{
  "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": 2.2293,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 2.007,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 6e-05,
      "loss": 2.1479,
      "step": 3
    },
    {
      "epoch": 0.03,
      "learning_rate": 8e-05,
      "loss": 1.9411,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 1.9661,
      "step": 5
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.931034482758621e-05,
      "loss": 1.8085,
      "step": 6
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.862068965517242e-05,
      "loss": 2.0453,
      "step": 7
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.793103448275862e-05,
      "loss": 1.7957,
      "step": 8
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.724137931034482e-05,
      "loss": 1.7825,
      "step": 9
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.655172413793105e-05,
      "loss": 1.4005,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.586206896551725e-05,
      "loss": 1.2935,
      "step": 11
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.517241379310345e-05,
      "loss": 1.508,
      "step": 12
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.448275862068966e-05,
      "loss": 1.7479,
      "step": 13
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.379310344827587e-05,
      "loss": 1.5322,
      "step": 14
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.310344827586207e-05,
      "loss": 1.6156,
      "step": 15
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.241379310344827e-05,
      "loss": 1.5161,
      "step": 16
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.172413793103448e-05,
      "loss": 1.3889,
      "step": 17
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.10344827586207e-05,
      "loss": 1.3077,
      "step": 18
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.034482758620691e-05,
      "loss": 1.2614,
      "step": 19
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.96551724137931e-05,
      "loss": 1.4132,
      "step": 20
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.896551724137931e-05,
      "loss": 1.3799,
      "step": 21
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.827586206896552e-05,
      "loss": 1.3482,
      "step": 22
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.758620689655173e-05,
      "loss": 1.3903,
      "step": 23
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.689655172413794e-05,
      "loss": 1.3016,
      "step": 24
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.620689655172413e-05,
      "loss": 1.3541,
      "step": 25
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.551724137931035e-05,
      "loss": 1.1017,
      "step": 26
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.482758620689656e-05,
      "loss": 1.3111,
      "step": 27
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.413793103448277e-05,
      "loss": 1.1006,
      "step": 28
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.344827586206896e-05,
      "loss": 1.3251,
      "step": 29
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.275862068965517e-05,
      "loss": 1.2726,
      "step": 30
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.206896551724138e-05,
      "loss": 1.3384,
      "step": 31
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.137931034482759e-05,
      "loss": 1.162,
      "step": 32
    },
    {
      "epoch": 0.22,
      "learning_rate": 8.06896551724138e-05,
      "loss": 1.3263,
      "step": 33
    },
    {
      "epoch": 0.23,
      "learning_rate": 8e-05,
      "loss": 1.3329,
      "step": 34
    },
    {
      "epoch": 0.23,
      "learning_rate": 7.931034482758621e-05,
      "loss": 1.1882,
      "step": 35
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.862068965517242e-05,
      "loss": 1.1654,
      "step": 36
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.793103448275862e-05,
      "loss": 1.2161,
      "step": 37
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.724137931034483e-05,
      "loss": 1.258,
      "step": 38
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.655172413793103e-05,
      "loss": 1.1031,
      "step": 39
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.586206896551724e-05,
      "loss": 1.1444,
      "step": 40
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.517241379310345e-05,
      "loss": 1.088,
      "step": 41
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.448275862068966e-05,
      "loss": 1.1113,
      "step": 42
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.379310344827587e-05,
      "loss": 1.2534,
      "step": 43
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.310344827586208e-05,
      "loss": 1.1533,
      "step": 44
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.241379310344828e-05,
      "loss": 1.323,
      "step": 45
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.172413793103448e-05,
      "loss": 1.2384,
      "step": 46
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.103448275862069e-05,
      "loss": 1.3594,
      "step": 47
    },
    {
      "epoch": 0.32,
      "learning_rate": 7.03448275862069e-05,
      "loss": 1.114,
      "step": 48
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.96551724137931e-05,
      "loss": 1.1204,
      "step": 49
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.896551724137931e-05,
      "loss": 1.0803,
      "step": 50
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.827586206896552e-05,
      "loss": 1.2556,
      "step": 51
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.758620689655173e-05,
      "loss": 1.1148,
      "step": 52
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.689655172413794e-05,
      "loss": 1.2603,
      "step": 53
