{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.82857142857143,
  "eval_steps": 500,
  "global_step": 430,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 5.1473,
      "step": 1
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 5.1654,
      "step": 2
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.615384615384616e-05,
      "loss": 4.4404,
      "step": 3
    },
    {
      "epoch": 0.09,
      "learning_rate": 6.153846153846155e-05,
      "loss": 2.1218,
      "step": 4
    },
    {
      "epoch": 0.11,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.7891,
      "step": 5
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.4084,
      "step": 6
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001076923076923077,
      "loss": 0.2285,
      "step": 7
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001230769230769231,
      "loss": 0.2082,
      "step": 8
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00013846153846153847,
      "loss": 0.1934,
      "step": 9
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.1951,
      "step": 10
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00016923076923076923,
      "loss": 0.1867,
      "step": 11
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018461538461538463,
      "loss": 0.1931,
      "step": 12
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.1895,
      "step": 13
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019999716210981734,
      "loss": 0.16,
      "step": 14
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019998864860034169,
      "loss": 0.2126,
      "step": 15
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001999744599547812,
      "loss": 0.1772,
      "step": 16
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001999545969784522,
      "loss": 0.1949,
      "step": 17
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019992906079873365,
      "loss": 0.1923,
      "step": 18
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019989785286500295,
      "loss": 0.1709,
      "step": 19
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001998609749485539,
      "loss": 0.1823,
      "step": 20
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001998184291424961,
      "loss": 0.1656,
      "step": 21
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019977021786163598,
      "loss": 0.194,
      "step": 22
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019971634384234003,
      "loss": 0.174,
      "step": 23
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019965681014237917,
      "loss": 0.1699,
      "step": 24
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019959162014075553,
      "loss": 0.1771,
      "step": 25
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019952077753751036,
      "loss": 0.1942,
      "step": 26
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019944428635351426,
      "loss": 0.1818,
      "step": 27
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019936215093023884,
      "loss": 0.1956,
      "step": 28
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001992743759295103,
      "loss": 0.1738,
      "step": 29
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019918096633324492,
      "loss": 0.1897,
      "step": 30
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001990819274431662,
      "loss": 0.1558,
      "step": 31
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019897726488050406,
      "loss": 0.2183,
      "step": 32
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019886698458567562,
      "loss": 0.1844,
      "step": 33
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019875109281794825,
      "loss": 0.1774,
      "step": 34
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019862959615508417,
      "loss": 0.1709,
      "step": 35
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019850250149296703,
      "loss": 0.2023,
      "step": 36
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00019836981604521076,
      "loss": 0.1717,
      "step": 37
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00019823154734274997,
      "loss": 0.1751,
      "step": 38
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001980877032334125,
      "loss": 0.1903,
      "step": 39
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019793829188147406,
      "loss": 0.2017,
      "step": 40
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00019778332176719483,
      "loss": 0.1651,
      "step": 41
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00019762280168633814,
      "loss": 0.1913,
      "step": 42
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001974567407496712,
      "loss": 0.1749,
      "step": 43
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001972851483824481,
      "loss": 0.1953,
      "step": 44
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00019710803432387465,
      "loss": 0.2126,
      "step": 45
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00019692540862655585,
      "loss": 0.181,
      "step": 46
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001967372816559252,
      "loss": 0.176,
      "step": 47
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00019654366408965635,
      "loss": 0.1655,
      "step": 48
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00019634456691705702,
      "loss": 0.1676,
      "step": 49
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00019614000143844558,
      "loss": 0.1438,
      "step": 50
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001959299792645092,
      "loss": 0.1915,
      "step": 51
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00019571451231564525,
      "loss": 0.2314,
      "step": 52
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00019549361282128445,
      "loss": 0.1736,
      "step": 53
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00019526729331919697,
      "loss": 0.1765,
      "step": 54
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00019503556665478067,
      "loss": 0.1969,
      "step": 55
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00019479844598033202,
      "loss": 0.1968,
      "step": 56
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001945559447542998,
      "loss": 0.1724,
      "step": 57
