{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 69.56521739130434,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.35,
      "learning_rate": 4.975e-05,
      "loss": 2.0249,
      "step": 1
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 2.9457,
      "step": 2
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.9250000000000004e-05,
      "loss": 2.0027,
      "step": 3
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.9e-05,
      "loss": 1.7133,
      "step": 4
    },
    {
      "epoch": 1.74,
      "learning_rate": 4.875e-05,
      "loss": 1.3105,
      "step": 5
    },
    {
      "epoch": 2.09,
      "learning_rate": 4.85e-05,
      "loss": 1.671,
      "step": 6
    },
    {
      "epoch": 2.43,
      "learning_rate": 4.825e-05,
      "loss": 1.0811,
      "step": 7
    },
    {
      "epoch": 2.78,
      "learning_rate": 4.8e-05,
      "loss": 1.0429,
      "step": 8
    },
    {
      "epoch": 3.13,
      "learning_rate": 4.775e-05,
      "loss": 0.8106,
      "step": 9
    },
    {
      "epoch": 3.48,
      "learning_rate": 4.75e-05,
      "loss": 0.6701,
      "step": 10
    },
    {
      "epoch": 3.83,
      "learning_rate": 4.7249999999999997e-05,
      "loss": 0.7937,
      "step": 11
    },
    {
      "epoch": 4.17,
      "learning_rate": 4.7e-05,
      "loss": 0.4486,
      "step": 12
    },
    {
      "epoch": 4.52,
      "learning_rate": 4.6750000000000005e-05,
      "loss": 0.3769,
      "step": 13
    },
    {
      "epoch": 4.87,
      "learning_rate": 4.6500000000000005e-05,
      "loss": 0.7175,
      "step": 14
    },
    {
      "epoch": 5.22,
      "learning_rate": 4.6250000000000006e-05,
      "loss": 0.4531,
      "step": 15
    },
    {
      "epoch": 5.57,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.5179,
      "step": 16
    },
    {
      "epoch": 5.91,
      "learning_rate": 4.575e-05,
      "loss": 0.5032,
      "step": 17
    },
    {
      "epoch": 6.26,
      "learning_rate": 4.55e-05,
      "loss": 0.3146,
      "step": 18
    },
    {
      "epoch": 6.61,
      "learning_rate": 4.525e-05,
      "loss": 0.4456,
      "step": 19
    },
    {
      "epoch": 6.96,
      "learning_rate": 4.5e-05,
      "loss": 0.4958,
      "step": 20
    },
    {
      "epoch": 7.3,
      "learning_rate": 4.4750000000000004e-05,
      "loss": 0.5074,
      "step": 21
    },
    {
      "epoch": 7.65,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 0.3419,
      "step": 22
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.4250000000000005e-05,
      "loss": 0.4738,
      "step": 23
    },
    {
      "epoch": 8.35,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.3103,
      "step": 24
    },
    {
      "epoch": 8.7,
      "learning_rate": 4.375e-05,
      "loss": 0.3316,
      "step": 25
    },
    {
      "epoch": 9.04,
      "learning_rate": 4.35e-05,
      "loss": 0.2852,
      "step": 26
    },
    {
      "epoch": 9.39,
      "learning_rate": 4.325e-05,
      "loss": 0.3347,
      "step": 27
    },
    {
      "epoch": 9.74,
      "learning_rate": 4.3e-05,
      "loss": 0.3021,
      "step": 28
    },
    {
      "epoch": 10.09,
      "learning_rate": 4.275e-05,
      "loss": 0.3012,
      "step": 29
    },
    {
      "epoch": 10.43,
      "learning_rate": 4.25e-05,
      "loss": 0.3022,
      "step": 30
    },
    {
      "epoch": 10.78,
      "learning_rate": 4.2250000000000004e-05,
      "loss": 0.4177,
      "step": 31
    },
    {
      "epoch": 11.13,
      "learning_rate": 4.2e-05,
      "loss": 0.315,
      "step": 32
    },
    {
      "epoch": 11.48,
      "learning_rate": 4.175e-05,
      "loss": 0.3257,
      "step": 33
    },
    {
      "epoch": 11.83,
      "learning_rate": 4.15e-05,
      "loss": 0.4222,
