{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.648720211827008,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.00019985795454545454,
      "loss": 3.3254,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001997159090909091,
      "loss": 3.1222,
      "step": 2
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019957386363636366,
      "loss": 2.9506,
      "step": 3
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001994318181818182,
      "loss": 2.8459,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019928977272727275,
      "loss": 2.7277,
      "step": 5
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019914772727272728,
      "loss": 2.6184,
      "step": 6
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001990056818181818,
      "loss": 2.5151,
      "step": 7
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019886363636363637,
      "loss": 2.4234,
      "step": 8
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019872159090909093,
      "loss": 2.3795,
      "step": 9
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019857954545454546,
      "loss": 2.3629,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019843750000000002,
      "loss": 2.3246,
      "step": 11
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019829545454545455,
      "loss": 2.2274,
      "step": 12
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019815340909090908,
      "loss": 2.2545,
      "step": 13
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019801136363636367,
      "loss": 2.2814,
      "step": 14
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001978693181818182,
      "loss": 2.2004,
      "step": 15
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019772727272727273,
      "loss": 2.1897,
      "step": 16
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001975852272727273,
      "loss": 2.2214,
      "step": 17
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019744318181818182,
      "loss": 2.2103,
      "step": 18
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019730113636363635,
      "loss": 2.1747,
      "step": 19
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019715909090909094,
      "loss": 2.2067,
      "step": 20
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019701704545454547,
      "loss": 2.1944,
      "step": 21
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000196875,
      "loss": 2.2088,
      "step": 22
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019673295454545456,
      "loss": 2.1786,
      "step": 23
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001965909090909091,
      "loss": 2.1242,
      "step": 24
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019644886363636365,
      "loss": 2.1233,
      "step": 25
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001963068181818182,
      "loss": 2.1616,
      "step": 26
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019616477272727274,
      "loss": 2.1175,
      "step": 27
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019602272727272727,
      "loss": 2.1242,
      "step": 28
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019588068181818183,
      "loss": 2.186,
      "step": 29
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019573863636363636,
      "loss": 2.1319,
      "step": 30
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019559659090909092,
      "loss": 2.1219,
      "step": 31
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019545454545454548,
      "loss": 2.1094,
      "step": 32
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001953125,
      "loss": 2.1355,
      "step": 33
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019517045454545454,
      "loss": 2.1231,
      "step": 34
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001950284090909091,
      "loss": 2.1089,
      "step": 35
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019488636363636366,
      "loss": 2.1329,
      "step": 36
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001947443181818182,
      "loss": 2.1159,
      "step": 37
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019460227272727275,
      "loss": 2.1001,
      "step": 38
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019446022727272728,
      "loss": 2.1084,
      "step": 39
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001943181818181818,
      "loss": 2.1431,
      "step": 40
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019417613636363637,
      "loss": 2.1111,
      "step": 41
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019403409090909093,
      "loss": 2.1067,
      "step": 42
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019389204545454546,
      "loss": 2.0974,
      "step": 43
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019375000000000002,
      "loss": 2.1001,
      "step": 44
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019360795454545455,
      "loss": 2.0721,
      "step": 45
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019346590909090908,
      "loss": 2.0786,
      "step": 46
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019332386363636367,
      "loss": 2.0882,
      "step": 47
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001931818181818182,
      "loss": 2.083,
      "step": 48
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019303977272727273,
      "loss": 2.1016,
      "step": 49
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001928977272727273,
      "loss": 2.0844,
      "step": 50
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019275568181818182,
      "loss": 2.0891,
      "step": 51
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019261363636363635,
      "loss": 2.053,
      "step": 52
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019247159090909094,
      "loss": 2.1013,
      "step": 53
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019232954545454547,
      "loss": 2.127,
      "step": 54
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001921875,
      "loss": 2.0909,
      "step": 55
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019204545454545456,
      "loss": 2.1026,
      "step": 56
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001919034090909091,
      "loss": 2.0689,
      "step": 57
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019176136363636365,
      "loss": 2.0475,
      "step": 58
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001916193181818182,
      "loss": 2.0645,
      "step": 59
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019147727272727274,
      "loss": 2.0469,
      "step": 60
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019133522727272727,
      "loss": 2.081,
      "step": 61
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019119318181818183,
      "loss": 2.0682,
      "step": 62
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019105113636363636,
      "loss": 2.0794,
      "step": 63
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019090909090909092,
      "loss": 2.0218,
      "step": 64
