{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 262,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 0.6182,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.5e-06,
      "loss": 0.5643,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-06,
      "loss": 0.3278,
      "step": 3
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.2989,
      "step": 4
    },
    {
      "epoch": 0.04,
      "learning_rate": 1e-05,
      "loss": 0.4602,
      "step": 5
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.25e-05,
      "loss": 0.2419,
      "step": 6
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.1365,
      "step": 7
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 0.1681,
      "step": 8
    },
    {
      "epoch": 0.07,
      "learning_rate": 2e-05,
      "loss": 0.2208,
      "step": 9
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.994805194805195e-05,
      "loss": 0.2965,
      "step": 10
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.98961038961039e-05,
      "loss": 0.2291,
      "step": 11
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9844155844155846e-05,
      "loss": 0.239,
      "step": 12
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9792207792207794e-05,
      "loss": 0.1757,
      "step": 13
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.974025974025974e-05,
      "loss": 0.1974,
      "step": 14
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.968831168831169e-05,
      "loss": 0.1589,
      "step": 15
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.963636363636364e-05,
      "loss": 0.1409,
      "step": 16
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9584415584415586e-05,
      "loss": 0.2429,
      "step": 17
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9532467532467533e-05,
      "loss": 0.2008,
      "step": 18
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9480519480519483e-05,
      "loss": 0.1727,
      "step": 19
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.942857142857143e-05,
      "loss": 0.2359,
      "step": 20
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9376623376623377e-05,
      "loss": 0.1524,
      "step": 21
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9324675324675325e-05,
      "loss": 0.1708,
      "step": 22
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9272727272727275e-05,
      "loss": 0.1446,
      "step": 23
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9220779220779222e-05,
      "loss": 0.1171,
      "step": 24
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.916883116883117e-05,
      "loss": 0.1835,
      "step": 25
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9116883116883117e-05,
      "loss": 0.1806,
      "step": 26
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9064935064935067e-05,
      "loss": 0.1147,
      "step": 27
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9012987012987014e-05,
      "loss": 0.1968,
      "step": 28
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.896103896103896e-05,
      "loss": 0.1194,
      "step": 29
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.8909090909090912e-05,
      "loss": 0.1694,
      "step": 30
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.885714285714286e-05,
      "loss": 0.0948,
      "step": 31
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8805194805194806e-05,
      "loss": 0.1289,
      "step": 32
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.8753246753246753e-05,
      "loss": 0.1513,
      "step": 33
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.8701298701298704e-05,
      "loss": 0.116,
      "step": 34
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.864935064935065e-05,
      "loss": 0.1036,
      "step": 35
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.8597402597402598e-05,
      "loss": 0.1255,
      "step": 36
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.8545454545454545e-05,
      "loss": 0.1422,
      "step": 37
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.8493506493506496e-05,
      "loss": 0.1181,
      "step": 38
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.8441558441558443e-05,
      "loss": 0.0667,
      "step": 39
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.838961038961039e-05,
      "loss": 0.1549,
      "step": 40
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.8337662337662337e-05,
      "loss": 0.1216,
      "step": 41
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.8285714285714288e-05,
      "loss": 0.124,
      "step": 42
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.8233766233766235e-05,
      "loss": 0.0541,
      "step": 43
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.1433,
      "step": 44
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.812987012987013e-05,
      "loss": 0.1909,
      "step": 45
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.807792207792208e-05,
      "loss": 0.1342,
      "step": 46
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.8025974025974027e-05,
