{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 438,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.7674,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.479,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.6796,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.6019,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.5698,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.3872,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.3398,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.4532,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012857142857142858,
      "loss": 1.3419,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.3282,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00015714285714285716,
      "loss": 1.4063,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.3195,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018571428571428572,
      "loss": 1.1619,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.4086,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999725503981394,
      "loss": 1.4226,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999890203099519,
      "loss": 1.2124,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019997529626249397,
      "loss": 1.1834,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019995608365087946,
      "loss": 1.4668,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019993138352986537,
      "loss": 1.2505,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001999011972554688,
      "loss": 1.3826,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019986552648489208,
      "loss": 1.3494,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019982437317643217,
      "loss": 1.2315,
      "step": 22
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019977773958937287,
      "loss": 1.3979,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019972562828386102,
      "loss": 1.1124,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019966804212076582,
      "loss": 1.4637,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001996049842615217,
      "loss": 1.2264,
      "step": 26
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019953645816795499,
      "loss": 1.2921,
      "step": 27
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019946246760209362,
      "loss": 1.2341,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019938301662596075,
      "loss": 1.2676,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019929810960135172,
      "loss": 1.2557,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019920775118959454,
      "loss": 1.2751,
      "step": 31
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001991119463512941,
      "loss": 1.1965,
      "step": 32
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001990107003460597,
      "loss": 1.2291,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001989040187322164,
      "loss": 1.2535,
      "step": 34
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019879190736649992,
      "loss": 1.3206,
      "step": 35
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019867437240373489,
      "loss": 1.3678,
      "step": 36
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019855142029649722,
      "loss": 1.2816,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019842305779475968,
      "loss": 1.379,
      "step": 38
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019828929194552143,
      "loss": 1.2207,
      "step": 39
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019815013009242104,
      "loss": 1.2713,
      "step": 40
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001980055798753334,
      "loss": 1.2709,
      "step": 41
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001978556492299504,
      "loss": 1.249,
      "step": 42
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019770034638734506,
      "loss": 1.5568,
      "step": 43
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019753967987351978,
      "loss": 1.256,
      "step": 44
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001973736585089382,
      "loss": 1.4316,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001972022914080411,
      "loss": 1.3448,
      "step": 46
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001970255879787458,
      "loss": 1.137,
      "step": 47
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001968435579219299,
      "loss": 1.1931,
      "step": 48
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001966562112308985,
      "loss": 1.2504,
      "step": 49
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019646355819083589,
      "loss": 1.3846,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019626560937824046,
      "loss": 1.1977,
      "step": 51
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019606237566034443,
      "loss": 1.2859,
      "step": 52
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019585386819451708,
      "loss": 1.3802,
      "step": 53
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019564009842765225,
      "loss": 1.342,
      "step": 54
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019542107809553992,
      "loss": 1.2094,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019519681922222195,
      "loss": 1.2858,
      "step": 56
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019496733411933188,
      "loss": 1.2035,
      "step": 57
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019473263538541914,
      "loss": 1.1805,
      "step": 58
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019449273590525735,
      "loss": 1.2136,
      "step": 59
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001942476488491369,
      "loss": 1.3127,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000193997387672142,
      "loss": 1.3307,
      "step": 61
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001937419661134121,
      "loss": 1.3789,
      "step": 62
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001934813981953873,
      "loss": 1.282,
      "step": 63