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019076704545454548,
      "loss": 2.0791,
      "step": 65
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000190625,
      "loss": 2.0506,
      "step": 66
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019048295454545454,
      "loss": 2.0581,
      "step": 67
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001903409090909091,
      "loss": 2.0614,
      "step": 68
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019019886363636366,
      "loss": 2.0743,
      "step": 69
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001900568181818182,
      "loss": 2.0934,
      "step": 70
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00018991477272727275,
      "loss": 2.0695,
      "step": 71
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018977272727272728,
      "loss": 2.0651,
      "step": 72
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00018963068181818181,
      "loss": 2.1002,
      "step": 73
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00018948863636363637,
      "loss": 2.0691,
      "step": 74
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018934659090909093,
      "loss": 2.0596,
      "step": 75
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018920454545454546,
      "loss": 2.0542,
      "step": 76
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018906250000000002,
      "loss": 2.0543,
      "step": 77
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018892045454545455,
      "loss": 2.0042,
      "step": 78
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018877840909090908,
      "loss": 2.0072,
      "step": 79
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018863636363636364,
      "loss": 2.0926,
      "step": 80
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001884943181818182,
      "loss": 2.0015,
      "step": 81
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018835227272727273,
      "loss": 2.0591,
      "step": 82
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001882102272727273,
      "loss": 2.0522,
      "step": 83
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018806818181818182,
      "loss": 2.0131,
      "step": 84
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018792613636363636,
      "loss": 2.0572,
      "step": 85
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018778409090909091,
      "loss": 2.0352,
      "step": 86
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018764204545454547,
      "loss": 1.9937,
      "step": 87
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001875,
      "loss": 2.0534,
      "step": 88
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00018735795454545456,
      "loss": 2.0151,
      "step": 89
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001872159090909091,
      "loss": 2.0281,
      "step": 90
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00018707386363636365,
      "loss": 2.0582,
      "step": 91
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00018693181818181818,
      "loss": 2.0173,
      "step": 92
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00018678977272727274,
      "loss": 2.0318,
      "step": 93
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00018664772727272727,
      "loss": 2.0747,
      "step": 94
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00018650568181818183,
      "loss": 2.0036,
      "step": 95
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00018636363636363636,
      "loss": 2.0215,
      "step": 96
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00018622159090909092,
      "loss": 2.0385,
      "step": 97
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00018607954545454545,
      "loss": 2.0247,
      "step": 98
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001859375,
      "loss": 2.0075,
      "step": 99
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00018579545454545454,
      "loss": 2.0134,
      "step": 100
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001856534090909091,
      "loss": 1.9908,
      "step": 101
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00018551136363636366,
      "loss": 2.0048,
      "step": 102
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001853693181818182,
      "loss": 1.9929,
      "step": 103
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00018522727272727273,
      "loss": 2.0545,
      "step": 104
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00018508522727272728,
      "loss": 2.0212,
      "step": 105
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00018494318181818182,
      "loss": 2.0154,
      "step": 106
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00018480113636363637,
      "loss": 1.988,
      "step": 107
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00018465909090909093,
      "loss": 2.004,
      "step": 108
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00018451704545454546,
      "loss": 1.9902,
      "step": 109
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.000184375,
      "loss": 2.0044,
      "step": 110
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00018423295454545455,
      "loss": 2.028,
      "step": 111
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00018409090909090909,
      "loss": 1.975,
      "step": 112
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00018394886363636364,
      "loss": 1.9654,
      "step": 113
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001838068181818182,
      "loss": 2.013,
      "step": 114
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00018366477272727273,
      "loss": 1.9918,
      "step": 115
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00018352272727272727,
      "loss": 2.0028,
      "step": 116
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00018338068181818182,
      "loss": 1.9906,
      "step": 117
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00018323863636363636,
      "loss": 1.9781,
      "step": 118
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00018309659090909091,
      "loss": 1.994,
      "step": 119
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00018295454545454547,
      "loss": 1.9732,
      "step": 120
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001828125,
      "loss": 1.9985,
      "step": 121
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00018267045454545454,
      "loss": 2.032,
      "step": 122
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001825284090909091,
      "loss": 1.9743,
      "step": 123
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00018238636363636365,
      "loss": 1.9857,
      "step": 124
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00018224431818181819,
      "loss": 2.0118,
      "step": 125
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00018210227272727274,
      "loss": 2.0151,
      "step": 126
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00018196022727272728,
      "loss": 1.9863,
      "step": 127
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.9959,
      "step": 128