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00019430807674052092,
      "loss": 0.2096,
      "step": 58
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00019405485600743942,
      "loss": 0.1861,
      "step": 59
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00019379629692730798,
      "loss": 0.1752,
      "step": 60
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00019353241417537214,
      "loss": 0.1746,
      "step": 61
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00019326322272903722,
      "loss": 0.175,
      "step": 62
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00019298873786701857,
      "loss": 0.1752,
      "step": 63
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00019270897516847403,
      "loss": 0.1719,
      "step": 64
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00019242395051212,
      "loss": 0.1814,
      "step": 65
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00019213368007532986,
      "loss": 0.1792,
      "step": 66
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00019183818033321614,
      "loss": 0.1683,
      "step": 67
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00019153746805769512,
      "loss": 0.175,
      "step": 68
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00019123156031653515,
      "loss": 0.1558,
      "step": 69
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00019092047447238773,
      "loss": 0.1907,
      "step": 70
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00019060422818180207,
      "loss": 0.2572,
      "step": 71
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00019028283939422308,
      "loss": 0.1781,
      "step": 72
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001899563263509725,
      "loss": 0.1659,
      "step": 73
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00018962470758421342,
      "loss": 0.174,
      "step": 74
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0001892880019158988,
      "loss": 0.1795,
      "step": 75
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00018894622845670283,
      "loss": 0.1712,
      "step": 76
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00018859940660493634,
      "loss": 0.1628,
      "step": 77
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00018824755604544594,
      "loss": 0.1901,
      "step": 78
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001878906967484966,
      "loss": 0.1549,
      "step": 79
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001875288489686382,
      "loss": 0.1972,
      "step": 80
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00018716203324355607,
      "loss": 0.1758,
      "step": 81
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00018679027039290497,
      "loss": 0.1772,
      "step": 82
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001864135815171279,
      "loss": 0.1839,
      "step": 83
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00018603198799625807,
      "loss": 0.192,
      "step": 84
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00018564551148870563,
      "loss": 0.1795,
      "step": 85
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00018525417393002824,
      "loss": 0.1731,
      "step": 86
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00018485799753168634,
      "loss": 0.1965,
      "step": 87
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00018445700477978205,
      "loss": 0.214,
      "step": 88
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0001840512184337833,
      "loss": 0.2024,
      "step": 89
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00018364066152523183,
      "loss": 0.1786,
      "step": 90
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00018322535735643605,
      "loss": 0.1938,
      "step": 91
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00018280532949914842,
      "loss": 0.1634,
      "step": 92
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0001823806017932276,
      "loss": 0.1655,
      "step": 93
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00018195119834528534,
      "loss": 0.1635,
      "step": 94
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00018151714352731822,
      "loss": 0.1938,
      "step": 95
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00018107846197532433,
      "loss": 0.1696,
      "step": 96
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00018063517858790516,
      "loss": 0.1806,
      "step": 97
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00018018731852485206,
      "loss": 0.1826,
      "step": 98
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00017973490720571864,
      "loss": 0.1976,
      "step": 99
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00017927797030837768,
      "loss": 0.1815,
      "step": 100
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00017881653376756394,
      "loss": 0.1818,
      "step": 101
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0001783506237734019,
      "loss": 0.1649,
      "step": 102
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00017788026676991963,
      "loss": 0.1684,
      "step": 103
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00017740548945354752,
      "loss": 0.1517,
      "step": 104
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00017692631877160326,
      "loss": 0.1871,
      "step": 105
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0001764427819207624,
      "loss": 0.1921,
      "step": 106
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0001759549063455145,
      "loss": 0.1659,
      "step": 107
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00017546271973660574,
      "loss": 0.1807,
      "step": 108
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.000174966250029467,
      "loss": 0.1808,
      "step": 109
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00017446552540262844,
      "loss": 0.1844,
      "step": 110
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0001739605742761201,
      "loss": 0.174,
      "step": 111
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00017345142530985887,
      "loss": 0.1752,
      "step": 112
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.00017293810740202182,