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001932156982230388,
      "loss": 1.3562,
      "step": 64
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019294488078308355,
      "loss": 1.2395,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019266896074318334,
      "loss": 1.2479,
      "step": 66
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001923879532511287,
      "loss": 1.2428,
      "step": 67
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001921018737340071,
      "loss": 1.2866,
      "step": 68
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019181073789735628,
      "loss": 1.2492,
      "step": 69
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019151456172430183,
      "loss": 1.2166,
      "step": 70
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001912133614746799,
      "loss": 1.2707,
      "step": 71
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001909071536841442,
      "loss": 1.1933,
      "step": 72
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001905959551632587,
      "loss": 1.1556,
      "step": 73
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019027978299657436,
      "loss": 1.3107,
      "step": 74
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001899586545416914,
      "loss": 1.1491,
      "step": 75
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018963258742830626,
      "loss": 1.2597,
      "step": 76
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018930159955724387,
      "loss": 1.1665,
      "step": 77
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018896570909947475,
      "loss": 1.2775,
      "step": 78
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018862493449511755,
      "loss": 1.3604,
      "step": 79
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018827929445242676,
      "loss": 1.2741,
      "step": 80
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018792880794676545,
      "loss": 1.2189,
      "step": 81
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001875734942195637,
      "loss": 1.199,
      "step": 82
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001872133727772622,
      "loss": 1.2576,
      "step": 83
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018684846339024142,
      "loss": 1.2084,
      "step": 84
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001864787860917361,
      "loss": 1.2359,
      "step": 85
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018610436117673555,
      "loss": 1.2863,
      "step": 86
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001857252092008695,
      "loss": 1.2989,
      "step": 87
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001853413509792795,
      "loss": 1.4557,
      "step": 88
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018495280758547622,
      "loss": 1.2275,
      "step": 89
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001845596003501826,
      "loss": 1.261,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018416175086016282,
      "loss": 1.2169,
      "step": 91
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018375928095703704,
      "loss": 1.3301,
      "step": 92
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001833522127360824,
      "loss": 1.2981,
      "step": 93
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001829405685450202,
      "loss": 1.1342,
      "step": 94
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018252437098278867,
      "loss": 1.1992,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001821036428983026,
      "loss": 1.201,
      "step": 96
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018167840738919882,
      "loss": 1.1617,
      "step": 97
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018124868780056814,
      "loss": 1.2717,
      "step": 98
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018081450772367382,
      "loss": 1.158,
      "step": 99
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018037589099465637,
      "loss": 1.2361,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001799328616932249,
      "loss": 1.1591,
      "step": 101
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017948544414133534,
      "loss": 1.2643,
      "step": 102
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017903366290185498,
      "loss": 1.3476,
      "step": 103
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017857754277721415,
      "loss": 1.1718,
      "step": 104
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017811710880804449,
      "loss": 1.3174,
      "step": 105
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017765238627180424,
      "loss": 1.2998,
      "step": 106
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017718340068139066,
      "loss": 1.1868,
      "step": 107
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017671017778373913,
      "loss": 1.3348,
      "step": 108
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017623274355841,
      "loss": 1.5578,
      "step": 109
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017575112421616202,
      "loss": 1.4431,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001752653461975136,
      "loss": 1.1016,
      "step": 111
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001747754361712911,
      "loss": 1.2214,
      "step": 112
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001742814210331649,
      "loss": 1.3365,
      "step": 113
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017378332790417273,
      "loss": 1.2054,
      "step": 114
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001732811841292307,
      "loss": 1.3726,
      "step": 115
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017277501727563224,
      "loss": 1.1261,
      "step": 116
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017226485513153456,
      "loss": 1.4755,
      "step": 117
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017175072570443312,
      "loss": 1.1085,
      "step": 118
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001712326572196241,