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00018167613636363637,
      "loss": 1.9642,
      "step": 129
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00018153409090909092,
      "loss": 1.953,
      "step": 130
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00018139204545454546,
      "loss": 1.9994,
      "step": 131
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00018125000000000001,
      "loss": 1.9557,
      "step": 132
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00018110795454545455,
      "loss": 2.0051,
      "step": 133
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001809659090909091,
      "loss": 1.9799,
      "step": 134
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00018082386363636366,
      "loss": 1.9696,
      "step": 135
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001806818181818182,
      "loss": 1.9664,
      "step": 136
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00018053977272727273,
      "loss": 1.9619,
      "step": 137
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00018039772727272729,
      "loss": 1.9833,
      "step": 138
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00018025568181818182,
      "loss": 1.9791,
      "step": 139
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00018011363636363638,
      "loss": 1.9777,
      "step": 140
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00017997159090909093,
      "loss": 1.9361,
      "step": 141
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00017982954545454547,
      "loss": 1.9449,
      "step": 142
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001796875,
      "loss": 1.9541,
      "step": 143
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00017954545454545456,
      "loss": 1.9867,
      "step": 144
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001794034090909091,
      "loss": 1.9433,
      "step": 145
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00017926136363636365,
      "loss": 1.9789,
      "step": 146
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001791193181818182,
      "loss": 1.9942,
      "step": 147
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00017897727272727274,
      "loss": 1.9724,
      "step": 148
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00017883522727272727,
      "loss": 1.9938,
      "step": 149
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00017869318181818183,
      "loss": 1.9264,
      "step": 150
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00017855113636363636,
      "loss": 1.9372,
      "step": 151
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00017840909090909092,
      "loss": 1.9463,
      "step": 152
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00017826704545454547,
      "loss": 1.9244,
      "step": 153
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.000178125,
      "loss": 1.9139,
      "step": 154
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00017798295454545454,
      "loss": 1.9612,
      "step": 155
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001778409090909091,
      "loss": 1.9399,
      "step": 156
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00017769886363636366,
      "loss": 1.906,
      "step": 157
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001775568181818182,
      "loss": 1.9294,
      "step": 158
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00017741477272727275,
      "loss": 1.9663,
      "step": 159
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00017727272727272728,
      "loss": 1.9257,
      "step": 160
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001771306818181818,
      "loss": 1.9416,
      "step": 161
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00017698863636363637,
      "loss": 1.94,
      "step": 162
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00017684659090909093,
      "loss": 1.9064,
      "step": 163
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00017670454545454546,
      "loss": 1.9363,
      "step": 164
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00017656250000000002,
      "loss": 1.9414,
      "step": 165
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00017642045454545455,
      "loss": 1.9526,
      "step": 166
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00017627840909090908,
      "loss": 1.9263,
      "step": 167
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00017613636363636366,
      "loss": 1.9251,
      "step": 168
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0001759943181818182,
      "loss": 1.9085,
      "step": 169
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00017585227272727273,
      "loss": 1.9287,
      "step": 170
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00017571022727272729,
      "loss": 1.9246,
      "step": 171
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00017556818181818182,
      "loss": 1.916,
      "step": 172
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00017542613636363635,
      "loss": 1.9297,
      "step": 173
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00017528409090909094,
      "loss": 1.8881,
      "step": 174
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00017514204545454547,
      "loss": 1.9208,
      "step": 175
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.000175,
      "loss": 1.9233,
      "step": 176
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00017485795454545456,
      "loss": 1.9309,
      "step": 177
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001747159090909091,
      "loss": 1.877,
      "step": 178
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00017457386363636365,
      "loss": 1.9083,
      "step": 179
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0001744318181818182,
      "loss": 1.8733,
      "step": 180
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00017428977272727274,
      "loss": 1.8905,
      "step": 181
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00017414772727272727,
      "loss": 1.9175,
      "step": 182
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00017400568181818183,
      "loss": 1.8846,
      "step": 183
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00017386363636363636,
      "loss": 1.8847,
      "step": 184
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00017372159090909092,
      "loss": 1.8948,
      "step": 185
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00017357954545454548,
      "loss": 1.8728,
      "step": 186
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0001734375,
      "loss": 1.8934,
      "step": 187
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00017329545454545454,
      "loss": 1.8796,
      "step": 188
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0001731534090909091,
      "loss": 1.902,
      "step": 189
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00017301136363636366,
      "loss": 1.8864,
      "step": 190
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001728693181818182,
      "loss": 1.8682,
      "step": 191