      "loss": 0.2,
      "step": 47
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.7974025974025974e-05,
      "loss": 0.1792,
      "step": 48
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.792207792207792e-05,
      "loss": 0.1465,
      "step": 49
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.7870129870129872e-05,
      "loss": 0.1363,
      "step": 50
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.781818181818182e-05,
      "loss": 0.0871,
      "step": 51
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.7766233766233766e-05,
      "loss": 0.2048,
      "step": 52
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.7714285714285717e-05,
      "loss": 0.0595,
      "step": 53
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.7662337662337664e-05,
      "loss": 0.1284,
      "step": 54
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.761038961038961e-05,
      "loss": 0.0633,
      "step": 55
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.7558441558441558e-05,
      "loss": 0.2136,
      "step": 56
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.750649350649351e-05,
      "loss": 0.1154,
      "step": 57
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.7454545454545456e-05,
      "loss": 0.0985,
      "step": 58
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.7402597402597403e-05,
      "loss": 0.0892,
      "step": 59
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.735064935064935e-05,
      "loss": 0.1087,
      "step": 60
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.72987012987013e-05,
      "loss": 0.1084,
      "step": 61
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.7246753246753248e-05,
      "loss": 0.0879,
      "step": 62
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.7194805194805195e-05,
      "loss": 0.1091,
      "step": 63
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 0.1548,
      "step": 64
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.7090909090909092e-05,
      "loss": 0.1025,
      "step": 65
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.703896103896104e-05,
      "loss": 0.0781,
      "step": 66
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.6987012987012987e-05,
      "loss": 0.1067,
      "step": 67
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.6935064935064934e-05,
      "loss": 0.1866,
      "step": 68
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.6883116883116884e-05,
      "loss": 0.1791,
      "step": 69
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.683116883116883e-05,
      "loss": 0.2136,
      "step": 70
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.677922077922078e-05,
      "loss": 0.1061,
      "step": 71
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.672727272727273e-05,
      "loss": 0.1349,
      "step": 72
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.6675324675324676e-05,
      "loss": 0.1122,
      "step": 73
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.6623376623376627e-05,
      "loss": 0.061,
      "step": 74
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.6571428571428574e-05,
      "loss": 0.1085,
      "step": 75
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.651948051948052e-05,
      "loss": 0.1395,
      "step": 76
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.646753246753247e-05,
      "loss": 0.0708,
      "step": 77
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.641558441558442e-05,
      "loss": 0.0938,
      "step": 78
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 0.0729,
      "step": 79
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.6311688311688313e-05,
      "loss": 0.1487,
      "step": 80
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.6259740259740264e-05,
      "loss": 0.1433,
      "step": 81
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.620779220779221e-05,
      "loss": 0.0832,
      "step": 82
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.6155844155844158e-05,
      "loss": 0.0998,
      "step": 83
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.6103896103896105e-05,
      "loss": 0.1013,
      "step": 84
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.6051948051948056e-05,
      "loss": 0.0669,
      "step": 85
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0882,
      "step": 86
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.594805194805195e-05,
      "loss": 0.0881,
      "step": 87
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.5896103896103897e-05,
      "loss": 0.1476,
      "step": 88
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.5844155844155847e-05,
      "loss": 0.0749,
      "step": 89
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.5792207792207795e-05,
      "loss": 0.1039,
      "step": 90
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.5740259740259742e-05,
      "loss": 0.063,
      "step": 91
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.568831168831169e-05,
      "loss": 0.0859,
      "step": 92