      "loss": 0.1788,
      "step": 113
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00017242064968740598,
      "loss": 0.1748,
      "step": 114
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.00017189908153577473,
      "loss": 0.1711,
      "step": 115
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0001713734325501908,
      "loss": 0.1741,
      "step": 116
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00017084373256533603,
      "loss": 0.1779,
      "step": 117
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.00017031001164581828,
      "loss": 0.1761,
      "step": 118
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.00016977230008446466,
      "loss": 0.1771,
      "step": 119
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.00016923062840060234,
      "loss": 0.1682,
      "step": 120
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.00016868502733832644,
      "loss": 0.175,
      "step": 121
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.00016813552786475495,
      "loss": 0.1804,
      "step": 122
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.00016758216116827105,
      "loss": 0.1724,
      "step": 123
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0001670249586567531,
      "loss": 0.2074,
      "step": 124
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.00016646395195579178,
      "loss": 0.1881,
      "step": 125
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.00016589917290689532,
      "loss": 0.1791,
      "step": 126
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.00016533065356568206,
      "loss": 0.1841,
      "step": 127
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00016475842620006118,
      "loss": 0.1779,
      "step": 128
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0001641825232884011,
      "loss": 0.1812,
      "step": 129
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.0001636029775176862,
      "loss": 0.1699,
      "step": 130
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.0001630198217816616,
      "loss": 0.1741,
      "step": 131
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.000162433089178966,
      "loss": 0.1683,
      "step": 132
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0001618428130112533,
      "loss": 0.1808,
      "step": 133
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.0001612490267813023,
      "loss": 0.1663,
      "step": 134
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0001606517641911153,
      "loss": 0.1684,
      "step": 135
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.00016005105914000507,
      "loss": 0.1675,
      "step": 136
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.00015944694572267096,
      "loss": 0.1706,
      "step": 137
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00015883945822726372,
      "loss": 0.1773,
      "step": 138
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.00015822863113343935,
      "loss": 0.1763,
      "step": 139
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.00015761449911040208,
      "loss": 0.1799,
      "step": 140
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.00015699709701493667,
      "loss": 0.1684,
      "step": 141
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0001563764598894301,
      "loss": 0.1742,
      "step": 142
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.0001557526229598824,
      "loss": 0.1751,
      "step": 143
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.0001551256216339076,
      "loss": 0.1754,
      "step": 144
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.00015449549149872376,
      "loss": 0.1764,
      "step": 145
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.00015386226831913348,
      "loss": 0.1703,
      "step": 146
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.00015322598803549356,
      "loss": 0.1731,
      "step": 147
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.00015258668676167546,
      "loss": 0.1741,
      "step": 148
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.00015194440078301536,
      "loss": 0.1703,
      "step": 149
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.00015129916655425468,
      "loss": 0.167,
      "step": 150
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.00015065102069747118,
      "loss": 0.1876,
      "step": 151
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.1761,
      "step": 152
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.00014934614141234618,
      "loss": 0.1592,
      "step": 153
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.000148689482046087,
      "loss": 0.1581,
      "step": 154
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.00014803005917176585,
      "loss": 0.1804,
      "step": 155
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.00014736791021677676,
      "loss": 0.1699,
      "step": 156
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.0001467030727632401,
      "loss": 0.2209,
      "step": 157
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.0001460355845458695,
      "loss": 0.177,
      "step": 158
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.00014536548344983016,
      "loss": 0.1828,
      "step": 159
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.00014469280750858854,
      "loss": 0.1725,
      "step": 160
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.00014401759490175362,
      "loss": 0.1645,
      "step": 161
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.00014333988395290992,
      "loss": 0.1754,
      "step": 162
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.00014265971312744252,
      "loss": 0.1867,
      "step": 163
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.00014197712103035346,
      "loss": 0.1735,
      "step": 164
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.00014129214640407102,
      "loss": 0.1767,
      "step": 165
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.00014060482812625055,
      "loss": 0.1657,
      "step": 166
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0001399152052075679,
      "loss": 0.1734,
      "step": 167
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.00013922331678950525,
      "loss": 0.1821,
      "step": 168