      "step": 34
    },
    {
      "epoch": 12.17,
      "learning_rate": 4.125e-05,
      "loss": 0.35,
      "step": 35
    },
    {
      "epoch": 12.52,
      "learning_rate": 4.1e-05,
      "loss": 0.2287,
      "step": 36
    },
    {
      "epoch": 12.87,
      "learning_rate": 4.075e-05,
      "loss": 0.324,
      "step": 37
    },
    {
      "epoch": 13.22,
      "learning_rate": 4.05e-05,
      "loss": 0.2167,
      "step": 38
    },
    {
      "epoch": 13.57,
      "learning_rate": 4.025e-05,
      "loss": 0.2734,
      "step": 39
    },
    {
      "epoch": 13.91,
      "learning_rate": 4e-05,
      "loss": 0.2169,
      "step": 40
    },
    {
      "epoch": 14.26,
      "learning_rate": 3.9750000000000004e-05,
      "loss": 0.1769,
      "step": 41
    },
    {
      "epoch": 14.61,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 0.2127,
      "step": 42
    },
    {
      "epoch": 14.96,
      "learning_rate": 3.9250000000000005e-05,
      "loss": 0.3576,
      "step": 43
    },
    {
      "epoch": 15.3,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.4379,
      "step": 44
    },
    {
      "epoch": 15.65,
      "learning_rate": 3.875e-05,
      "loss": 0.2296,
      "step": 45
    },
    {
      "epoch": 16.0,
      "learning_rate": 3.85e-05,
      "loss": 0.2771,
      "step": 46
    },
    {
      "epoch": 16.35,
      "learning_rate": 3.825e-05,
      "loss": 0.2787,
      "step": 47
    },
    {
      "epoch": 16.7,
      "learning_rate": 3.8e-05,
      "loss": 0.2917,
      "step": 48
    },
    {
      "epoch": 17.04,
      "learning_rate": 3.775e-05,
      "loss": 0.1987,
      "step": 49
    },
    {
      "epoch": 17.39,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.2037,
      "step": 50
    },
    {
      "epoch": 17.74,
      "learning_rate": 3.7250000000000004e-05,
      "loss": 0.2432,
      "step": 51
    },
    {
      "epoch": 18.09,
      "learning_rate": 3.7e-05,
      "loss": 0.2408,
      "step": 52
    },
    {
      "epoch": 18.43,
      "learning_rate": 3.675e-05,
      "loss": 0.3092,
      "step": 53
    },
    {
      "epoch": 18.78,
      "learning_rate": 3.65e-05,
      "loss": 0.239,
      "step": 54
    },
    {
      "epoch": 19.13,
      "learning_rate": 3.625e-05,
      "loss": 0.2615,
      "step": 55
    },
    {
      "epoch": 19.48,
      "learning_rate": 3.6e-05,
      "loss": 0.3466,
      "step": 56
    },
    {
      "epoch": 19.83,
      "learning_rate": 3.575e-05,
      "loss": 0.2688,
      "step": 57
    },
    {
      "epoch": 20.17,
      "learning_rate": 3.55e-05,
      "loss": 0.3091,
      "step": 58
    },
    {
      "epoch": 20.52,
      "learning_rate": 3.525e-05,
      "loss": 0.2815,
      "step": 59
    },
    {
      "epoch": 20.87,
      "learning_rate": 3.5e-05,
      "loss": 0.2555,
      "step": 60
    },
    {
      "epoch": 21.22,
      "learning_rate": 3.475e-05,
      "loss": 0.2404,
      "step": 61
    },
    {
      "epoch": 21.57,
      "learning_rate": 3.45e-05,
      "loss": 0.2588,
      "step": 62
    },
    {
      "epoch": 21.91,
      "learning_rate": 3.4250000000000006e-05,
      "loss": 0.2423,
      "step": 63
    },
    {
      "epoch": 22.26,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.1742,
      "step": 64
    },
    {
      "epoch": 22.61,
      "learning_rate": 3.375000000000001e-05,
      "loss": 0.2551,
      "step": 65
    },
    {
      "epoch": 22.96,
      "learning_rate": 3.35e-05,
      "loss": 0.2193,
      "step": 66
    },
    {
      "epoch": 23.3,
      "learning_rate": 3.325e-05,
      "loss": 0.3251,
      "step": 67
    },
    {
      "epoch": 23.65,
      "learning_rate": 3.3e-05,
      "loss": 0.1836,
      "step": 68
    },
    {