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00017272727272727275,
      "loss": 1.8662,
      "step": 192
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00017258522727272728,
      "loss": 1.8526,
      "step": 193
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0001724431818181818,
      "loss": 1.8682,
      "step": 194
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00017230113636363637,
      "loss": 1.8205,
      "step": 195
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00017215909090909093,
      "loss": 1.8726,
      "step": 196
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00017201704545454546,
      "loss": 1.8241,
      "step": 197
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00017187500000000002,
      "loss": 1.9,
      "step": 198
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00017173295454545455,
      "loss": 1.8496,
      "step": 199
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00017159090909090908,
      "loss": 1.8562,
      "step": 200
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00017144886363636367,
      "loss": 1.8594,
      "step": 201
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0001713068181818182,
      "loss": 1.8606,
      "step": 202
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00017116477272727273,
      "loss": 1.8712,
      "step": 203
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0001710227272727273,
      "loss": 1.897,
      "step": 204
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00017088068181818182,
      "loss": 1.8287,
      "step": 205
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00017073863636363635,
      "loss": 1.8698,
      "step": 206
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00017059659090909094,
      "loss": 1.8611,
      "step": 207
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00017045454545454547,
      "loss": 1.8161,
      "step": 208
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0001703125,
      "loss": 1.8303,
      "step": 209
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00017017045454545456,
      "loss": 1.8423,
      "step": 210
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0001700284090909091,
      "loss": 1.861,
      "step": 211
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00016988636363636365,
      "loss": 1.864,
      "step": 212
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001697443181818182,
      "loss": 1.8448,
      "step": 213
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00016960227272727274,
      "loss": 1.8463,
      "step": 214
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00016946022727272727,
      "loss": 1.8482,
      "step": 215
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00016931818181818183,
      "loss": 1.8289,
      "step": 216
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00016917613636363636,
      "loss": 1.8352,
      "step": 217
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00016903409090909092,
      "loss": 1.8161,
      "step": 218
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00016889204545454548,
      "loss": 1.8512,
      "step": 219
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00016875,
      "loss": 1.8211,
      "step": 220
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00016860795454545454,
      "loss": 1.7831,
      "step": 221
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0001684659090909091,
      "loss": 1.8232,
      "step": 222
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00016832386363636366,
      "loss": 1.8253,
      "step": 223
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0001681818181818182,
      "loss": 1.7994,
      "step": 224
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00016803977272727275,
      "loss": 1.8405,
      "step": 225
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.00016789772727272728,
      "loss": 1.816,
      "step": 226
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0001677556818181818,
      "loss": 1.8343,
      "step": 227
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.00016761363636363637,
      "loss": 1.8068,
      "step": 228
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00016747159090909093,
      "loss": 1.8337,
      "step": 229
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.00016732954545454546,
      "loss": 1.8269,
      "step": 230
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00016718750000000002,
      "loss": 1.8243,
      "step": 231
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.00016704545454545455,
      "loss": 1.7766,
      "step": 232
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.00016690340909090908,
      "loss": 1.8144,
      "step": 233
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.00016676136363636367,
      "loss": 1.8113,
      "step": 234
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0001666193181818182,
      "loss": 1.8086,
      "step": 235
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00016647727272727273,
      "loss": 1.785,
      "step": 236
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0001663352272727273,
      "loss": 1.7884,
      "step": 237
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.00016619318181818182,
      "loss": 1.7953,
      "step": 238
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.00016605113636363635,
      "loss": 1.8013,
      "step": 239
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.00016590909090909094,
      "loss": 1.8074,
      "step": 240
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.00016576704545454547,
      "loss": 1.82,
      "step": 241
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.000165625,
      "loss": 1.7665,
      "step": 242
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.00016548295454545456,
      "loss": 1.7638,
      "step": 243
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0001653409090909091,
      "loss": 1.7724,
      "step": 244
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.00016519886363636365,
      "loss": 1.7917,
      "step": 245
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0001650568181818182,
      "loss": 1.8442,
      "step": 246
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.00016491477272727274,
      "loss": 1.7887,
      "step": 247
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00016477272727272727,
      "loss": 1.8055,
      "step": 248
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.00016463068181818183,
      "loss": 1.7754,
      "step": 249
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.00016448863636363636,
      "loss": 1.7948,
      "step": 250
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.00016434659090909092,
      "loss": 1.8332,
      "step": 251
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.00016420454545454548,
      "loss": 1.772,
      "step": 252
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0001640625,
      "loss": 1.7781,
      "step": 253
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.00016392045454545454,
      "loss": 1.7714,
      "step": 254