      "loss": 1.1907,
      "step": 119
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.177,
      "step": 120
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017018481705776211,
      "loss": 1.3567,
      "step": 121
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016965510290629972,
      "loss": 1.2203,
      "step": 122
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016912156474515263,
      "loss": 1.2713,
      "step": 123
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016858423186514107,
      "loss": 1.259,
      "step": 124
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016804313376541226,
      "loss": 1.2689,
      "step": 125
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016749830015182107,
      "loss": 1.2313,
      "step": 126
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016694976093529896,
      "loss": 1.3463,
      "step": 127
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016639754623021225,
      "loss": 1.1488,
      "step": 128
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001658416863527084,
      "loss": 1.2683,
      "step": 129
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016528221181905217,
      "loss": 1.3241,
      "step": 130
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001647191533439499,
      "loss": 1.2318,
      "step": 131
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016415254183886355,
      "loss": 1.262,
      "step": 132
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016358240841031352,
      "loss": 1.0975,
      "step": 133
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016300878435817113,
      "loss": 1.4011,
      "step": 134
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016243170117394,
      "loss": 1.1241,
      "step": 135
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016185119053902747,
      "loss": 1.3117,
      "step": 136
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016126728432300515,
      "loss": 1.1575,
      "step": 137
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016068001458185936,
      "loss": 1.2994,
      "step": 138
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001600894135562312,
      "loss": 1.2535,
      "step": 139
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015949551366964675,
      "loss": 1.1151,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015889834752673684,
      "loss": 1.2376,
      "step": 141
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001582979479114472,
      "loss": 1.2403,
      "step": 142
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015769434778523868,
      "loss": 1.2529,
      "step": 143
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015708758028527752,
      "loss": 1.1528,
      "step": 144
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015647767872261633,
      "loss": 1.2316,
      "step": 145
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015586467658036524,
      "loss": 1.0899,
      "step": 146
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015524860751185376,
      "loss": 0.9716,
      "step": 147
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015462950533878317,
      "loss": 1.1498,
      "step": 148
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015400740404936979,
      "loss": 1.1439,
      "step": 149
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001533823377964791,
      "loss": 1.2853,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015275434089575055,
      "loss": 1.3359,
      "step": 151
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000152123447823714,
      "loss": 1.1899,
      "step": 152
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015148969321589673,
      "loss": 1.2058,
      "step": 153
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015085311186492206,
      "loss": 1.0606,
      "step": 154
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015021373871859924,
      "loss": 1.1693,
      "step": 155
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014957160887800494,
      "loss": 1.4608,
      "step": 156
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014892675759555605,
      "loss": 1.1654,
      "step": 157
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014827922027307451,
      "loss": 1.2638,
      "step": 158
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014762903245984368,
      "loss": 1.377,
      "step": 159
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001469762298506568,
      "loss": 1.2937,
      "step": 160
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001463208482838573,
      "loss": 1.1174,
      "step": 161
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001456629237393713,
      "loss": 1.1493,
      "step": 162
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014500249233673248,
      "loss": 1.2626,
      "step": 163
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014433959033309887,
      "loss": 1.2071,
      "step": 164
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014367425412126265,
      "loss": 1.3357,
      "step": 165
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014300652022765207,
      "loss": 1.1992,
      "step": 166
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014233642531032614,
      "loss": 1.1616,
      "step": 167
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014166400615696231,
      "loss": 1.3137,
      "step": 168
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001409892996828366,
      "loss": 1.2868,
      "step": 169
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014031234292879725,
      "loss": 1.2584,
      "step": 170
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013963317305923094,
      "loss": 1.3188,
      "step": 171
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013895182736002276,
      "loss": 1.0481,
      "step": 172
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000138268343236509,
      "loss": 1.312,
      "step": 173
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013758275821142382,