      "epoch": 24.0,
      "learning_rate": 3.275e-05,
      "loss": 0.1561,
      "step": 69
    },
    {
      "epoch": 24.35,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 0.226,
      "step": 70
    },
    {
      "epoch": 24.7,
      "learning_rate": 3.2250000000000005e-05,
      "loss": 0.129,
      "step": 71
    },
    {
      "epoch": 25.04,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.2349,
      "step": 72
    },
    {
      "epoch": 25.39,
      "learning_rate": 3.175e-05,
      "loss": 0.1885,
      "step": 73
    },
    {
      "epoch": 25.74,
      "learning_rate": 3.15e-05,
      "loss": 0.1659,
      "step": 74
    },
    {
      "epoch": 26.09,
      "learning_rate": 3.125e-05,
      "loss": 0.1611,
      "step": 75
    },
    {
      "epoch": 26.43,
      "learning_rate": 3.1e-05,
      "loss": 0.1922,
      "step": 76
    },
    {
      "epoch": 26.78,
      "learning_rate": 3.075e-05,
      "loss": 0.2673,
      "step": 77
    },
    {
      "epoch": 27.13,
      "learning_rate": 3.05e-05,
      "loss": 0.2417,
      "step": 78
    },
    {
      "epoch": 27.48,
      "learning_rate": 3.025e-05,
      "loss": 0.1435,
      "step": 79
    },
    {
      "epoch": 27.83,
      "learning_rate": 3e-05,
      "loss": 0.1883,
      "step": 80
    },
    {
      "epoch": 28.17,
      "learning_rate": 2.975e-05,
      "loss": 0.2541,
      "step": 81
    },
    {
      "epoch": 28.52,
      "learning_rate": 2.95e-05,
      "loss": 0.2781,
      "step": 82
    },
    {
      "epoch": 28.87,
      "learning_rate": 2.925e-05,
      "loss": 0.2035,
      "step": 83
    },
    {
      "epoch": 29.22,
      "learning_rate": 2.9e-05,
      "loss": 0.1572,
      "step": 84
    },
    {
      "epoch": 29.57,
      "learning_rate": 2.8749999999999997e-05,
      "loss": 0.2049,
      "step": 85
    },
    {
      "epoch": 29.91,
      "learning_rate": 2.8499999999999998e-05,
      "loss": 0.214,
      "step": 86
    },
    {
      "epoch": 30.26,
      "learning_rate": 2.825e-05,
      "loss": 0.1437,
      "step": 87
    },
    {
      "epoch": 30.61,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.2487,
      "step": 88
    },
    {
      "epoch": 30.96,
      "learning_rate": 2.7750000000000004e-05,
      "loss": 0.1652,
      "step": 89
    },
    {
      "epoch": 31.3,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 0.2676,
      "step": 90
    },
    {
      "epoch": 31.65,
      "learning_rate": 2.725e-05,
      "loss": 0.1596,
      "step": 91
    },
    {
      "epoch": 32.0,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.1471,
      "step": 92
    },
    {
      "epoch": 32.35,
      "learning_rate": 2.6750000000000003e-05,
      "loss": 0.1817,
      "step": 93
    },
    {
      "epoch": 32.7,
      "learning_rate": 2.6500000000000004e-05,
      "loss": 0.1454,
      "step": 94
    },
    {
      "epoch": 33.04,
      "learning_rate": 2.625e-05,
      "loss": 0.2518,
      "step": 95
    },
    {
      "epoch": 33.39,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.226,
      "step": 96
    },
    {
      "epoch": 33.74,
      "learning_rate": 2.5750000000000002e-05,
      "loss": 0.1982,
      "step": 97
    },
    {
      "epoch": 34.09,
      "learning_rate": 2.5500000000000003e-05,
      "loss": 0.202,
      "step": 98
    },
    {
      "epoch": 34.43,
      "learning_rate": 2.525e-05,
      "loss": 0.1526,
      "step": 99
    },
    {
      "epoch": 34.78,
      "learning_rate": 2.5e-05,
      "loss": 0.2016,
      "step": 100
    },
    {
      "epoch": 35.13,
      "learning_rate": 2.4750000000000002e-05,
      "loss": 0.1659,
      "step": 101
    },
    {
      "epoch": 35.48,
      "learning_rate": 2.45e-05,
      "loss": 0.1135,