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.00013852920214212964,
      "loss": 0.1839,
      "step": 169
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.00013783290066186391,
      "loss": 0.1958,
      "step": 170
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.00013713445186925075,
      "loss": 0.1815,
      "step": 171
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.00013643389540670962,
      "loss": 0.1716,
      "step": 172
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.00013573127103628667,
      "loss": 0.1688,
      "step": 173
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.00013502661863739793,
      "loss": 0.1664,
      "step": 174
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00013431997820456592,
      "loss": 0.1638,
      "step": 175
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.0001336113898451496,
      "loss": 0.2074,
      "step": 176
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.0001329008937770679,
      "loss": 0.1675,
      "step": 177
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.0001321885303265172,
      "loss": 0.1556,
      "step": 178
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.00013147433992568227,
      "loss": 0.1653,
      "step": 179
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.00013075836311044175,
      "loss": 0.1603,
      "step": 180
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.0001300406405180671,
      "loss": 0.1758,
      "step": 181
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.0001293212128849163,
      "loss": 0.1949,
      "step": 182
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.00012860012104412165,
      "loss": 0.17,
      "step": 183
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.0001278774059232723,
      "loss": 0.1662,
      "step": 184
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.00012715310854209124,
      "loss": 0.1571,
      "step": 185
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.00012642727001010694,
      "loss": 0.1979,
      "step": 186
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.00012569993152432028,
      "loss": 0.1666,
      "step": 187
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.00012497113436686627,
      "loss": 0.1065,
      "step": 188
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.00012424091990267087,
      "loss": 0.1146,
      "step": 189
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.0001235093295771032,
      "loss": 0.1749,
      "step": 190
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.00012277640491362341,
      "loss": 0.1256,
      "step": 191
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.0001220421875114256,
      "loss": 0.1835,
      "step": 192
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.0001213067190430769,
      "loss": 0.1628,
      "step": 193
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.00012057004125215223,
      "loss": 0.256,
      "step": 194
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.00011983219595086506,
      "loss": 0.146,
      "step": 195
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.00011909322501769406,
      "loss": 0.1682,
      "step": 196
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.0001183531703950064,
      "loss": 0.1794,
      "step": 197
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.00011761207408667703,
      "loss": 0.1905,
      "step": 198
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.00011686997815570473,
      "loss": 0.1749,
      "step": 199
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.00011612692472182463,
      "loss": 0.1775,
      "step": 200
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.00011538295595911764,
      "loss": 0.1672,
      "step": 201
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.00011463811409361667,
      "loss": 0.2042,
      "step": 202
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.00011389244140091013,
      "loss": 0.1714,
      "step": 203
    },
    {
      "epoch": 4.66,
      "learning_rate": 0.00011314598020374231,
      "loss": 0.1637,
      "step": 204
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.00011239877286961122,
      "loss": 0.1786,
      "step": 205
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.00011165086180836406,
      "loss": 0.175,
      "step": 206
    },
    {
      "epoch": 4.73,
      "learning_rate": 0.00011090228946979,
      "loss": 0.1763,
      "step": 207
    },
    {
      "epoch": 4.75,
      "learning_rate": 0.00011015309834121081,
      "loss": 0.1941,
      "step": 208
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.00010940333094506952,
      "loss": 0.1452,
      "step": 209
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.00010865302983651673,
      "loss": 0.1719,
      "step": 210
    },
    {
      "epoch": 4.82,
      "learning_rate": 0.00010790223760099549,
      "loss": 0.1697,
      "step": 211
    },
    {
      "epoch": 4.85,
      "learning_rate": 0.00010715099685182408,
      "loss": 0.1644,
      "step": 212
    },
    {
      "epoch": 4.87,
      "learning_rate": 0.00010639935022777741,
      "loss": 0.1683,
      "step": 213
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.00010564734039066699,
      "loss": 0.1746,
      "step": 214
    },
    {
      "epoch": 4.91,
      "learning_rate": 0.00010489501002291952,
      "loss": 0.1606,
      "step": 215
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.00010414240182515429,
      "loss": 0.1841,
      "step": 216
    },
    {
      "epoch": 4.96,
      "learning_rate": 0.00010338955851375962,
      "loss": 0.1833,
      "step": 217
    },
    {
      "epoch": 4.98,
      "learning_rate": 0.00010263652281846837,
      "loss": 0.1802,
      "step": 218
    },
    {
      "epoch": 5.01,
      "learning_rate": 0.00010188333747993264,
      "loss": 0.1675,
      "step": 219
    },
    {
      "epoch": 5.03,
      "learning_rate": 0.00010113004524729799,
      "loss": 0.1598,
      "step": 220
    },
    {
      "epoch": 5.05,
      "learning_rate": 0.00010037668887577709,
      "loss": 0.1612,
      "step": 221
    },
    {
      "epoch": 5.07,
      "learning_rate": 9.962331112422293e-05,
      "loss": 0.1812,
      "step": 222
    },
    {
      "epoch": 5.1,