      "loss": 1.0606,
      "step": 174
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013689510992283922,
      "loss": 1.276,
      "step": 175
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013620543612209861,
      "loss": 1.39,
      "step": 176
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013551377467174456,
      "loss": 1.1824,
      "step": 177
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001348201635434399,
      "loss": 1.1213,
      "step": 178
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013412464081588322,
      "loss": 1.2384,
      "step": 179
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001334272446727185,
      "loss": 1.0606,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013272801340043867,
      "loss": 1.147,
      "step": 181
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013202698538628376,
      "loss": 1.1966,
      "step": 182
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001313241991161336,
      "loss": 1.2423,
      "step": 183
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013061969317239468,
      "loss": 1.1797,
      "step": 184
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012991350623188245,
      "loss": 1.4082,
      "step": 185
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012920567706369758,
      "loss": 1.0627,
      "step": 186
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001284962445270978,
      "loss": 1.233,
      "step": 187
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001277852475693644,
      "loss": 1.1788,
      "step": 188
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012707272522366426,
      "loss": 1.0949,
      "step": 189
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012635871660690676,
      "loss": 1.1947,
      "step": 190
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012564326091759646,
      "loss": 1.1302,
      "step": 191
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012492639743368097,
      "loss": 1.2702,
      "step": 192
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001242081655103947,
      "loss": 1.1206,
      "step": 193
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012348860457809838,
      "loss": 1.2226,
      "step": 194
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001227677541401142,
      "loss": 1.1773,
      "step": 195
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012204565377055718,
      "loss": 1.1343,
      "step": 196
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001213223431121627,
      "loss": 1.1041,
      "step": 197
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012059786187410984,
      "loss": 1.0455,
      "step": 198
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011987224982984176,
      "loss": 1.2509,
      "step": 199
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011914554681488188,
      "loss": 1.143,
      "step": 200
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011841779272464703,
      "loss": 1.3258,
      "step": 201
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001176890275122573,
      "loss": 1.2916,
      "step": 202
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011695929118634256,
      "loss": 1.1948,
      "step": 203
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011622862380884601,
      "loss": 1.2079,
      "step": 204
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011549706549282486,
      "loss": 1.0284,
      "step": 205
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011476465640024814,
      "loss": 1.2139,
      "step": 206
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011403143673979183,
      "loss": 1.1924,
      "step": 207
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011329744676463143,
      "loss": 1.1459,
      "step": 208
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011256272677023214,
      "loss": 0.992,
      "step": 209
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011182731709213659,
      "loss": 1.1304,
      "step": 210
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011109125810375054,
      "loss": 1.2196,
      "step": 211
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001103545902141263,
      "loss": 1.1904,
      "step": 212
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010961735386574448,
      "loss": 1.2486,
      "step": 213
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010887958953229349,
      "loss": 1.2505,
      "step": 214
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010814133771644783,
      "loss": 1.1688,
      "step": 215
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010740263894764429,
      "loss": 1.1316,
      "step": 216
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010666353377985711,
      "loss": 1.0465,
      "step": 217
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010592406278937144,
      "loss": 1.1121,
      "step": 218
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010518426657255585,
      "loss": 1.0605,
      "step": 219
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010444418574363353,
      "loss": 1.0242,
      "step": 220
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001037038609324527,
      "loss": 1.1648,
      "step": 221
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010296333278225599,
      "loss": 1.2036,
      "step": 222
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010222264194744918,
      "loss": 1.1253,
      "step": 223
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010148182909136928,
      "loss": 1.0713,
      "step": 224
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010074093488405223,
      "loss": 1.0154,
      "step": 225
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.2678,
      "step": 226
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.92590651159478e-05,
      "loss": 1.2334,
      "step": 227
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.851817090863073e-05,
      "loss": 1.2362,
      "step": 228