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.563636363636364e-05,
      "loss": 0.1242,
      "step": 93
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.5584415584415587e-05,
      "loss": 0.0212,
      "step": 94
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.5532467532467534e-05,
      "loss": 0.0985,
      "step": 95
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.548051948051948e-05,
      "loss": 0.0693,
      "step": 96
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.542857142857143e-05,
      "loss": 0.0513,
      "step": 97
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.537662337662338e-05,
      "loss": 0.0501,
      "step": 98
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.5324675324675326e-05,
      "loss": 0.0782,
      "step": 99
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.5272727272727276e-05,
      "loss": 0.0441,
      "step": 100
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.5220779220779223e-05,
      "loss": 0.0612,
      "step": 101
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.516883116883117e-05,
      "loss": 0.0882,
      "step": 102
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.511688311688312e-05,
      "loss": 0.2014,
      "step": 103
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.5064935064935066e-05,
      "loss": 0.1176,
      "step": 104
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.5012987012987015e-05,
      "loss": 0.0952,
      "step": 105
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.4961038961038962e-05,
      "loss": 0.0877,
      "step": 106
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.4909090909090911e-05,
      "loss": 0.074,
      "step": 107
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.4857142857142858e-05,
      "loss": 0.0882,
      "step": 108
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4805194805194807e-05,
      "loss": 0.0598,
      "step": 109
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4753246753246754e-05,
      "loss": 0.1338,
      "step": 110
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.4701298701298703e-05,
      "loss": 0.0816,
      "step": 111
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.464935064935065e-05,
      "loss": 0.0763,
      "step": 112
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.45974025974026e-05,
      "loss": 0.0444,
      "step": 113
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.4545454545454546e-05,
      "loss": 0.0537,
      "step": 114
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.4493506493506495e-05,
      "loss": 0.0675,
      "step": 115
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.4441558441558442e-05,
      "loss": 0.2089,
      "step": 116
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.4389610389610391e-05,
      "loss": 0.0752,
      "step": 117
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.433766233766234e-05,
      "loss": 0.0674,
      "step": 118
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 0.0596,
      "step": 119
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.4233766233766236e-05,
      "loss": 0.1523,
      "step": 120
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.4181818181818183e-05,
      "loss": 0.077,
      "step": 121
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.4129870129870132e-05,
      "loss": 0.1388,
      "step": 122
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.4077922077922079e-05,
      "loss": 0.0716,
      "step": 123
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4025974025974028e-05,
      "loss": 0.0984,
      "step": 124
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3974025974025975e-05,
      "loss": 0.1308,
      "step": 125
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.3922077922077924e-05,
      "loss": 0.0642,
      "step": 126
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.3870129870129871e-05,
      "loss": 0.1113,
      "step": 127
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.381818181818182e-05,
      "loss": 0.0397,
      "step": 128
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3766233766233767e-05,
      "loss": 0.0342,
      "step": 129
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.3714285714285716e-05,
      "loss": 0.1108,
      "step": 130
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.3662337662337663e-05,
      "loss": 0.0723,
      "step": 131
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.06459677964448929,
      "eval_pearson": 0.8674211714097221,
      "eval_runtime": 5.7452,
      "eval_samples_per_second": 40.381,
      "eval_spearmanr": 0.8448753866690789,
      "eval_steps_per_second": 2.611,
      "step": 131
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.3610389610389612e-05,
      "loss": 0.0269,
      "step": 132
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.3558441558441559e-05,
      "loss": 0.0426,
      "step": 133
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.3506493506493508e-05,
      "loss": 0.0297,
      "step": 134
