{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 30.236220472440944,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.000499599358974359,
      "loss": 3.1389,
      "step": 1
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000499198717948718,
      "loss": 2.8569,
      "step": 2
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004987980769230769,
      "loss": 2.75,
      "step": 3
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004983974358974359,
      "loss": 2.7375,
      "step": 4
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004979967948717949,
      "loss": 2.7342,
      "step": 5
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0004975961538461539,
      "loss": 2.753,
      "step": 6
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0004971955128205128,
      "loss": 2.7124,
      "step": 7
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0004967948717948718,
      "loss": 2.7038,
      "step": 8
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0004963942307692308,
      "loss": 2.6142,
      "step": 9
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0004959935897435898,
      "loss": 2.6427,
      "step": 10
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0004955929487179487,
      "loss": 2.6265,
      "step": 11
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0004951923076923077,
      "loss": 2.6352,
      "step": 12
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0004947916666666667,
      "loss": 2.616,
      "step": 13
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0004943910256410257,
      "loss": 2.6937,
      "step": 14
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0004939903846153846,
      "loss": 2.6719,
      "step": 15
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0004935897435897436,
      "loss": 2.6043,
      "step": 16
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0004931891025641026,
      "loss": 2.565,
      "step": 17
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0004927884615384616,
      "loss": 2.5776,
      "step": 18
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0004923878205128205,
      "loss": 2.6326,
      "step": 19
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0004919871794871795,
      "loss": 2.5868,
      "step": 20
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0004915865384615384,
      "loss": 2.5499,
      "step": 21
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0004911858974358974,
      "loss": 2.5823,
      "step": 22
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0004907852564102564,
      "loss": 2.5858,
      "step": 23
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0004903846153846154,
      "loss": 2.5688,
      "step": 24
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004899839743589743,
      "loss": 2.57,
      "step": 25
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004895833333333333,
      "loss": 2.5569,
      "step": 26
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004891826923076923,
      "loss": 2.5067,
      "step": 27
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004887820512820513,
      "loss": 2.4936,
      "step": 28
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004883814102564103,
      "loss": 2.5958,
      "step": 29
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00048798076923076925,
      "loss": 2.5213,
      "step": 30
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004875801282051282,
      "loss": 2.6369,
      "step": 31
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004871794871794872,
      "loss": 2.578,
      "step": 32
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00048677884615384615,
      "loss": 2.6214,
      "step": 33
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00048637820512820515,
      "loss": 2.6193,
      "step": 34
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0004859775641025641,
      "loss": 2.5948,
      "step": 35
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0004855769230769231,
      "loss": 2.5615,
      "step": 36
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00048517628205128205,
      "loss": 2.5246,
      "step": 37
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00048477564102564105,
      "loss": 2.4585,
      "step": 38
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000484375,
      "loss": 2.5621,
      "step": 39
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.000483974358974359,
      "loss": 2.571,
      "step": 40
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00048357371794871795,
      "loss": 2.5382,
      "step": 41
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00048317307692307695,
      "loss": 2.5028,
      "step": 42
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0004827724358974359,
      "loss": 2.4812,
      "step": 43
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0004823717948717949,
      "loss": 2.5161,
      "step": 44
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00048197115384615384,
      "loss": 2.4557,
      "step": 45
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00048157051282051285,
      "loss": 2.4617,
      "step": 46
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0004811698717948718,
      "loss": 2.5267,
      "step": 47
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0004807692307692308,
      "loss": 2.4555,
      "step": 48
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00048036858974358974,
      "loss": 2.37,
      "step": 49
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00047996794871794875,
      "loss": 2.4829,
      "step": 50
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0004795673076923077,
      "loss": 2.5022,
      "step": 51
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0004791666666666667,
      "loss": 2.4958,
      "step": 52
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0004787660256410257,
      "loss": 2.4358,
      "step": 53
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00047836538461538464,
      "loss": 2.4742,
      "step": 54
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00047796474358974365,
      "loss": 2.4158,
      "step": 55
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0004775641025641026,
      "loss": 2.5216,
      "step": 56
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0004771634615384616,
      "loss": 2.5239,
      "step": 57
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00047676282051282054,
      "loss": 2.3946,
      "step": 58
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0004763621794871795,
      "loss": 2.4457,
      "step": 59
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00047596153846153844,
      "loss": 2.4379,
      "step": 60
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00047556089743589744,
      "loss": 2.4812,
      "step": 61
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0004751602564102564,
      "loss": 2.4153,
      "step": 62
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0004747596153846154,
      "loss": 2.4115,
      "step": 63
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00047435897435897434,
      "loss": 2.3637,
      "step": 64
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00047395833333333334,
      "loss": 2.3741,
      "step": 65
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0004735576923076923,
      "loss": 2.4461,
      "step": 66
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0004731570512820513,
      "loss": 2.4694,
      "step": 67
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00047275641025641024,
      "loss": 2.5177,
      "step": 68
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00047235576923076924,
      "loss": 2.4964,
      "step": 69
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0004719551282051282,
      "loss": 2.5114,
      "step": 70
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0004715544871794872,
      "loss": 2.4447,
      "step": 71
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00047115384615384613,
      "loss": 2.4112,
      "step": 72
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00047075320512820514,
      "loss": 2.4585,
      "step": 73
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0004703525641025641,
      "loss": 2.4696,
      "step": 74
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0004699519230769231,
      "loss": 2.3813,
      "step": 75
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00046955128205128203,
      "loss": 2.4962,
      "step": 76
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00046915064102564104,
      "loss": 2.4392,
      "step": 77
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00046875,
      "loss": 2.3436,
      "step": 78
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.000468349358974359,
      "loss": 2.4758,
      "step": 79
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.000467948717948718,
      "loss": 2.4026,
      "step": 80
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00046754807692307693,
      "loss": 2.3728,
      "step": 81
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00046714743589743594,
      "loss": 2.395,
      "step": 82
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0004667467948717949,
      "loss": 2.2767,
      "step": 83
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0004663461538461539,
      "loss": 2.3483,
      "step": 84
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00046594551282051283,
      "loss": 2.2911,
      "step": 85
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00046554487179487183,
      "loss": 2.3502,
      "step": 86
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0004651442307692308,
      "loss": 2.3532,
      "step": 87
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0004647435897435898,
      "loss": 2.266,
      "step": 88
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00046434294871794873,
      "loss": 2.3046,
      "step": 89
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00046394230769230773,
      "loss": 2.2458,
      "step": 90
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0004635416666666667,
      "loss": 2.3324,
      "step": 91
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0004631410256410257,
      "loss": 2.3016,
      "step": 92
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00046274038461538463,
      "loss": 2.379,
      "step": 93
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00046233974358974363,
      "loss": 2.3075,
      "step": 94
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0004619391025641026,
      "loss": 2.3942,
      "step": 95
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0004615384615384616,
      "loss": 2.2891,
      "step": 96
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00046113782051282053,
      "loss": 2.4199,
      "step": 97
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0004607371794871795,
      "loss": 2.3662,
      "step": 98
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0004603365384615384,
      "loss": 2.3346,
      "step": 99
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0004599358974358974,
      "loss": 2.2607,
      "step": 100
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0004595352564102564,
      "loss": 2.3446,
      "step": 101
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0004591346153846154,
      "loss": 2.3649,
      "step": 102
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0004587339743589743,
      "loss": 2.2394,
      "step": 103
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0004583333333333333,
      "loss": 2.3278,
      "step": 104
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0004579326923076923,
      "loss": 2.2725,
      "step": 105
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0004575320512820513,
      "loss": 2.3328,
      "step": 106
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.0004571314102564103,
      "loss": 2.296,
      "step": 107
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0004567307692307692,
      "loss": 2.2562,
      "step": 108
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0004563301282051282,
      "loss": 2.3062,
      "step": 109
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0004559294871794872,
      "loss": 2.3125,
      "step": 110
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0004555288461538462,
      "loss": 2.3257,
      "step": 111
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0004551282051282051,
      "loss": 2.3431,
      "step": 112
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.0004547275641025641,
      "loss": 2.3507,
      "step": 113
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.00045432692307692307,
      "loss": 2.3621,
      "step": 114
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0004539262820512821,
      "loss": 2.2937,
      "step": 115
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.000453525641025641,
      "loss": 2.3356,
      "step": 116
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.000453125,
      "loss": 2.2228,
      "step": 117
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.00045272435897435897,
      "loss": 2.3189,
      "step": 118
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00045232371794871797,
      "loss": 2.3605,
      "step": 119
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.0004519230769230769,
      "loss": 2.1857,
      "step": 120
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0004515224358974359,
      "loss": 2.1538,
      "step": 121
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.00045112179487179487,
      "loss": 2.2092,
      "step": 122
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.00045072115384615387,
      "loss": 2.2089,
      "step": 123
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0004503205128205128,
      "loss": 2.1746,
      "step": 124
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.0004499198717948718,
      "loss": 2.1455,
      "step": 125
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.00044951923076923077,
      "loss": 2.119,
      "step": 126
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.00044911858974358977,
      "loss": 2.2341,
      "step": 127
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.0004487179487179487,
      "loss": 2.2275,
      "step": 128
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0004483173076923077,
      "loss": 2.176,
      "step": 129
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0004479166666666667,
      "loss": 2.1187,
      "step": 130
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.00044751602564102567,
      "loss": 2.1175,
      "step": 131
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.00044711538461538467,
      "loss": 2.1818,
      "step": 132
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.0004467147435897436,
      "loss": 2.1193,
      "step": 133
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.0004463141025641026,
      "loss": 2.2079,
      "step": 134
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.00044591346153846157,
      "loss": 2.1361,
      "step": 135
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.00044551282051282057,
      "loss": 2.2246,
      "step": 136
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.00044511217948717946,
      "loss": 2.1139,
      "step": 137
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.00044471153846153846,
      "loss": 2.1058,
      "step": 138
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0004443108974358974,
      "loss": 2.1442,
      "step": 139
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0004439102564102564,
      "loss": 2.1039,
      "step": 140
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.00044350961538461536,
      "loss": 2.1884,
      "step": 141
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.00044310897435897436,
      "loss": 2.21,
      "step": 142
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.0004427083333333333,
      "loss": 2.1139,
      "step": 143
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0004423076923076923,
      "loss": 2.1049,
      "step": 144
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.00044190705128205126,
      "loss": 2.1282,
      "step": 145
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.00044150641025641026,
      "loss": 2.1803,
      "step": 146
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.0004411057692307692,
      "loss": 2.1406,
      "step": 147
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0004407051282051282,
      "loss": 2.1841,
      "step": 148
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.00044030448717948716,
      "loss": 2.1961,
      "step": 149
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.00043990384615384616,
      "loss": 2.1265,
      "step": 150
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.0004395032051282051,
      "loss": 2.1708,
      "step": 151
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0004391025641025641,
      "loss": 2.1555,
      "step": 152
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.00043870192307692306,
      "loss": 2.1463,
      "step": 153
    },
    {
      "epoch": 3.88,
      "learning_rate": 0.00043830128205128206,
      "loss": 2.1947,
      "step": 154
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.000437900641025641,
      "loss": 2.1962,
      "step": 155
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0004375,
      "loss": 2.2109,
      "step": 156
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.000437099358974359,
      "loss": 2.1556,
      "step": 157
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.00043669871794871796,
      "loss": 2.1605,
      "step": 158
