8474,
      "step": 35
    },
    {
      "epoch": 0.24,
      "learning_rate": 8e-05,
      "loss": 1.8122,
      "step": 36
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.931034482758621e-05,
      "loss": 1.6398,
      "step": 37
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.862068965517242e-05,
      "loss": 1.6086,
      "step": 38
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.793103448275862e-05,
      "loss": 1.7449,
      "step": 39
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.724137931034483e-05,
      "loss": 1.9173,
      "step": 40
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.655172413793103e-05,
      "loss": 1.8231,
      "step": 41
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.586206896551724e-05,
      "loss": 1.4738,
      "step": 42
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.517241379310345e-05,
      "loss": 2.0624,
      "step": 43
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.448275862068966e-05,
      "loss": 1.647,
      "step": 44
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.379310344827587e-05,
      "loss": 1.8032,
      "step": 45
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.310344827586208e-05,
      "loss": 1.7987,
      "step": 46
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.241379310344828e-05,
      "loss": 1.5151,
      "step": 47
    },
    {
      "epoch": 0.32,
      "learning_rate": 7.172413793103448e-05,
      "loss": 1.7683,
      "step": 48
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.103448275862069e-05,
      "loss": 1.8269,
      "step": 49
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.03448275862069e-05,
      "loss": 1.6995,
      "step": 50
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.96551724137931e-05,
      "loss": 1.651,
      "step": 51
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.896551724137931e-05,
      "loss": 1.656,
      "step": 52
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.827586206896552e-05,
      "loss": 1.792,
      "step": 53
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.758620689655173e-05,
      "loss": 1.9257,
      "step": 54
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.689655172413794e-05,
      "loss": 1.8985,
      "step": 55
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.620689655172415e-05,
      "loss": 1.8121,
      "step": 56
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.551724137931034e-05,
      "loss": 1.8805,
      "step": 57
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.482758620689655e-05,
      "loss": 1.3778,
      "step": 58
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.413793103448276e-05,
      "loss": 1.48,
      "step": 59
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.344827586206897e-05,
      "loss": 1.6645,
      "step": 60
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.275862068965517e-05,
      "loss": 1.4213,
      "step": 61
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.206896551724138e-05,
      "loss": 1.7486,
      "step": 62
    },
    {
      "epoch": 0.42,
      "learning_rate": 6.137931034482759e-05,
      "loss": 1.7681,
      "step": 63
    },
    {
      "epoch": 0.43,
      "learning_rate": 6.068965517241379e-05,
      "loss": 1.6553,
      "step": 64
    },
    {
      "epoch": 0.43,
      "learning_rate": 6e-05,
      "loss": 1.767,
      "step": 65
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.93103448275862e-05,
      "loss": 1.75,
      "step": 66
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.862068965517241e-05,
      "loss": 1.6383,
      "step": 67
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.7931034482758627e-05,
      "loss": 1.5974,
      "step": 68
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.7241379310344835e-05,
      "loss": 1.8813,
      "step": 69
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.6551724137931037e-05,
      "loss": 1.829,
      "step": 70
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.5862068965517245e-05,
      "loss": 1.7594,
      "step": 71
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.517241379310345e-05,
      "loss": 1.6688,
      "step": 72
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.4482758620689655e-05,
      "loss": 1.4562,
      "step": 73
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.379310344827586e-05,
      "loss": 1.6862,
      "step": 74
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.3103448275862065e-05,
      "loss": 1.6709,
      "step": 75
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.241379310344828e-05,
      "loss": 1.7101,
      "step": 76
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.172413793103449e-05,
      "loss": 1.7654,
      "step": 77
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.10344827586207e-05,
      "loss": 1.8005,
      "step": 78
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.03448275862069e-05,
      "loss": 1.6221,
      "step": 79
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.9655172413793107e-05,
      "loss": 1.8204,
      "step": 80
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.896551724137931e-05,
      "loss": 1.4855,
      "step": 81
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.827586206896552e-05,
      "loss": 1.7683,
      "step": 82
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.7586206896551725e-05,
      "loss": 1.7431,
      "step": 83
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.689655172413793e-05,
      "loss": 1.6112,
      "step": 84
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.6206896551724135e-05,
      "loss": 1.7732,
      "step": 85
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.551724137931035e-05,
      "loss": 1.4928,
      "step": 86
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.482758620689655e-05,
      "loss": 1.6838,
      "step": 87
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.413793103448276e-05,
      "loss": 1.3589,
      "step": 88
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.344827586206897e-05,
      "loss": 1.5891,
      "step": 89
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.275862068965518e-05,
      "loss": 1.6386,
      "step": 90
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.2068965517241385e-05,
      "loss": 1.8267,
      "step": 91
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.1379310344827587e-05,
      "loss": 1.695,
      "step": 92
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.0689655172413795e-05,
      "loss": 1.7492,
      "step": 93
    },
    {
      "epoch": 0.63,
      "learning_rate": 4e-05,
      "loss": 1.3784,
      "step": 94
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.931034482758621e-05,
      "loss": 1.6347,
      "step": 95