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.777735805255087e-05,
      "loss": 1.261,
      "step": 229
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.703666721774402e-05,
      "loss": 1.0949,
      "step": 230
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.629613906754731e-05,
      "loss": 1.4044,
      "step": 231
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.555581425636648e-05,
      "loss": 1.1616,
      "step": 232
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.481573342744419e-05,
      "loss": 1.0162,
      "step": 233
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.407593721062859e-05,
      "loss": 1.2492,
      "step": 234
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.33364662201429e-05,
      "loss": 1.1703,
      "step": 235
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.259736105235572e-05,
      "loss": 1.1257,
      "step": 236
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.18586622835522e-05,
      "loss": 1.1351,
      "step": 237
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.112041046770653e-05,
      "loss": 1.3618,
      "step": 238
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.038264613425556e-05,
      "loss": 1.0293,
      "step": 239
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.96454097858737e-05,
      "loss": 1.2353,
      "step": 240
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.890874189624951e-05,
      "loss": 1.0402,
      "step": 241
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.817268290786343e-05,
      "loss": 1.1703,
      "step": 242
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.743727322976787e-05,
      "loss": 1.154,
      "step": 243
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.670255323536858e-05,
      "loss": 1.1215,
      "step": 244
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.596856326020821e-05,
      "loss": 1.0841,
      "step": 245
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.523534359975189e-05,
      "loss": 1.0127,
      "step": 246
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.450293450717517e-05,
      "loss": 1.149,
      "step": 247
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.3771376191154e-05,
      "loss": 1.1336,
      "step": 248
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.304070881365747e-05,
      "loss": 1.1274,
      "step": 249
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.231097248774274e-05,
      "loss": 1.0389,
      "step": 250
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.158220727535299e-05,
      "loss": 1.1231,
      "step": 251
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.085445318511813e-05,
      "loss": 0.9329,
      "step": 252
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.012775017015828e-05,
      "loss": 1.1147,
      "step": 253
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.940213812589018e-05,
      "loss": 1.0832,
      "step": 254
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.867765688783733e-05,
      "loss": 1.1802,
      "step": 255
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.795434622944281e-05,
      "loss": 1.1738,
      "step": 256
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.723224585988584e-05,
      "loss": 1.0246,
      "step": 257
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.651139542190164e-05,
      "loss": 1.2217,
      "step": 258
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.579183448960531e-05,
      "loss": 1.0989,
      "step": 259
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.507360256631904e-05,
      "loss": 1.1477,
      "step": 260
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.435673908240357e-05,
      "loss": 1.1377,
      "step": 261
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.364128339309326e-05,
      "loss": 1.0929,
      "step": 262
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.292727477633575e-05,
      "loss": 1.0974,
      "step": 263
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.221475243063563e-05,
      "loss": 1.2126,
      "step": 264
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.150375547290225e-05,
      "loss": 1.0974,
      "step": 265
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.079432293630244e-05,
      "loss": 1.1057,
      "step": 266
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.008649376811756e-05,
      "loss": 1.1579,
      "step": 267
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.938030682760532e-05,
      "loss": 1.1736,
      "step": 268
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.867580088386646e-05,
      "loss": 1.0662,
      "step": 269
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.797301461371625e-05,
      "loss": 1.2125,
      "step": 270
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.727198659956133e-05,
      "loss": 1.1253,
      "step": 271
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.65727553272815e-05,
      "loss": 1.0973,
      "step": 272
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.58753591841168e-05,
      "loss": 1.2053,
      "step": 273
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.517983645656014e-05,
      "loss": 1.1743,
      "step": 274
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.448622532825545e-05,
      "loss": 1.2297,
      "step": 275
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.379456387790138e-05,
      "loss": 1.1378,
      "step": 276
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.310489007716083e-05,
      "loss": 1.2174,
      "step": 277
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.24172417885762e-05,
      "loss": 1.2263,
      "step": 278
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.173165676349103e-05,
      "loss": 1.148,
      "step": 279
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.104817263997727e-05,
      "loss": 1.0725,
      "step": 280
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.036682694076907e-05,
      "loss": 1.1362,
      "step": 281
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.96876570712028e-05,