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.00043629807692307696,
      "loss": 2.155,
      "step": 159
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.0004358974358974359,
      "loss": 2.0347,
      "step": 160
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.0004354967948717949,
      "loss": 1.9321,
      "step": 161
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00043509615384615386,
      "loss": 2.0034,
      "step": 162
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.00043469551282051286,
      "loss": 2.0203,
      "step": 163
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.0004342948717948718,
      "loss": 1.9189,
      "step": 164
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.0004338942307692308,
      "loss": 1.9868,
      "step": 165
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.00043349358974358976,
      "loss": 1.9343,
      "step": 166
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.00043309294871794876,
      "loss": 1.8894,
      "step": 167
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.0004326923076923077,
      "loss": 1.9735,
      "step": 168
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.0004322916666666667,
      "loss": 2.0012,
      "step": 169
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.00043189102564102565,
      "loss": 1.9087,
      "step": 170
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.00043149038461538466,
      "loss": 1.9213,
      "step": 171
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.0004310897435897436,
      "loss": 2.0195,
      "step": 172
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.0004306891025641026,
      "loss": 1.9806,
      "step": 173
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.00043028846153846155,
      "loss": 1.9731,
      "step": 174
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.00042988782051282056,
      "loss": 1.9282,
      "step": 175
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.00042948717948717945,
      "loss": 1.9433,
      "step": 176
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.00042908653846153845,
      "loss": 1.9633,
      "step": 177
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.0004286858974358974,
      "loss": 1.9918,
      "step": 178
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.0004282852564102564,
      "loss": 1.9265,
      "step": 179
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.00042788461538461535,
      "loss": 1.9198,
      "step": 180
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.00042748397435897435,
      "loss": 2.0159,
      "step": 181
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.0004270833333333333,
      "loss": 1.9474,
      "step": 182
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.0004266826923076923,
      "loss": 2.0152,
      "step": 183
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0004262820512820513,
      "loss": 1.9006,
      "step": 184
    },
    {
      "epoch": 4.66,
      "learning_rate": 0.00042588141025641025,
      "loss": 1.9862,
      "step": 185
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.00042548076923076925,
      "loss": 1.9945,
      "step": 186
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0004250801282051282,
      "loss": 1.985,
      "step": 187
    },
    {
      "epoch": 4.74,
      "learning_rate": 0.0004246794871794872,
      "loss": 1.9899,
      "step": 188
    },
    {
      "epoch": 4.76,
      "learning_rate": 0.00042427884615384615,
      "loss": 2.0149,
      "step": 189
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.00042387820512820515,
      "loss": 1.9768,
      "step": 190
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.0004234775641025641,
      "loss": 2.0204,
      "step": 191
    },
    {
      "epoch": 4.84,
      "learning_rate": 0.0004230769230769231,
      "loss": 1.9343,
      "step": 192
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.00042267628205128205,
      "loss": 2.0574,
      "step": 193
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.00042227564102564105,
      "loss": 2.0245,
      "step": 194
    },
    {
      "epoch": 4.91,
      "learning_rate": 0.000421875,
      "loss": 2.0356,
      "step": 195
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.000421474358974359,
      "loss": 1.9984,
      "step": 196
    },
    {
      "epoch": 4.96,
      "learning_rate": 0.00042107371794871794,
      "loss": 1.9826,
      "step": 197
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.00042067307692307695,
      "loss": 1.9846,
      "step": 198
    },
    {
      "epoch": 5.01,
      "learning_rate": 0.0004202724358974359,
      "loss": 1.8931,
      "step": 199
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.0004198717948717949,
      "loss": 1.7642,
      "step": 200
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.00041947115384615384,
      "loss": 1.7235,
      "step": 201
    },
    {
      "epoch": 5.09,
      "learning_rate": 0.00041907051282051285,
      "loss": 1.7058,
      "step": 202
    },
    {
      "epoch": 5.11,
      "learning_rate": 0.0004186698717948718,
      "loss": 1.8022,
      "step": 203
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.0004182692307692308,
      "loss": 1.7819,
      "step": 204
    },
    {
      "epoch": 5.17,
      "learning_rate": 0.00041786858974358974,
      "loss": 1.7047,
      "step": 205
    },
    {
      "epoch": 5.19,
      "learning_rate": 0.00041746794871794874,
      "loss": 1.773,
      "step": 206
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.0004170673076923077,
      "loss": 1.7324,
      "step": 207
    },
    {
      "epoch": 5.24,
      "learning_rate": 0.0004166666666666667,
      "loss": 1.7862,
      "step": 208
    },
    {
      "epoch": 5.27,
      "learning_rate": 0.0004162660256410257,
      "loss": 1.764,
      "step": 209
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.00041586538461538464,
      "loss": 1.7156,
      "step": 210
    },
    {
      "epoch": 5.32,
      "learning_rate": 0.00041546474358974364,
      "loss": 1.7948,
      "step": 211
    },
    {
      "epoch": 5.34,
      "learning_rate": 0.0004150641025641026,
      "loss": 1.7608,
      "step": 212
    },
    {
      "epoch": 5.37,
      "learning_rate": 0.0004146634615384616,
      "loss": 1.7204,
      "step": 213
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.00041426282051282054,
      "loss": 1.7691,
      "step": 214
    },
    {
      "epoch": 5.42,
      "learning_rate": 0.0004138621794871795,
      "loss": 1.7969,
      "step": 215
    },
    {
      "epoch": 5.44,
      "learning_rate": 0.00041346153846153844,
      "loss": 1.7194,
      "step": 216
    },
    {
      "epoch": 5.47,
      "learning_rate": 0.00041306089743589744,
      "loss": 1.7022,
      "step": 217
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.0004126602564102564,
      "loss": 1.8287,
      "step": 218
    },
    {
      "epoch": 5.52,
      "learning_rate": 0.0004122596153846154,
      "loss": 1.7074,
      "step": 219
    },
    {
      "epoch": 5.54,
      "learning_rate": 0.00041185897435897434,
      "loss": 1.8354,
      "step": 220
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.00041145833333333334,
      "loss": 1.791,
      "step": 221
    },
    {
      "epoch": 5.59,
      "learning_rate": 0.0004110576923076923,
      "loss": 1.7633,
      "step": 222
    },
    {
      "epoch": 5.62,
      "learning_rate": 0.0004106570512820513,
      "loss": 1.811,
      "step": 223
    },
    {
      "epoch": 5.64,
      "learning_rate": 0.00041025641025641023,
      "loss": 1.7498,
      "step": 224
    },
    {
      "epoch": 5.67,
      "learning_rate": 0.00040985576923076924,
      "loss": 1.7662,
      "step": 225
    },
    {
      "epoch": 5.69,
      "learning_rate": 0.0004094551282051282,
      "loss": 1.7686,
      "step": 226
    },
    {
      "epoch": 5.72,
      "learning_rate": 0.0004090544871794872,
      "loss": 1.8357,
      "step": 227
    },
    {
      "epoch": 5.74,
      "learning_rate": 0.00040865384615384613,
      "loss": 1.7981,
      "step": 228
    },
    {
      "epoch": 5.77,
      "learning_rate": 0.00040825320512820513,
      "loss": 1.7502,
      "step": 229
    },
    {
      "epoch": 5.8,
      "learning_rate": 0.0004078525641025641,
      "loss": 1.7666,
      "step": 230
    },
    {
      "epoch": 5.82,
      "learning_rate": 0.0004074519230769231,
      "loss": 1.798,
      "step": 231
    },
    {
      "epoch": 5.85,
      "learning_rate": 0.00040705128205128203,
      "loss": 1.8072,
      "step": 232
    },
    {
      "epoch": 5.87,
      "learning_rate": 0.00040665064102564103,
      "loss": 1.7611,
      "step": 233
    },
    {
      "epoch": 5.9,
      "learning_rate": 0.00040625000000000004,
      "loss": 1.8126,
      "step": 234
    },
    {
      "epoch": 5.92,
      "learning_rate": 0.000405849358974359,
      "loss": 1.8361,
      "step": 235
    },
    {
      "epoch": 5.95,
      "learning_rate": 0.000405448717948718,
      "loss": 1.7938,
      "step": 236
    },
    {
      "epoch": 5.97,
      "learning_rate": 0.00040504807692307693,
      "loss": 1.7524,
      "step": 237
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00040464743589743593,
      "loss": 1.7601,
      "step": 238
    },
    {
      "epoch": 6.02,
      "learning_rate": 0.0004042467948717949,
      "loss": 1.5373,
      "step": 239
    },
    {
      "epoch": 6.05,
      "learning_rate": 0.0004038461538461539,
      "loss": 1.5108,
      "step": 240
    },
    {
      "epoch": 6.07,
      "learning_rate": 0.00040344551282051283,
      "loss": 1.568,
      "step": 241
    },
    {
      "epoch": 6.1,
      "learning_rate": 0.00040304487179487183,
      "loss": 1.5175,
      "step": 242
    },
    {
      "epoch": 6.12,
      "learning_rate": 0.0004026442307692308,
      "loss": 1.5748,
      "step": 243
    },
    {
      "epoch": 6.15,
      "learning_rate": 0.0004022435897435898,
      "loss": 1.4772,
      "step": 244
    },
    {
      "epoch": 6.17,
      "learning_rate": 0.00040184294871794873,
      "loss": 1.5035,
      "step": 245
    },
    {
      "epoch": 6.2,
      "learning_rate": 0.00040144230769230773,
      "loss": 1.5318,
      "step": 246
    },
    {
      "epoch": 6.22,
      "learning_rate": 0.0004010416666666667,
      "loss": 1.5139,
      "step": 247
    },
    {
      "epoch": 6.25,
      "learning_rate": 0.0004006410256410257,
      "loss": 1.5599,
      "step": 248
    },
    {
      "epoch": 6.27,
      "learning_rate": 0.00040024038461538463,
      "loss": 1.5475,
      "step": 249
    },
    {
      "epoch": 6.3,
      "learning_rate": 0.00039983974358974363,
      "loss": 1.4819,
      "step": 250
    },
    {
      "epoch": 6.32,
      "learning_rate": 0.0003994391025641026,
      "loss": 1.5419,
      "step": 251
    },
    {
      "epoch": 6.35,
      "learning_rate": 0.0003990384615384616,
      "loss": 1.6027,
      "step": 252
    },
    {
      "epoch": 6.37,
      "learning_rate": 0.00039863782051282053,
      "loss": 1.5683,
      "step": 253
    },
    {
      "epoch": 6.4,
      "learning_rate": 0.0003982371794871795,
      "loss": 1.5963,
      "step": 254
    },
    {
      "epoch": 6.43,
      "learning_rate": 0.0003978365384615384,
      "loss": 1.5874,
      "step": 255
    },
    {
      "epoch": 6.45,
      "learning_rate": 0.0003974358974358974,
      "loss": 1.5161,
      "step": 256
    },
    {
      "epoch": 6.48,
      "learning_rate": 0.00039703525641025637,
      "loss": 1.57,
      "step": 257
    },
    {
      "epoch": 6.5,
      "learning_rate": 0.0003966346153846154,
      "loss": 1.534,
      "step": 258
    },
    {
      "epoch": 6.53,
      "learning_rate": 0.0003962339743589743,
      "loss": 1.5513,
      "step": 259
    },
    {
      "epoch": 6.55,
      "learning_rate": 0.0003958333333333333,
      "loss": 1.5454,
      "step": 260
    },
    {
      "epoch": 6.58,
      "learning_rate": 0.0003954326923076923,
      "loss": 1.5695,
      "step": 261
    },
    {
      "epoch": 6.6,
      "learning_rate": 0.0003950320512820513,
      "loss": 1.5777,
      "step": 262
    },
    {
      "epoch": 6.63,
      "learning_rate": 0.0003946314102564103,
      "loss": 1.5629,
      "step": 263
    },
    {
      "epoch": 6.65,
      "learning_rate": 0.0003942307692307692,
      "loss": 1.5031,
      "step": 264
    },
    {
      "epoch": 6.68,
      "learning_rate": 0.0003938301282051282,
      "loss": 1.5964,
      "step": 265
    },
    {
      "epoch": 6.7,
      "learning_rate": 0.00039342948717948717,
      "loss": 1.5472,
      "step": 266
    },
    {
      "epoch": 6.73,
      "learning_rate": 0.0003930288461538462,
      "loss": 1.5654,
      "step": 267
    },
    {
      "epoch": 6.75,
      "learning_rate": 0.0003926282051282051,
      "loss": 1.5932,
      "step": 268
    },
    {
      "epoch": 6.78,
      "learning_rate": 0.0003922275641025641,
      "loss": 1.6037,
      "step": 269
    },
    {
      "epoch": 6.8,
      "learning_rate": 0.00039182692307692307,
      "loss": 1.6394,
      "step": 270
    },
    {
      "epoch": 6.83,
      "learning_rate": 0.00039142628205128207,
      "loss": 1.5745,
      "step": 271
    },
    {
      "epoch": 6.85,
      "learning_rate": 0.000391025641025641,
      "loss": 1.6512,
      "step": 272
    },
    {
      "epoch": 6.88,
      "learning_rate": 0.000390625,
      "loss": 1.6107,
      "step": 273
    },
    {
      "epoch": 6.9,
      "learning_rate": 0.00039022435897435897,
      "loss": 1.5798,
      "step": 274
    },
    {
      "epoch": 6.93,
      "learning_rate": 0.00038982371794871797,
      "loss": 1.6087,
      "step": 275
    },
    {
      "epoch": 6.95,
      "learning_rate": 0.0003894230769230769,
      "loss": 1.5362,
      "step": 276
    },
    {
      "epoch": 6.98,
      "learning_rate": 0.0003890224358974359,
      "loss": 1.5899,
      "step": 277
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.00038862179487179487,
      "loss": 1.59,
      "step": 278
    },
    {
      "epoch": 7.03,
      "learning_rate": 0.00038822115384615387,
      "loss": 1.3327,
      "step": 279
    },
    {
      "epoch": 7.06,
      "learning_rate": 0.0003878205128205128,
      "loss": 1.3214,
      "step": 280
    },
    {
      "epoch": 7.08,
      "learning_rate": 0.0003874198717948718,
      "loss": 1.2891,
      "step": 281
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.00038701923076923077,
      "loss": 1.3321,
      "step": 282
    },
    {
      "epoch": 7.13,
      "learning_rate": 0.00038661858974358977,
      "loss": 1.284,
      "step": 283
    },
    {
      "epoch": 7.16,
      "learning_rate": 0.0003862179487179487,
      "loss": 1.3346,
      "step": 284
    },
    {
      "epoch": 7.18,
      "learning_rate": 0.0003858173076923077,
      "loss": 1.2874,
      "step": 285
    },
    {
      "epoch": 7.21,
      "learning_rate": 0.0003854166666666667,
      "loss": 1.3104,
      "step": 286
    },
    {
      "epoch": 7.23,
      "learning_rate": 0.00038501602564102567,
      "loss": 1.3138,
      "step": 287
    },
    {
      "epoch": 7.26,
      "learning_rate": 0.00038461538461538467,
      "loss": 1.2871,
      "step": 288
    },
    {
      "epoch": 7.28,
      "learning_rate": 0.0003842147435897436,
      "loss": 1.2885,
      "step": 289
    },
    {
      "epoch": 7.31,
      "learning_rate": 0.0003838141025641026,
      "loss": 1.338,
      "step": 290
    },
    {
      "epoch": 7.33,
      "learning_rate": 0.00038341346153846157,
      "loss": 1.3189,
      "step": 291
    },
    {
      "epoch": 7.36,
      "learning_rate": 0.00038301282051282057,
      "loss": 1.3013,
      "step": 292
    },
    {
      "epoch": 7.38,
      "learning_rate": 0.00038261217948717946,
      "loss": 1.3505,
      "step": 293
    },
    {
      "epoch": 7.41,
      "learning_rate": 0.00038221153846153846,
      "loss": 1.3469,
      "step": 294
    },
    {
      "epoch": 7.43,
      "learning_rate": 0.0003818108974358974,
      "loss": 1.3156,
      "step": 295
    },
    {
      "epoch": 7.46,
      "learning_rate": 0.0003814102564102564,
      "loss": 1.3796,
      "step": 296
    },
    {
      "epoch": 7.48,
      "learning_rate": 0.00038100961538461536,
      "loss": 1.3649,
      "step": 297
    },
    {
      "epoch": 7.51,
      "learning_rate": 0.00038060897435897436,
      "loss": 1.3483,
      "step": 298
    },
    {
      "epoch": 7.53,
      "learning_rate": 0.0003802083333333333,
      "loss": 1.3481,
      "step": 299
    },
    {
      "epoch": 7.56,
      "learning_rate": 0.0003798076923076923,
      "loss": 1.334,
      "step": 300
    },
    {
      "epoch": 7.58,
      "learning_rate": 0.00037940705128205126,
      "loss": 1.3495,
      "step": 301
    },
    {
      "epoch": 7.61,
      "learning_rate": 0.00037900641025641026,
      "loss": 1.4102,
      "step": 302
    },
    {
      "epoch": 7.63,
      "learning_rate": 0.0003786057692307692,
      "loss": 1.3794,
      "step": 303
    },
    {
      "epoch": 7.66,
      "learning_rate": 0.0003782051282051282,
      "loss": 1.3802,
      "step": 304
    },
    {
      "epoch": 7.69,
      "learning_rate": 0.00037780448717948716,
      "loss": 1.3835,
      "step": 305
    },
    {
      "epoch": 7.71,
      "learning_rate": 0.00037740384615384616,
      "loss": 1.4197,
      "step": 306
    },
    {
      "epoch": 7.74,
      "learning_rate": 0.0003770032051282051,
      "loss": 1.3947,
      "step": 307
    },
    {
      "epoch": 7.76,
      "learning_rate": 0.0003766025641025641,
      "loss": 1.3891,
      "step": 308
    },
    {
      "epoch": 7.79,
      "learning_rate": 0.00037620192307692306,
      "loss": 1.3904,
      "step": 309
    },
    {
      "epoch": 7.81,
      "learning_rate": 0.00037580128205128206,