      "learning_rate": 9.886995475270205e-05,
      "loss": 0.1853,
      "step": 223
    },
    {
      "epoch": 5.12,
      "learning_rate": 9.811666252006742e-05,
      "loss": 0.1369,
      "step": 224
    },
    {
      "epoch": 5.14,
      "learning_rate": 9.73634771815317e-05,
      "loss": 0.1563,
      "step": 225
    },
    {
      "epoch": 5.17,
      "learning_rate": 9.661044148624037e-05,
      "loss": 0.1466,
      "step": 226
    },
    {
      "epoch": 5.19,
      "learning_rate": 9.58575981748457e-05,
      "loss": 0.1343,
      "step": 227
    },
    {
      "epoch": 5.21,
      "learning_rate": 9.510498997708049e-05,
      "loss": 0.1231,
      "step": 228
    },
    {
      "epoch": 5.23,
      "learning_rate": 9.435265960933302e-05,
      "loss": 0.1472,
      "step": 229
    },
    {
      "epoch": 5.26,
      "learning_rate": 9.360064977222262e-05,
      "loss": 0.1681,
      "step": 230
    },
    {
      "epoch": 5.28,
      "learning_rate": 9.284900314817597e-05,
      "loss": 0.2364,
      "step": 231
    },
    {
      "epoch": 5.3,
      "learning_rate": 9.209776239900453e-05,
      "loss": 0.1228,
      "step": 232
    },
    {
      "epoch": 5.33,
      "learning_rate": 9.134697016348327e-05,
      "loss": 0.1417,
      "step": 233
    },
    {
      "epoch": 5.35,
      "learning_rate": 9.05966690549305e-05,
      "loss": 0.1512,
      "step": 234
    },
    {
      "epoch": 5.37,
      "learning_rate": 8.984690165878921e-05,
      "loss": 0.1248,
      "step": 235
    },
    {
      "epoch": 5.39,
      "learning_rate": 8.909771053021002e-05,
      "loss": 0.1252,
      "step": 236
    },
    {
      "epoch": 5.42,
      "learning_rate": 8.834913819163595e-05,
      "loss": 0.1341,
      "step": 237
    },
    {
      "epoch": 5.44,
      "learning_rate": 8.760122713038881e-05,
      "loss": 0.1644,
      "step": 238
    },
    {
      "epoch": 5.46,
      "learning_rate": 8.685401979625774e-05,
      "loss": 0.0977,
      "step": 239
    },
    {
      "epoch": 5.49,
      "learning_rate": 8.610755859908991e-05,
      "loss": 0.1699,
      "step": 240
    },
    {
      "epoch": 5.51,
      "learning_rate": 8.536188590638334e-05,
      "loss": 0.1196,
      "step": 241
    },
    {
      "epoch": 5.53,
      "learning_rate": 8.46170440408824e-05,
      "loss": 0.0777,
      "step": 242
    },
    {
      "epoch": 5.55,
      "learning_rate": 8.387307527817539e-05,
      "loss": 0.1266,
      "step": 243
    },
    {
      "epoch": 5.58,
      "learning_rate": 8.313002184429529e-05,
      "loss": 0.1463,
      "step": 244
    },
    {
      "epoch": 5.6,
      "learning_rate": 8.238792591332299e-05,
      "loss": 0.1037,
      "step": 245
    },
    {
      "epoch": 5.62,
      "learning_rate": 8.164682960499361e-05,
      "loss": 0.1385,
      "step": 246
    },
    {
      "epoch": 5.65,
      "learning_rate": 8.090677498230596e-05,
      "loss": 0.0932,
      "step": 247
    },
    {
      "epoch": 5.67,
      "learning_rate": 8.016780404913496e-05,
      "loss": 0.1294,
      "step": 248
    },
    {
      "epoch": 5.69,
      "learning_rate": 7.942995874784776e-05,
      "loss": 0.191,
      "step": 249
    },
    {
      "epoch": 5.71,
      "learning_rate": 7.869328095692312e-05,
      "loss": 0.1488,
      "step": 250
    },
    {
      "epoch": 5.74,
      "learning_rate": 7.795781248857443e-05,
      "loss": 0.1259,
      "step": 251
    },
    {
      "epoch": 5.76,
      "learning_rate": 7.72235950863766e-05,
      "loss": 0.1266,
      "step": 252
    },
    {
      "epoch": 5.78,
      "learning_rate": 7.64906704228968e-05,
      "loss": 0.1172,
      "step": 253
    },
    {
      "epoch": 5.81,
      "learning_rate": 7.575908009732918e-05,
      "loss": 0.1032,
      "step": 254
    },
    {
      "epoch": 5.83,
      "learning_rate": 7.502886563313376e-05,
      "loss": 0.0891,
      "step": 255
    },
    {
      "epoch": 5.85,
      "learning_rate": 7.430006847567972e-05,
      "loss": 0.0909,
      "step": 256
    },
    {
      "epoch": 5.87,
      "learning_rate": 7.357272998989308e-05,
      "loss": 0.1367,
      "step": 257
    },
    {
      "epoch": 5.9,
      "learning_rate": 7.284689145790878e-05,
      "loss": 0.0965,
      "step": 258
    },
    {
      "epoch": 5.92,
      "learning_rate": 7.21225940767277e-05,
      "loss": 0.1868,
      "step": 259
    },
    {
      "epoch": 5.94,
      "learning_rate": 7.139987895587836e-05,
      "loss": 0.3087,
      "step": 260
    },
    {
      "epoch": 5.97,
      "learning_rate": 7.067878711508375e-05,
      "loss": 0.1388,
      "step": 261
    },
    {
      "epoch": 5.99,
      "learning_rate": 6.995935948193294e-05,
      "loss": 0.142,
      "step": 262
    },
    {
      "epoch": 6.01,
      "learning_rate": 6.924163688955825e-05,
      "loss": 0.1212,
      "step": 263
    },
    {
      "epoch": 6.03,
      "learning_rate": 6.852566007431773e-05,
      "loss": 0.1369,
      "step": 264
    },
    {
      "epoch": 6.06,
      "learning_rate": 6.781146967348284e-05,
      "loss": 0.0927,
      "step": 265
    },
    {
      "epoch": 6.08,
      "learning_rate": 6.709910622293212e-05,
      "loss": 0.1146,
      "step": 266
    },
    {
      "epoch": 6.1,
      "learning_rate": 6.638861015485043e-05,
      "loss": 0.1059,
      "step": 267
    },
    {
      "epoch": 6.13,
      "learning_rate": 6.568002179543409e-05,
      "loss": 0.1108,
      "step": 268
    },
    {
      "epoch": 6.15,
      "learning_rate": 6.497338136260209e-05,
      "loss": 0.1333,
      "step": 269
    },
    {
      "epoch": 6.17,
      "learning_rate": 6.426872896371331e-05,
      "loss": 0.115,
      "step": 270
    },
    {
      "epoch": 6.19,
      "learning_rate": 6.356610459329038e-05,
      "loss": 0.0776,
      "step": 271
    },
    {
      "epoch": 6.22,
      "learning_rate": 6.286554813074925e-05,
      "loss": 0.1038,
      "step": 272
    },
    {
      "epoch": 6.24,
      "learning_rate": 6.21670993381361e-05,
      "loss": 0.0796,
      "step": 273
    },
    {
      "epoch": 6.26,
      "learning_rate": 6.147079785787038e-05,
      "loss": 0.0982,
      "step": 274
    },
    {
      "epoch": 6.29,
      "learning_rate": 6.0776683210494766e-05,
      "loss": 0.114,
      "step": 275
    },
    {
      "epoch": 6.31,