      "step": 102
    },
    {
      "epoch": 35.83,
      "learning_rate": 2.425e-05,
      "loss": 0.2228,
      "step": 103
    },
    {
      "epoch": 36.17,
      "learning_rate": 2.4e-05,
      "loss": 0.2902,
      "step": 104
    },
    {
      "epoch": 36.52,
      "learning_rate": 2.375e-05,
      "loss": 0.1695,
      "step": 105
    },
    {
      "epoch": 36.87,
      "learning_rate": 2.35e-05,
      "loss": 0.1114,
      "step": 106
    },
    {
      "epoch": 37.22,
      "learning_rate": 2.3250000000000003e-05,
      "loss": 0.1969,
      "step": 107
    },
    {
      "epoch": 37.57,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.2099,
      "step": 108
    },
    {
      "epoch": 37.91,
      "learning_rate": 2.275e-05,
      "loss": 0.1552,
      "step": 109
    },
    {
      "epoch": 38.26,
      "learning_rate": 2.25e-05,
      "loss": 0.1426,
      "step": 110
    },
    {
      "epoch": 38.61,
      "learning_rate": 2.2250000000000002e-05,
      "loss": 0.2567,
      "step": 111
    },
    {
      "epoch": 38.96,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.1783,
      "step": 112
    },
    {
      "epoch": 39.3,
      "learning_rate": 2.175e-05,
      "loss": 0.1611,
      "step": 113
    },
    {
      "epoch": 39.65,
      "learning_rate": 2.15e-05,
      "loss": 0.2217,
      "step": 114
    },
    {
      "epoch": 40.0,
      "learning_rate": 2.125e-05,
      "loss": 0.1905,
      "step": 115
    },
    {
      "epoch": 40.35,
      "learning_rate": 2.1e-05,
      "loss": 0.1544,
      "step": 116
    },
    {
      "epoch": 40.7,
      "learning_rate": 2.075e-05,
      "loss": 0.1325,
      "step": 117
    },
    {
      "epoch": 41.04,
      "learning_rate": 2.05e-05,
      "loss": 0.2089,
      "step": 118
    },
    {
      "epoch": 41.39,
      "learning_rate": 2.025e-05,
      "loss": 0.1378,
      "step": 119
    },
    {
      "epoch": 41.74,
      "learning_rate": 2e-05,
      "loss": 0.2517,
      "step": 120
    },
    {
      "epoch": 42.09,
      "learning_rate": 1.9750000000000002e-05,
      "loss": 0.137,
      "step": 121
    },
    {
      "epoch": 42.43,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 0.2732,
      "step": 122
    },
    {
      "epoch": 42.78,
      "learning_rate": 1.925e-05,
      "loss": 0.1259,
      "step": 123
    },
    {
      "epoch": 43.13,
      "learning_rate": 1.9e-05,
      "loss": 0.1292,
      "step": 124
    },
    {
      "epoch": 43.48,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.1421,
      "step": 125
    },
    {
      "epoch": 43.83,
      "learning_rate": 1.85e-05,
      "loss": 0.2085,
      "step": 126
    },
    {
      "epoch": 44.17,
      "learning_rate": 1.825e-05,
      "loss": 0.1539,
      "step": 127
    },
    {
      "epoch": 44.52,
      "learning_rate": 1.8e-05,
      "loss": 0.2149,
      "step": 128
    },
    {
      "epoch": 44.87,
      "learning_rate": 1.775e-05,
      "loss": 0.1326,
      "step": 129
    },
    {
      "epoch": 45.22,
      "learning_rate": 1.75e-05,
      "loss": 0.1912,
      "step": 130
    },
    {
      "epoch": 45.57,
      "learning_rate": 1.725e-05,
      "loss": 0.114,
      "step": 131
    },
    {
      "epoch": 45.91,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.2012,
      "step": 132
    },
    {
      "epoch": 46.26,
      "learning_rate": 1.675e-05,
      "loss": 0.1161,
      "step": 133
    },
    {
      "epoch": 46.61,
      "learning_rate": 1.65e-05,
      "loss": 0.1082,
      "step": 134
    },
    {
      "epoch": 46.96,
      "learning_rate": 1.6250000000000002e-05,
      "loss": 0.1639,
      "step": 135
    },
    {
      "epoch": 47.3,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.141,