      "loss": 1.3937,
      "step": 310
    },
    {
      "epoch": 7.84,
      "learning_rate": 0.000375400641025641,
      "loss": 1.4258,
      "step": 311
    },
    {
      "epoch": 7.86,
      "learning_rate": 0.000375,
      "loss": 1.3816,
      "step": 312
    },
    {
      "epoch": 7.89,
      "learning_rate": 0.000374599358974359,
      "loss": 1.4251,
      "step": 313
    },
    {
      "epoch": 7.91,
      "learning_rate": 0.00037419871794871796,
      "loss": 1.3946,
      "step": 314
    },
    {
      "epoch": 7.94,
      "learning_rate": 0.00037379807692307696,
      "loss": 1.3968,
      "step": 315
    },
    {
      "epoch": 7.96,
      "learning_rate": 0.0003733974358974359,
      "loss": 1.4108,
      "step": 316
    },
    {
      "epoch": 7.99,
      "learning_rate": 0.0003729967948717949,
      "loss": 1.4673,
      "step": 317
    },
    {
      "epoch": 8.01,
      "learning_rate": 0.00037259615384615386,
      "loss": 1.2339,
      "step": 318
    },
    {
      "epoch": 8.04,
      "learning_rate": 0.00037219551282051286,
      "loss": 1.1775,
      "step": 319
    },
    {
      "epoch": 8.06,
      "learning_rate": 0.0003717948717948718,
      "loss": 1.1061,
      "step": 320
    },
    {
      "epoch": 8.09,
      "learning_rate": 0.0003713942307692308,
      "loss": 1.0912,
      "step": 321
    },
    {
      "epoch": 8.11,
      "learning_rate": 0.00037099358974358975,
      "loss": 1.1214,
      "step": 322
    },
    {
      "epoch": 8.14,
      "learning_rate": 0.00037059294871794876,
      "loss": 1.1537,
      "step": 323
    },
    {
      "epoch": 8.16,
      "learning_rate": 0.0003701923076923077,
      "loss": 1.116,
      "step": 324
    },
    {
      "epoch": 8.19,
      "learning_rate": 0.0003697916666666667,
      "loss": 1.1292,
      "step": 325
    },
    {
      "epoch": 8.21,
      "learning_rate": 0.00036939102564102565,
      "loss": 1.0948,
      "step": 326
    },
    {
      "epoch": 8.24,
      "learning_rate": 0.00036899038461538466,
      "loss": 1.0968,
      "step": 327
    },
    {
      "epoch": 8.26,
      "learning_rate": 0.0003685897435897436,
      "loss": 1.118,
      "step": 328
    },
    {
      "epoch": 8.29,
      "learning_rate": 0.0003681891025641026,
      "loss": 1.1488,
      "step": 329
    },
    {
      "epoch": 8.31,
      "learning_rate": 0.00036778846153846155,
      "loss": 1.137,
      "step": 330
    },
    {
      "epoch": 8.34,
      "learning_rate": 0.00036738782051282055,
      "loss": 1.0832,
      "step": 331
    },
    {
      "epoch": 8.37,
      "learning_rate": 0.00036698717948717945,
      "loss": 1.1609,
      "step": 332
    },
    {
      "epoch": 8.39,
      "learning_rate": 0.00036658653846153845,
      "loss": 1.1497,
      "step": 333
    },
    {
      "epoch": 8.42,
      "learning_rate": 0.0003661858974358974,
      "loss": 1.1289,
      "step": 334
    },
    {
      "epoch": 8.44,
      "learning_rate": 0.0003657852564102564,
      "loss": 1.1938,
      "step": 335
    },
    {
      "epoch": 8.47,
      "learning_rate": 0.00036538461538461535,
      "loss": 1.1441,
      "step": 336
    },
    {
      "epoch": 8.49,
      "learning_rate": 0.00036498397435897435,
      "loss": 1.1233,
      "step": 337
    },
    {
      "epoch": 8.52,
      "learning_rate": 0.0003645833333333333,
      "loss": 1.1273,
      "step": 338
    },
    {
      "epoch": 8.54,
      "learning_rate": 0.0003641826923076923,
      "loss": 1.1498,
      "step": 339
    },
    {
      "epoch": 8.57,
      "learning_rate": 0.0003637820512820513,
      "loss": 1.1848,
      "step": 340
    },
    {
      "epoch": 8.59,
      "learning_rate": 0.00036338141025641025,
      "loss": 1.1991,
      "step": 341
    },
    {
      "epoch": 8.62,
      "learning_rate": 0.00036298076923076925,
      "loss": 1.1705,
      "step": 342
    },
    {
      "epoch": 8.64,
      "learning_rate": 0.0003625801282051282,
      "loss": 1.1613,
      "step": 343
    },
    {
      "epoch": 8.67,
      "learning_rate": 0.0003621794871794872,
      "loss": 1.2599,
      "step": 344
    },
    {
      "epoch": 8.69,
      "learning_rate": 0.00036177884615384615,
      "loss": 1.1824,
      "step": 345
    },
    {
      "epoch": 8.72,
      "learning_rate": 0.00036137820512820515,
      "loss": 1.1763,
      "step": 346
    },
    {
      "epoch": 8.74,
      "learning_rate": 0.0003609775641025641,
      "loss": 1.1882,
      "step": 347
    },
    {
      "epoch": 8.77,
      "learning_rate": 0.0003605769230769231,
      "loss": 1.2043,
      "step": 348
    },
    {
      "epoch": 8.79,
      "learning_rate": 0.00036017628205128204,
      "loss": 1.2123,
      "step": 349
    },
    {
      "epoch": 8.82,
      "learning_rate": 0.00035977564102564105,
      "loss": 1.1831,
      "step": 350
    },
    {
      "epoch": 8.84,
      "learning_rate": 0.000359375,
      "loss": 1.2265,
      "step": 351
    },
    {
      "epoch": 8.87,
      "learning_rate": 0.000358974358974359,
      "loss": 1.1658,
      "step": 352
    },
    {
      "epoch": 8.89,
      "learning_rate": 0.00035857371794871794,
      "loss": 1.1787,
      "step": 353
    },
    {
      "epoch": 8.92,
      "learning_rate": 0.00035817307692307695,
      "loss": 1.1904,
      "step": 354
    },
    {
      "epoch": 8.94,
      "learning_rate": 0.0003577724358974359,
      "loss": 1.2753,
      "step": 355
    },
    {
      "epoch": 8.97,
      "learning_rate": 0.0003573717948717949,
      "loss": 1.2076,
      "step": 356
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.00035697115384615384,
      "loss": 1.2433,
      "step": 357
    },
    {
      "epoch": 9.02,
      "learning_rate": 0.00035657051282051284,
      "loss": 0.9733,
      "step": 358
    },
    {
      "epoch": 9.05,
      "learning_rate": 0.0003561698717948718,
      "loss": 0.9765,
      "step": 359
    },
    {
      "epoch": 9.07,
      "learning_rate": 0.0003557692307692308,
      "loss": 0.9626,
      "step": 360
    },
    {
      "epoch": 9.1,
      "learning_rate": 0.00035536858974358974,
      "loss": 0.9382,
      "step": 361
    },
    {
      "epoch": 9.12,
      "learning_rate": 0.00035496794871794874,
      "loss": 0.8644,
      "step": 362
    },
    {
      "epoch": 9.15,
      "learning_rate": 0.0003545673076923077,
      "loss": 0.9299,
      "step": 363
    },
    {
      "epoch": 9.17,
      "learning_rate": 0.0003541666666666667,
      "loss": 0.9618,
      "step": 364
    },
    {
      "epoch": 9.2,
      "learning_rate": 0.0003537660256410257,
      "loss": 0.9417,
      "step": 365
    },
    {
      "epoch": 9.22,
      "learning_rate": 0.00035336538461538464,
      "loss": 0.9873,
      "step": 366
    },
    {
      "epoch": 9.25,
      "learning_rate": 0.00035296474358974364,
      "loss": 0.9135,
      "step": 367
    },
    {
      "epoch": 9.27,
      "learning_rate": 0.0003525641025641026,
      "loss": 0.9652,
      "step": 368
    },
    {
      "epoch": 9.3,
      "learning_rate": 0.0003521634615384616,
      "loss": 0.9347,
      "step": 369
    },
    {
      "epoch": 9.32,
      "learning_rate": 0.00035176282051282054,
      "loss": 0.914,
      "step": 370
    },
    {
      "epoch": 9.35,
      "learning_rate": 0.0003513621794871795,
      "loss": 0.9622,
      "step": 371
    },
    {
      "epoch": 9.37,
      "learning_rate": 0.00035096153846153844,
      "loss": 0.9652,
      "step": 372
    },
    {
      "epoch": 9.4,
      "learning_rate": 0.00035056089743589744,
      "loss": 0.8865,
      "step": 373
    },
    {
      "epoch": 9.42,
      "learning_rate": 0.0003501602564102564,
      "loss": 0.9997,
      "step": 374
    },
    {
      "epoch": 9.45,
      "learning_rate": 0.0003497596153846154,
      "loss": 0.9695,
      "step": 375
    },
    {
      "epoch": 9.47,
      "learning_rate": 0.00034935897435897433,
      "loss": 1.0172,
      "step": 376
    },
    {
      "epoch": 9.5,
      "learning_rate": 0.00034895833333333334,
      "loss": 0.9955,
      "step": 377
    },
    {
      "epoch": 9.52,
      "learning_rate": 0.0003485576923076923,
      "loss": 0.9902,
      "step": 378
    },
    {
      "epoch": 9.55,
      "learning_rate": 0.0003481570512820513,
      "loss": 1.0225,
      "step": 379
    },
    {
      "epoch": 9.57,
      "learning_rate": 0.00034775641025641023,
      "loss": 0.9773,
      "step": 380
    },
    {
      "epoch": 9.6,
      "learning_rate": 0.00034735576923076923,
      "loss": 0.9947,
      "step": 381
    },
    {
      "epoch": 9.63,
      "learning_rate": 0.0003469551282051282,
      "loss": 1.0234,
      "step": 382
    },
    {
      "epoch": 9.65,
      "learning_rate": 0.0003465544871794872,
      "loss": 0.9692,
      "step": 383
    },
    {
      "epoch": 9.68,
      "learning_rate": 0.00034615384615384613,
      "loss": 0.9782,
      "step": 384
    },
    {
      "epoch": 9.7,
      "learning_rate": 0.00034575320512820513,
      "loss": 1.0416,
      "step": 385
    },
    {
      "epoch": 9.73,
      "learning_rate": 0.0003453525641025641,
      "loss": 1.0008,
      "step": 386
    },
    {
      "epoch": 9.75,
      "learning_rate": 0.0003449519230769231,
      "loss": 1.0854,
      "step": 387
    },
    {
      "epoch": 9.78,
      "learning_rate": 0.00034455128205128203,
      "loss": 1.085,
      "step": 388
    },
    {
      "epoch": 9.8,
      "learning_rate": 0.00034415064102564103,
      "loss": 1.007,
      "step": 389
    },
    {
      "epoch": 9.83,
      "learning_rate": 0.00034375,
      "loss": 1.0516,
      "step": 390
    },
    {
      "epoch": 9.85,
      "learning_rate": 0.000343349358974359,
      "loss": 0.9729,
      "step": 391
    },
    {
      "epoch": 9.88,
      "learning_rate": 0.000342948717948718,
      "loss": 1.0174,
      "step": 392
    },
    {
      "epoch": 9.9,
      "learning_rate": 0.00034254807692307693,
      "loss": 1.0392,
      "step": 393
    },
    {
      "epoch": 9.93,
      "learning_rate": 0.00034214743589743593,
      "loss": 1.0534,
      "step": 394
    },
    {
      "epoch": 9.95,
      "learning_rate": 0.0003417467948717949,
      "loss": 1.0584,
      "step": 395
    },
    {
      "epoch": 9.98,
      "learning_rate": 0.0003413461538461539,
      "loss": 1.0727,
      "step": 396
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.00034094551282051283,
      "loss": 1.0023,
      "step": 397
    },
    {
      "epoch": 10.03,
      "learning_rate": 0.00034054487179487183,
      "loss": 0.8029,
      "step": 398
    },
    {
      "epoch": 10.05,
      "learning_rate": 0.0003401442307692308,
      "loss": 0.7901,
      "step": 399
    },
    {
      "epoch": 10.08,
      "learning_rate": 0.0003397435897435898,
      "loss": 0.7791,
      "step": 400
    },
    {
      "epoch": 10.1,
      "learning_rate": 0.00033934294871794873,
      "loss": 0.7635,
      "step": 401
    },
    {
      "epoch": 10.13,
      "learning_rate": 0.00033894230769230773,
      "loss": 0.7713,
      "step": 402
    },
    {
      "epoch": 10.15,
      "learning_rate": 0.0003385416666666667,
      "loss": 0.827,
      "step": 403
    },
    {
      "epoch": 10.18,
      "learning_rate": 0.0003381410256410257,
      "loss": 0.7844,
      "step": 404
    },
    {
      "epoch": 10.2,
      "learning_rate": 0.00033774038461538463,
      "loss": 0.7839,
      "step": 405
    },
    {
      "epoch": 10.23,
      "learning_rate": 0.00033733974358974363,
      "loss": 0.7702,
      "step": 406
    },
    {
      "epoch": 10.26,
      "learning_rate": 0.0003369391025641026,
      "loss": 0.7855,
      "step": 407
    },
    {
      "epoch": 10.28,
      "learning_rate": 0.0003365384615384616,
      "loss": 0.7669,
      "step": 408
    },
    {
      "epoch": 10.31,
      "learning_rate": 0.0003361378205128205,
      "loss": 0.8054,
      "step": 409
    },
    {
      "epoch": 10.33,
      "learning_rate": 0.0003357371794871795,
      "loss": 0.7792,
      "step": 410
    },
    {
      "epoch": 10.36,
      "learning_rate": 0.0003353365384615384,
      "loss": 0.7986,
      "step": 411
    },
    {
      "epoch": 10.38,
      "learning_rate": 0.0003349358974358974,
      "loss": 0.8269,
      "step": 412
    },
    {
      "epoch": 10.41,
      "learning_rate": 0.00033453525641025637,
      "loss": 0.7923,
      "step": 413
    },
    {
      "epoch": 10.43,
      "learning_rate": 0.00033413461538461537,
      "loss": 0.8242,
      "step": 414
    },
    {
      "epoch": 10.46,
      "learning_rate": 0.0003337339743589743,
      "loss": 0.8496,
      "step": 415
    },
    {
      "epoch": 10.48,
      "learning_rate": 0.0003333333333333333,
      "loss": 0.8236,
      "step": 416
    },
    {
      "epoch": 10.51,
      "learning_rate": 0.0003329326923076923,
      "loss": 0.8685,
      "step": 417
    },
    {
      "epoch": 10.53,
      "learning_rate": 0.00033253205128205127,
      "loss": 0.8542,
      "step": 418
    },
    {
      "epoch": 10.56,
      "learning_rate": 0.0003321314102564103,
      "loss": 0.8185,
      "step": 419
    },
    {
      "epoch": 10.58,
      "learning_rate": 0.0003317307692307692,
      "loss": 0.8477,
      "step": 420
    },
    {
      "epoch": 10.61,
      "learning_rate": 0.0003313301282051282,
      "loss": 0.8372,
      "step": 421
    },
    {
      "epoch": 10.63,
      "learning_rate": 0.00033092948717948717,
      "loss": 0.8731,
      "step": 422
    },
    {
      "epoch": 10.66,
      "learning_rate": 0.00033052884615384617,
      "loss": 0.8322,
      "step": 423
    },
    {
      "epoch": 10.68,
      "learning_rate": 0.0003301282051282051,
      "loss": 0.8514,
      "step": 424
    },
    {
      "epoch": 10.71,
      "learning_rate": 0.0003297275641025641,
      "loss": 0.8564,
      "step": 425
    },
    {
      "epoch": 10.73,
      "learning_rate": 0.00032932692307692307,
      "loss": 0.8278,
      "step": 426
    },
    {
      "epoch": 10.76,
      "learning_rate": 0.00032892628205128207,
      "loss": 0.8408,
      "step": 427
    },
    {
      "epoch": 10.78,
      "learning_rate": 0.000328525641025641,
      "loss": 0.8438,
      "step": 428
    },
    {
      "epoch": 10.81,
      "learning_rate": 0.000328125,
      "loss": 0.8862,
      "step": 429
    },
    {
      "epoch": 10.83,
      "learning_rate": 0.00032772435897435897,
      "loss": 0.8631,
      "step": 430
    },
    {
      "epoch": 10.86,
      "learning_rate": 0.00032732371794871797,
      "loss": 0.883,
      "step": 431
    },
    {
      "epoch": 10.89,
      "learning_rate": 0.0003269230769230769,
      "loss": 0.8644,
      "step": 432
    },
    {
      "epoch": 10.91,
      "learning_rate": 0.0003265224358974359,
      "loss": 0.8907,
      "step": 433
    },
    {
      "epoch": 10.94,
      "learning_rate": 0.00032612179487179487,
      "loss": 0.9141,
      "step": 434
    },
    {
      "epoch": 10.96,
      "learning_rate": 0.00032572115384615387,
      "loss": 0.8877,
      "step": 435
    },
    {
      "epoch": 10.99,
      "learning_rate": 0.0003253205128205128,
      "loss": 0.8521,
      "step": 436
    },
    {
      "epoch": 11.01,
      "learning_rate": 0.0003249198717948718,
      "loss": 0.7842,
      "step": 437
    },
    {
      "epoch": 11.04,
      "learning_rate": 0.00032451923076923077,
      "loss": 0.6516,
      "step": 438
    },
    {
      "epoch": 11.06,
      "learning_rate": 0.00032411858974358977,
      "loss": 0.6549,
      "step": 439
    },
    {
      "epoch": 11.09,
      "learning_rate": 0.0003237179487179487,
      "loss": 0.6736,
      "step": 440
    },
    {
      "epoch": 11.11,
      "learning_rate": 0.0003233173076923077,
      "loss": 0.6625,
      "step": 441
    },
    {
      "epoch": 11.14,
      "learning_rate": 0.0003229166666666667,
      "loss": 0.6466,
      "step": 442
    },
    {
      "epoch": 11.16,
      "learning_rate": 0.00032251602564102567,
      "loss": 0.6362,
      "step": 443
    },
    {
      "epoch": 11.19,
      "learning_rate": 0.00032211538461538467,
      "loss": 0.674,
      "step": 444
    },
    {
      "epoch": 11.21,
      "learning_rate": 0.0003217147435897436,
      "loss": 0.6509,
      "step": 445
    },
    {
      "epoch": 11.24,
      "learning_rate": 0.0003213141025641026,
      "loss": 0.618,
      "step": 446
    },
    {
      "epoch": 11.26,
      "learning_rate": 0.00032091346153846156,
      "loss": 0.6654,
      "step": 447
    },
    {
      "epoch": 11.29,
      "learning_rate": 0.00032051282051282057,
      "loss": 0.6632,
      "step": 448
    },
    {
      "epoch": 11.31,
      "learning_rate": 0.00032011217948717946,
      "loss": 0.6599,
      "step": 449
    },
    {
      "epoch": 11.34,
      "learning_rate": 0.00031971153846153846,
      "loss": 0.6537,
      "step": 450
    },
    {
      "epoch": 11.36,
      "learning_rate": 0.0003193108974358974,
      "loss": 0.678,
      "step": 451
    },
    {
      "epoch": 11.39,
      "learning_rate": 0.0003189102564102564,
      "loss": 0.684,
      "step": 452
    },
    {
      "epoch": 11.41,
      "learning_rate": 0.00031850961538461536,
      "loss": 0.6419,
      "step": 453
    },
    {
      "epoch": 11.44,
      "learning_rate": 0.00031810897435897436,
      "loss": 0.6614,
      "step": 454
    },
    {
      "epoch": 11.46,
      "learning_rate": 0.0003177083333333333,
      "loss": 0.7037,
      "step": 455
    },
    {
      "epoch": 11.49,
      "learning_rate": 0.0003173076923076923,
      "loss": 0.6944,
      "step": 456
    },
    {
      "epoch": 11.51,
      "learning_rate": 0.00031690705128205126,
      "loss": 0.6818,
      "step": 457
    },
    {
      "epoch": 11.54,
      "learning_rate": 0.00031650641025641026,
      "loss": 0.692,
      "step": 458
    },
    {
      "epoch": 11.57,
      "learning_rate": 0.0003161057692307692,
      "loss": 0.7028,
      "step": 459
    },
    {
      "epoch": 11.59,