      "loss": 1.0239,
      "step": 282
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.9010700317163404e-05,
      "loss": 1.102,
      "step": 283
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.8335993843037695e-05,
      "loss": 1.0572,
      "step": 284
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.7663574689673847e-05,
      "loss": 1.2498,
      "step": 285
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.699347977234799e-05,
      "loss": 1.1782,
      "step": 286
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.6325745878737355e-05,
      "loss": 1.0844,
      "step": 287
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.566040966690115e-05,
      "loss": 1.2224,
      "step": 288
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.4997507663267546e-05,
      "loss": 1.1441,
      "step": 289
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.43370762606287e-05,
      "loss": 1.2026,
      "step": 290
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.367915171614273e-05,
      "loss": 1.2394,
      "step": 291
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.302377014934322e-05,
      "loss": 1.0419,
      "step": 292
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.2370967540156346e-05,
      "loss": 0.9862,
      "step": 293
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.172077972692553e-05,
      "loss": 1.0682,
      "step": 294
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.1073242404443974e-05,
      "loss": 1.1262,
      "step": 295
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.042839112199509e-05,
      "loss": 1.1062,
      "step": 296
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.978626128140074e-05,
      "loss": 0.9907,
      "step": 297
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.914688813507797e-05,
      "loss": 1.1321,
      "step": 298
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.851030678410331e-05,
      "loss": 1.2056,
      "step": 299
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.7876552176286005e-05,
      "loss": 1.1657,
      "step": 300
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.724565910424946e-05,
      "loss": 1.0266,
      "step": 301
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.661766220352097e-05,
      "loss": 0.9024,
      "step": 302
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.59925959506302e-05,
      "loss": 1.5604,
      "step": 303
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.5370494661216835e-05,
      "loss": 1.0028,
      "step": 304
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.475139248814625e-05,
      "loss": 1.0763,
      "step": 305
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.4135323419634766e-05,
      "loss": 1.0086,
      "step": 306
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.352232127738368e-05,
      "loss": 1.0214,
      "step": 307
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.2912419714722496e-05,
      "loss": 0.9547,
      "step": 308
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.230565221476131e-05,
      "loss": 1.0584,
      "step": 309
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.170205208855281e-05,
      "loss": 1.2047,
      "step": 310
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.1101652473263195e-05,
      "loss": 1.0804,
      "step": 311
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.0504486330353264e-05,
      "loss": 1.0394,
      "step": 312
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.9910586443768806e-05,
      "loss": 1.1128,
      "step": 313
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.931998541814069e-05,
      "loss": 1.2576,
      "step": 314
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.873271567699485e-05,
      "loss": 1.0032,
      "step": 315
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.814880946097252e-05,
      "loss": 1.0491,
      "step": 316
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.756829882606001e-05,
      "loss": 1.0629,
      "step": 317
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.69912156418289e-05,
      "loss": 1.0391,
      "step": 318
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.641759158968649e-05,
      "loss": 1.0735,
      "step": 319
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.584745816113648e-05,
      "loss": 1.0636,
      "step": 320
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.528084665605013e-05,
      "loss": 1.0232,
      "step": 321
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.471778818094785e-05,
      "loss": 1.2711,
      "step": 322
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.4158313647291604e-05,
      "loss": 0.9995,
      "step": 323
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.360245376978779e-05,
      "loss": 1.1935,
      "step": 324
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.3050239064701016e-05,
      "loss": 1.2296,
      "step": 325
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.250169984817897e-05,
      "loss": 1.1118,
      "step": 326
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.1956866234587766e-05,
      "loss": 1.0869,
      "step": 327
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.1415768134858945e-05,
      "loss": 1.1736,
      "step": 328
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0878435254847394e-05,
      "loss": 0.9783,
      "step": 329
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.034489709370033e-05,
      "loss": 1.0698,
      "step": 330
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9815182942237885e-05,
      "loss": 1.0023,
      "step": 331
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.9884,
      "step": 332
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8767342780375926e-05,
      "loss": 1.1866,
      "step": 333
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8249274295566864e-05,
      "loss": 1.1612,
      "step": 334
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.7735144868465458e-05,
      "loss": 1.0186,
      "step": 335