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.620689655172415e-05,
      "loss": 1.442,
      "step": 54
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.551724137931034e-05,
      "loss": 1.1207,
      "step": 55
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.482758620689655e-05,
      "loss": 1.4429,
      "step": 56
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.482758620689655e-05,
      "loss": 1.1722,
      "step": 57
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.413793103448276e-05,
      "loss": 1.3962,
      "step": 58
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.344827586206897e-05,
      "loss": 1.2407,
      "step": 59
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.275862068965517e-05,
      "loss": 1.0778,
      "step": 60
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.206896551724138e-05,
      "loss": 1.2103,
      "step": 61
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.137931034482759e-05,
      "loss": 1.1721,
      "step": 62
    },
    {
      "epoch": 0.42,
      "learning_rate": 6.068965517241379e-05,
      "loss": 1.0806,
      "step": 63
    },
    {
      "epoch": 0.43,
      "learning_rate": 6e-05,
      "loss": 1.276,
      "step": 64
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.93103448275862e-05,
      "loss": 1.3421,
      "step": 65
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.862068965517241e-05,
      "loss": 1.2496,
      "step": 66
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.7931034482758627e-05,
      "loss": 0.9466,
      "step": 67
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.7241379310344835e-05,
      "loss": 1.3298,
      "step": 68
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.6551724137931037e-05,
      "loss": 1.1273,
      "step": 69
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.5862068965517245e-05,
      "loss": 1.3189,
      "step": 70
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.517241379310345e-05,
      "loss": 1.1226,
      "step": 71
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.4482758620689655e-05,
      "loss": 1.1242,
      "step": 72
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.379310344827586e-05,
      "loss": 1.2395,
      "step": 73
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.3103448275862065e-05,
      "loss": 1.1385,
      "step": 74
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.241379310344828e-05,
      "loss": 1.4045,
      "step": 75
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.172413793103449e-05,
      "loss": 1.2756,
      "step": 76
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.10344827586207e-05,
      "loss": 1.3189,
      "step": 77
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.03448275862069e-05,
      "loss": 1.2318,
      "step": 78
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.9655172413793107e-05,
      "loss": 1.0645,
      "step": 79
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.896551724137931e-05,
      "loss": 1.2349,
      "step": 80
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.827586206896552e-05,
      "loss": 1.1248,
      "step": 81
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.7586206896551725e-05,
      "loss": 1.5145,
      "step": 82
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.689655172413793e-05,
      "loss": 1.138,
      "step": 83
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.6206896551724135e-05,
      "loss": 1.0639,
      "step": 84
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.551724137931035e-05,
      "loss": 1.357,
      "step": 85
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.482758620689655e-05,
      "loss": 1.1459,
      "step": 86
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.413793103448276e-05,
      "loss": 1.0465,
      "step": 87
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.344827586206897e-05,
      "loss": 1.2478,
      "step": 88
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.275862068965518e-05,
      "loss": 1.0688,
      "step": 89
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.2068965517241385e-05,
      "loss": 1.2847,
      "step": 90
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.1379310344827587e-05,
      "loss": 1.2504,
      "step": 91
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.0689655172413795e-05,
      "loss": 1.1649,
      "step": 92
    },
    {
      "epoch": 0.62,
      "learning_rate": 4e-05,
      "loss": 1.2221,
      "step": 93
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.931034482758621e-05,
      "loss": 1.024,
      "step": 94
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.862068965517241e-05,
      "loss": 1.262,
      "step": 95
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.793103448275862e-05,
      "loss": 1.3909,
      "step": 96
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.724137931034483e-05,
      "loss": 1.2316,
      "step": 97
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.655172413793104e-05,
      "loss": 1.1374,
      "step": 98
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.586206896551724e-05,
      "loss": 1.4087,
      "step": 99
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.517241379310345e-05,
      "loss": 1.4166,
      "step": 100
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.4482758620689657e-05,
      "loss": 1.2136,
      "step": 101
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.3793103448275865e-05,
      "loss": 1.2016,
      "step": 102
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.310344827586207e-05,
      "loss": 1.2509,
      "step": 103
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.2413793103448275e-05,
      "loss": 1.189,
      "step": 104