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0001637784090909091,
      "loss": 1.793,
      "step": 255
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.8038,
      "step": 256
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0001634943181818182,
      "loss": 1.8137,
      "step": 257
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.00016335227272727275,
      "loss": 1.7726,
      "step": 258
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00016321022727272728,
      "loss": 1.7753,
      "step": 259
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0001630681818181818,
      "loss": 1.7553,
      "step": 260
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.00016292613636363637,
      "loss": 1.7518,
      "step": 261
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00016278409090909093,
      "loss": 1.7724,
      "step": 262
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.00016264204545454546,
      "loss": 1.7266,
      "step": 263
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.00016250000000000002,
      "loss": 1.8032,
      "step": 264
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00016235795454545455,
      "loss": 1.7345,
      "step": 265
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.00016221590909090908,
      "loss": 1.7249,
      "step": 266
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.00016207386363636364,
      "loss": 1.7218,
      "step": 267
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.0001619318181818182,
      "loss": 1.7092,
      "step": 268
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.00016178977272727273,
      "loss": 1.6807,
      "step": 269
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0001616477272727273,
      "loss": 1.7264,
      "step": 270
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.00016150568181818182,
      "loss": 1.726,
      "step": 271
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.00016136363636363635,
      "loss": 1.6986,
      "step": 272
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.0001612215909090909,
      "loss": 1.68,
      "step": 273
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.00016107954545454547,
      "loss": 1.6677,
      "step": 274
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0001609375,
      "loss": 1.7137,
      "step": 275
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.00016079545454545456,
      "loss": 1.6671,
      "step": 276
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.0001606534090909091,
      "loss": 1.6873,
      "step": 277
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.00016051136363636365,
      "loss": 1.6694,
      "step": 278
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00016036931818181818,
      "loss": 1.7003,
      "step": 279
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.00016022727272727274,
      "loss": 1.6861,
      "step": 280
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.00016008522727272727,
      "loss": 1.6881,
      "step": 281
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.00015994318181818183,
      "loss": 1.6848,
      "step": 282
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.00015980113636363636,
      "loss": 1.6872,
      "step": 283
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.00015965909090909092,
      "loss": 1.6975,
      "step": 284
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.00015951704545454545,
      "loss": 1.6708,
      "step": 285
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.000159375,
      "loss": 1.6985,
      "step": 286
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.00015923295454545454,
      "loss": 1.6586,
      "step": 287
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0001590909090909091,
      "loss": 1.6707,
      "step": 288
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.00015894886363636366,
      "loss": 1.6576,
      "step": 289
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0001588068181818182,
      "loss": 1.6625,
      "step": 290
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.00015866477272727275,
      "loss": 1.677,
      "step": 291
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.00015852272727272728,
      "loss": 1.6599,
      "step": 292
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0001583806818181818,
      "loss": 1.6674,
      "step": 293
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.00015823863636363637,
      "loss": 1.6707,
      "step": 294
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.00015809659090909093,
      "loss": 1.6788,
      "step": 295
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.00015795454545454546,
      "loss": 1.6686,
      "step": 296
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.00015781250000000002,
      "loss": 1.6488,
      "step": 297
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.00015767045454545455,
      "loss": 1.6806,
      "step": 298
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.00015752840909090908,
      "loss": 1.6862,
      "step": 299
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.00015738636363636364,
      "loss": 1.6499,
      "step": 300
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0001572443181818182,
      "loss": 1.6245,
      "step": 301
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.00015710227272727273,
      "loss": 1.6268,
      "step": 302
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.0001569602272727273,
      "loss": 1.6438,
      "step": 303
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.00015681818181818182,
      "loss": 1.6681,
      "step": 304
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.00015667613636363635,
      "loss": 1.6582,
      "step": 305
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0001565340909090909,
      "loss": 1.6432,
      "step": 306
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.00015639204545454547,
      "loss": 1.617,
      "step": 307
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.00015625,
      "loss": 1.6569,
      "step": 308
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.00015610795454545456,
      "loss": 1.6276,
      "step": 309
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0001559659090909091,
      "loss": 1.6432,
      "step": 310
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.00015582386363636365,
      "loss": 1.6132,
      "step": 311
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.00015568181818181818,
      "loss": 1.5997,
      "step": 312
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.00015553977272727274,
      "loss": 1.6154,
      "step": 313
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.00015539772727272727,
      "loss": 1.5862,
      "step": 314
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.00015525568181818183,
      "loss": 1.6233,
      "step": 315
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.00015511363636363636,
      "loss": 1.6265,
      "step": 316
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.00015497159090909092,
      "loss": 1.6171,