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.3454545454545455e-05,
      "loss": 0.0406,
      "step": 135
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.3402597402597404e-05,
      "loss": 0.0259,
      "step": 136
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.3350649350649351e-05,
      "loss": 0.0384,
      "step": 137
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.32987012987013e-05,
      "loss": 0.0637,
      "step": 138
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.3246753246753249e-05,
      "loss": 0.0543,
      "step": 139
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.3194805194805196e-05,
      "loss": 0.0543,
      "step": 140
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.3142857142857145e-05,
      "loss": 0.0526,
      "step": 141
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.3090909090909092e-05,
      "loss": 0.0121,
      "step": 142
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.303896103896104e-05,
      "loss": 0.0576,
      "step": 143
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.2987012987012988e-05,
      "loss": 0.0205,
      "step": 144
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.2935064935064937e-05,
      "loss": 0.0426,
      "step": 145
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.2883116883116884e-05,
      "loss": 0.0858,
      "step": 146
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.2831168831168832e-05,
      "loss": 0.0456,
      "step": 147
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.277922077922078e-05,
      "loss": 0.0616,
      "step": 148
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.2727272727272728e-05,
      "loss": 0.0474,
      "step": 149
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.2675324675324676e-05,
      "loss": 0.0369,
      "step": 150
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.2623376623376624e-05,
      "loss": 0.0237,
      "step": 151
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.2571428571428572e-05,
      "loss": 0.0291,
      "step": 152
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.251948051948052e-05,
      "loss": 0.0559,
      "step": 153
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.2467532467532468e-05,
      "loss": 0.0905,
      "step": 154
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.2415584415584416e-05,
      "loss": 0.0536,
      "step": 155
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.2363636363636364e-05,
      "loss": 0.0142,
      "step": 156
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.2311688311688312e-05,
      "loss": 0.0391,
      "step": 157
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.2259740259740261e-05,
      "loss": 0.0321,
      "step": 158
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.2207792207792208e-05,
      "loss": 0.0324,
      "step": 159
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.2155844155844157e-05,
      "loss": 0.0833,
      "step": 160
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.2103896103896104e-05,
      "loss": 0.0434,
      "step": 161
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.2051948051948053e-05,
      "loss": 0.0499,
      "step": 162
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.2e-05,
      "loss": 0.0202,
      "step": 163
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.1948051948051949e-05,
      "loss": 0.0661,
      "step": 164
    },
    {
      "epoch": 1.26,
      "learning_rate": 1.1896103896103896e-05,
      "loss": 0.029,
      "step": 165
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.1844155844155845e-05,
      "loss": 0.0241,
      "step": 166
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.1792207792207792e-05,
      "loss": 0.0645,
      "step": 167
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.1740259740259741e-05,
      "loss": 0.0404,
      "step": 168
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.1688311688311688e-05,
      "loss": 0.0446,
      "step": 169
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.1636363636363637e-05,
      "loss": 0.0473,
      "step": 170
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.1584415584415584e-05,
      "loss": 0.0664,
      "step": 171
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.1532467532467533e-05,
      "loss": 0.0592,
      "step": 172
    },
    {
      "epoch": 1.32,
      "learning_rate": 1.148051948051948e-05,
      "loss": 0.0133,
      "step": 173
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 0.0477,
      "step": 174
    },
    {
      "epoch": 1.34,
      "learning_rate": 1.1376623376623376e-05,
      "loss": 0.0168,
      "step": 175
    },
    {
      "epoch": 1.34,
      "learning_rate": 1.1324675324675325e-05,
      "loss": 0.0306,
      "step": 176
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.1272727272727272e-05,
      "loss": 0.0503,
      "step": 177
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.1220779220779221e-05,
      "loss": 0.0434,
      "step": 178