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7224982724367776e-05,
      "loss": 1.1382,
      "step": 336
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6718815870769287e-05,
      "loss": 1.0752,
      "step": 337
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6216672095827266e-05,
      "loss": 1.0572,
      "step": 338
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5718578966835117e-05,
      "loss": 1.1551,
      "step": 339
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.5224563828708902e-05,
      "loss": 1.1094,
      "step": 340
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4734653802486428e-05,
      "loss": 1.0506,
      "step": 341
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4248875783837987e-05,
      "loss": 1.185,
      "step": 342
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3767256441590014e-05,
      "loss": 0.823,
      "step": 343
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.328982221626087e-05,
      "loss": 1.0136,
      "step": 344
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2816599318609368e-05,
      "loss": 1.13,
      "step": 345
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.234761372819577e-05,
      "loss": 1.0324,
      "step": 346
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1882891191955534e-05,
      "loss": 1.0539,
      "step": 347
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1422457222785873e-05,
      "loss": 1.1255,
      "step": 348
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0966337098145037e-05,
      "loss": 1.0934,
      "step": 349
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0514555858664663e-05,
      "loss": 1.2765,
      "step": 350
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0067138306775124e-05,
      "loss": 0.9743,
      "step": 351
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9624109005343672e-05,
      "loss": 1.1101,
      "step": 352
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.918549227632619e-05,
      "loss": 1.2542,
      "step": 353
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.875131219943187e-05,
      "loss": 1.2118,
      "step": 354
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.832159261080122e-05,
      "loss": 0.925,
      "step": 355
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7896357101697404e-05,
      "loss": 1.0461,
      "step": 356
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.747562901721135e-05,
      "loss": 0.914,
      "step": 357
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.7059431454979824e-05,
      "loss": 1.0492,
      "step": 358
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6647787263917612e-05,
      "loss": 1.2384,
      "step": 359
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6240719042963002e-05,
      "loss": 1.2198,
      "step": 360
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5838249139837202e-05,
      "loss": 1.1803,
      "step": 361
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5440399649817385e-05,
      "loss": 1.0166,
      "step": 362
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5047192414523815e-05,
      "loss": 0.9622,
      "step": 363
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4658649020720538e-05,
      "loss": 1.04,
      "step": 364
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.42747907991305e-05,
      "loss": 1.0195,
      "step": 365
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3895638823264446e-05,
      "loss": 1.1031,
      "step": 366
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.352121390826393e-05,
      "loss": 1.1878,
      "step": 367
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3151536609758586e-05,
      "loss": 1.3069,
      "step": 368
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.27866272227378e-05,
      "loss": 1.2004,
      "step": 369
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2426505780436326e-05,
      "loss": 1.1324,
      "step": 370
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2071192053234581e-05,
      "loss": 1.3239,
      "step": 371
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1720705547573263e-05,
      "loss": 1.0881,
      "step": 372
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1375065504882465e-05,
      "loss": 1.0445,
      "step": 373
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.103429090052528e-05,
      "loss": 1.0811,
      "step": 374
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0698400442756152e-05,
      "loss": 1.0309,
      "step": 375
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0367412571693747e-05,
      "loss": 1.1477,
      "step": 376
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0041345458308616e-05,
      "loss": 1.0614,
      "step": 377
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.720217003425647e-06,
      "loss": 1.2404,
      "step": 378
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.404044836741343e-06,
      "loss": 1.1101,
      "step": 379
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.092846315855841e-06,
      "loss": 1.1387,
      "step": 380
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.786638525320146e-06,
      "loss": 1.1928,
      "step": 381
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.485438275698154e-06,
      "loss": 1.1997,
      "step": 382
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.189262102643746e-06,
      "loss": 1.0821,
      "step": 383
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.89812626599291e-06,
      "loss": 1.0979,
      "step": 384
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.612046748871327e-06,
      "loss": 1.1719,
      "step": 385
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.331039256816663e-06,
      "loss": 1.1024,
      "step": 386
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.0551192169164505e-06,
      "loss": 1.1508,
      "step": 387
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.7843017769612215e-06,
      "loss": 1.0387,
      "step": 388