      "learning_rate": 0.0003157051282051282,
      "loss": 0.7009,
      "step": 460
    },
    {
      "epoch": 11.62,
      "learning_rate": 0.00031530448717948716,
      "loss": 0.7325,
      "step": 461
    },
    {
      "epoch": 11.64,
      "learning_rate": 0.00031490384615384616,
      "loss": 0.6738,
      "step": 462
    },
    {
      "epoch": 11.67,
      "learning_rate": 0.0003145032051282051,
      "loss": 0.7008,
      "step": 463
    },
    {
      "epoch": 11.69,
      "learning_rate": 0.0003141025641025641,
      "loss": 0.6838,
      "step": 464
    },
    {
      "epoch": 11.72,
      "learning_rate": 0.00031370192307692306,
      "loss": 0.726,
      "step": 465
    },
    {
      "epoch": 11.74,
      "learning_rate": 0.00031330128205128206,
      "loss": 0.7167,
      "step": 466
    },
    {
      "epoch": 11.77,
      "learning_rate": 0.000312900641025641,
      "loss": 0.7236,
      "step": 467
    },
    {
      "epoch": 11.79,
      "learning_rate": 0.0003125,
      "loss": 0.7076,
      "step": 468
    },
    {
      "epoch": 11.82,
      "learning_rate": 0.000312099358974359,
      "loss": 0.7415,
      "step": 469
    },
    {
      "epoch": 11.84,
      "learning_rate": 0.00031169871794871796,
      "loss": 0.7313,
      "step": 470
    },
    {
      "epoch": 11.87,
      "learning_rate": 0.00031129807692307696,
      "loss": 0.7403,
      "step": 471
    },
    {
      "epoch": 11.89,
      "learning_rate": 0.0003108974358974359,
      "loss": 0.7145,
      "step": 472
    },
    {
      "epoch": 11.92,
      "learning_rate": 0.0003104967948717949,
      "loss": 0.7532,
      "step": 473
    },
    {
      "epoch": 11.94,
      "learning_rate": 0.00031009615384615385,
      "loss": 0.7326,
      "step": 474
    },
    {
      "epoch": 11.97,
      "learning_rate": 0.00030969551282051286,
      "loss": 0.7699,
      "step": 475
    },
    {
      "epoch": 11.99,
      "learning_rate": 0.0003092948717948718,
      "loss": 0.7251,
      "step": 476
    },
    {
      "epoch": 12.02,
      "learning_rate": 0.0003088942307692308,
      "loss": 0.5773,
      "step": 477
    },
    {
      "epoch": 12.04,
      "learning_rate": 0.00030849358974358975,
      "loss": 0.5288,
      "step": 478
    },
    {
      "epoch": 12.07,
      "learning_rate": 0.00030809294871794876,
      "loss": 0.5312,
      "step": 479
    },
    {
      "epoch": 12.09,
      "learning_rate": 0.0003076923076923077,
      "loss": 0.5445,
      "step": 480
    },
    {
      "epoch": 12.12,
      "learning_rate": 0.0003072916666666667,
      "loss": 0.5218,
      "step": 481
    },
    {
      "epoch": 12.14,
      "learning_rate": 0.00030689102564102565,
      "loss": 0.5311,
      "step": 482
    },
    {
      "epoch": 12.17,
      "learning_rate": 0.00030649038461538465,
      "loss": 0.5541,
      "step": 483
    },
    {
      "epoch": 12.2,
      "learning_rate": 0.0003060897435897436,
      "loss": 0.5242,
      "step": 484
    },
    {
      "epoch": 12.22,
      "learning_rate": 0.0003056891025641026,
      "loss": 0.5302,
      "step": 485
    },
    {
      "epoch": 12.25,
      "learning_rate": 0.00030528846153846155,
      "loss": 0.536,
      "step": 486
    },
    {
      "epoch": 12.27,
      "learning_rate": 0.00030488782051282055,
      "loss": 0.5545,
      "step": 487
    },
    {
      "epoch": 12.3,
      "learning_rate": 0.00030448717948717945,
      "loss": 0.5476,
      "step": 488
    },
    {
      "epoch": 12.32,
      "learning_rate": 0.00030408653846153845,
      "loss": 0.5528,
      "step": 489
    },
    {
      "epoch": 12.35,
      "learning_rate": 0.0003036858974358974,
      "loss": 0.5633,
      "step": 490
    },
    {
      "epoch": 12.37,
      "learning_rate": 0.0003032852564102564,
      "loss": 0.571,
      "step": 491
    },
    {
      "epoch": 12.4,
      "learning_rate": 0.00030288461538461535,
      "loss": 0.5637,
      "step": 492
    },
    {
      "epoch": 12.42,
      "learning_rate": 0.00030248397435897435,
      "loss": 0.5613,
      "step": 493
    },
    {
      "epoch": 12.45,
      "learning_rate": 0.0003020833333333333,
      "loss": 0.5999,
      "step": 494
    },
    {
      "epoch": 12.47,
      "learning_rate": 0.0003016826923076923,
      "loss": 0.5633,
      "step": 495
    },
    {
      "epoch": 12.5,
      "learning_rate": 0.0003012820512820513,
      "loss": 0.5811,
      "step": 496
    },
    {
      "epoch": 12.52,
      "learning_rate": 0.00030088141025641025,
      "loss": 0.5711,
      "step": 497
    },
    {
      "epoch": 12.55,
      "learning_rate": 0.00030048076923076925,
      "loss": 0.5669,
      "step": 498
    },
    {
      "epoch": 12.57,
      "learning_rate": 0.0003000801282051282,
      "loss": 0.5424,
      "step": 499
    },
    {
      "epoch": 12.6,
      "learning_rate": 0.0002996794871794872,
      "loss": 0.5592,
      "step": 500
    },
    {
      "epoch": 12.62,
      "learning_rate": 0.00029927884615384614,
      "loss": 0.5645,
      "step": 501
    },
    {
      "epoch": 12.65,
      "learning_rate": 0.00029887820512820515,
      "loss": 0.6089,
      "step": 502
    },
    {
      "epoch": 12.67,
      "learning_rate": 0.0002984775641025641,
      "loss": 0.57,
      "step": 503
    },
    {
      "epoch": 12.7,
      "learning_rate": 0.0002980769230769231,
      "loss": 0.57,
      "step": 504
    },
    {
      "epoch": 12.72,
      "learning_rate": 0.00029767628205128204,
      "loss": 0.5511,
      "step": 505
    },
    {
      "epoch": 12.75,
      "learning_rate": 0.00029727564102564105,
      "loss": 0.5765,
      "step": 506
    },
    {
      "epoch": 12.77,
      "learning_rate": 0.000296875,
      "loss": 0.5896,
      "step": 507
    },
    {
      "epoch": 12.8,
      "learning_rate": 0.000296474358974359,
      "loss": 0.6329,
      "step": 508
    },
    {
      "epoch": 12.83,
      "learning_rate": 0.00029607371794871794,
      "loss": 0.5682,
      "step": 509
    },
    {
      "epoch": 12.85,
      "learning_rate": 0.00029567307692307694,
      "loss": 0.58,
      "step": 510
    },
    {
      "epoch": 12.88,
      "learning_rate": 0.0002952724358974359,
      "loss": 0.6014,
      "step": 511
    },
    {
      "epoch": 12.9,
      "learning_rate": 0.0002948717948717949,
      "loss": 0.6082,
      "step": 512
    },
    {
      "epoch": 12.93,
      "learning_rate": 0.00029447115384615384,
      "loss": 0.6392,
      "step": 513
    },
    {
      "epoch": 12.95,
      "learning_rate": 0.00029407051282051284,
      "loss": 0.609,
      "step": 514
    },
    {
      "epoch": 12.98,
      "learning_rate": 0.0002936698717948718,
      "loss": 0.6247,
      "step": 515
    },
    {
      "epoch": 13.0,
      "learning_rate": 0.0002932692307692308,
      "loss": 0.5943,
      "step": 516
    },
    {
      "epoch": 13.03,
      "learning_rate": 0.00029286858974358974,
      "loss": 0.4499,
      "step": 517
    },
    {
      "epoch": 13.05,
      "learning_rate": 0.00029246794871794874,
      "loss": 0.4412,
      "step": 518
    },
    {
      "epoch": 13.08,
      "learning_rate": 0.0002920673076923077,
      "loss": 0.4409,
      "step": 519
    },
    {
      "epoch": 13.1,
      "learning_rate": 0.0002916666666666667,
      "loss": 0.4505,
      "step": 520
    },
    {
      "epoch": 13.13,
      "learning_rate": 0.0002912660256410257,
      "loss": 0.4489,
      "step": 521
    },
    {
      "epoch": 13.15,
      "learning_rate": 0.00029086538461538464,
      "loss": 0.4235,
      "step": 522
    },
    {
      "epoch": 13.18,
      "learning_rate": 0.00029046474358974364,
      "loss": 0.4276,
      "step": 523
    },
    {
      "epoch": 13.2,
      "learning_rate": 0.0002900641025641026,
      "loss": 0.4544,
      "step": 524
    },
    {
      "epoch": 13.23,
      "learning_rate": 0.0002896634615384616,
      "loss": 0.4625,
      "step": 525
    },
    {
      "epoch": 13.25,
      "learning_rate": 0.00028926282051282054,
      "loss": 0.4266,
      "step": 526
    },
    {
      "epoch": 13.28,
      "learning_rate": 0.0002888621794871795,
      "loss": 0.4459,
      "step": 527
    },
    {
      "epoch": 13.3,
      "learning_rate": 0.00028846153846153843,
      "loss": 0.4261,
      "step": 528
    },
    {
      "epoch": 13.33,
      "learning_rate": 0.00028806089743589744,
      "loss": 0.4376,
      "step": 529
    },
    {
      "epoch": 13.35,
      "learning_rate": 0.0002876602564102564,
      "loss": 0.4418,
      "step": 530
    },
    {
      "epoch": 13.38,
      "learning_rate": 0.0002872596153846154,
      "loss": 0.4667,
      "step": 531
    },
    {
      "epoch": 13.4,
      "learning_rate": 0.00028685897435897433,
      "loss": 0.4504,
      "step": 532
    },
    {
      "epoch": 13.43,
      "learning_rate": 0.00028645833333333333,
      "loss": 0.4691,
      "step": 533
    },
    {
      "epoch": 13.46,
      "learning_rate": 0.0002860576923076923,
      "loss": 0.4684,
      "step": 534
    },
    {
      "epoch": 13.48,
      "learning_rate": 0.0002856570512820513,
      "loss": 0.467,
      "step": 535
    },
    {
      "epoch": 13.51,
      "learning_rate": 0.00028525641025641023,
      "loss": 0.4716,
      "step": 536
    },
    {
      "epoch": 13.53,
      "learning_rate": 0.00028485576923076923,
      "loss": 0.4619,
      "step": 537
    },
    {
      "epoch": 13.56,
      "learning_rate": 0.0002844551282051282,
      "loss": 0.4775,
      "step": 538
    },
    {
      "epoch": 13.58,
      "learning_rate": 0.0002840544871794872,
      "loss": 0.4568,
      "step": 539
    },
    {
      "epoch": 13.61,
      "learning_rate": 0.00028365384615384613,
      "loss": 0.4763,
      "step": 540
    },
    {
      "epoch": 13.63,
      "learning_rate": 0.00028325320512820513,
      "loss": 0.466,
      "step": 541
    },
    {
      "epoch": 13.66,
      "learning_rate": 0.0002828525641025641,
      "loss": 0.4543,
      "step": 542
    },
    {
      "epoch": 13.68,
      "learning_rate": 0.0002824519230769231,
      "loss": 0.4666,
      "step": 543
    },
    {
      "epoch": 13.71,
      "learning_rate": 0.00028205128205128203,
      "loss": 0.489,
      "step": 544
    },
    {
      "epoch": 13.73,
      "learning_rate": 0.00028165064102564103,
      "loss": 0.491,
      "step": 545
    },
    {
      "epoch": 13.76,
      "learning_rate": 0.00028125000000000003,
      "loss": 0.4847,
      "step": 546
    },
    {
      "epoch": 13.78,
      "learning_rate": 0.000280849358974359,
      "loss": 0.4899,
      "step": 547
    },
    {
      "epoch": 13.81,
      "learning_rate": 0.000280448717948718,
      "loss": 0.5169,
      "step": 548
    },
    {
      "epoch": 13.83,
      "learning_rate": 0.00028004807692307693,
      "loss": 0.4968,
      "step": 549
    },
    {
      "epoch": 13.86,
      "learning_rate": 0.00027964743589743593,
      "loss": 0.4774,
      "step": 550
    },
    {
      "epoch": 13.88,
      "learning_rate": 0.0002792467948717949,
      "loss": 0.5105,
      "step": 551
    },
    {
      "epoch": 13.91,
      "learning_rate": 0.0002788461538461539,
      "loss": 0.4997,
      "step": 552
    },
    {
      "epoch": 13.93,
      "learning_rate": 0.00027844551282051283,
      "loss": 0.5088,
      "step": 553
    },
    {
      "epoch": 13.96,
      "learning_rate": 0.00027804487179487183,
      "loss": 0.5091,
      "step": 554
    },
    {
      "epoch": 13.98,
      "learning_rate": 0.0002776442307692308,
      "loss": 0.532,
      "step": 555
    },
    {
      "epoch": 14.01,
      "learning_rate": 0.0002772435897435898,
      "loss": 0.4487,
      "step": 556
    },
    {
      "epoch": 14.03,
      "learning_rate": 0.00027684294871794873,
      "loss": 0.3525,
      "step": 557
    },
    {
      "epoch": 14.06,
      "learning_rate": 0.00027644230769230773,
      "loss": 0.3715,
      "step": 558
    },
    {
      "epoch": 14.09,
      "learning_rate": 0.0002760416666666667,
      "loss": 0.3547,
      "step": 559
    },
    {
      "epoch": 14.11,
      "learning_rate": 0.0002756410256410257,
      "loss": 0.3862,
      "step": 560
    },
    {
      "epoch": 14.14,
      "learning_rate": 0.0002752403846153846,
      "loss": 0.3514,
      "step": 561
    },
    {
      "epoch": 14.16,
      "learning_rate": 0.00027483974358974363,
      "loss": 0.362,
      "step": 562
    },
    {
      "epoch": 14.19,
      "learning_rate": 0.0002744391025641026,
      "loss": 0.3457,
      "step": 563
    },
    {
      "epoch": 14.21,
      "learning_rate": 0.0002740384615384616,
      "loss": 0.3662,
      "step": 564
    },
    {
      "epoch": 14.24,
      "learning_rate": 0.0002736378205128205,
      "loss": 0.3746,
      "step": 565
    },
    {
      "epoch": 14.26,
      "learning_rate": 0.00027323717948717947,
      "loss": 0.3388,
      "step": 566
    },
    {
      "epoch": 14.29,
      "learning_rate": 0.0002728365384615384,
      "loss": 0.3824,
      "step": 567
    },
    {
      "epoch": 14.31,
      "learning_rate": 0.0002724358974358974,
      "loss": 0.3584,
      "step": 568
    },
    {
      "epoch": 14.34,
      "learning_rate": 0.00027203525641025637,
      "loss": 0.3544,
      "step": 569
    },
    {
      "epoch": 14.36,
      "learning_rate": 0.00027163461538461537,
      "loss": 0.3721,
      "step": 570
    },
    {
      "epoch": 14.39,
      "learning_rate": 0.0002712339743589743,
      "loss": 0.3769,
      "step": 571
    },
    {
      "epoch": 14.41,
      "learning_rate": 0.0002708333333333333,
      "loss": 0.3872,
      "step": 572
    },
    {
      "epoch": 14.44,
      "learning_rate": 0.0002704326923076923,
      "loss": 0.363,
      "step": 573
    },
    {
      "epoch": 14.46,
      "learning_rate": 0.00027003205128205127,
      "loss": 0.3842,
      "step": 574
    },
    {
      "epoch": 14.49,
      "learning_rate": 0.00026963141025641027,
      "loss": 0.3737,
      "step": 575
    },
    {
      "epoch": 14.51,
      "learning_rate": 0.0002692307692307692,
      "loss": 0.3981,
      "step": 576
    },
    {
      "epoch": 14.54,
      "learning_rate": 0.0002688301282051282,
      "loss": 0.3656,
      "step": 577
    },
    {
      "epoch": 14.56,
      "learning_rate": 0.00026842948717948717,
      "loss": 0.3852,
      "step": 578
    },
    {
      "epoch": 14.59,
      "learning_rate": 0.00026802884615384617,
      "loss": 0.3865,
      "step": 579
    },
    {
      "epoch": 14.61,
      "learning_rate": 0.0002676282051282051,
      "loss": 0.3747,
      "step": 580
    },
    {
      "epoch": 14.64,
      "learning_rate": 0.0002672275641025641,
      "loss": 0.3729,
      "step": 581
    },
    {
      "epoch": 14.66,
      "learning_rate": 0.00026682692307692307,
      "loss": 0.3785,
      "step": 582
    },
    {
      "epoch": 14.69,
      "learning_rate": 0.00026642628205128207,
      "loss": 0.4018,
      "step": 583
    },
    {
      "epoch": 14.71,
      "learning_rate": 0.000266025641025641,
      "loss": 0.3854,
      "step": 584
    },
    {
      "epoch": 14.74,
      "learning_rate": 0.000265625,
      "loss": 0.4161,
      "step": 585
    },
    {
      "epoch": 14.77,
      "learning_rate": 0.00026522435897435897,
      "loss": 0.4093,
      "step": 586
    },
    {
      "epoch": 14.79,
      "learning_rate": 0.00026482371794871797,
      "loss": 0.4126,
      "step": 587
    },
    {
      "epoch": 14.82,
      "learning_rate": 0.0002644230769230769,
      "loss": 0.3977,
      "step": 588
    },
    {
      "epoch": 14.84,
      "learning_rate": 0.0002640224358974359,
      "loss": 0.4286,
      "step": 589
    },
    {
      "epoch": 14.87,
      "learning_rate": 0.00026362179487179487,
      "loss": 0.4371,
      "step": 590
    },
    {
      "epoch": 14.89,
      "learning_rate": 0.00026322115384615387,
      "loss": 0.4066,
      "step": 591
    },
    {
      "epoch": 14.92,
      "learning_rate": 0.0002628205128205128,
      "loss": 0.433,
      "step": 592
    },
    {
      "epoch": 14.94,
      "learning_rate": 0.0002624198717948718,
      "loss": 0.4361,
      "step": 593
    },
    {
      "epoch": 14.97,
      "learning_rate": 0.00026201923076923076,
      "loss": 0.4276,
      "step": 594
    },
    {
      "epoch": 14.99,
      "learning_rate": 0.00026161858974358977,
      "loss": 0.4401,
      "step": 595
    },
    {
      "epoch": 15.02,
      "learning_rate": 0.0002612179487179487,
      "loss": 0.3514,
      "step": 596
    },
    {
      "epoch": 15.04,
      "learning_rate": 0.0002608173076923077,
      "loss": 0.306,
      "step": 597
    },
    {
      "epoch": 15.07,
      "learning_rate": 0.0002604166666666667,
      "loss": 0.2862,
      "step": 598
    },
    {
      "epoch": 15.09,
      "learning_rate": 0.00026001602564102566,
      "loss": 0.3042,
      "step": 599
    },
    {
      "epoch": 15.12,
      "learning_rate": 0.00025961538461538467,
      "loss": 0.2978,
      "step": 600
    },
    {
      "epoch": 15.14,
      "learning_rate": 0.0002592147435897436,
      "loss": 0.2975,
      "step": 601
    },
    {
      "epoch": 15.17,
      "learning_rate": 0.0002588141025641026,
      "loss": 0.3172,
      "step": 602
    },
    {
      "epoch": 15.19,
      "learning_rate": 0.00025841346153846156,
      "loss": 0.3046,
      "step": 603
    },
    {
      "epoch": 15.22,
      "learning_rate": 0.00025801282051282057,
      "loss": 0.3008,
      "step": 604
    },
    {
      "epoch": 15.24,
      "learning_rate": 0.00025761217948717946,
      "loss": 0.2956,
      "step": 605
    },
    {
      "epoch": 15.27,
      "learning_rate": 0.00025721153846153846,
      "loss": 0.3137,
      "step": 606
    },
    {
      "epoch": 15.29,
      "learning_rate": 0.0002568108974358974,
      "loss": 0.2961,
      "step": 607
    },
    {
      "epoch": 15.32,
      "learning_rate": 0.0002564102564102564,
      "loss": 0.3059,
      "step": 608
    },