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.172413793103448e-05,
      "loss": 1.3552,
      "step": 105
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.103448275862069e-05,
      "loss": 1.1281,
      "step": 106
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.0344827586206897e-05,
      "loss": 1.3008,
      "step": 107
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.96551724137931e-05,
      "loss": 1.249,
      "step": 108
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.8965517241379313e-05,
      "loss": 0.994,
      "step": 109
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.8275862068965518e-05,
      "loss": 1.2791,
      "step": 110
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.7586206896551727e-05,
      "loss": 1.2621,
      "step": 111
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.689655172413793e-05,
      "loss": 1.3775,
      "step": 112
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.620689655172414e-05,
      "loss": 0.8981,
      "step": 113
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.551724137931035e-05,
      "loss": 1.3001,
      "step": 114
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.4827586206896553e-05,
      "loss": 1.3469,
      "step": 115
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.413793103448276e-05,
      "loss": 1.3073,
      "step": 116
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3448275862068967e-05,
      "loss": 1.3737,
      "step": 117
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2758620689655175e-05,
      "loss": 1.1672,
      "step": 118
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.206896551724138e-05,
      "loss": 1.1311,
      "step": 119
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.137931034482759e-05,
      "loss": 1.1298,
      "step": 120
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.0689655172413793e-05,
      "loss": 1.1022,
      "step": 121
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 1.1768,
      "step": 122
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.9310344827586207e-05,
      "loss": 1.127,
      "step": 123
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.8620689655172415e-05,
      "loss": 1.427,
      "step": 124
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.793103448275862e-05,
      "loss": 1.1697,
      "step": 125
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.7241379310344828e-05,
      "loss": 1.0438,
      "step": 126
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.6551724137931037e-05,
      "loss": 1.0684,
      "step": 127
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.586206896551724e-05,
      "loss": 1.174,
      "step": 128
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.5172413793103448e-05,
      "loss": 1.2778,
      "step": 129
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.4482758620689657e-05,
      "loss": 1.4606,
      "step": 130
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.3793103448275863e-05,
      "loss": 1.2492,
      "step": 131
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.310344827586207e-05,
      "loss": 1.0584,
      "step": 132
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.2413793103448277e-05,
      "loss": 1.2099,
      "step": 133
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.1724137931034483e-05,
      "loss": 1.0901,
      "step": 134
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.103448275862069e-05,
      "loss": 1.1183,
      "step": 135
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.0344827586206897e-05,
      "loss": 0.9985,
      "step": 136
    },
    {
      "epoch": 0.91,
      "learning_rate": 9.655172413793103e-06,
      "loss": 1.2695,
      "step": 137
    },
    {
      "epoch": 0.92,
      "learning_rate": 8.96551724137931e-06,
      "loss": 1.3367,
      "step": 138
    },
    {
      "epoch": 0.93,
      "learning_rate": 8.275862068965518e-06,
      "loss": 1.2725,
      "step": 139
    },
    {
      "epoch": 0.93,
      "learning_rate": 7.586206896551724e-06,
      "loss": 1.3437,
      "step": 140
    },
    {
      "epoch": 0.94,
      "learning_rate": 6.896551724137932e-06,
      "loss": 1.314,
      "step": 141
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.206896551724138e-06,
      "loss": 1.2984,
      "step": 142
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.517241379310345e-06,
      "loss": 1.0817,
      "step": 143
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.827586206896552e-06,
      "loss": 1.2493,
      "step": 144
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.137931034482759e-06,
      "loss": 1.2914,
      "step": 145
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.448275862068966e-06,
      "loss": 1.3364,
      "step": 146
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.7586206896551725e-06,
      "loss": 1.2835,
      "step": 147
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.0689655172413796e-06,
      "loss": 1.1986,
      "step": 148
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.3793103448275862e-06,
      "loss": 1.1952,
      "step": 149
    },
    {
      "epoch": 1.0,
      "learning_rate": 6.896551724137931e-07,
      "loss": 1.2522,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.2197036743164062,
      "eval_runtime": 24.7422,
      "eval_samples_per_second": 8.083,
      "eval_steps_per_second": 1.01,
      "step": 150
    },
    {
      "epoch": 1.0,
      "step": 150,
      "total_flos": 7657713303552000.0,
      "train_loss": 1.2855440950393677,
      "train_runtime": 278.1355,
      "train_samples_per_second": 2.157,
      "train_steps_per_second": 0.539
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 7657713303552000.0,
  "trial_name": null,
  "trial_params": null
}