      "step": 136
    },
    {
      "epoch": 47.65,
      "learning_rate": 1.575e-05,
      "loss": 0.1522,
      "step": 137
    },
    {
      "epoch": 48.0,
      "learning_rate": 1.55e-05,
      "loss": 0.1918,
      "step": 138
    },
    {
      "epoch": 48.35,
      "learning_rate": 1.525e-05,
      "loss": 0.2514,
      "step": 139
    },
    {
      "epoch": 48.7,
      "learning_rate": 1.5e-05,
      "loss": 0.1446,
      "step": 140
    },
    {
      "epoch": 49.04,
      "learning_rate": 1.475e-05,
      "loss": 0.2332,
      "step": 141
    },
    {
      "epoch": 49.39,
      "learning_rate": 1.45e-05,
      "loss": 0.1704,
      "step": 142
    },
    {
      "epoch": 49.74,
      "learning_rate": 1.4249999999999999e-05,
      "loss": 0.1637,
      "step": 143
    },
    {
      "epoch": 50.09,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.1337,
      "step": 144
    },
    {
      "epoch": 50.43,
      "learning_rate": 1.3750000000000002e-05,
      "loss": 0.1205,
      "step": 145
    },
    {
      "epoch": 50.78,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 0.2873,
      "step": 146
    },
    {
      "epoch": 51.13,
      "learning_rate": 1.3250000000000002e-05,
      "loss": 0.0932,
      "step": 147
    },
    {
      "epoch": 51.48,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.1206,
      "step": 148
    },
    {
      "epoch": 51.83,
      "learning_rate": 1.2750000000000002e-05,
      "loss": 0.1392,
      "step": 149
    },
    {
      "epoch": 52.17,
      "learning_rate": 1.25e-05,
      "loss": 0.2465,
      "step": 150
    },
    {
      "epoch": 52.52,
      "learning_rate": 1.225e-05,
      "loss": 0.2555,
      "step": 151
    },
    {
      "epoch": 52.87,
      "learning_rate": 1.2e-05,
      "loss": 0.1533,
      "step": 152
    },
    {
      "epoch": 53.22,
      "learning_rate": 1.175e-05,
      "loss": 0.0969,
      "step": 153
    },
    {
      "epoch": 53.57,
      "learning_rate": 1.1500000000000002e-05,
      "loss": 0.1249,
      "step": 154
    },
    {
      "epoch": 53.91,
      "learning_rate": 1.125e-05,
      "loss": 0.0881,
      "step": 155
    },
    {
      "epoch": 54.26,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.1939,
      "step": 156
    },
    {
      "epoch": 54.61,
      "learning_rate": 1.075e-05,
      "loss": 0.1402,
      "step": 157
    },
    {
      "epoch": 54.96,
      "learning_rate": 1.05e-05,
      "loss": 0.1483,
      "step": 158
    },
    {
      "epoch": 55.3,
      "learning_rate": 1.025e-05,
      "loss": 0.1085,
      "step": 159
    },
    {
      "epoch": 55.65,
      "learning_rate": 1e-05,
      "loss": 0.1076,
      "step": 160
    },
    {
      "epoch": 56.0,
      "learning_rate": 9.750000000000002e-06,
      "loss": 0.1524,
      "step": 161
    },
    {
      "epoch": 56.35,
      "learning_rate": 9.5e-06,
      "loss": 0.1808,
      "step": 162
    },
    {
      "epoch": 56.7,
      "learning_rate": 9.25e-06,
      "loss": 0.1656,
      "step": 163
    },
    {
      "epoch": 57.04,
      "learning_rate": 9e-06,
      "loss": 0.2004,
      "step": 164
    },
    {
      "epoch": 57.39,
      "learning_rate": 8.75e-06,
      "loss": 0.1343,
      "step": 165
    },
    {
      "epoch": 57.74,
      "learning_rate": 8.500000000000002e-06,
      "loss": 0.2315,
      "step": 166
    },
    {
      "epoch": 58.09,
      "learning_rate": 8.25e-06,
      "loss": 0.1788,
      "step": 167
    },
    {
      "epoch": 58.43,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.2261,
      "step": 168
    },
    {
      "epoch": 58.78,
      "learning_rate": 7.75e-06,
      "loss": 0.1278,
      "step": 169
    },
    {
      "epoch": 59.13,
      "learning_rate": 7.5e-06,