      "step": 317
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.00015482954545454545,
      "loss": 1.6303,
      "step": 318
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.0001546875,
      "loss": 1.6272,
      "step": 319
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.00015454545454545454,
      "loss": 1.6183,
      "step": 320
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0001544034090909091,
      "loss": 1.6205,
      "step": 321
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.00015426136363636366,
      "loss": 1.6099,
      "step": 322
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.0001541193181818182,
      "loss": 1.5973,
      "step": 323
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.00015397727272727272,
      "loss": 1.6247,
      "step": 324
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.00015383522727272728,
      "loss": 1.6041,
      "step": 325
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.00015369318181818181,
      "loss": 1.5835,
      "step": 326
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.00015355113636363637,
      "loss": 1.608,
      "step": 327
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.00015340909090909093,
      "loss": 1.6155,
      "step": 328
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.00015326704545454546,
      "loss": 1.5777,
      "step": 329
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.000153125,
      "loss": 1.5969,
      "step": 330
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.00015298295454545455,
      "loss": 1.5904,
      "step": 331
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.00015284090909090909,
      "loss": 1.586,
      "step": 332
    },
    {
      "epoch": 3.76,
      "learning_rate": 0.00015269886363636364,
      "loss": 1.582,
      "step": 333
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0001525568181818182,
      "loss": 1.548,
      "step": 334
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.00015241477272727273,
      "loss": 1.5564,
      "step": 335
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.00015227272727272727,
      "loss": 1.5506,
      "step": 336
    },
    {
      "epoch": 3.81,
      "learning_rate": 0.00015213068181818182,
      "loss": 1.5526,
      "step": 337
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.00015198863636363636,
      "loss": 1.5564,
      "step": 338
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.00015184659090909091,
      "loss": 1.5598,
      "step": 339
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.00015170454545454547,
      "loss": 1.5679,
      "step": 340
    },
    {
      "epoch": 3.85,
      "learning_rate": 0.0001515625,
      "loss": 1.549,
      "step": 341
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.00015142045454545454,
      "loss": 1.5672,
      "step": 342
    },
    {
      "epoch": 3.88,
      "learning_rate": 0.0001512784090909091,
      "loss": 1.5399,
      "step": 343
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.00015113636363636365,
      "loss": 1.5576,
      "step": 344
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.00015099431818181818,
      "loss": 1.549,
      "step": 345
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.00015085227272727274,
      "loss": 1.5345,
      "step": 346
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.00015071022727272728,
      "loss": 1.5015,
      "step": 347
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0001505681818181818,
      "loss": 1.5221,
      "step": 348
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.00015042613636363637,
      "loss": 1.556,
      "step": 349
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.00015028409090909092,
      "loss": 1.5276,
      "step": 350
    },
    {
      "epoch": 3.97,
      "learning_rate": 0.00015014204545454546,
      "loss": 1.552,
      "step": 351
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.5377,
      "step": 352
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.00014985795454545455,
      "loss": 1.5576,
      "step": 353
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00014971590909090908,
      "loss": 1.5295,
      "step": 354
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.00014957386363636366,
      "loss": 1.4842,
      "step": 355
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.0001494318181818182,
      "loss": 1.4803,
      "step": 356
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.00014928977272727273,
      "loss": 1.4559,
      "step": 357
    },
    {
      "epoch": 4.04,
      "learning_rate": 0.00014914772727272728,
      "loss": 1.4777,
      "step": 358
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.00014900568181818182,
      "loss": 1.4343,
      "step": 359
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.00014886363636363635,
      "loss": 1.4699,
      "step": 360
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00014872159090909093,
      "loss": 1.4452,
      "step": 361
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.00014857954545454546,
      "loss": 1.4461,
      "step": 362
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.0001484375,
      "loss": 1.4523,
      "step": 363
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.00014829545454545455,
      "loss": 1.4425,
      "step": 364
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.0001481534090909091,
      "loss": 1.4559,
      "step": 365
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.00014801136363636365,
      "loss": 1.4193,
      "step": 366
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.0001478693181818182,
      "loss": 1.4136,
      "step": 367
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.00014772727272727274,
      "loss": 1.445,
      "step": 368
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.00014758522727272727,
      "loss": 1.4304,
      "step": 369
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.00014744318181818183,
      "loss": 1.3996,
      "step": 370
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.00014730113636363636,
      "loss": 1.4247,
      "step": 371
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.00014715909090909092,
      "loss": 1.4303,
      "step": 372
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.00014701704545454547,
      "loss": 1.4219,
      "step": 373
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.000146875,
      "loss": 1.4538,
      "step": 374
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.00014673295454545454,
      "loss": 1.4391,
      "step": 375
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.0001465909090909091,
      "loss": 1.4482,
      "step": 376
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.00014644886363636365,
      "loss": 1.4208,
      "step": 377
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.00014630681818181819,
      "loss": 1.4111,
      "step": 378
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.00014616477272727274,
      "loss": 1.4318,
      "step": 379
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.00014602272727272728,