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.518601804612734e-06,
      "loss": 1.2251,
      "step": 389
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.258033886587911e-06,
      "loss": 1.241,
      "step": 390
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.00261232785797e-06,
      "loss": 1.2481,
      "step": 391
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.7523511508631336e-06,
      "loss": 1.2674,
      "step": 392
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.50726409474267e-06,
      "loss": 1.0774,
      "step": 393
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.267364614580861e-06,
      "loss": 1.2461,
      "step": 394
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.032665880668119e-06,
      "loss": 1.0963,
      "step": 395
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.803180777778049e-06,
      "loss": 1.252,
      "step": 396
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.578921904460076e-06,
      "loss": 1.0251,
      "step": 397
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.359901572347758e-06,
      "loss": 0.9214,
      "step": 398
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.146131805482944e-06,
      "loss": 1.1498,
      "step": 399
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.937624339655599e-06,
      "loss": 0.8854,
      "step": 400
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.734390621759565e-06,
      "loss": 1.221,
      "step": 401
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.5364418091641373e-06,
      "loss": 1.0589,
      "step": 402
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.343788769101486e-06,
      "loss": 1.1017,
      "step": 403
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.156442078070143e-06,
      "loss": 1.0694,
      "step": 404
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.974412021254236e-06,
      "loss": 1.2257,
      "step": 405
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.7977085919589254e-06,
      "loss": 1.1377,
      "step": 406
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.6263414910618012e-06,
      "loss": 1.0816,
      "step": 407
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.460320126480242e-06,
      "loss": 0.9841,
      "step": 408
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.2996536126549395e-06,
      "loss": 1.2322,
      "step": 409
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.144350770049597e-06,
      "loss": 0.9069,
      "step": 410
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.9944201246666074e-06,
      "loss": 1.0551,
      "step": 411
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8498699075789939e-06,
      "loss": 1.0453,
      "step": 412
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7107080544785937e-06,
      "loss": 0.9641,
      "step": 413
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.576942205240317e-06,
      "loss": 1.1408,
      "step": 414
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4485797035027727e-06,
      "loss": 1.2242,
      "step": 415
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3256275962651222e-06,
      "loss": 1.0917,
      "step": 416
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.208092633500102e-06,
      "loss": 1.0118,
      "step": 417
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0959812677835968e-06,
      "loss": 1.0072,
      "step": 418
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.892996539403232e-07,
      "loss": 1.0862,
      "step": 419
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.880536487059333e-07,
      "loss": 1.0861,
      "step": 420
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.922488104054825e-07,
      "loss": 1.1889,
      "step": 421
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.018903986483083e-07,
      "loss": 0.9407,
      "step": 422
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.169833740392595e-07,
      "loss": 1.0854,
      "step": 423
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.375323979063928e-07,
      "loss": 1.0511,
      "step": 424
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.635418320450335e-07,
      "loss": 0.9293,
      "step": 425
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.950157384783104e-07,
      "loss": 0.9677,
      "step": 426
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.319578792342126e-07,
      "loss": 1.1209,
      "step": 427
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.7437171613898807e-07,
      "loss": 1.1188,
      "step": 428
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.2226041062715086e-07,
      "loss": 1.2072,
      "step": 429
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.7562682356786487e-07,
      "loss": 1.0988,
      "step": 430
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.344735151079246e-07,
      "loss": 1.1216,
      "step": 431
    },
    {
      "epoch": 0.99,
      "learning_rate": 9.88027445312123e-08,
      "loss": 1.1095,
      "step": 432
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.861647013461925e-08,
      "loss": 1.1363,
      "step": 433
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.391634912056519e-08,
      "loss": 1.0079,
      "step": 434
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.4703737506037715e-08,
      "loss": 1.0498,
      "step": 435
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.0979690048107394e-08,
      "loss": 1.0434,
      "step": 436
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.7449601860629613e-09,
      "loss": 1.0162,
      "step": 437
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.0504,
      "step": 438
    },
    {
      "epoch": 1.0,
      "step": 438,
      "total_flos": 8.085704333380813e+16,
      "train_loss": 1.1821429170157811,
      "train_runtime": 1894.5999,
      "train_samples_per_second": 3.695,
      "train_steps_per_second": 0.231
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 438,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 8.085704333380813e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}