      "loss": 0.171,
      "step": 170
    },
    {
      "epoch": 59.48,
      "learning_rate": 7.25e-06,
      "loss": 0.2194,
      "step": 171
    },
    {
      "epoch": 59.83,
      "learning_rate": 7.000000000000001e-06,
      "loss": 0.1238,
      "step": 172
    },
    {
      "epoch": 60.17,
      "learning_rate": 6.750000000000001e-06,
      "loss": 0.0954,
      "step": 173
    },
    {
      "epoch": 60.52,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.1611,
      "step": 174
    },
    {
      "epoch": 60.87,
      "learning_rate": 6.25e-06,
      "loss": 0.175,
      "step": 175
    },
    {
      "epoch": 61.22,
      "learning_rate": 6e-06,
      "loss": 0.0937,
      "step": 176
    },
    {
      "epoch": 61.57,
      "learning_rate": 5.750000000000001e-06,
      "loss": 0.1717,
      "step": 177
    },
    {
      "epoch": 61.91,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.2054,
      "step": 178
    },
    {
      "epoch": 62.26,
      "learning_rate": 5.25e-06,
      "loss": 0.1226,
      "step": 179
    },
    {
      "epoch": 62.61,
      "learning_rate": 5e-06,
      "loss": 0.1087,
      "step": 180
    },
    {
      "epoch": 62.96,
      "learning_rate": 4.75e-06,
      "loss": 0.2178,
      "step": 181
    },
    {
      "epoch": 63.3,
      "learning_rate": 4.5e-06,
      "loss": 0.1176,
      "step": 182
    },
    {
      "epoch": 63.65,
      "learning_rate": 4.250000000000001e-06,
      "loss": 0.1652,
      "step": 183
    },
    {
      "epoch": 64.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0758,
      "step": 184
    },
    {
      "epoch": 64.35,
      "learning_rate": 3.75e-06,
      "loss": 0.1378,
      "step": 185
    },
    {
      "epoch": 64.7,
      "learning_rate": 3.5000000000000004e-06,
      "loss": 0.1681,
      "step": 186
    },
    {
      "epoch": 65.04,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.1048,
      "step": 187
    },
    {
      "epoch": 65.39,
      "learning_rate": 3e-06,
      "loss": 0.2369,
      "step": 188
    },
    {
      "epoch": 65.74,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.1683,
      "step": 189
    },
    {
      "epoch": 66.09,
      "learning_rate": 2.5e-06,
      "loss": 0.0896,
      "step": 190
    },
    {
      "epoch": 66.43,
      "learning_rate": 2.25e-06,
      "loss": 0.1213,
      "step": 191
    },
    {
      "epoch": 66.78,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.2128,
      "step": 192
    },
    {
      "epoch": 67.13,
      "learning_rate": 1.7500000000000002e-06,
      "loss": 0.2779,
      "step": 193
    },
    {
      "epoch": 67.48,
      "learning_rate": 1.5e-06,
      "loss": 0.1962,
      "step": 194
    },
    {
      "epoch": 67.83,
      "learning_rate": 1.25e-06,
      "loss": 0.0697,
      "step": 195
    },
    {
      "epoch": 68.17,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0885,
      "step": 196
    },
    {
      "epoch": 68.52,
      "learning_rate": 7.5e-07,
      "loss": 0.147,
      "step": 197
    },
    {
      "epoch": 68.87,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.1484,
      "step": 198
    },
    {
      "epoch": 69.22,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 0.1452,
      "step": 199
    },
    {
      "epoch": 69.57,
      "learning_rate": 0.0,
      "loss": 0.1727,
      "step": 200
    },
    {
      "epoch": 69.57,
      "step": 200,
      "total_flos": 4580083569891060.0,
      "train_loss": 0.2846686257049441,
      "train_runtime": 4604.0545,
      "train_samples_per_second": 7.95,
      "train_steps_per_second": 0.043
    }
  ],
  "max_steps": 200,
  "num_train_epochs": 100,
  "total_flos": 4580083569891060.0,
  "trial_name": null,
  "trial_params": null
}