      "loss": 1.3913,
      "step": 380
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.0001458806818181818,
      "loss": 1.3847,
      "step": 381
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.00014573863636363637,
      "loss": 1.4254,
      "step": 382
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.00014559659090909093,
      "loss": 1.4143,
      "step": 383
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.4362,
      "step": 384
    },
    {
      "epoch": 4.35,
      "learning_rate": 0.00014531250000000002,
      "loss": 1.386,
      "step": 385
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.00014517045454545455,
      "loss": 1.4009,
      "step": 386
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.00014502840909090908,
      "loss": 1.4089,
      "step": 387
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.00014488636363636366,
      "loss": 1.4117,
      "step": 388
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.0001447443181818182,
      "loss": 1.3788,
      "step": 389
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.00014460227272727273,
      "loss": 1.3573,
      "step": 390
    },
    {
      "epoch": 4.42,
      "learning_rate": 0.00014446022727272729,
      "loss": 1.4133,
      "step": 391
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.00014431818181818182,
      "loss": 1.3866,
      "step": 392
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.00014417613636363635,
      "loss": 1.3883,
      "step": 393
    },
    {
      "epoch": 4.45,
      "learning_rate": 0.00014403409090909093,
      "loss": 1.3741,
      "step": 394
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.00014389204545454547,
      "loss": 1.358,
      "step": 395
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.00014375,
      "loss": 1.3893,
      "step": 396
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.00014360795454545456,
      "loss": 1.4062,
      "step": 397
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.0001434659090909091,
      "loss": 1.3795,
      "step": 398
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.00014332386363636365,
      "loss": 1.3472,
      "step": 399
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.0001431818181818182,
      "loss": 1.3408,
      "step": 400
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.00014303977272727274,
      "loss": 1.3801,
      "step": 401
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.00014289772727272727,
      "loss": 1.3709,
      "step": 402
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.00014275568181818183,
      "loss": 1.3653,
      "step": 403
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.00014261363636363636,
      "loss": 1.4089,
      "step": 404
    },
    {
      "epoch": 4.58,
      "learning_rate": 0.00014247159090909092,
      "loss": 1.3281,
      "step": 405
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.00014232954545454548,
      "loss": 1.328,
      "step": 406
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.0001421875,
      "loss": 1.3458,
      "step": 407
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.00014204545454545454,
      "loss": 1.3425,
      "step": 408
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.0001419034090909091,
      "loss": 1.3236,
      "step": 409
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.00014176136363636366,
      "loss": 1.3439,
      "step": 410
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0001416193181818182,
      "loss": 1.3397,
      "step": 411
    },
    {
      "epoch": 4.65,
      "learning_rate": 0.00014147727272727275,
      "loss": 1.329,
      "step": 412
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.00014133522727272728,
      "loss": 1.3377,
      "step": 413
    },
    {
      "epoch": 4.68,
      "learning_rate": 0.0001411931818181818,
      "loss": 1.343,
      "step": 414
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.00014105113636363637,
      "loss": 1.3185,
      "step": 415
    },
    {
      "epoch": 4.7,
      "learning_rate": 0.00014090909090909093,
      "loss": 1.3174,
      "step": 416
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.00014076704545454546,
      "loss": 1.3231,
      "step": 417
    },
    {
      "epoch": 4.72,
      "learning_rate": 0.00014062500000000002,
      "loss": 1.3407,
      "step": 418
    },
    {
      "epoch": 4.73,
      "learning_rate": 0.00014048295454545455,
      "loss": 1.3138,
      "step": 419
    },
    {
      "epoch": 4.74,
      "learning_rate": 0.00014034090909090908,
      "loss": 1.3134,
      "step": 420
    },
    {
      "epoch": 4.76,
      "learning_rate": 0.00014019886363636367,
      "loss": 1.3187,
      "step": 421
    },
    {
      "epoch": 4.77,
      "learning_rate": 0.0001400568181818182,
      "loss": 1.2781,
      "step": 422
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.00013991477272727273,
      "loss": 1.3254,
      "step": 423
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.0001397727272727273,
      "loss": 1.2929,
      "step": 424
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.00013963068181818182,
      "loss": 1.2953,
      "step": 425
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.00013948863636363635,
      "loss": 1.3202,
      "step": 426
    },
    {
      "epoch": 4.82,
      "learning_rate": 0.00013934659090909094,
      "loss": 1.3118,
      "step": 427
    },
    {
      "epoch": 4.84,
      "learning_rate": 0.00013920454545454547,
      "loss": 1.3046,
      "step": 428
    },
    {
      "epoch": 4.85,
      "learning_rate": 0.0001390625,
      "loss": 1.2708,
      "step": 429
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.00013892045454545456,
      "loss": 1.2835,
      "step": 430
    },
    {
      "epoch": 4.87,
      "learning_rate": 0.0001387784090909091,
      "loss": 1.2728,
      "step": 431
    },
    {
      "epoch": 4.88,
      "learning_rate": 0.00013863636363636365,
      "loss": 1.3107,
      "step": 432
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0001384943181818182,
      "loss": 1.2615,
      "step": 433
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.00013835227272727274,
      "loss": 1.2754,
      "step": 434
    },
    {
      "epoch": 4.91,
      "learning_rate": 0.00013821022727272727,
      "loss": 1.3018,
      "step": 435
    },
    {
      "epoch": 4.93,
      "learning_rate": 0.00013806818181818183,
      "loss": 1.2878,
      "step": 436
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.00013792613636363636,
      "loss": 1.2595,
      "step": 437
    },
    {
      "epoch": 4.95,
      "learning_rate": 0.00013778409090909092,
      "loss": 1.2688,
      "step": 438
    },
    {
      "epoch": 4.96,
      "learning_rate": 0.00013764204545454548,
      "loss": 1.2669,
      "step": 439
    },
    {
      "epoch": 4.97,
      "learning_rate": 0.0001375,
      "loss": 1.2861,
      "step": 440
    },
    {
      "epoch": 4.98,
      "learning_rate": 0.00013735795454545454,
      "loss": 1.2536,
      "step": 441