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.116883116883117e-05,
      "loss": 0.0416,
      "step": 179
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.1116883116883117e-05,
      "loss": 0.0259,
      "step": 180
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.1064935064935066e-05,
      "loss": 0.044,
      "step": 181
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.1012987012987013e-05,
      "loss": 0.07,
      "step": 182
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.0961038961038962e-05,
      "loss": 0.0812,
      "step": 183
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 0.0328,
      "step": 184
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.0857142857142858e-05,
      "loss": 0.0379,
      "step": 185
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.0805194805194805e-05,
      "loss": 0.0684,
      "step": 186
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.0753246753246754e-05,
      "loss": 0.048,
      "step": 187
    },
    {
      "epoch": 1.44,
      "learning_rate": 1.0701298701298701e-05,
      "loss": 0.0565,
      "step": 188
    },
    {
      "epoch": 1.44,
      "learning_rate": 1.064935064935065e-05,
      "loss": 0.0508,
      "step": 189
    },
    {
      "epoch": 1.45,
      "learning_rate": 1.0597402597402597e-05,
      "loss": 0.0537,
      "step": 190
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.0545454545454546e-05,
      "loss": 0.0232,
      "step": 191
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.0493506493506493e-05,
      "loss": 0.0333,
      "step": 192
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.0441558441558442e-05,
      "loss": 0.0847,
      "step": 193
    },
    {
      "epoch": 1.48,
      "learning_rate": 1.0389610389610389e-05,
      "loss": 0.0659,
      "step": 194
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.0337662337662338e-05,
      "loss": 0.0485,
      "step": 195
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.0285714285714285e-05,
      "loss": 0.0193,
      "step": 196
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.0233766233766234e-05,
      "loss": 0.0559,
      "step": 197
    },
    {
      "epoch": 1.51,
      "learning_rate": 1.0181818181818182e-05,
      "loss": 0.0376,
      "step": 198
    },
    {
      "epoch": 1.52,
      "learning_rate": 1.012987012987013e-05,
      "loss": 0.0386,
      "step": 199
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.0077922077922078e-05,
      "loss": 0.0406,
      "step": 200
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.0025974025974026e-05,
      "loss": 0.016,
      "step": 201
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.974025974025974e-06,
      "loss": 0.027,
      "step": 202
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.922077922077923e-06,
      "loss": 0.0343,
      "step": 203
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.87012987012987e-06,
      "loss": 0.0303,
      "step": 204
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.81818181818182e-06,
      "loss": 0.0481,
      "step": 205
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.766233766233766e-06,
      "loss": 0.0339,
      "step": 206
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.714285714285715e-06,
      "loss": 0.0372,
      "step": 207
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.662337662337662e-06,
      "loss": 0.0792,
      "step": 208
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.610389610389611e-06,
      "loss": 0.0273,
      "step": 209
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.558441558441558e-06,
      "loss": 0.0486,
      "step": 210
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.506493506493507e-06,
      "loss": 0.0287,
      "step": 211
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.454545454545456e-06,
      "loss": 0.0521,
      "step": 212
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.402597402597403e-06,
      "loss": 0.0829,
      "step": 213
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.350649350649352e-06,
      "loss": 0.0569,
      "step": 214
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.298701298701299e-06,
      "loss": 0.0398,
      "step": 215
    },
    {
      "epoch": 1.65,
      "learning_rate": 9.246753246753248e-06,
      "loss": 0.015,
      "step": 216
    },
    {
      "epoch": 1.66,
      "learning_rate": 9.194805194805195e-06,
      "loss": 0.0262,
      "step": 217
    },
    {
      "epoch": 1.66,
      "learning_rate": 9.142857142857144e-06,
      "loss": 0.0245,
      "step": 218
    },
    {
      "epoch": 1.67,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.0387,
      "step": 219
    },
    {
      "epoch": 1.68,
      "learning_rate": 9.03896103896104e-06,
      "loss": 0.0183,
      "step": 220
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.987012987012987e-06,
      "loss": 0.0219,
      "step": 221
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.935064935064936e-06,
      "loss": 0.0277,
      "step": 222