      "learning_rate": 6.0084794792432155e-05,
      "loss": 0.0922,
      "step": 276
    },
    {
      "epoch": 6.33,
      "learning_rate": 5.93951718737495e-05,
      "loss": 0.0725,
      "step": 277
    },
    {
      "epoch": 6.35,
      "learning_rate": 5.8707853595928985e-05,
      "loss": 0.0855,
      "step": 278
    },
    {
      "epoch": 6.38,
      "learning_rate": 5.802287896964658e-05,
      "loss": 0.1254,
      "step": 279
    },
    {
      "epoch": 6.4,
      "learning_rate": 5.734028687255751e-05,
      "loss": 0.1193,
      "step": 280
    },
    {
      "epoch": 6.42,
      "learning_rate": 5.666011604709005e-05,
      "loss": 0.1212,
      "step": 281
    },
    {
      "epoch": 6.45,
      "learning_rate": 5.598240509824642e-05,
      "loss": 0.1744,
      "step": 282
    },
    {
      "epoch": 6.47,
      "learning_rate": 5.530719249141147e-05,
      "loss": 0.062,
      "step": 283
    },
    {
      "epoch": 6.49,
      "learning_rate": 5.463451655016988e-05,
      "loss": 0.1408,
      "step": 284
    },
    {
      "epoch": 6.51,
      "learning_rate": 5.39644154541305e-05,
      "loss": 0.0819,
      "step": 285
    },
    {
      "epoch": 6.54,
      "learning_rate": 5.329692723675994e-05,
      "loss": 0.118,
      "step": 286
    },
    {
      "epoch": 6.56,
      "learning_rate": 5.263208978322326e-05,
      "loss": 0.0602,
      "step": 287
    },
    {
      "epoch": 6.58,
      "learning_rate": 5.1969940828234184e-05,
      "loss": 0.0708,
      "step": 288
    },
    {
      "epoch": 6.61,
      "learning_rate": 5.131051795391302e-05,
      "loss": 0.107,
      "step": 289
    },
    {
      "epoch": 6.63,
      "learning_rate": 5.065385858765383e-05,
      "loss": 0.0621,
      "step": 290
    },
    {
      "epoch": 6.65,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0428,
      "step": 291
    },
    {
      "epoch": 6.67,
      "learning_rate": 4.934897930252886e-05,
      "loss": 0.111,
      "step": 292
    },
    {
      "epoch": 6.7,
      "learning_rate": 4.870083344574531e-05,
      "loss": 0.1184,
      "step": 293
    },
    {
      "epoch": 6.72,
      "learning_rate": 4.805559921698464e-05,
      "loss": 0.0919,
      "step": 294
    },
    {
      "epoch": 6.74,
      "learning_rate": 4.7413313238324556e-05,
      "loss": 0.0477,
      "step": 295
    },
    {
      "epoch": 6.77,
      "learning_rate": 4.6774011964506435e-05,
      "loss": 0.0738,
      "step": 296
    },
    {
      "epoch": 6.79,
      "learning_rate": 4.613773168086657e-05,
      "loss": 0.101,
      "step": 297
    },
    {
      "epoch": 6.81,
      "learning_rate": 4.550450850127625e-05,
      "loss": 0.0585,
      "step": 298
    },
    {
      "epoch": 6.83,
      "learning_rate": 4.4874378366092476e-05,
      "loss": 0.0443,
      "step": 299
    },
    {
      "epoch": 6.86,
      "learning_rate": 4.42473770401176e-05,
      "loss": 0.1272,
      "step": 300
    },
    {
      "epoch": 6.88,
      "learning_rate": 4.3623540110569935e-05,
      "loss": 0.1569,
      "step": 301
    },
    {
      "epoch": 6.9,
      "learning_rate": 4.300290298506333e-05,
      "loss": 0.0314,
      "step": 302
    },
    {
      "epoch": 6.93,
      "learning_rate": 4.238550088959796e-05,
      "loss": 0.1179,
      "step": 303
    },
    {
      "epoch": 6.95,
      "learning_rate": 4.1771368866560665e-05,
      "loss": 0.1037,
      "step": 304
    },
    {
      "epoch": 6.97,
      "learning_rate": 4.116054177273627e-05,
      "loss": 0.0898,
      "step": 305
    },
    {
      "epoch": 6.99,
      "learning_rate": 4.0553054277329074e-05,
      "loss": 0.1015,
      "step": 306
    },
    {
      "epoch": 7.02,
      "learning_rate": 3.9948940859994966e-05,
      "loss": 0.0652,
      "step": 307
    },
    {
      "epoch": 7.04,
      "learning_rate": 3.9348235808884724e-05,
      "loss": 0.0403,
      "step": 308
    },
    {
      "epoch": 7.06,
      "learning_rate": 3.875097321869768e-05,
      "loss": 0.0501,
      "step": 309
    },
    {
      "epoch": 7.09,
      "learning_rate": 3.815718698874672e-05,
      "loss": 0.0874,
      "step": 310
    },
    {
      "epoch": 7.11,
      "learning_rate": 3.7566910821034005e-05,
      "loss": 0.0336,
      "step": 311
    },
    {
      "epoch": 7.13,
      "learning_rate": 3.698017821833844e-05,
      "loss": 0.0606,
      "step": 312
    },
    {
      "epoch": 7.15,
      "learning_rate": 3.6397022482313805e-05,
      "loss": 0.0154,
      "step": 313
    },
    {
      "epoch": 7.18,
      "learning_rate": 3.5817476711598906e-05,
      "loss": 0.0232,
      "step": 314
    },
    {
      "epoch": 7.2,
      "learning_rate": 3.524157379993882e-05,
      "loss": 0.0202,
      "step": 315
    },
    {
      "epoch": 7.22,
      "learning_rate": 3.466934643431795e-05,
      "loss": 0.0991,
      "step": 316
    },
    {
      "epoch": 7.25,
      "learning_rate": 3.4100827093104694e-05,
      "loss": 0.1159,
      "step": 317
    },
    {
      "epoch": 7.27,
      "learning_rate": 3.353604804420821e-05,
      "loss": 0.012,
      "step": 318
    },
    {
      "epoch": 7.29,
      "learning_rate": 3.2975041343246936e-05,
      "loss": 0.0735,
      "step": 319
    },
    {
      "epoch": 7.31,
      "learning_rate": 3.241783883172895e-05,
      "loss": 0.0097,
      "step": 320
    },
    {
      "epoch": 7.34,
      "learning_rate": 3.186447213524508e-05,
      "loss": 0.03,
      "step": 321
    },
    {
      "epoch": 7.36,
      "learning_rate": 3.131497266167357e-05,
      "loss": 0.0764,
      "step": 322
    },
    {
      "epoch": 7.38,
      "learning_rate": 3.076937159939768e-05,
      "loss": 0.0166,
      "step": 323
    },
    {
      "epoch": 7.41,
      "learning_rate": 3.0227699915535367e-05,
      "loss": 0.1195,
      "step": 324
    },
    {
      "epoch": 7.43,
      "learning_rate": 2.968998835418174e-05,
      "loss": 0.117,
      "step": 325
    },
    {
      "epoch": 7.45,
      "learning_rate": 2.9156267434663963e-05,
      "loss": 0.0241,
      "step": 326
    },
    {
      "epoch": 7.47,
      "learning_rate": 2.862656744980926e-05,
      "loss": 0.0874,
      "step": 327
    },
    {
      "epoch": 7.5,
      "learning_rate": 2.81009184642253e-05,
      "loss": 0.062,
      "step": 328
    },
    {