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.0001372159090909091,
      "loss": 1.2584,
      "step": 442
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00013707386363636366,
      "loss": 1.2203,
      "step": 443
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.0001369318181818182,
      "loss": 1.1796,
      "step": 444
    },
    {
      "epoch": 5.03,
      "learning_rate": 0.00013678977272727275,
      "loss": 1.1856,
      "step": 445
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.00013664772727272728,
      "loss": 1.1801,
      "step": 446
    },
    {
      "epoch": 5.05,
      "learning_rate": 0.0001365056818181818,
      "loss": 1.1761,
      "step": 447
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.00013636363636363637,
      "loss": 1.1495,
      "step": 448
    },
    {
      "epoch": 5.07,
      "learning_rate": 0.00013622159090909093,
      "loss": 1.1903,
      "step": 449
    },
    {
      "epoch": 5.08,
      "learning_rate": 0.00013607954545454546,
      "loss": 1.1778,
      "step": 450
    },
    {
      "epoch": 5.1,
      "learning_rate": 0.00013593750000000002,
      "loss": 1.1902,
      "step": 451
    },
    {
      "epoch": 5.11,
      "learning_rate": 0.00013579545454545455,
      "loss": 1.1597,
      "step": 452
    },
    {
      "epoch": 5.12,
      "learning_rate": 0.00013565340909090908,
      "loss": 1.1529,
      "step": 453
    },
    {
      "epoch": 5.13,
      "learning_rate": 0.00013551136363636364,
      "loss": 1.1627,
      "step": 454
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.0001353693181818182,
      "loss": 1.1613,
      "step": 455
    },
    {
      "epoch": 5.15,
      "learning_rate": 0.00013522727272727273,
      "loss": 1.1336,
      "step": 456
    },
    {
      "epoch": 5.16,
      "learning_rate": 0.0001350852272727273,
      "loss": 1.1369,
      "step": 457
    },
    {
      "epoch": 5.17,
      "learning_rate": 0.00013494318181818182,
      "loss": 1.1592,
      "step": 458
    },
    {
      "epoch": 5.19,
      "learning_rate": 0.00013480113636363635,
      "loss": 1.1482,
      "step": 459
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.00013465909090909094,
      "loss": 1.1857,
      "step": 460
    },
    {
      "epoch": 5.21,
      "learning_rate": 0.00013451704545454547,
      "loss": 1.1651,
      "step": 461
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.000134375,
      "loss": 1.1544,
      "step": 462
    },
    {
      "epoch": 5.23,
      "learning_rate": 0.00013423295454545456,
      "loss": 1.125,
      "step": 463
    },
    {
      "epoch": 5.24,
      "learning_rate": 0.0001340909090909091,
      "loss": 1.167,
      "step": 464
    },
    {
      "epoch": 5.25,
      "learning_rate": 0.00013394886363636365,
      "loss": 1.1316,
      "step": 465
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.0001338068181818182,
      "loss": 1.1604,
      "step": 466
    },
    {
      "epoch": 5.28,
      "learning_rate": 0.00013366477272727274,
      "loss": 1.2005,
      "step": 467
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.00013352272727272727,
      "loss": 1.1496,
      "step": 468
    },
    {
      "epoch": 5.3,
      "learning_rate": 0.00013338068181818183,
      "loss": 1.1331,
      "step": 469
    },
    {
      "epoch": 5.31,
      "learning_rate": 0.00013323863636363636,
      "loss": 1.1414,
      "step": 470
    },
    {
      "epoch": 5.32,
      "learning_rate": 0.00013309659090909092,
      "loss": 1.0945,
      "step": 471
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.00013295454545454548,
      "loss": 1.1305,
      "step": 472
    },
    {
      "epoch": 5.34,
      "learning_rate": 0.0001328125,
      "loss": 1.1293,
      "step": 473
    },
    {
      "epoch": 5.35,
      "learning_rate": 0.00013267045454545454,
      "loss": 1.163,
      "step": 474
    },
    {
      "epoch": 5.37,
      "learning_rate": 0.0001325284090909091,
      "loss": 1.1236,
      "step": 475
    },
    {
      "epoch": 5.38,
      "learning_rate": 0.00013238636363636366,
      "loss": 1.1236,
      "step": 476
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.0001322443181818182,
      "loss": 1.1228,
      "step": 477
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.00013210227272727275,
      "loss": 1.0993,
      "step": 478
    },
    {
      "epoch": 5.41,
      "learning_rate": 0.00013196022727272728,
      "loss": 1.1139,
      "step": 479
    },
    {
      "epoch": 5.42,
      "learning_rate": 0.0001318181818181818,
      "loss": 1.1019,
      "step": 480
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.00013167613636363637,
      "loss": 1.0935,
      "step": 481
    },
    {
      "epoch": 5.45,
      "learning_rate": 0.00013153409090909093,
      "loss": 1.1067,
      "step": 482
    },
    {
      "epoch": 5.46,
      "learning_rate": 0.00013139204545454546,
      "loss": 1.0848,
      "step": 483
    },
    {
      "epoch": 5.47,
      "learning_rate": 0.00013125000000000002,
      "loss": 1.1188,
      "step": 484
    },
    {
      "epoch": 5.48,
      "learning_rate": 0.00013110795454545455,
      "loss": 1.1275,
      "step": 485
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.00013096590909090908,
      "loss": 1.1211,
      "step": 486
    },
    {
      "epoch": 5.5,
      "learning_rate": 0.00013082386363636364,
      "loss": 1.1049,
      "step": 487
    },
    {
      "epoch": 5.51,
      "learning_rate": 0.0001306818181818182,
      "loss": 1.1057,
      "step": 488
    },
    {
      "epoch": 5.52,
      "learning_rate": 0.00013053977272727273,
      "loss": 1.0909,
      "step": 489
    },
    {
      "epoch": 5.54,
      "learning_rate": 0.0001303977272727273,
      "loss": 1.1138,
      "step": 490
    },
    {
      "epoch": 5.55,
      "learning_rate": 0.00013025568181818182,
      "loss": 1.1094,
      "step": 491
    },
    {
      "epoch": 5.56,
      "learning_rate": 0.00013011363636363635,
      "loss": 1.1187,
      "step": 492
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.0001299715909090909,
      "loss": 1.1039,
      "step": 493
    },
    {
      "epoch": 5.58,
      "learning_rate": 0.00012982954545454547,
      "loss": 1.056,
      "step": 494
    },
    {
      "epoch": 5.59,
      "learning_rate": 0.0001296875,
      "loss": 1.0842,
      "step": 495
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.00012954545454545456,
      "loss": 1.0749,
      "step": 496
    },
    {
      "epoch": 5.61,
      "learning_rate": 0.0001294034090909091,
      "loss": 1.1121,
      "step": 497
    },
    {
      "epoch": 5.63,
      "learning_rate": 0.00012926136363636365,
      "loss": 1.0772,
      "step": 498
    },
    {
      "epoch": 5.64,
      "learning_rate": 0.00012911931818181818,
      "loss": 1.0845,
      "step": 499
    },
    {
      "epoch": 5.65,
      "learning_rate": 0.00012897727272727274,
      "loss": 1.0534,
      "step": 500
    }
  ],
  "logging_steps": 1,
  "max_steps": 1408,
  "num_train_epochs": 16,
  "save_steps": 100,
  "total_flos": 6.820509352598323e+17,
  "trial_name": null,
  "trial_params": null
}