    {
      "epoch": 15.34,
      "learning_rate": 0.00025600961538461536,
      "loss": 0.3077,
      "step": 609
    },
    {
      "epoch": 15.37,
      "learning_rate": 0.00025560897435897436,
      "loss": 0.3189,
      "step": 610
    },
    {
      "epoch": 15.4,
      "learning_rate": 0.0002552083333333333,
      "loss": 0.309,
      "step": 611
    },
    {
      "epoch": 15.42,
      "learning_rate": 0.0002548076923076923,
      "loss": 0.3324,
      "step": 612
    },
    {
      "epoch": 15.45,
      "learning_rate": 0.00025440705128205126,
      "loss": 0.3159,
      "step": 613
    },
    {
      "epoch": 15.47,
      "learning_rate": 0.00025400641025641026,
      "loss": 0.3188,
      "step": 614
    },
    {
      "epoch": 15.5,
      "learning_rate": 0.0002536057692307692,
      "loss": 0.3174,
      "step": 615
    },
    {
      "epoch": 15.52,
      "learning_rate": 0.0002532051282051282,
      "loss": 0.3074,
      "step": 616
    },
    {
      "epoch": 15.55,
      "learning_rate": 0.00025280448717948716,
      "loss": 0.3145,
      "step": 617
    },
    {
      "epoch": 15.57,
      "learning_rate": 0.00025240384615384616,
      "loss": 0.317,
      "step": 618
    },
    {
      "epoch": 15.6,
      "learning_rate": 0.0002520032051282051,
      "loss": 0.318,
      "step": 619
    },
    {
      "epoch": 15.62,
      "learning_rate": 0.0002516025641025641,
      "loss": 0.3236,
      "step": 620
    },
    {
      "epoch": 15.65,
      "learning_rate": 0.00025120192307692305,
      "loss": 0.3282,
      "step": 621
    },
    {
      "epoch": 15.67,
      "learning_rate": 0.00025080128205128206,
      "loss": 0.3394,
      "step": 622
    },
    {
      "epoch": 15.7,
      "learning_rate": 0.000250400641025641,
      "loss": 0.3278,
      "step": 623
    },
    {
      "epoch": 15.72,
      "learning_rate": 0.00025,
      "loss": 0.3255,
      "step": 624
    },
    {
      "epoch": 15.75,
      "learning_rate": 0.000249599358974359,
      "loss": 0.3256,
      "step": 625
    },
    {
      "epoch": 15.77,
      "learning_rate": 0.00024919871794871795,
      "loss": 0.3379,
      "step": 626
    },
    {
      "epoch": 15.8,
      "learning_rate": 0.00024879807692307696,
      "loss": 0.3384,
      "step": 627
    },
    {
      "epoch": 15.82,
      "learning_rate": 0.0002483974358974359,
      "loss": 0.3483,
      "step": 628
    },
    {
      "epoch": 15.85,
      "learning_rate": 0.0002479967948717949,
      "loss": 0.3478,
      "step": 629
    },
    {
      "epoch": 15.87,
      "learning_rate": 0.00024759615384615385,
      "loss": 0.337,
      "step": 630
    },
    {
      "epoch": 15.9,
      "learning_rate": 0.00024719551282051286,
      "loss": 0.3287,
      "step": 631
    },
    {
      "epoch": 15.92,
      "learning_rate": 0.0002467948717948718,
      "loss": 0.3478,
      "step": 632
    },
    {
      "epoch": 15.95,
      "learning_rate": 0.0002463942307692308,
      "loss": 0.3567,
      "step": 633
    },
    {
      "epoch": 15.97,
      "learning_rate": 0.00024599358974358975,
      "loss": 0.3359,
      "step": 634
    },
    {
      "epoch": 16.0,
      "learning_rate": 0.0002455929487179487,
      "loss": 0.3492,
      "step": 635
    },
    {
      "epoch": 16.03,
      "learning_rate": 0.0002451923076923077,
      "loss": 0.2497,
      "step": 636
    },
    {
      "epoch": 16.05,
      "learning_rate": 0.00024479166666666665,
      "loss": 0.2416,
      "step": 637
    },
    {
      "epoch": 16.08,
      "learning_rate": 0.00024439102564102565,
      "loss": 0.2576,
      "step": 638
    },
    {
      "epoch": 16.1,
      "learning_rate": 0.00024399038461538463,
      "loss": 0.243,
      "step": 639
    },
    {
      "epoch": 16.13,
      "learning_rate": 0.0002435897435897436,
      "loss": 0.2527,
      "step": 640
    },
    {
      "epoch": 16.15,
      "learning_rate": 0.00024318910256410258,
      "loss": 0.2606,
      "step": 641
    },
    {
      "epoch": 16.18,
      "learning_rate": 0.00024278846153846155,
      "loss": 0.2555,
      "step": 642
    },
    {
      "epoch": 16.2,
      "learning_rate": 0.00024238782051282052,
      "loss": 0.2581,
      "step": 643
    },
    {
      "epoch": 16.23,
      "learning_rate": 0.0002419871794871795,
      "loss": 0.2508,
      "step": 644
    },
    {
      "epoch": 16.25,
      "learning_rate": 0.00024158653846153847,
      "loss": 0.281,
      "step": 645
    },
    {
      "epoch": 16.28,
      "learning_rate": 0.00024118589743589745,
      "loss": 0.2626,
      "step": 646
    },
    {
      "epoch": 16.3,
      "learning_rate": 0.00024078525641025642,
      "loss": 0.2668,
      "step": 647
    },
    {
      "epoch": 16.33,
      "learning_rate": 0.0002403846153846154,
      "loss": 0.2675,
      "step": 648
    },
    {
      "epoch": 16.35,
      "learning_rate": 0.00023998397435897437,
      "loss": 0.2491,
      "step": 649
    },
    {
      "epoch": 16.38,
      "learning_rate": 0.00023958333333333335,
      "loss": 0.2459,
      "step": 650
    },
    {
      "epoch": 16.4,
      "learning_rate": 0.00023918269230769232,
      "loss": 0.2515,
      "step": 651
    },
    {
      "epoch": 16.43,
      "learning_rate": 0.0002387820512820513,
      "loss": 0.2612,
      "step": 652
    },
    {
      "epoch": 16.45,
      "learning_rate": 0.00023838141025641027,
      "loss": 0.2612,
      "step": 653
    },
    {
      "epoch": 16.48,
      "learning_rate": 0.00023798076923076922,
      "loss": 0.265,
      "step": 654
    },
    {
      "epoch": 16.5,
      "learning_rate": 0.0002375801282051282,
      "loss": 0.2634,
      "step": 655
    },
    {
      "epoch": 16.53,
      "learning_rate": 0.00023717948717948717,
      "loss": 0.2839,
      "step": 656
    },
    {
      "epoch": 16.55,
      "learning_rate": 0.00023677884615384614,
      "loss": 0.2595,
      "step": 657
    },
    {
      "epoch": 16.58,
      "learning_rate": 0.00023637820512820512,
      "loss": 0.2764,
      "step": 658
    },
    {
      "epoch": 16.6,
      "learning_rate": 0.0002359775641025641,
      "loss": 0.2553,
      "step": 659
    },
    {
      "epoch": 16.63,
      "learning_rate": 0.00023557692307692307,
      "loss": 0.2716,
      "step": 660
    },
    {
      "epoch": 16.66,
      "learning_rate": 0.00023517628205128204,
      "loss": 0.289,
      "step": 661
    },
    {
      "epoch": 16.68,
      "learning_rate": 0.00023477564102564102,
      "loss": 0.2483,
      "step": 662
    },
    {
      "epoch": 16.71,
      "learning_rate": 0.000234375,
      "loss": 0.269,
      "step": 663
    },
    {
      "epoch": 16.73,
      "learning_rate": 0.000233974358974359,
      "loss": 0.2738,
      "step": 664
    },
    {
      "epoch": 16.76,
      "learning_rate": 0.00023357371794871797,
      "loss": 0.2646,
      "step": 665
    },
    {
      "epoch": 16.78,
      "learning_rate": 0.00023317307692307694,
      "loss": 0.2793,
      "step": 666
    },
    {
      "epoch": 16.81,
      "learning_rate": 0.00023277243589743592,
      "loss": 0.2666,
      "step": 667
    },
    {
      "epoch": 16.83,
      "learning_rate": 0.0002323717948717949,
      "loss": 0.2799,
      "step": 668
    },
    {
      "epoch": 16.86,
      "learning_rate": 0.00023197115384615387,
      "loss": 0.2677,
      "step": 669
    },
    {
      "epoch": 16.88,
      "learning_rate": 0.00023157051282051284,
      "loss": 0.2889,
      "step": 670
    },
    {
      "epoch": 16.91,
      "learning_rate": 0.00023116987179487182,
      "loss": 0.2869,
      "step": 671
    },
    {
      "epoch": 16.93,
      "learning_rate": 0.0002307692307692308,
      "loss": 0.2814,
      "step": 672
    },
    {
      "epoch": 16.96,
      "learning_rate": 0.00023036858974358974,
      "loss": 0.2881,
      "step": 673
    },
    {
      "epoch": 16.98,
      "learning_rate": 0.0002299679487179487,
      "loss": 0.2777,
      "step": 674
    },
    {
      "epoch": 17.01,
      "learning_rate": 0.0002295673076923077,
      "loss": 0.2713,
      "step": 675
    },
    {
      "epoch": 17.03,
      "learning_rate": 0.00022916666666666666,
      "loss": 0.2176,
      "step": 676
    },
    {
      "epoch": 17.06,
      "learning_rate": 0.00022876602564102564,
      "loss": 0.2032,
      "step": 677
    },
    {
      "epoch": 17.08,
      "learning_rate": 0.0002283653846153846,
      "loss": 0.2207,
      "step": 678
    },
    {
      "epoch": 17.11,
      "learning_rate": 0.0002279647435897436,
      "loss": 0.2183,
      "step": 679
    },
    {
      "epoch": 17.13,
      "learning_rate": 0.00022756410256410256,
      "loss": 0.2238,
      "step": 680
    },
    {
      "epoch": 17.16,
      "learning_rate": 0.00022716346153846154,
      "loss": 0.2126,
      "step": 681
    },
    {
      "epoch": 17.18,
      "learning_rate": 0.0002267628205128205,
      "loss": 0.2104,
      "step": 682
    },
    {
      "epoch": 17.21,
      "learning_rate": 0.00022636217948717949,
      "loss": 0.2151,
      "step": 683
    },
    {
      "epoch": 17.23,
      "learning_rate": 0.00022596153846153846,
      "loss": 0.2093,
      "step": 684
    },
    {
      "epoch": 17.26,
      "learning_rate": 0.00022556089743589743,
      "loss": 0.2308,
      "step": 685
    },
    {
      "epoch": 17.29,
      "learning_rate": 0.0002251602564102564,
      "loss": 0.2276,
      "step": 686
    },
    {
      "epoch": 17.31,
      "learning_rate": 0.00022475961538461538,
      "loss": 0.2328,
      "step": 687
    },
    {
      "epoch": 17.34,
      "learning_rate": 0.00022435897435897436,
      "loss": 0.2076,
      "step": 688
    },
    {
      "epoch": 17.36,
      "learning_rate": 0.00022395833333333336,
      "loss": 0.2125,
      "step": 689
    },
    {
      "epoch": 17.39,
      "learning_rate": 0.00022355769230769234,
      "loss": 0.2181,
      "step": 690
    },
    {
      "epoch": 17.41,
      "learning_rate": 0.0002231570512820513,
      "loss": 0.2153,
      "step": 691
    },
    {
      "epoch": 17.44,
      "learning_rate": 0.00022275641025641028,
      "loss": 0.2122,
      "step": 692
    },
    {
      "epoch": 17.46,
      "learning_rate": 0.00022235576923076923,
      "loss": 0.2262,
      "step": 693
    },
    {
      "epoch": 17.49,
      "learning_rate": 0.0002219551282051282,
      "loss": 0.2206,
      "step": 694
    },
    {
      "epoch": 17.51,
      "learning_rate": 0.00022155448717948718,
      "loss": 0.2223,
      "step": 695
    },
    {
      "epoch": 17.54,
      "learning_rate": 0.00022115384615384616,
      "loss": 0.2306,
      "step": 696
    },
    {
      "epoch": 17.56,
      "learning_rate": 0.00022075320512820513,
      "loss": 0.213,
      "step": 697
    },
    {
      "epoch": 17.59,
      "learning_rate": 0.0002203525641025641,
      "loss": 0.2198,
      "step": 698
    },
    {
      "epoch": 17.61,
      "learning_rate": 0.00021995192307692308,
      "loss": 0.2299,
      "step": 699
    },
    {
      "epoch": 17.64,
      "learning_rate": 0.00021955128205128206,
      "loss": 0.2213,
      "step": 700
    },
    {
      "epoch": 17.66,
      "learning_rate": 0.00021915064102564103,
      "loss": 0.2183,
      "step": 701
    },
    {
      "epoch": 17.69,
      "learning_rate": 0.00021875,
      "loss": 0.2301,
      "step": 702
    },
    {
      "epoch": 17.71,
      "learning_rate": 0.00021834935897435898,
      "loss": 0.2348,
      "step": 703
    },
    {
      "epoch": 17.74,
      "learning_rate": 0.00021794871794871795,
      "loss": 0.229,
      "step": 704
    },
    {
      "epoch": 17.76,
      "learning_rate": 0.00021754807692307693,
      "loss": 0.2397,
      "step": 705
    },
    {
      "epoch": 17.79,
      "learning_rate": 0.0002171474358974359,
      "loss": 0.2254,
      "step": 706
    },
    {
      "epoch": 17.81,
      "learning_rate": 0.00021674679487179488,
      "loss": 0.2306,
      "step": 707
    },
    {
      "epoch": 17.84,
      "learning_rate": 0.00021634615384615385,
      "loss": 0.2388,
      "step": 708
    },
    {
      "epoch": 17.86,
      "learning_rate": 0.00021594551282051283,
      "loss": 0.2374,
      "step": 709
    },
    {
      "epoch": 17.89,
      "learning_rate": 0.0002155448717948718,
      "loss": 0.2412,
      "step": 710
    },
    {
      "epoch": 17.91,
      "learning_rate": 0.00021514423076923078,
      "loss": 0.2203,
      "step": 711
    },
    {
      "epoch": 17.94,
      "learning_rate": 0.00021474358974358972,
      "loss": 0.2359,
      "step": 712
    },
    {
      "epoch": 17.97,
      "learning_rate": 0.0002143429487179487,
      "loss": 0.2343,
      "step": 713
    },
    {
      "epoch": 17.99,
      "learning_rate": 0.00021394230769230767,
      "loss": 0.2397,
      "step": 714
    },
    {
      "epoch": 18.02,
      "learning_rate": 0.00021354166666666665,
      "loss": 0.2055,
      "step": 715
    },
    {
      "epoch": 18.04,
      "learning_rate": 0.00021314102564102565,
      "loss": 0.1723,
      "step": 716
    },
    {
      "epoch": 18.07,
      "learning_rate": 0.00021274038461538463,
      "loss": 0.1782,
      "step": 717
    },
    {
      "epoch": 18.09,
      "learning_rate": 0.0002123397435897436,
      "loss": 0.1813,
      "step": 718
    },
    {
      "epoch": 18.12,
      "learning_rate": 0.00021193910256410257,
      "loss": 0.1834,
      "step": 719
    },
    {
      "epoch": 18.14,
      "learning_rate": 0.00021153846153846155,
      "loss": 0.1759,
      "step": 720
    },
    {
      "epoch": 18.17,
      "learning_rate": 0.00021113782051282052,
      "loss": 0.1855,
      "step": 721
    },
    {
      "epoch": 18.19,
      "learning_rate": 0.0002107371794871795,
      "loss": 0.1756,
      "step": 722
    },
    {
      "epoch": 18.22,
      "learning_rate": 0.00021033653846153847,
      "loss": 0.1783,
      "step": 723
    },
    {
      "epoch": 18.24,
      "learning_rate": 0.00020993589743589745,
      "loss": 0.1899,
      "step": 724
    },
    {
      "epoch": 18.27,
      "learning_rate": 0.00020953525641025642,
      "loss": 0.1817,
      "step": 725
    },
    {
      "epoch": 18.29,
      "learning_rate": 0.0002091346153846154,
      "loss": 0.1856,
      "step": 726
    },
    {
      "epoch": 18.32,
      "learning_rate": 0.00020873397435897437,
      "loss": 0.1849,
      "step": 727
    },
    {
      "epoch": 18.34,
      "learning_rate": 0.00020833333333333335,
      "loss": 0.1758,
      "step": 728
    },
    {
      "epoch": 18.37,
      "learning_rate": 0.00020793269230769232,
      "loss": 0.1907,
      "step": 729
    },
    {
      "epoch": 18.39,
      "learning_rate": 0.0002075320512820513,
      "loss": 0.1836,
      "step": 730
    },
    {
      "epoch": 18.42,
      "learning_rate": 0.00020713141025641027,
      "loss": 0.1828,
      "step": 731
    },
    {
      "epoch": 18.44,
      "learning_rate": 0.00020673076923076922,
      "loss": 0.1916,
      "step": 732
    },
    {
      "epoch": 18.47,
      "learning_rate": 0.0002063301282051282,
      "loss": 0.1849,
      "step": 733
    },
    {
      "epoch": 18.49,
      "learning_rate": 0.00020592948717948717,
      "loss": 0.1929,
      "step": 734
    },
    {
      "epoch": 18.52,
      "learning_rate": 0.00020552884615384614,
      "loss": 0.1779,
      "step": 735
    },
    {
      "epoch": 18.54,
      "learning_rate": 0.00020512820512820512,
      "loss": 0.1805,
      "step": 736
    },
    {
      "epoch": 18.57,
      "learning_rate": 0.0002047275641025641,
      "loss": 0.1891,
      "step": 737
    },
    {
      "epoch": 18.6,
      "learning_rate": 0.00020432692307692307,
      "loss": 0.1932,
      "step": 738
    },
    {
      "epoch": 18.62,
      "learning_rate": 0.00020392628205128204,
      "loss": 0.1923,
      "step": 739
    },
    {
      "epoch": 18.65,
      "learning_rate": 0.00020352564102564102,
      "loss": 0.1882,
      "step": 740
    },
    {
      "epoch": 18.67,
      "learning_rate": 0.00020312500000000002,
      "loss": 0.2012,
      "step": 741
    },
    {
      "epoch": 18.7,
      "learning_rate": 0.000202724358974359,
      "loss": 0.1963,
      "step": 742
    },
    {
      "epoch": 18.72,
      "learning_rate": 0.00020232371794871797,
      "loss": 0.202,
      "step": 743
    },
    {
      "epoch": 18.75,
      "learning_rate": 0.00020192307692307694,
      "loss": 0.1996,
      "step": 744
    },
    {
      "epoch": 18.77,
      "learning_rate": 0.00020152243589743592,
      "loss": 0.2056,
      "step": 745
    },
    {
      "epoch": 18.8,
      "learning_rate": 0.0002011217948717949,
      "loss": 0.1946,
      "step": 746
    },
    {
      "epoch": 18.82,
      "learning_rate": 0.00020072115384615387,
      "loss": 0.1954,
      "step": 747
    },
    {
      "epoch": 18.85,
      "learning_rate": 0.00020032051282051284,
      "loss": 0.1966,
      "step": 748
    },
    {
      "epoch": 18.87,
      "learning_rate": 0.00019991987179487182,
      "loss": 0.2077,
      "step": 749
    },
    {
      "epoch": 18.9,
      "learning_rate": 0.0001995192307692308,
      "loss": 0.2,
      "step": 750
    },
    {
      "epoch": 18.92,
      "learning_rate": 0.00019911858974358974,
      "loss": 0.2092,
      "step": 751
    },
    {
      "epoch": 18.95,
      "learning_rate": 0.0001987179487179487,
      "loss": 0.2023,
      "step": 752
    },
    {
      "epoch": 18.97,
      "learning_rate": 0.0001983173076923077,
      "loss": 0.2056,
      "step": 753
    },
    {
      "epoch": 19.0,
      "learning_rate": 0.00019791666666666666,
      "loss": 0.2059,
      "step": 754
    },
    {
      "epoch": 19.02,
      "learning_rate": 0.00019751602564102564,
      "loss": 0.1581,
      "step": 755
    },
    {
      "epoch": 19.05,
      "learning_rate": 0.0001971153846153846,
      "loss": 0.155,
      "step": 756
    },
    {
      "epoch": 19.07,
      "learning_rate": 0.00019671474358974359,