      "epoch": 7.52,
      "learning_rate": 2.757935031259402e-05,
      "loss": 0.0262,
      "step": 329
    },
    {
      "epoch": 7.54,
      "learning_rate": 2.7061892597978177e-05,
      "loss": 0.1282,
      "step": 330
    },
    {
      "epoch": 7.57,
      "learning_rate": 2.6548574690141125e-05,
      "loss": 0.0045,
      "step": 331
    },
    {
      "epoch": 7.59,
      "learning_rate": 2.603942572387993e-05,
      "loss": 0.0423,
      "step": 332
    },
    {
      "epoch": 7.61,
      "learning_rate": 2.553447459737157e-05,
      "loss": 0.0448,
      "step": 333
    },
    {
      "epoch": 7.63,
      "learning_rate": 2.5033749970533015e-05,
      "loss": 0.0534,
      "step": 334
    },
    {
      "epoch": 7.66,
      "learning_rate": 2.4537280263394258e-05,
      "loss": 0.04,
      "step": 335
    },
    {
      "epoch": 7.68,
      "learning_rate": 2.4045093654485518e-05,
      "loss": 0.0356,
      "step": 336
    },
    {
      "epoch": 7.7,
      "learning_rate": 2.355721807923761e-05,
      "loss": 0.0786,
      "step": 337
    },
    {
      "epoch": 7.73,
      "learning_rate": 2.307368122839675e-05,
      "loss": 0.0441,
      "step": 338
    },
    {
      "epoch": 7.75,
      "learning_rate": 2.2594510546452507e-05,
      "loss": 0.0155,
      "step": 339
    },
    {
      "epoch": 7.77,
      "learning_rate": 2.2119733230080408e-05,
      "loss": 0.0217,
      "step": 340
    },
    {
      "epoch": 7.79,
      "learning_rate": 2.1649376226598106e-05,
      "loss": 0.0472,
      "step": 341
    },
    {
      "epoch": 7.82,
      "learning_rate": 2.1183466232436088e-05,
      "loss": 0.0354,
      "step": 342
    },
    {
      "epoch": 7.84,
      "learning_rate": 2.0722029691622336e-05,
      "loss": 0.0702,
      "step": 343
    },
    {
      "epoch": 7.86,
      "learning_rate": 2.026509279428137e-05,
      "loss": 0.0759,
      "step": 344
    },
    {
      "epoch": 7.89,
      "learning_rate": 1.9812681475147942e-05,
      "loss": 0.1333,
      "step": 345
    },
    {
      "epoch": 7.91,
      "learning_rate": 1.9364821412094857e-05,
      "loss": 0.0323,
      "step": 346
    },
    {
      "epoch": 7.93,
      "learning_rate": 1.8921538024675678e-05,
      "loss": 0.0105,
      "step": 347
    },
    {
      "epoch": 7.95,
      "learning_rate": 1.848285647268181e-05,
      "loss": 0.0554,
      "step": 348
    },
    {
      "epoch": 7.98,
      "learning_rate": 1.8048801654714688e-05,
      "loss": 0.045,
      "step": 349
    },
    {
      "epoch": 8.0,
      "learning_rate": 1.761939820677241e-05,
      "loss": 0.0068,
      "step": 350
    },
    {
      "epoch": 8.02,
      "learning_rate": 1.7194670500851616e-05,
      "loss": 0.024,
      "step": 351
    },
    {
      "epoch": 8.05,
      "learning_rate": 1.6774642643563953e-05,
      "loss": 0.0245,
      "step": 352
    },
    {
      "epoch": 8.07,
      "learning_rate": 1.6359338474768193e-05,
      "loss": 0.0177,
      "step": 353
    },
    {
      "epoch": 8.09,
      "learning_rate": 1.594878156621672e-05,
      "loss": 0.0234,
      "step": 354
    },
    {
      "epoch": 8.11,
      "learning_rate": 1.554299522021796e-05,
      "loss": 0.0174,
      "step": 355
    },
    {
      "epoch": 8.14,
      "learning_rate": 1.5142002468313699e-05,
      "loss": 0.0074,
      "step": 356
    },
    {
      "epoch": 8.16,
      "learning_rate": 1.4745826069971758e-05,
      "loss": 0.0468,
      "step": 357
    },
    {
      "epoch": 8.18,
      "learning_rate": 1.4354488511294417e-05,
      "loss": 0.0051,
      "step": 358
    },
    {
      "epoch": 8.21,
      "learning_rate": 1.3968012003741948e-05,
      "loss": 0.0042,
      "step": 359
    },
    {
      "epoch": 8.23,
      "learning_rate": 1.35864184828721e-05,
      "loss": 0.0071,
      "step": 360
    },
    {
      "epoch": 8.25,
      "learning_rate": 1.3209729607095023e-05,
      "loss": 0.0074,
      "step": 361
    },
    {
      "epoch": 8.27,
      "learning_rate": 1.2837966756443975e-05,
      "loss": 0.0087,
      "step": 362
    },
    {
      "epoch": 8.3,
      "learning_rate": 1.2471151031361794e-05,
      "loss": 0.0081,
      "step": 363
    },
    {
      "epoch": 8.32,
      "learning_rate": 1.2109303251503434e-05,
      "loss": 0.0068,
      "step": 364
    },
    {
      "epoch": 8.34,
      "learning_rate": 1.1752443954554082e-05,
      "loss": 0.0068,
      "step": 365
    },
    {
      "epoch": 8.37,
      "learning_rate": 1.1400593395063686e-05,
      "loss": 0.01,
      "step": 366
    },
    {
      "epoch": 8.39,
      "learning_rate": 1.1053771543297198e-05,
      "loss": 0.0078,
      "step": 367
    },
    {
      "epoch": 8.41,
      "learning_rate": 1.0711998084101205e-05,
      "loss": 0.0106,
      "step": 368
    },
    {
      "epoch": 8.43,
      "learning_rate": 1.0375292415786575e-05,
      "loss": 0.0035,
      "step": 369
    },
    {
      "epoch": 8.46,
      "learning_rate": 1.0043673649027518e-05,
      "loss": 0.0715,
      "step": 370
    },
    {
      "epoch": 8.48,
      "learning_rate": 9.717160605776932e-06,
      "loss": 0.0093,
      "step": 371
    },
    {
      "epoch": 8.5,
      "learning_rate": 9.39577181819794e-06,
      "loss": 0.0815,
      "step": 372
    },
    {
      "epoch": 8.53,
      "learning_rate": 9.07952552761232e-06,
      "loss": 0.0086,
      "step": 373
    },
    {
      "epoch": 8.55,
      "learning_rate": 8.768439683464868e-06,
      "loss": 0.0138,
      "step": 374
    },
    {
      "epoch": 8.57,
      "learning_rate": 8.462531942304896e-06,
      "loss": 0.0132,
      "step": 375
    },
    {
      "epoch": 8.59,
      "learning_rate": 8.161819666783888e-06,
      "loss": 0.0141,
      "step": 376
    },
    {
      "epoch": 8.62,
      "learning_rate": 7.866319924670163e-06,
      "loss": 0.0477,
      "step": 377
    },
    {
      "epoch": 8.64,
      "learning_rate": 7.576049487880033e-06,
      "loss": 0.0103,
      "step": 378
    },
    {
      "epoch": 8.66,
      "learning_rate": 7.291024831525961e-06,
      "loss": 0.0044,
      "step": 379
    },
    {
      "epoch": 8.69,
      "learning_rate": 7.011262132981456e-06,
      "loss": 0.051,
      "step": 380
    },
    {
      "epoch": 8.71,
      "learning_rate": 6.7367772709627905e-06,
      "loss": 0.0031,