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.862068965517241e-05,
      "loss": 1.7281,
      "step": 96
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.793103448275862e-05,
      "loss": 1.6843,
      "step": 97
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.724137931034483e-05,
      "loss": 1.6242,
      "step": 98
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.655172413793104e-05,
      "loss": 1.7026,
      "step": 99
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.586206896551724e-05,
      "loss": 1.7324,
      "step": 100
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.517241379310345e-05,
      "loss": 1.6897,
      "step": 101
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.4482758620689657e-05,
      "loss": 1.5846,
      "step": 102
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.3793103448275865e-05,
      "loss": 1.5537,
      "step": 103
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.310344827586207e-05,
      "loss": 1.8668,
      "step": 104
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.2413793103448275e-05,
      "loss": 1.7463,
      "step": 105
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.172413793103448e-05,
      "loss": 1.5203,
      "step": 106
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.103448275862069e-05,
      "loss": 1.3329,
      "step": 107
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.0344827586206897e-05,
      "loss": 1.6129,
      "step": 108
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.96551724137931e-05,
      "loss": 1.532,
      "step": 109
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.8965517241379313e-05,
      "loss": 1.7466,
      "step": 110
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.8275862068965518e-05,
      "loss": 1.4547,
      "step": 111
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.7586206896551727e-05,
      "loss": 1.431,
      "step": 112
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.689655172413793e-05,
      "loss": 1.4853,
      "step": 113
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.620689655172414e-05,
      "loss": 1.637,
      "step": 114
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.551724137931035e-05,
      "loss": 1.9718,
      "step": 115
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.4827586206896553e-05,
      "loss": 1.596,
      "step": 116
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.413793103448276e-05,
      "loss": 1.7287,
      "step": 117
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.3448275862068967e-05,
      "loss": 1.5844,
      "step": 118
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2758620689655175e-05,
      "loss": 1.7246,
      "step": 119
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.206896551724138e-05,
      "loss": 1.5478,
      "step": 120
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.137931034482759e-05,
      "loss": 1.4383,
      "step": 121
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.0689655172413793e-05,
      "loss": 1.6823,
      "step": 122
    },
    {
      "epoch": 0.82,
      "learning_rate": 2e-05,
      "loss": 1.7525,
      "step": 123
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.9310344827586207e-05,
      "loss": 1.6107,
      "step": 124
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.8620689655172415e-05,
      "loss": 1.6018,
      "step": 125
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.793103448275862e-05,
      "loss": 1.6314,
      "step": 126
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.7241379310344828e-05,
      "loss": 1.5003,
      "step": 127
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.6551724137931037e-05,
      "loss": 1.4919,
      "step": 128
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.586206896551724e-05,
      "loss": 1.8272,
      "step": 129
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.5172413793103448e-05,
      "loss": 1.5074,
      "step": 130
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.4482758620689657e-05,
      "loss": 1.7366,
      "step": 131
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.3793103448275863e-05,
      "loss": 1.3988,
      "step": 132
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.310344827586207e-05,
      "loss": 1.632,
      "step": 133
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.2413793103448277e-05,
      "loss": 1.5597,
      "step": 134
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.1724137931034483e-05,
      "loss": 1.6295,
      "step": 135
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.103448275862069e-05,
      "loss": 1.5595,
      "step": 136
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.0344827586206897e-05,
      "loss": 1.402,
      "step": 137
    },
    {
      "epoch": 0.92,
      "learning_rate": 9.655172413793103e-06,
      "loss": 1.7277,
      "step": 138
    },
    {
      "epoch": 0.93,
      "learning_rate": 8.96551724137931e-06,
      "loss": 1.4683,
      "step": 139
    },
    {
      "epoch": 0.93,
      "learning_rate": 8.275862068965518e-06,
      "loss": 1.5718,
      "step": 140
    },
    {
      "epoch": 0.94,
      "learning_rate": 7.586206896551724e-06,
      "loss": 1.664,
      "step": 141
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.896551724137932e-06,
      "loss": 1.6229,
      "step": 142
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.206896551724138e-06,
      "loss": 1.5403,
      "step": 143
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.517241379310345e-06,
      "loss": 1.6401,
      "step": 144
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.827586206896552e-06,
      "loss": 1.5122,
      "step": 145
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.137931034482759e-06,
      "loss": 1.894,
      "step": 146
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.448275862068966e-06,
      "loss": 1.7059,
      "step": 147
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.7586206896551725e-06,
      "loss": 1.553,
      "step": 148
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.0689655172413796e-06,
      "loss": 1.9253,
      "step": 149
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.3793103448275862e-06,
      "loss": 1.7004,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6279702186584473,
      "eval_runtime": 9.8166,
      "eval_samples_per_second": 20.374,
      "eval_steps_per_second": 2.547,
      "step": 150
    },
    {
      "epoch": 1.0,
      "step": 150,
      "total_flos": 2345174699212800.0,
      "train_loss": 1.8411440300941466,
      "train_runtime": 145.3238,
      "train_samples_per_second": 4.129,
      "train_steps_per_second": 1.032
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 2345174699212800.0,
  "trial_name": null,
  "trial_params": null
}