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.883116883116883e-06,
      "loss": 0.0405,
      "step": 223
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.831168831168832e-06,
      "loss": 0.0244,
      "step": 224
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.779220779220779e-06,
      "loss": 0.0429,
      "step": 225
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.727272727272728e-06,
      "loss": 0.0305,
      "step": 226
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.675324675324675e-06,
      "loss": 0.0854,
      "step": 227
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.623376623376624e-06,
      "loss": 0.0534,
      "step": 228
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.571428571428571e-06,
      "loss": 0.0111,
      "step": 229
    },
    {
      "epoch": 1.76,
      "learning_rate": 8.51948051948052e-06,
      "loss": 0.0519,
      "step": 230
    },
    {
      "epoch": 1.76,
      "learning_rate": 8.467532467532467e-06,
      "loss": 0.0748,
      "step": 231
    },
    {
      "epoch": 1.77,
      "learning_rate": 8.415584415584416e-06,
      "loss": 0.0264,
      "step": 232
    },
    {
      "epoch": 1.78,
      "learning_rate": 8.363636363636365e-06,
      "loss": 0.0368,
      "step": 233
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.311688311688313e-06,
      "loss": 0.0257,
      "step": 234
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.25974025974026e-06,
      "loss": 0.0169,
      "step": 235
    },
    {
      "epoch": 1.8,
      "learning_rate": 8.20779220779221e-06,
      "loss": 0.0402,
      "step": 236
    },
    {
      "epoch": 1.81,
      "learning_rate": 8.155844155844157e-06,
      "loss": 0.0432,
      "step": 237
    },
    {
      "epoch": 1.82,
      "learning_rate": 8.103896103896105e-06,
      "loss": 0.0836,
      "step": 238
    },
    {
      "epoch": 1.82,
      "learning_rate": 8.051948051948052e-06,
      "loss": 0.0301,
      "step": 239
    },
    {
      "epoch": 1.83,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0126,
      "step": 240
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.948051948051948e-06,
      "loss": 0.0316,
      "step": 241
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.896103896103897e-06,
      "loss": 0.0223,
      "step": 242
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.844155844155844e-06,
      "loss": 0.0208,
      "step": 243
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.792207792207793e-06,
      "loss": 0.0336,
      "step": 244
    },
    {
      "epoch": 1.87,
      "learning_rate": 7.74025974025974e-06,
      "loss": 0.0576,
      "step": 245
    },
    {
      "epoch": 1.88,
      "learning_rate": 7.68831168831169e-06,
      "loss": 0.0184,
      "step": 246
    },
    {
      "epoch": 1.89,
      "learning_rate": 7.636363636363638e-06,
      "loss": 0.0408,
      "step": 247
    },
    {
      "epoch": 1.89,
      "learning_rate": 7.584415584415585e-06,
      "loss": 0.0293,
      "step": 248
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.532467532467533e-06,
      "loss": 0.0262,
      "step": 249
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.480519480519481e-06,
      "loss": 0.0193,
      "step": 250
    },
    {
      "epoch": 1.92,
      "learning_rate": 7.428571428571429e-06,
      "loss": 0.0256,
      "step": 251
    },
    {
      "epoch": 1.92,
      "learning_rate": 7.376623376623377e-06,
      "loss": 0.025,
      "step": 252
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.324675324675325e-06,
      "loss": 0.0286,
      "step": 253
    },
    {
      "epoch": 1.94,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.0171,
      "step": 254
    },
    {
      "epoch": 1.95,
      "learning_rate": 7.220779220779221e-06,
      "loss": 0.0183,
      "step": 255
    },
    {
      "epoch": 1.95,
      "learning_rate": 7.16883116883117e-06,
      "loss": 0.0371,
      "step": 256
    },
    {
      "epoch": 1.96,
      "learning_rate": 7.116883116883118e-06,
      "loss": 0.0259,
      "step": 257
    },
    {
      "epoch": 1.97,
      "learning_rate": 7.064935064935066e-06,
      "loss": 0.0262,
      "step": 258
    },
    {
      "epoch": 1.98,
      "learning_rate": 7.012987012987014e-06,
      "loss": 0.0617,
      "step": 259
    },
    {
      "epoch": 1.98,
      "learning_rate": 6.961038961038962e-06,
      "loss": 0.0294,
      "step": 260
    },
    {
      "epoch": 1.99,
      "learning_rate": 6.90909090909091e-06,
      "loss": 0.0321,
      "step": 261
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.857142857142858e-06,
      "loss": 0.0433,
      "step": 262
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.032243285328149796,
      "eval_pearson": 0.9475021617385655,
      "eval_runtime": 5.4815,
      "eval_samples_per_second": 42.324,
      "eval_spearmanr": 0.9019723638288173,
      "eval_steps_per_second": 2.736,
      "step": 262
    }
  ],
  "max_steps": 393,
  "num_train_epochs": 3,
  "total_flos": 1095477709712160.0,
  "trial_name": null,
  "trial_params": null
}