      "step": 381
    },
    {
      "epoch": 8.73,
      "learning_rate": 6.467585824627887e-06,
      "loss": 0.016,
      "step": 382
    },
    {
      "epoch": 8.75,
      "learning_rate": 6.203703072692013e-06,
      "loss": 0.0054,
      "step": 383
    },
    {
      "epoch": 8.78,
      "learning_rate": 5.945143992560587e-06,
      "loss": 0.0042,
      "step": 384
    },
    {
      "epoch": 8.8,
      "learning_rate": 5.691923259479093e-06,
      "loss": 0.0133,
      "step": 385
    },
    {
      "epoch": 8.82,
      "learning_rate": 5.444055245700208e-06,
      "loss": 0.026,
      "step": 386
    },
    {
      "epoch": 8.85,
      "learning_rate": 5.201554019667965e-06,
      "loss": 0.0347,
      "step": 387
    },
    {
      "epoch": 8.87,
      "learning_rate": 4.964433345219355e-06,
      "loss": 0.0498,
      "step": 388
    },
    {
      "epoch": 8.89,
      "learning_rate": 4.732706680803045e-06,
      "loss": 0.0218,
      "step": 389
    },
    {
      "epoch": 8.91,
      "learning_rate": 4.506387178715565e-06,
      "loss": 0.0094,
      "step": 390
    },
    {
      "epoch": 8.94,
      "learning_rate": 4.285487684354772e-06,
      "loss": 0.0798,
      "step": 391
    },
    {
      "epoch": 8.96,
      "learning_rate": 4.070020735490809e-06,
      "loss": 0.0036,
      "step": 392
    },
    {
      "epoch": 8.98,
      "learning_rate": 3.859998561554434e-06,
      "loss": 0.0086,
      "step": 393
    },
    {
      "epoch": 9.01,
      "learning_rate": 3.655433082942972e-06,
      "loss": 0.0673,
      "step": 394
    },
    {
      "epoch": 9.03,
      "learning_rate": 3.4563359103436886e-06,
      "loss": 0.0103,
      "step": 395
    },
    {
      "epoch": 9.05,
      "learning_rate": 3.262718344074811e-06,
      "loss": 0.0038,
      "step": 396
    },
    {
      "epoch": 9.07,
      "learning_rate": 3.0745913734441355e-06,
      "loss": 0.0127,
      "step": 397
    },
    {
      "epoch": 9.1,
      "learning_rate": 2.891965676125352e-06,
      "loss": 0.0093,
      "step": 398
    },
    {
      "epoch": 9.12,
      "learning_rate": 2.7148516175519277e-06,
      "loss": 0.0137,
      "step": 399
    },
    {
      "epoch": 9.14,
      "learning_rate": 2.5432592503288e-06,
      "loss": 0.0027,
      "step": 400
    },
    {
      "epoch": 9.17,
      "learning_rate": 2.377198313661877e-06,
      "loss": 0.0102,
      "step": 401
    },
    {
      "epoch": 9.19,
      "learning_rate": 2.2166782328051803e-06,
      "loss": 0.0051,
      "step": 402
    },
    {
      "epoch": 9.21,
      "learning_rate": 2.0617081185259512e-06,
      "loss": 0.0027,
      "step": 403
    },
    {
      "epoch": 9.23,
      "learning_rate": 1.912296766587507e-06,
      "loss": 0.0074,
      "step": 404
    },
    {
      "epoch": 9.26,
      "learning_rate": 1.7684526572500416e-06,
      "loss": 0.0029,
      "step": 405
    },
    {
      "epoch": 9.28,
      "learning_rate": 1.6301839547892328e-06,
      "loss": 0.0106,
      "step": 406
    },
    {
      "epoch": 9.3,
      "learning_rate": 1.4974985070329683e-06,
      "loss": 0.0243,
      "step": 407
    },
    {
      "epoch": 9.33,
      "learning_rate": 1.3704038449158573e-06,
      "loss": 0.0031,
      "step": 408
    },
    {
      "epoch": 9.35,
      "learning_rate": 1.2489071820517396e-06,
      "loss": 0.0041,
      "step": 409
    },
    {
      "epoch": 9.37,
      "learning_rate": 1.1330154143243787e-06,
      "loss": 0.0096,
      "step": 410
    },
    {
      "epoch": 9.39,
      "learning_rate": 1.0227351194959545e-06,
      "loss": 0.0103,
      "step": 411
    },
    {
      "epoch": 9.42,
      "learning_rate": 9.180725568338044e-07,
      "loss": 0.0069,
      "step": 412
    },
    {
      "epoch": 9.44,
      "learning_rate": 8.190336667550868e-07,
      "loss": 0.0048,
      "step": 413
    },
    {
      "epoch": 9.46,
      "learning_rate": 7.256240704897166e-07,
      "loss": 0.0057,
      "step": 414
    },
    {
      "epoch": 9.49,
      "learning_rate": 6.378490697611761e-07,
      "loss": 0.003,
      "step": 415
    },
    {
      "epoch": 9.51,
      "learning_rate": 5.55713646485756e-07,
      "loss": 0.0067,
      "step": 416
    },
    {
      "epoch": 9.53,
      "learning_rate": 4.79222462489648e-07,
      "loss": 0.0036,
      "step": 417
    },
    {
      "epoch": 9.55,
      "learning_rate": 4.0837985924448984e-07,
      "loss": 0.0055,
      "step": 418
    },
    {
      "epoch": 9.58,
      "learning_rate": 3.431898576208292e-07,
      "loss": 0.0027,
      "step": 419
    },
    {
      "epoch": 9.6,
      "learning_rate": 2.836561576599839e-07,
      "loss": 0.0069,
      "step": 420
    },
    {
      "epoch": 9.62,
      "learning_rate": 2.2978213836400975e-07,
      "loss": 0.0185,
      "step": 421
    },
    {
      "epoch": 9.65,
      "learning_rate": 1.815708575038988e-07,
      "loss": 0.0238,
      "step": 422
    },
    {
      "epoch": 9.67,
      "learning_rate": 1.3902505144608446e-07,
      "loss": 0.012,
      "step": 423
    },
    {
      "epoch": 9.69,
      "learning_rate": 1.0214713499706597e-07,
      "loss": 0.003,
      "step": 424
    },
    {
      "epoch": 9.71,
      "learning_rate": 7.093920126638454e-08,
      "loss": 0.0022,
      "step": 425
    },
    {
      "epoch": 9.74,
      "learning_rate": 4.54030215478074e-08,
      "loss": 0.0037,
      "step": 426
    },
    {
      "epoch": 9.76,
      "learning_rate": 2.5540045218819253e-08,
      "loss": 0.0024,
      "step": 427
    },
    {
      "epoch": 9.78,
      "learning_rate": 1.1351399658321438e-08,
      "loss": 0.0027,
      "step": 428
    },
    {
      "epoch": 9.81,
      "learning_rate": 2.8378901826831005e-09,
      "loss": 0.0033,
      "step": 429
    },
    {
      "epoch": 9.83,
      "learning_rate": 0.0,
      "loss": 0.0051,
      "step": 430
    },
    {
      "epoch": 9.83,
      "step": 430,
      "total_flos": 2.686707530150707e+16,
      "train_loss": 0.1627144819580365,
      "train_runtime": 335.6804,
      "train_samples_per_second": 20.794,
      "train_steps_per_second": 1.281
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 430,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 50000,
  "total_flos": 2.686707530150707e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}