      "loss": 0.156,
      "step": 757
    },
    {
      "epoch": 19.1,
      "learning_rate": 0.00019631410256410256,
      "loss": 0.161,
      "step": 758
    },
    {
      "epoch": 19.12,
      "learning_rate": 0.00019591346153846154,
      "loss": 0.1608,
      "step": 759
    },
    {
      "epoch": 19.15,
      "learning_rate": 0.0001955128205128205,
      "loss": 0.1576,
      "step": 760
    },
    {
      "epoch": 19.17,
      "learning_rate": 0.00019511217948717948,
      "loss": 0.1539,
      "step": 761
    },
    {
      "epoch": 19.2,
      "learning_rate": 0.00019471153846153846,
      "loss": 0.1549,
      "step": 762
    },
    {
      "epoch": 19.23,
      "learning_rate": 0.00019431089743589743,
      "loss": 0.1593,
      "step": 763
    },
    {
      "epoch": 19.25,
      "learning_rate": 0.0001939102564102564,
      "loss": 0.162,
      "step": 764
    },
    {
      "epoch": 19.28,
      "learning_rate": 0.00019350961538461538,
      "loss": 0.1591,
      "step": 765
    },
    {
      "epoch": 19.3,
      "learning_rate": 0.00019310897435897436,
      "loss": 0.1569,
      "step": 766
    },
    {
      "epoch": 19.33,
      "learning_rate": 0.00019270833333333336,
      "loss": 0.1628,
      "step": 767
    },
    {
      "epoch": 19.35,
      "learning_rate": 0.00019230769230769233,
      "loss": 0.1529,
      "step": 768
    },
    {
      "epoch": 19.38,
      "learning_rate": 0.0001919070512820513,
      "loss": 0.1606,
      "step": 769
    },
    {
      "epoch": 19.4,
      "learning_rate": 0.00019150641025641028,
      "loss": 0.1564,
      "step": 770
    },
    {
      "epoch": 19.43,
      "learning_rate": 0.00019110576923076923,
      "loss": 0.1599,
      "step": 771
    },
    {
      "epoch": 19.45,
      "learning_rate": 0.0001907051282051282,
      "loss": 0.1653,
      "step": 772
    },
    {
      "epoch": 19.48,
      "learning_rate": 0.00019030448717948718,
      "loss": 0.1587,
      "step": 773
    },
    {
      "epoch": 19.5,
      "learning_rate": 0.00018990384615384616,
      "loss": 0.1683,
      "step": 774
    },
    {
      "epoch": 19.53,
      "learning_rate": 0.00018950320512820513,
      "loss": 0.157,
      "step": 775
    },
    {
      "epoch": 19.55,
      "learning_rate": 0.0001891025641025641,
      "loss": 0.1588,
      "step": 776
    },
    {
      "epoch": 19.58,
      "learning_rate": 0.00018870192307692308,
      "loss": 0.1709,
      "step": 777
    },
    {
      "epoch": 19.6,
      "learning_rate": 0.00018830128205128205,
      "loss": 0.1635,
      "step": 778
    },
    {
      "epoch": 19.63,
      "learning_rate": 0.00018790064102564103,
      "loss": 0.1581,
      "step": 779
    },
    {
      "epoch": 19.65,
      "learning_rate": 0.0001875,
      "loss": 0.1664,
      "step": 780
    },
    {
      "epoch": 19.68,
      "learning_rate": 0.00018709935897435898,
      "loss": 0.1712,
      "step": 781
    },
    {
      "epoch": 19.7,
      "learning_rate": 0.00018669871794871795,
      "loss": 0.165,
      "step": 782
    },
    {
      "epoch": 19.73,
      "learning_rate": 0.00018629807692307693,
      "loss": 0.1692,
      "step": 783
    },
    {
      "epoch": 19.75,
      "learning_rate": 0.0001858974358974359,
      "loss": 0.1658,
      "step": 784
    },
    {
      "epoch": 19.78,
      "learning_rate": 0.00018549679487179488,
      "loss": 0.1702,
      "step": 785
    },
    {
      "epoch": 19.8,
      "learning_rate": 0.00018509615384615385,
      "loss": 0.1672,
      "step": 786
    },
    {
      "epoch": 19.83,
      "learning_rate": 0.00018469551282051283,
      "loss": 0.1708,
      "step": 787
    },
    {
      "epoch": 19.86,
      "learning_rate": 0.0001842948717948718,
      "loss": 0.1705,
      "step": 788
    },
    {
      "epoch": 19.88,
      "learning_rate": 0.00018389423076923078,
      "loss": 0.1853,
      "step": 789
    },
    {
      "epoch": 19.91,
      "learning_rate": 0.00018349358974358972,
      "loss": 0.1701,
      "step": 790
    },
    {
      "epoch": 19.93,
      "learning_rate": 0.0001830929487179487,
      "loss": 0.1726,
      "step": 791
    },
    {
      "epoch": 19.96,
      "learning_rate": 0.00018269230769230767,
      "loss": 0.1829,
      "step": 792
    },
    {
      "epoch": 19.98,
      "learning_rate": 0.00018229166666666665,
      "loss": 0.1749,
      "step": 793
    },
    {
      "epoch": 20.01,
      "learning_rate": 0.00018189102564102565,
      "loss": 0.1559,
      "step": 794
    },
    {
      "epoch": 20.03,
      "learning_rate": 0.00018149038461538462,
      "loss": 0.1424,
      "step": 795
    },
    {
      "epoch": 20.06,
      "learning_rate": 0.0001810897435897436,
      "loss": 0.1386,
      "step": 796
    },
    {
      "epoch": 20.08,
      "learning_rate": 0.00018068910256410257,
      "loss": 0.1388,
      "step": 797
    },
    {
      "epoch": 20.11,
      "learning_rate": 0.00018028846153846155,
      "loss": 0.1385,
      "step": 798
    },
    {
      "epoch": 20.13,
      "learning_rate": 0.00017988782051282052,
      "loss": 0.1349,
      "step": 799
    },
    {
      "epoch": 20.16,
      "learning_rate": 0.0001794871794871795,
      "loss": 0.1357,
      "step": 800
    },
    {
      "epoch": 20.18,
      "learning_rate": 0.00017908653846153847,
      "loss": 0.1384,
      "step": 801
    },
    {
      "epoch": 20.21,
      "learning_rate": 0.00017868589743589745,
      "loss": 0.1425,
      "step": 802
    },
    {
      "epoch": 20.23,
      "learning_rate": 0.00017828525641025642,
      "loss": 0.1337,
      "step": 803
    },
    {
      "epoch": 20.26,
      "learning_rate": 0.0001778846153846154,
      "loss": 0.136,
      "step": 804
    },
    {
      "epoch": 20.28,
      "learning_rate": 0.00017748397435897437,
      "loss": 0.1382,
      "step": 805
    },
    {
      "epoch": 20.31,
      "learning_rate": 0.00017708333333333335,
      "loss": 0.1396,
      "step": 806
    },
    {
      "epoch": 20.33,
      "learning_rate": 0.00017668269230769232,
      "loss": 0.1411,
      "step": 807
    },
    {
      "epoch": 20.36,
      "learning_rate": 0.0001762820512820513,
      "loss": 0.1375,
      "step": 808
    },
    {
      "epoch": 20.38,
      "learning_rate": 0.00017588141025641027,
      "loss": 0.1457,
      "step": 809
    },
    {
      "epoch": 20.41,
      "learning_rate": 0.00017548076923076922,
      "loss": 0.1447,
      "step": 810
    },
    {
      "epoch": 20.43,
      "learning_rate": 0.0001750801282051282,
      "loss": 0.1381,
      "step": 811
    },
    {
      "epoch": 20.46,
      "learning_rate": 0.00017467948717948717,
      "loss": 0.1443,
      "step": 812
    },
    {
      "epoch": 20.49,
      "learning_rate": 0.00017427884615384614,
      "loss": 0.1427,
      "step": 813
    },
    {
      "epoch": 20.51,
      "learning_rate": 0.00017387820512820512,
      "loss": 0.1425,
      "step": 814
    },
    {
      "epoch": 20.54,
      "learning_rate": 0.0001734775641025641,
      "loss": 0.1428,
      "step": 815
    },
    {
      "epoch": 20.56,
      "learning_rate": 0.00017307692307692307,
      "loss": 0.1454,
      "step": 816
    },
    {
      "epoch": 20.59,
      "learning_rate": 0.00017267628205128204,
      "loss": 0.1422,
      "step": 817
    },
    {
      "epoch": 20.61,
      "learning_rate": 0.00017227564102564102,
      "loss": 0.1426,
      "step": 818
    },
    {
      "epoch": 20.64,
      "learning_rate": 0.000171875,
      "loss": 0.1453,
      "step": 819
    },
    {
      "epoch": 20.66,
      "learning_rate": 0.000171474358974359,
      "loss": 0.1472,
      "step": 820
    },
    {
      "epoch": 20.69,
      "learning_rate": 0.00017107371794871797,
      "loss": 0.1479,
      "step": 821
    },
    {
      "epoch": 20.71,
      "learning_rate": 0.00017067307692307694,
      "loss": 0.1387,
      "step": 822
    },
    {
      "epoch": 20.74,
      "learning_rate": 0.00017027243589743592,
      "loss": 0.15,
      "step": 823
    },
    {
      "epoch": 20.76,
      "learning_rate": 0.0001698717948717949,
      "loss": 0.1429,
      "step": 824
    },
    {
      "epoch": 20.79,
      "learning_rate": 0.00016947115384615387,
      "loss": 0.1532,
      "step": 825
    },
    {
      "epoch": 20.81,
      "learning_rate": 0.00016907051282051284,
      "loss": 0.1452,
      "step": 826
    },
    {
      "epoch": 20.84,
      "learning_rate": 0.00016866987179487181,
      "loss": 0.1445,
      "step": 827
    },
    {
      "epoch": 20.86,
      "learning_rate": 0.0001682692307692308,
      "loss": 0.1461,
      "step": 828
    },
    {
      "epoch": 20.89,
      "learning_rate": 0.00016786858974358974,
      "loss": 0.1544,
      "step": 829
    },
    {
      "epoch": 20.91,
      "learning_rate": 0.0001674679487179487,
      "loss": 0.1476,
      "step": 830
    },
    {
      "epoch": 20.94,
      "learning_rate": 0.00016706730769230769,
      "loss": 0.1535,
      "step": 831
    },
    {
      "epoch": 20.96,
      "learning_rate": 0.00016666666666666666,
      "loss": 0.1498,
      "step": 832
    },
    {
      "epoch": 20.99,
      "learning_rate": 0.00016626602564102564,
      "loss": 0.1514,
      "step": 833
    },
    {
      "epoch": 21.01,
      "learning_rate": 0.0001658653846153846,
      "loss": 0.1405,
      "step": 834
    },
    {
      "epoch": 21.04,
      "learning_rate": 0.00016546474358974359,
      "loss": 0.1218,
      "step": 835
    },
    {
      "epoch": 21.06,
      "learning_rate": 0.00016506410256410256,
      "loss": 0.1228,
      "step": 836
    },
    {
      "epoch": 21.09,
      "learning_rate": 0.00016466346153846153,
      "loss": 0.119,
      "step": 837
    },
    {
      "epoch": 21.11,
      "learning_rate": 0.0001642628205128205,
      "loss": 0.1278,
      "step": 838
    },
    {
      "epoch": 21.14,
      "learning_rate": 0.00016386217948717948,
      "loss": 0.1205,
      "step": 839
    },
    {
      "epoch": 21.17,
      "learning_rate": 0.00016346153846153846,
      "loss": 0.1234,
      "step": 840
    },
    {
      "epoch": 21.19,
      "learning_rate": 0.00016306089743589743,
      "loss": 0.1226,
      "step": 841
    },
    {
      "epoch": 21.22,
      "learning_rate": 0.0001626602564102564,
      "loss": 0.1216,
      "step": 842
    },
    {
      "epoch": 21.24,
      "learning_rate": 0.00016225961538461538,
      "loss": 0.1221,
      "step": 843
    },
    {
      "epoch": 21.27,
      "learning_rate": 0.00016185897435897436,
      "loss": 0.1234,
      "step": 844
    },
    {
      "epoch": 21.29,
      "learning_rate": 0.00016145833333333336,
      "loss": 0.1226,
      "step": 845
    },
    {
      "epoch": 21.32,
      "learning_rate": 0.00016105769230769233,
      "loss": 0.1224,
      "step": 846
    },
    {
      "epoch": 21.34,
      "learning_rate": 0.0001606570512820513,
      "loss": 0.1266,
      "step": 847
    },
    {
      "epoch": 21.37,
      "learning_rate": 0.00016025641025641028,
      "loss": 0.1267,
      "step": 848
    },
    {
      "epoch": 21.39,
      "learning_rate": 0.00015985576923076923,
      "loss": 0.129,
      "step": 849
    },
    {
      "epoch": 21.42,
      "learning_rate": 0.0001594551282051282,
      "loss": 0.1213,
      "step": 850
    },
    {
      "epoch": 21.44,
      "learning_rate": 0.00015905448717948718,
      "loss": 0.1273,
      "step": 851
    },
    {
      "epoch": 21.47,
      "learning_rate": 0.00015865384615384616,
      "loss": 0.1352,
      "step": 852
    },
    {
      "epoch": 21.49,
      "learning_rate": 0.00015825320512820513,
      "loss": 0.1328,
      "step": 853
    },
    {
      "epoch": 21.52,
      "learning_rate": 0.0001578525641025641,
      "loss": 0.1253,
      "step": 854
    },
    {
      "epoch": 21.54,
      "learning_rate": 0.00015745192307692308,
      "loss": 0.1267,
      "step": 855
    },
    {
      "epoch": 21.57,
      "learning_rate": 0.00015705128205128205,
      "loss": 0.1325,
      "step": 856
    },
    {
      "epoch": 21.59,
      "learning_rate": 0.00015665064102564103,
      "loss": 0.1267,
      "step": 857
    },
    {
      "epoch": 21.62,
      "learning_rate": 0.00015625,
      "loss": 0.1326,
      "step": 858
    },
    {
      "epoch": 21.64,
      "learning_rate": 0.00015584935897435898,
      "loss": 0.1319,
      "step": 859
    },
    {
      "epoch": 21.67,
      "learning_rate": 0.00015544871794871795,
      "loss": 0.1262,
      "step": 860
    },
    {
      "epoch": 21.69,
      "learning_rate": 0.00015504807692307693,
      "loss": 0.1334,
      "step": 861
    },
    {
      "epoch": 21.72,
      "learning_rate": 0.0001546474358974359,
      "loss": 0.1347,
      "step": 862
    },
    {
      "epoch": 21.74,
      "learning_rate": 0.00015424679487179488,
      "loss": 0.1322,
      "step": 863
    },
    {
      "epoch": 21.77,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.1321,
      "step": 864
    },
    {
      "epoch": 21.8,
      "learning_rate": 0.00015344551282051283,
      "loss": 0.128,
      "step": 865
    },
    {
      "epoch": 21.82,
      "learning_rate": 0.0001530448717948718,
      "loss": 0.1365,
      "step": 866
    },
    {
      "epoch": 21.85,
      "learning_rate": 0.00015264423076923078,
      "loss": 0.137,
      "step": 867
    },
    {
      "epoch": 21.87,
      "learning_rate": 0.00015224358974358972,
      "loss": 0.1322,
      "step": 868
    },
    {
      "epoch": 21.9,
      "learning_rate": 0.0001518429487179487,
      "loss": 0.1341,
      "step": 869
    },
    {
      "epoch": 21.92,
      "learning_rate": 0.00015144230769230767,
      "loss": 0.1334,
      "step": 870
    },
    {
      "epoch": 21.95,
      "learning_rate": 0.00015104166666666665,
      "loss": 0.1339,
      "step": 871
    },
    {
      "epoch": 21.97,
      "learning_rate": 0.00015064102564102565,
      "loss": 0.1301,
      "step": 872
    },
    {
      "epoch": 22.0,
      "learning_rate": 0.00015024038461538462,
      "loss": 0.1325,
      "step": 873
    },
    {
      "epoch": 22.02,
      "learning_rate": 0.0001498397435897436,
      "loss": 0.1153,
      "step": 874
    },
    {
      "epoch": 22.05,
      "learning_rate": 0.00014943910256410257,
      "loss": 0.1113,
      "step": 875
    },
    {
      "epoch": 22.07,
      "learning_rate": 0.00014903846153846155,
      "loss": 0.1138,
      "step": 876
    },
    {
      "epoch": 22.1,
      "learning_rate": 0.00014863782051282052,
      "loss": 0.1136,
      "step": 877
    },
    {
      "epoch": 22.12,
      "learning_rate": 0.0001482371794871795,
      "loss": 0.1096,
      "step": 878
    },
    {
      "epoch": 22.15,
      "learning_rate": 0.00014783653846153847,
      "loss": 0.116,
      "step": 879
    },
    {
      "epoch": 22.17,
      "learning_rate": 0.00014743589743589745,
      "loss": 0.1122,
      "step": 880
    },
    {
      "epoch": 22.2,
      "learning_rate": 0.00014703525641025642,
      "loss": 0.1132,
      "step": 881
    },
    {
      "epoch": 22.22,
      "learning_rate": 0.0001466346153846154,
      "loss": 0.1128,
      "step": 882
    },
    {
      "epoch": 22.25,
      "learning_rate": 0.00014623397435897437,
      "loss": 0.1134,
      "step": 883
    },
    {
      "epoch": 22.27,
      "learning_rate": 0.00014583333333333335,
      "loss": 0.1065,
      "step": 884
    },
    {
      "epoch": 22.3,
      "learning_rate": 0.00014543269230769232,
      "loss": 0.117,
      "step": 885
    },
    {
      "epoch": 22.32,
      "learning_rate": 0.0001450320512820513,
      "loss": 0.112,
      "step": 886
    },
    {
      "epoch": 22.35,
      "learning_rate": 0.00014463141025641027,
      "loss": 0.1145,
      "step": 887
    },
    {
      "epoch": 22.37,
      "learning_rate": 0.00014423076923076922,
      "loss": 0.1128,
      "step": 888
    },
    {
      "epoch": 22.4,
      "learning_rate": 0.0001438301282051282,
      "loss": 0.1132,
      "step": 889
    },
    {
      "epoch": 22.43,
      "learning_rate": 0.00014342948717948717,
      "loss": 0.1143,
      "step": 890
    },
    {
      "epoch": 22.45,
      "learning_rate": 0.00014302884615384614,
      "loss": 0.1172,
      "step": 891
    },
    {
      "epoch": 22.48,
      "learning_rate": 0.00014262820512820512,
      "loss": 0.1143,
      "step": 892
    },
    {
      "epoch": 22.5,
      "learning_rate": 0.0001422275641025641,
      "loss": 0.1164,
      "step": 893
    },
    {
      "epoch": 22.53,
      "learning_rate": 0.00014182692307692307,
      "loss": 0.1197,
      "step": 894
    },
    {
      "epoch": 22.55,
      "learning_rate": 0.00014142628205128204,
      "loss": 0.1152,
      "step": 895
    },
    {
      "epoch": 22.58,
      "learning_rate": 0.00014102564102564101,
      "loss": 0.1243,
      "step": 896
    },
    {
      "epoch": 22.6,
      "learning_rate": 0.00014062500000000002,
      "loss": 0.1167,
      "step": 897
    },
    {
      "epoch": 22.63,
      "learning_rate": 0.000140224358974359,
      "loss": 0.1224,
      "step": 898
    },
    {
      "epoch": 22.65,
      "learning_rate": 0.00013982371794871797,
      "loss": 0.1192,
      "step": 899
    },
    {
      "epoch": 22.68,
      "learning_rate": 0.00013942307692307694,
      "loss": 0.1184,
      "step": 900
    },
    {
      "epoch": 22.7,
      "learning_rate": 0.00013902243589743592,
      "loss": 0.1169,
      "step": 901
    },
    {
      "epoch": 22.73,
      "learning_rate": 0.0001386217948717949,
      "loss": 0.1169,
      "step": 902
    },
    {
      "epoch": 22.75,
      "learning_rate": 0.00013822115384615386,
      "loss": 0.1177,
      "step": 903
    },
    {
      "epoch": 22.78,
      "learning_rate": 0.00013782051282051284,
      "loss": 0.1175,
      "step": 904
    },
    {
      "epoch": 22.8,
      "learning_rate": 0.00013741987179487181,
      "loss": 0.1164,
      "step": 905
    },
    {
      "epoch": 22.83,
      "learning_rate": 0.0001370192307692308,
      "loss": 0.1215,
      "step": 906
    },
    {
      "epoch": 22.85,
      "learning_rate": 0.00013661858974358974,
      "loss": 0.1204,
      "step": 907
    },
    {
      "epoch": 22.88,
      "learning_rate": 0.0001362179487179487,
      "loss": 0.1208,
      "step": 908
    },
    {
      "epoch": 22.9,
      "learning_rate": 0.00013581730769230769,
      "loss": 0.1175,
      "step": 909
    },
    {
      "epoch": 22.93,
      "learning_rate": 0.00013541666666666666,
      "loss": 0.1214,
      "step": 910
    },
    {
      "epoch": 22.95,
      "learning_rate": 0.00013501602564102564,
      "loss": 0.1243,
      "step": 911
    },
    {
      "epoch": 22.98,
      "learning_rate": 0.0001346153846153846,
      "loss": 0.1266,
      "step": 912
    },
    {
      "epoch": 23.0,
      "learning_rate": 0.00013421474358974358,
      "loss": 0.1226,
      "step": 913
    },
    {
      "epoch": 23.03,
      "learning_rate": 0.00013381410256410256,
      "loss": 0.1058,
      "step": 914
    },
    {
      "epoch": 23.06,
      "learning_rate": 0.00013341346153846153,
      "loss": 0.1034,
      "step": 915
    },
    {
      "epoch": 23.08,
      "learning_rate": 0.0001330128205128205,
      "loss": 0.1026,
      "step": 916
    },
    {
      "epoch": 23.11,
      "learning_rate": 0.00013261217948717948,
      "loss": 0.1026,
      "step": 917
    },
    {
      "epoch": 23.13,
      "learning_rate": 0.00013221153846153846,
      "loss": 0.1028,
      "step": 918
    },
    {
      "epoch": 23.16,
      "learning_rate": 0.00013181089743589743,
      "loss": 0.1024,
      "step": 919
    },
    {
      "epoch": 23.18,
      "learning_rate": 0.0001314102564102564,
      "loss": 0.1042,
      "step": 920
    },
    {
      "epoch": 23.21,
      "learning_rate": 0.00013100961538461538,
      "loss": 0.0992,
      "step": 921
    },
    {
      "epoch": 23.23,
      "learning_rate": 0.00013060897435897436,
      "loss": 0.1048,
      "step": 922
    },
    {
      "epoch": 23.26,
      "learning_rate": 0.00013020833333333336,
      "loss": 0.1006,
      "step": 923
    },
    {
      "epoch": 23.28,
      "learning_rate": 0.00012980769230769233,
      "loss": 0.1041,
      "step": 924
    },
    {
      "epoch": 23.31,
      "learning_rate": 0.0001294070512820513,
      "loss": 0.1036,
      "step": 925
    },
    {
      "epoch": 23.33,
      "learning_rate": 0.00012900641025641028,
      "loss": 0.1045,
      "step": 926
    },
    {
      "epoch": 23.36,
      "learning_rate": 0.00012860576923076923,
      "loss": 0.1048,
      "step": 927
    },
    {
      "epoch": 23.38,
      "learning_rate": 0.0001282051282051282,
      "loss": 0.1082,
      "step": 928
    },
    {
      "epoch": 23.41,
      "learning_rate": 0.00012780448717948718,
      "loss": 0.1092,
      "step": 929
    },
    {
      "epoch": 23.43,
      "learning_rate": 0.00012740384615384615,
      "loss": 0.1085,
      "step": 930
    },
    {
      "epoch": 23.46,
      "learning_rate": 0.00012700320512820513,
      "loss": 0.1037,
      "step": 931
    },
    {
      "epoch": 23.48,
      "learning_rate": 0.0001266025641025641,
      "loss": 0.109,
      "step": 932
    },
    {
      "epoch": 23.51,
      "learning_rate": 0.00012620192307692308,
      "loss": 0.1076,
      "step": 933
    },
    {
      "epoch": 23.53,
      "learning_rate": 0.00012580128205128205,
      "loss": 0.1062,
      "step": 934
    },
    {
      "epoch": 23.56,
      "learning_rate": 0.00012540064102564103,
      "loss": 0.1049,
      "step": 935
    },
    {
      "epoch": 23.58,
      "learning_rate": 0.000125,
      "loss": 0.1057,
      "step": 936
    },
    {
      "epoch": 23.61,
      "learning_rate": 0.00012459935897435898,
      "loss": 0.1106,
      "step": 937
    },
    {
      "epoch": 23.63,
      "learning_rate": 0.00012419871794871795,
      "loss": 0.1134,
      "step": 938
    },
    {
      "epoch": 23.66,
      "learning_rate": 0.00012379807692307693,
      "loss": 0.1124,
      "step": 939
    },
    {
      "epoch": 23.69,
      "learning_rate": 0.0001233974358974359,
      "loss": 0.105,
      "step": 940
    },
    {
      "epoch": 23.71,
      "learning_rate": 0.00012299679487179488,
      "loss": 0.113,
      "step": 941
    },
    {
      "epoch": 23.74,
      "learning_rate": 0.00012259615384615385,
      "loss": 0.1104,
      "step": 942
    },
    {
      "epoch": 23.76,
      "learning_rate": 0.00012219551282051283,
      "loss": 0.1136,
      "step": 943
    },
    {
      "epoch": 23.79,
      "learning_rate": 0.0001217948717948718,
      "loss": 0.1104,
      "step": 944
    },
    {
      "epoch": 23.81,
      "learning_rate": 0.00012139423076923077,
      "loss": 0.1054,
      "step": 945
    },
    {
      "epoch": 23.84,
      "learning_rate": 0.00012099358974358975,
      "loss": 0.1109,
      "step": 946
    },
    {
      "epoch": 23.86,
      "learning_rate": 0.00012059294871794872,
      "loss": 0.1062,
      "step": 947
    },
    {
      "epoch": 23.89,
      "learning_rate": 0.0001201923076923077,
      "loss": 0.1185,
      "step": 948
    },
    {
      "epoch": 23.91,
      "learning_rate": 0.00011979166666666667,
      "loss": 0.1138,
      "step": 949
    },
    {
      "epoch": 23.94,
      "learning_rate": 0.00011939102564102565,
      "loss": 0.1119,
      "step": 950
    },
    {
      "epoch": 23.96,
      "learning_rate": 0.00011899038461538461,
      "loss": 0.1114,
      "step": 951
    },
    {
      "epoch": 23.99,
      "learning_rate": 0.00011858974358974358,
      "loss": 0.1122,
      "step": 952
    },
    {
      "epoch": 24.01,
      "learning_rate": 0.00011818910256410256,
      "loss": 0.1051,
      "step": 953
    },
    {
      "epoch": 24.04,
      "learning_rate": 0.00011778846153846153,
      "loss": 0.0924,
      "step": 954
    },
    {
      "epoch": 24.06,
      "learning_rate": 0.00011738782051282051,
      "loss": 0.0977,
      "step": 955
    },
    {
      "epoch": 24.09,
      "learning_rate": 0.0001169871794871795,
      "loss": 0.0945,
      "step": 956
    },
    {
      "epoch": 24.11,
      "learning_rate": 0.00011658653846153847,
      "loss": 0.0958,
      "step": 957
    },
    {
      "epoch": 24.14,
      "learning_rate": 0.00011618589743589745,
      "loss": 0.0934,
      "step": 958
    },
    {
      "epoch": 24.16,
      "learning_rate": 0.00011578525641025642,
      "loss": 0.0952,
      "step": 959
    },
    {
      "epoch": 24.19,
      "learning_rate": 0.0001153846153846154,
      "loss": 0.0993,
      "step": 960
    },
    {
      "epoch": 24.21,
      "learning_rate": 0.00011498397435897436,
      "loss": 0.0978,
      "step": 961
    },
    {
      "epoch": 24.24,
      "learning_rate": 0.00011458333333333333,
      "loss": 0.0984,
      "step": 962
    },
    {
      "epoch": 24.26,
      "learning_rate": 0.0001141826923076923,
      "loss": 0.1019,
      "step": 963
    },
    {
      "epoch": 24.29,
      "learning_rate": 0.00011378205128205128,
      "loss": 0.0994,
      "step": 964
    },
    {
      "epoch": 24.31,
      "learning_rate": 0.00011338141025641026,
      "loss": 0.1006,
      "step": 965
    },
    {
      "epoch": 24.34,
      "learning_rate": 0.00011298076923076923,
      "loss": 0.0971,
      "step": 966
    },
    {
      "epoch": 24.37,
      "learning_rate": 0.0001125801282051282,
      "loss": 0.1008,
      "step": 967
    },
    {
      "epoch": 24.39,
      "learning_rate": 0.00011217948717948718,
      "loss": 0.0948,
      "step": 968
    },
    {
      "epoch": 24.42,
      "learning_rate": 0.00011177884615384617,
      "loss": 0.1026,
      "step": 969
    },
    {
      "epoch": 24.44,
      "learning_rate": 0.00011137820512820514,
      "loss": 0.0966,
      "step": 970
    },
    {
      "epoch": 24.47,
      "learning_rate": 0.0001109775641025641,
      "loss": 0.1004,
      "step": 971
    },
    {
      "epoch": 24.49,
      "learning_rate": 0.00011057692307692308,
      "loss": 0.1031,
      "step": 972
    },
    {
      "epoch": 24.52,
      "learning_rate": 0.00011017628205128205,
      "loss": 0.0984,
      "step": 973
    },
    {
      "epoch": 24.54,
      "learning_rate": 0.00010977564102564103,
      "loss": 0.0988,
      "step": 974
    },
    {
      "epoch": 24.57,
      "learning_rate": 0.000109375,
      "loss": 0.1048,
      "step": 975
    },
    {
      "epoch": 24.59,
      "learning_rate": 0.00010897435897435898,
      "loss": 0.0987,
      "step": 976
    },
    {
      "epoch": 24.62,
      "learning_rate": 0.00010857371794871795,
      "loss": 0.1026,
      "step": 977
    },
    {
      "epoch": 24.64,
      "learning_rate": 0.00010817307692307693,
      "loss": 0.1015,
      "step": 978
    },
    {
      "epoch": 24.67,
      "learning_rate": 0.0001077724358974359,
      "loss": 0.102,
      "step": 979
    },
    {
      "epoch": 24.69,
      "learning_rate": 0.00010737179487179486,
      "loss": 0.1005,
      "step": 980
    },
    {
      "epoch": 24.72,
      "learning_rate": 0.00010697115384615384,
      "loss": 0.1042,
      "step": 981
    },
    {
      "epoch": 24.74,
      "learning_rate": 0.00010657051282051283,
      "loss": 0.1046,
      "step": 982
    },
    {
      "epoch": 24.77,
      "learning_rate": 0.0001061698717948718,
      "loss": 0.0976,
      "step": 983
    },
    {
      "epoch": 24.79,
      "learning_rate": 0.00010576923076923077,
      "loss": 0.1014,
      "step": 984
    },
    {
      "epoch": 24.82,
      "learning_rate": 0.00010536858974358975,
      "loss": 0.1028,
      "step": 985
    },
    {
      "epoch": 24.84,
      "learning_rate": 0.00010496794871794872,
      "loss": 0.1022,
      "step": 986
    },
    {
      "epoch": 24.87,
      "learning_rate": 0.0001045673076923077,
      "loss": 0.1021,
      "step": 987
    },
    {
      "epoch": 24.89,
      "learning_rate": 0.00010416666666666667,
      "loss": 0.1047,
      "step": 988
    },
    {
      "epoch": 24.92,
      "learning_rate": 0.00010376602564102565,
      "loss": 0.1062,
      "step": 989
    },
    {
      "epoch": 24.94,
      "learning_rate": 0.00010336538461538461,
      "loss": 0.1028,
      "step": 990
    },
    {
      "epoch": 24.97,
      "learning_rate": 0.00010296474358974358,
      "loss": 0.1051,
      "step": 991
    },
    {
      "epoch": 25.0,
      "learning_rate": 0.00010256410256410256,
      "loss": 0.1047,
      "step": 992
    },
    {
      "epoch": 25.02,
      "learning_rate": 0.00010216346153846153,
      "loss": 0.097,
      "step": 993
    },
    {
      "epoch": 25.05,
      "learning_rate": 0.00010176282051282051,
      "loss": 0.0963,
      "step": 994
    },
    {
      "epoch": 25.07,
      "learning_rate": 0.0001013621794871795,
      "loss": 0.0888,
      "step": 995
    },
    {
      "epoch": 25.1,
      "learning_rate": 0.00010096153846153847,
      "loss": 0.089,
      "step": 996
    },
    {
      "epoch": 25.12,
      "learning_rate": 0.00010056089743589745,
      "loss": 0.0911,
      "step": 997
    },
    {
      "epoch": 25.15,
      "learning_rate": 0.00010016025641025642,
      "loss": 0.0916,
      "step": 998
    },
    {
      "epoch": 25.17,
      "learning_rate": 9.97596153846154e-05,
      "loss": 0.089,
      "step": 999
    },
    {
      "epoch": 25.2,
      "learning_rate": 9.935897435897436e-05,
      "loss": 0.0883,
      "step": 1000
    },
    {
      "epoch": 25.22,
      "learning_rate": 9.895833333333333e-05,
      "loss": 0.0999,
      "step": 1001
    },
    {
      "epoch": 25.25,
      "learning_rate": 9.85576923076923e-05,
      "loss": 0.0918,
      "step": 1002
    },
    {
      "epoch": 25.27,
      "learning_rate": 9.815705128205128e-05,
      "loss": 0.0953,
      "step": 1003
    },
    {
      "epoch": 25.3,
      "learning_rate": 9.775641025641025e-05,
      "loss": 0.0917,
      "step": 1004
    },
    {
      "epoch": 25.32,
      "learning_rate": 9.735576923076923e-05,
      "loss": 0.0913,
      "step": 1005
    },
    {
      "epoch": 25.35,
      "learning_rate": 9.69551282051282e-05,
      "loss": 0.0912,
      "step": 1006
    },
    {
      "epoch": 25.37,
      "learning_rate": 9.655448717948718e-05,
      "loss": 0.0897,
      "step": 1007
    },
    {
      "epoch": 25.4,
      "learning_rate": 9.615384615384617e-05,
      "loss": 0.0924,
      "step": 1008
    },
    {
      "epoch": 25.42,
      "learning_rate": 9.575320512820514e-05,
      "loss": 0.0939,
      "step": 1009
    },
    {
      "epoch": 25.45,
      "learning_rate": 9.53525641025641e-05,
      "loss": 0.0931,
      "step": 1010
    },
    {
      "epoch": 25.47,
      "learning_rate": 9.495192307692308e-05,
      "loss": 0.0919,
      "step": 1011
    },
    {
      "epoch": 25.5,
      "learning_rate": 9.455128205128205e-05,
      "loss": 0.0926,
      "step": 1012
    },
    {
      "epoch": 25.52,
      "learning_rate": 9.415064102564103e-05,
      "loss": 0.0958,
      "step": 1013
    },
    {
      "epoch": 25.55,
      "learning_rate": 9.375e-05,
      "loss": 0.097,
      "step": 1014
    },
    {
      "epoch": 25.57,
      "learning_rate": 9.334935897435898e-05,
      "loss": 0.0946,
      "step": 1015
    },
    {
      "epoch": 25.6,
      "learning_rate": 9.294871794871795e-05,
      "loss": 0.0943,
      "step": 1016
    },
    {
      "epoch": 25.63,
      "learning_rate": 9.254807692307693e-05,
      "loss": 0.0931,
      "step": 1017
    },
    {
      "epoch": 25.65,
      "learning_rate": 9.21474358974359e-05,
      "loss": 0.094,
      "step": 1018
    },
    {
      "epoch": 25.68,
      "learning_rate": 9.174679487179486e-05,
      "loss": 0.0971,
      "step": 1019
    },
    {
      "epoch": 25.7,
      "learning_rate": 9.134615384615384e-05,
      "loss": 0.0972,
      "step": 1020
    },
    {
      "epoch": 25.73,
      "learning_rate": 9.094551282051282e-05,
      "loss": 0.1061,
      "step": 1021
    },
    {
      "epoch": 25.75,
      "learning_rate": 9.05448717948718e-05,
      "loss": 0.0974,
      "step": 1022
    },
    {
      "epoch": 25.78,
      "learning_rate": 9.014423076923077e-05,
      "loss": 0.0964,
      "step": 1023
    },
    {
      "epoch": 25.8,
      "learning_rate": 8.974358974358975e-05,
      "loss": 0.095,
      "step": 1024
    },
    {
      "epoch": 25.83,
      "learning_rate": 8.934294871794872e-05,
      "loss": 0.1016,
      "step": 1025
    },
    {
      "epoch": 25.85,
      "learning_rate": 8.89423076923077e-05,
      "loss": 0.0959,
      "step": 1026
    },
    {
      "epoch": 25.88,
      "learning_rate": 8.854166666666667e-05,
      "loss": 0.1008,
      "step": 1027
    },
    {
      "epoch": 25.9,
      "learning_rate": 8.814102564102565e-05,
      "loss": 0.1004,
      "step": 1028
    },
    {
      "epoch": 25.93,
      "learning_rate": 8.774038461538461e-05,
      "loss": 0.0959,
      "step": 1029
    },
    {
      "epoch": 25.95,
      "learning_rate": 8.733974358974358e-05,
      "loss": 0.0958,
      "step": 1030
    },
    {
      "epoch": 25.98,
      "learning_rate": 8.693910256410256e-05,
      "loss": 0.0961,
      "step": 1031
    },
    {
      "epoch": 26.0,
      "learning_rate": 8.653846153846153e-05,
      "loss": 0.0957,
      "step": 1032
    },
    {
      "epoch": 26.03,
      "learning_rate": 8.613782051282051e-05,
      "loss": 0.0855,
      "step": 1033
    },
    {
      "epoch": 26.05,
      "learning_rate": 8.57371794871795e-05,
      "loss": 0.0835,
      "step": 1034
    },
    {
      "epoch": 26.08,
      "learning_rate": 8.533653846153847e-05,
      "loss": 0.0886,
      "step": 1035
    },
    {
      "epoch": 26.1,
      "learning_rate": 8.493589743589745e-05,
      "loss": 0.0918,
      "step": 1036
    },
    {
      "epoch": 26.13,
      "learning_rate": 8.453525641025642e-05,
      "loss": 0.0837,
      "step": 1037
    },
    {
      "epoch": 26.15,
      "learning_rate": 8.41346153846154e-05,
      "loss": 0.088,
      "step": 1038
    },
    {
      "epoch": 26.18,
      "learning_rate": 8.373397435897436e-05,
      "loss": 0.0928,
      "step": 1039
    },
    {
      "epoch": 26.2,
      "learning_rate": 8.333333333333333e-05,
      "loss": 0.0871,
      "step": 1040
    },
    {
      "epoch": 26.23,
      "learning_rate": 8.29326923076923e-05,
      "loss": 0.0863,
      "step": 1041
    },
    {
      "epoch": 26.26,
      "learning_rate": 8.253205128205128e-05,
      "loss": 0.0876,
      "step": 1042
    },
    {
      "epoch": 26.28,
      "learning_rate": 8.213141025641025e-05,
      "loss": 0.0888,
      "step": 1043
    },
    {
      "epoch": 26.31,
      "learning_rate": 8.173076923076923e-05,
      "loss": 0.0898,
      "step": 1044
    },
    {
      "epoch": 26.33,
      "learning_rate": 8.13301282051282e-05,
      "loss": 0.09,
      "step": 1045
    },
    {
      "epoch": 26.36,
      "learning_rate": 8.092948717948718e-05,
      "loss": 0.0906,
      "step": 1046
    },
    {
      "epoch": 26.38,
      "learning_rate": 8.052884615384617e-05,
      "loss": 0.091,
      "step": 1047
    },
    {
      "epoch": 26.41,
      "learning_rate": 8.012820512820514e-05,
      "loss": 0.0885,
      "step": 1048
    },
    {
      "epoch": 26.43,
      "learning_rate": 7.97275641025641e-05,
      "loss": 0.0896,
      "step": 1049
    },
    {
      "epoch": 26.46,
      "learning_rate": 7.932692307692308e-05,
      "loss": 0.0891,
      "step": 1050
    },
    {
      "epoch": 26.48,
      "learning_rate": 7.892628205128205e-05,
      "loss": 0.0875,
      "step": 1051
    },
    {
      "epoch": 26.51,
      "learning_rate": 7.852564102564103e-05,
      "loss": 0.0906,
      "step": 1052
    },
    {
      "epoch": 26.53,
      "learning_rate": 7.8125e-05,
      "loss": 0.0913,
      "step": 1053
    },
    {
      "epoch": 26.56,
      "learning_rate": 7.772435897435898e-05,
      "loss": 0.0898,
      "step": 1054
    },
    {
      "epoch": 26.58,
      "learning_rate": 7.732371794871795e-05,
      "loss": 0.0887,
      "step": 1055
    },
    {
      "epoch": 26.61,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.0916,
      "step": 1056
    },
    {
      "epoch": 26.63,
      "learning_rate": 7.65224358974359e-05,
      "loss": 0.0934,
      "step": 1057
    },
    {
      "epoch": 26.66,
      "learning_rate": 7.612179487179486e-05,
      "loss": 0.0864,
      "step": 1058
    },
    {
      "epoch": 26.68,
      "learning_rate": 7.572115384615384e-05,
      "loss": 0.0929,
      "step": 1059
    },
    {
      "epoch": 26.71,
      "learning_rate": 7.532051282051282e-05,
      "loss": 0.0893,
      "step": 1060
    },
    {
      "epoch": 26.73,
      "learning_rate": 7.49198717948718e-05,
      "loss": 0.0926,
      "step": 1061
    },
    {
      "epoch": 26.76,
      "learning_rate": 7.451923076923077e-05,
      "loss": 0.0931,
      "step": 1062
    },
    {
      "epoch": 26.78,
      "learning_rate": 7.411858974358975e-05,
      "loss": 0.0921,
      "step": 1063
    },
    {
      "epoch": 26.81,
      "learning_rate": 7.371794871794872e-05,
      "loss": 0.0882,
      "step": 1064
    },
    {
      "epoch": 26.83,
      "learning_rate": 7.33173076923077e-05,
      "loss": 0.0937,
      "step": 1065
    },
    {
      "epoch": 26.86,
      "learning_rate": 7.291666666666667e-05,
      "loss": 0.0913,
      "step": 1066
    },
    {
      "epoch": 26.89,
      "learning_rate": 7.251602564102565e-05,
      "loss": 0.0925,
      "step": 1067
    },
    {
      "epoch": 26.91,
      "learning_rate": 7.211538461538461e-05,
      "loss": 0.0942,
      "step": 1068
    },
    {
      "epoch": 26.94,
      "learning_rate": 7.171474358974358e-05,
      "loss": 0.097,
      "step": 1069
    },
    {
      "epoch": 26.96,
      "learning_rate": 7.131410256410256e-05,
      "loss": 0.0922,
      "step": 1070
    },
    {
      "epoch": 26.99,
      "learning_rate": 7.091346153846153e-05,
      "loss": 0.0925,
      "step": 1071
    },
    {
      "epoch": 27.01,
      "learning_rate": 7.051282051282051e-05,
      "loss": 0.0887,
      "step": 1072
    },
    {
      "epoch": 27.04,
      "learning_rate": 7.01121794871795e-05,
      "loss": 0.0831,
      "step": 1073
    },
    {
      "epoch": 27.06,
      "learning_rate": 6.971153846153847e-05,
      "loss": 0.084,
      "step": 1074
    },
    {
      "epoch": 27.09,
      "learning_rate": 6.931089743589744e-05,
      "loss": 0.083,
      "step": 1075
    },
    {
      "epoch": 27.11,
      "learning_rate": 6.891025641025642e-05,
      "loss": 0.0857,
      "step": 1076
    },
    {
      "epoch": 27.14,
      "learning_rate": 6.85096153846154e-05,
      "loss": 0.0837,
      "step": 1077
    },
    {
      "epoch": 27.16,
      "learning_rate": 6.810897435897436e-05,
      "loss": 0.0854,
      "step": 1078
    },
    {
      "epoch": 27.19,
      "learning_rate": 6.770833333333333e-05,
      "loss": 0.0877,
      "step": 1079
    },
    {
      "epoch": 27.21,
      "learning_rate": 6.73076923076923e-05,
      "loss": 0.0861,
      "step": 1080
    },
    {
      "epoch": 27.24,
      "learning_rate": 6.690705128205128e-05,
      "loss": 0.0825,
      "step": 1081
    },
    {
      "epoch": 27.26,
      "learning_rate": 6.650641025641025e-05,
      "loss": 0.0831,
      "step": 1082
    },
    {
      "epoch": 27.29,
      "learning_rate": 6.610576923076923e-05,
      "loss": 0.086,
      "step": 1083
    },
    {
      "epoch": 27.31,
      "learning_rate": 6.57051282051282e-05,
      "loss": 0.0838,
      "step": 1084
    },
    {
      "epoch": 27.34,
      "learning_rate": 6.530448717948718e-05,
      "loss": 0.0857,
      "step": 1085
    },
    {
      "epoch": 27.36,
      "learning_rate": 6.490384615384617e-05,
      "loss": 0.0836,
      "step": 1086
    },
    {
      "epoch": 27.39,
      "learning_rate": 6.450320512820514e-05,
      "loss": 0.0875,
      "step": 1087
    },
    {
      "epoch": 27.41,
      "learning_rate": 6.41025641025641e-05,
      "loss": 0.0848,
      "step": 1088
    },
    {
      "epoch": 27.44,
      "learning_rate": 6.370192307692308e-05,
      "loss": 0.084,
      "step": 1089
    },
    {
      "epoch": 27.46,
      "learning_rate": 6.330128205128205e-05,
      "loss": 0.0845,
      "step": 1090
    },
    {
      "epoch": 27.49,
      "learning_rate": 6.290064102564103e-05,
      "loss": 0.0876,
      "step": 1091
    },
    {
      "epoch": 27.51,
      "learning_rate": 6.25e-05,
      "loss": 0.0907,
      "step": 1092
    },
    {
      "epoch": 27.54,
      "learning_rate": 6.209935897435898e-05,
      "loss": 0.0864,
      "step": 1093
    },
    {
      "epoch": 27.57,
      "learning_rate": 6.169871794871795e-05,
      "loss": 0.087,
      "step": 1094
    },
    {
      "epoch": 27.59,
      "learning_rate": 6.129807692307693e-05,
      "loss": 0.0902,
      "step": 1095
    },
    {
      "epoch": 27.62,
      "learning_rate": 6.08974358974359e-05,
      "loss": 0.0862,
      "step": 1096
    },
    {
      "epoch": 27.64,
      "learning_rate": 6.0496794871794875e-05,
      "loss": 0.0864,
      "step": 1097
    },
    {
      "epoch": 27.67,
      "learning_rate": 6.009615384615385e-05,
      "loss": 0.0868,
      "step": 1098
    },
    {
      "epoch": 27.69,
      "learning_rate": 5.9695512820512824e-05,
      "loss": 0.0905,
      "step": 1099
    },
    {
      "epoch": 27.72,
      "learning_rate": 5.929487179487179e-05,
      "loss": 0.0881,
      "step": 1100
    },
    {
      "epoch": 27.74,
      "learning_rate": 5.889423076923077e-05,
      "loss": 0.0883,
      "step": 1101
    },
    {
      "epoch": 27.77,
      "learning_rate": 5.849358974358975e-05,
      "loss": 0.0852,
      "step": 1102
    },
    {
      "epoch": 27.79,
      "learning_rate": 5.809294871794872e-05,
      "loss": 0.0838,
      "step": 1103
    },
    {
      "epoch": 27.82,
      "learning_rate": 5.76923076923077e-05,
      "loss": 0.0866,
      "step": 1104
    },
    {
      "epoch": 27.84,
      "learning_rate": 5.7291666666666666e-05,
      "loss": 0.0893,
      "step": 1105
    },
    {
      "epoch": 27.87,
      "learning_rate": 5.689102564102564e-05,
      "loss": 0.0881,
      "step": 1106
    },
    {
      "epoch": 27.89,
      "learning_rate": 5.6490384615384615e-05,
      "loss": 0.0889,
      "step": 1107
    },
    {
      "epoch": 27.92,
      "learning_rate": 5.608974358974359e-05,
      "loss": 0.087,
      "step": 1108
    },
    {
      "epoch": 27.94,
      "learning_rate": 5.568910256410257e-05,
      "loss": 0.089,
      "step": 1109
    },
    {
      "epoch": 27.97,
      "learning_rate": 5.528846153846154e-05,
      "loss": 0.0889,
      "step": 1110
    },
    {
      "epoch": 27.99,
      "learning_rate": 5.4887820512820514e-05,
      "loss": 0.09,
      "step": 1111
    },
    {
      "epoch": 28.02,
      "learning_rate": 5.448717948717949e-05,
      "loss": 0.0838,
      "step": 1112
    },
    {
      "epoch": 28.04,
      "learning_rate": 5.408653846153846e-05,
      "loss": 0.0834,
      "step": 1113
    },
    {
      "epoch": 28.07,
      "learning_rate": 5.368589743589743e-05,
      "loss": 0.0831,
      "step": 1114
    },
    {
      "epoch": 28.09,
      "learning_rate": 5.328525641025641e-05,
      "loss": 0.0804,
      "step": 1115
    },
    {
      "epoch": 28.12,
      "learning_rate": 5.288461538461539e-05,
      "loss": 0.0823,
      "step": 1116
    },
    {
      "epoch": 28.14,
      "learning_rate": 5.248397435897436e-05,
      "loss": 0.0823,
      "step": 1117
    },
    {
      "epoch": 28.17,
      "learning_rate": 5.208333333333334e-05,
      "loss": 0.0778,
      "step": 1118
    },
    {
      "epoch": 28.2,
      "learning_rate": 5.1682692307692305e-05,
      "loss": 0.084,
      "step": 1119
    },
    {
      "epoch": 28.22,
      "learning_rate": 5.128205128205128e-05,
      "loss": 0.0816,
      "step": 1120
    },
    {
      "epoch": 28.25,
      "learning_rate": 5.0881410256410254e-05,
      "loss": 0.0827,
      "step": 1121
    },
    {
      "epoch": 28.27,
      "learning_rate": 5.0480769230769235e-05,
      "loss": 0.0842,
      "step": 1122
    },
    {
      "epoch": 28.3,
      "learning_rate": 5.008012820512821e-05,
      "loss": 0.0816,
      "step": 1123
    },
    {
      "epoch": 28.32,
      "learning_rate": 4.967948717948718e-05,
      "loss": 0.0853,
      "step": 1124
    },
    {
      "epoch": 28.35,
      "learning_rate": 4.927884615384615e-05,
      "loss": 0.0793,
      "step": 1125
    },
    {
      "epoch": 28.37,
      "learning_rate": 4.887820512820513e-05,
      "loss": 0.0831,
      "step": 1126
    },
    {
      "epoch": 28.4,
      "learning_rate": 4.84775641025641e-05,
      "loss": 0.0824,
      "step": 1127
    },
    {
      "epoch": 28.42,
      "learning_rate": 4.8076923076923084e-05,
      "loss": 0.0851,
      "step": 1128
    },
    {
      "epoch": 28.45,
      "learning_rate": 4.767628205128205e-05,
      "loss": 0.0842,
      "step": 1129
    },
    {
      "epoch": 28.47,
      "learning_rate": 4.7275641025641026e-05,
      "loss": 0.0806,
      "step": 1130
    },
    {
      "epoch": 28.5,
      "learning_rate": 4.6875e-05,
      "loss": 0.0849,
      "step": 1131
    },
    {
      "epoch": 28.52,
      "learning_rate": 4.6474358974358976e-05,
      "loss": 0.0823,
      "step": 1132
    },
    {
      "epoch": 28.55,
      "learning_rate": 4.607371794871795e-05,
      "loss": 0.0841,
      "step": 1133
    },
    {
      "epoch": 28.57,
      "learning_rate": 4.567307692307692e-05,
      "loss": 0.0842,
      "step": 1134
    },
    {
      "epoch": 28.6,
      "learning_rate": 4.52724358974359e-05,
      "loss": 0.0833,
      "step": 1135
    },
    {
      "epoch": 28.62,
      "learning_rate": 4.4871794871794874e-05,
      "loss": 0.082,
      "step": 1136
    },
    {
      "epoch": 28.65,
      "learning_rate": 4.447115384615385e-05,
      "loss": 0.0867,
      "step": 1137
    },
    {
      "epoch": 28.67,
      "learning_rate": 4.4070512820512824e-05,
      "loss": 0.0845,
      "step": 1138
    },
    {
      "epoch": 28.7,
      "learning_rate": 4.366987179487179e-05,
      "loss": 0.0853,
      "step": 1139
    },
    {
      "epoch": 28.72,
      "learning_rate": 4.3269230769230766e-05,
      "loss": 0.0835,
      "step": 1140
    },
    {
      "epoch": 28.75,
      "learning_rate": 4.286858974358975e-05,
      "loss": 0.0884,
      "step": 1141
    },
    {
      "epoch": 28.77,
      "learning_rate": 4.246794871794872e-05,
      "loss": 0.0857,
      "step": 1142
    },
    {
      "epoch": 28.8,
      "learning_rate": 4.20673076923077e-05,
      "loss": 0.084,
      "step": 1143
    },
    {
      "epoch": 28.83,
      "learning_rate": 4.1666666666666665e-05,
      "loss": 0.0843,
      "step": 1144
    },
    {
      "epoch": 28.85,
      "learning_rate": 4.126602564102564e-05,
      "loss": 0.0827,
      "step": 1145
    },
    {
      "epoch": 28.88,
      "learning_rate": 4.0865384615384615e-05,
      "loss": 0.0826,
      "step": 1146
    },
    {
      "epoch": 28.9,
      "learning_rate": 4.046474358974359e-05,
      "loss": 0.0851,
      "step": 1147
    },
    {
      "epoch": 28.93,
      "learning_rate": 4.006410256410257e-05,
      "loss": 0.0851,
      "step": 1148
    },
    {
      "epoch": 28.95,
      "learning_rate": 3.966346153846154e-05,
      "loss": 0.0848,
      "step": 1149
    },
    {
      "epoch": 28.98,
      "learning_rate": 3.9262820512820513e-05,
      "loss": 0.0828,
      "step": 1150
    },
    {
      "epoch": 29.0,
      "learning_rate": 3.886217948717949e-05,
      "loss": 0.0834,
      "step": 1151
    },
    {
      "epoch": 29.03,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.0815,
      "step": 1152
    },
    {
      "epoch": 29.05,
      "learning_rate": 3.806089743589743e-05,
      "loss": 0.0806,
      "step": 1153
    },
    {
      "epoch": 29.08,
      "learning_rate": 3.766025641025641e-05,
      "loss": 0.0787,
      "step": 1154
    },
    {
      "epoch": 29.1,
      "learning_rate": 3.725961538461539e-05,
      "loss": 0.0772,
      "step": 1155
    },
    {
      "epoch": 29.13,
      "learning_rate": 3.685897435897436e-05,
      "loss": 0.0794,
      "step": 1156
    },
    {
      "epoch": 29.15,
      "learning_rate": 3.6458333333333336e-05,
      "loss": 0.0799,
      "step": 1157
    },
    {
      "epoch": 29.18,
      "learning_rate": 3.6057692307692304e-05,
      "loss": 0.0803,
      "step": 1158
    },
    {
      "epoch": 29.2,
      "learning_rate": 3.565705128205128e-05,
      "loss": 0.0829,
      "step": 1159
    },
    {
      "epoch": 29.23,
      "learning_rate": 3.5256410256410254e-05,
      "loss": 0.0795,
      "step": 1160
    },
    {
      "epoch": 29.25,
      "learning_rate": 3.4855769230769235e-05,
      "loss": 0.0795,
      "step": 1161
    },
    {
      "epoch": 29.28,
      "learning_rate": 3.445512820512821e-05,
      "loss": 0.0786,
      "step": 1162
    },
    {
      "epoch": 29.3,
      "learning_rate": 3.405448717948718e-05,
      "loss": 0.0778,
      "step": 1163
    },
    {
      "epoch": 29.33,
      "learning_rate": 3.365384615384615e-05,
      "loss": 0.0774,
      "step": 1164
    },
    {
      "epoch": 29.35,
      "learning_rate": 3.325320512820513e-05,
      "loss": 0.0806,
      "step": 1165
    },
    {
      "epoch": 29.38,
      "learning_rate": 3.28525641025641e-05,
      "loss": 0.0789,
      "step": 1166
    },
    {
      "epoch": 29.4,
      "learning_rate": 3.245192307692308e-05,
      "loss": 0.0788,
      "step": 1167
    },
    {
      "epoch": 29.43,
      "learning_rate": 3.205128205128205e-05,
      "loss": 0.0825,
      "step": 1168
    },
    {
      "epoch": 29.46,
      "learning_rate": 3.1650641025641026e-05,
      "loss": 0.0804,
      "step": 1169
    },
    {
      "epoch": 29.48,
      "learning_rate": 3.125e-05,
      "loss": 0.0806,
      "step": 1170
    },
    {
      "epoch": 29.51,
      "learning_rate": 3.0849358974358975e-05,
      "loss": 0.0824,
      "step": 1171
    },
    {
      "epoch": 29.53,
      "learning_rate": 3.044871794871795e-05,
      "loss": 0.0804,
      "step": 1172
    },
    {
      "epoch": 29.56,
      "learning_rate": 3.0048076923076925e-05,
      "loss": 0.0831,
      "step": 1173
    },
    {
      "epoch": 29.58,
      "learning_rate": 2.9647435897435896e-05,
      "loss": 0.0796,
      "step": 1174
    },
    {
      "epoch": 29.61,
      "learning_rate": 2.9246794871794874e-05,
      "loss": 0.0816,
      "step": 1175
    },
    {
      "epoch": 29.63,
      "learning_rate": 2.884615384615385e-05,
      "loss": 0.0862,
      "step": 1176
    },
    {
      "epoch": 29.66,
      "learning_rate": 2.844551282051282e-05,
      "loss": 0.0825,
      "step": 1177
    },
    {
      "epoch": 29.68,
      "learning_rate": 2.8044871794871795e-05,
      "loss": 0.082,
      "step": 1178
    },
    {
      "epoch": 29.71,
      "learning_rate": 2.764423076923077e-05,
      "loss": 0.082,
      "step": 1179
    },
    {
      "epoch": 29.73,
      "learning_rate": 2.7243589743589744e-05,
      "loss": 0.0844,
      "step": 1180
    },
    {
      "epoch": 29.76,
      "learning_rate": 2.6842948717948716e-05,
      "loss": 0.0823,
      "step": 1181
    },
    {
      "epoch": 29.78,
      "learning_rate": 2.6442307692307694e-05,
      "loss": 0.0822,
      "step": 1182
    },
    {
      "epoch": 29.81,
      "learning_rate": 2.604166666666667e-05,
      "loss": 0.0833,
      "step": 1183
    },
    {
      "epoch": 29.83,
      "learning_rate": 2.564102564102564e-05,
      "loss": 0.0853,
      "step": 1184
    },
    {
      "epoch": 29.86,
      "learning_rate": 2.5240384615384618e-05,
      "loss": 0.0803,
      "step": 1185
    },
    {
      "epoch": 29.88,
      "learning_rate": 2.483974358974359e-05,
      "loss": 0.0809,
      "step": 1186
    },
    {
      "epoch": 29.91,
      "learning_rate": 2.4439102564102564e-05,
      "loss": 0.0828,
      "step": 1187
    },
    {
      "epoch": 29.93,
      "learning_rate": 2.4038461538461542e-05,
      "loss": 0.0815,
      "step": 1188
    },
    {
      "epoch": 29.96,
      "learning_rate": 2.3637820512820513e-05,
      "loss": 0.0847,
      "step": 1189
    },
    {
      "epoch": 29.98,
      "learning_rate": 2.3237179487179488e-05,
      "loss": 0.0801,
      "step": 1190
    },
    {
      "epoch": 30.01,
      "learning_rate": 2.283653846153846e-05,
      "loss": 0.0794,
      "step": 1191
    },
    {
      "epoch": 30.03,
      "learning_rate": 2.2435897435897437e-05,
      "loss": 0.0779,
      "step": 1192
    },
    {
      "epoch": 30.06,
      "learning_rate": 2.2035256410256412e-05,
      "loss": 0.0769,
      "step": 1193
    },
    {
      "epoch": 30.09,
      "learning_rate": 2.1634615384615383e-05,
      "loss": 0.0766,
      "step": 1194
    },
    {
      "epoch": 30.11,
      "learning_rate": 2.123397435897436e-05,
      "loss": 0.0778,
      "step": 1195
    },
    {
      "epoch": 30.14,
      "learning_rate": 2.0833333333333333e-05,
      "loss": 0.0811,
      "step": 1196
    },
    {
      "epoch": 30.16,
      "learning_rate": 2.0432692307692307e-05,
      "loss": 0.0779,
      "step": 1197
    },
    {
      "epoch": 30.19,
      "learning_rate": 2.0032051282051285e-05,
      "loss": 0.0788,
      "step": 1198
    },
    {
      "epoch": 30.21,
      "learning_rate": 1.9631410256410257e-05,
      "loss": 0.0805,
      "step": 1199
    },
    {
      "epoch": 30.24,
      "learning_rate": 1.923076923076923e-05,
      "loss": 0.0791,
      "step": 1200
    }
  ],
  "logging_steps": 1,
  "max_steps": 1248,
  "num_train_epochs": 32,
  "save_steps": 100,
  "total_flos": 6.758843226530304e+17,
  "trial_name": null,
  "trial_params": null
}