{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.7219,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.6864,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 1.6849,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.333333333333333e-05,
      "loss": 1.8717,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.646,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 1.5204,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.5921,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010666666666666667,
      "loss": 1.3637,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012,
      "loss": 1.438,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.4821,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014666666666666666,
      "loss": 1.3257,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016,
      "loss": 1.098,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00017333333333333334,
      "loss": 1.2053,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001866666666666667,
      "loss": 1.1787,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.1686,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999790210013988,
      "loss": 1.1888,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001999916084885832,
      "loss": 1.354,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999811194293973,
      "loss": 1.2289,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019996643536268204,
      "loss": 1.2066,
      "step": 19
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019994755690455152,
      "loss": 1.2076,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019992448484710797,
      "loss": 1.1769,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001998972201584088,
      "loss": 1.0123,
      "step": 22
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019986576398242566,
      "loss": 1.4415,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019983011763899673,
      "loss": 1.4028,
      "step": 24
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019979028262377118,
      "loss": 1.2477,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019974626060814647,
      "loss": 1.3016,
      "step": 26
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019969805343919821,
      "loss": 1.0543,
      "step": 27
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019964566313960264,
      "loss": 1.416,
      "step": 28
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019958909190755187,
      "loss": 1.0205,
      "step": 29
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001995283421166614,
      "loss": 1.2208,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019946341631587087,
      "loss": 1.1953,
      "step": 31
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001993943172293368,
      "loss": 1.4558,
      "step": 32
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019932104775631846,
      "loss": 1.154,
      "step": 33
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019924361097105623,
      "loss": 1.296,
      "step": 34
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019916201012264254,
      "loss": 1.1406,
      "step": 35
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001990762486348855,
      "loss": 1.1657,
      "step": 36
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019898633010616542,
      "loss": 1.2168,
      "step": 37
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019889225830928365,
      "loss": 1.3055,
      "step": 38
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001987940371913044,
      "loss": 1.2532,
      "step": 39
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019869167087338907,
      "loss": 1.3164,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019858516365062334,
      "loss": 1.0849,
      "step": 41
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019847451999183694,
      "loss": 1.3489,
      "step": 42
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001983597445394162,
      "loss": 1.2201,
      "step": 43
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019824084210910925,
      "loss": 1.2299,
      "step": 44
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001981178176898239,
      "loss": 1.2114,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019799067644341844,
      "loss": 1.2803,
      "step": 46
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001978594237044849,
      "loss": 1.1191,
      "step": 47
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001977240649801253,
      "loss": 1.0978,
      "step": 48
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019758460594972068,
      "loss": 0.9227,
      "step": 49
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019744105246469263,
      "loss": 1.1387,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019729341054825782,
      "loss": 1.1379,
      "step": 51
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019714168639517544,
      "loss": 1.2521,
      "step": 52
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019698588637148703,
      "loss": 1.2173,
      "step": 53
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001968260170142496,
      "loss": 1.1976,
      "step": 54
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019666208503126112,
      "loss": 1.3079,
      "step": 55
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019649409730077935,
      "loss": 1.0566,
      "step": 56
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019632206087123296,
      "loss": 1.0518,
      "step": 57
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000196145982960926,
      "loss": 0.9927,
      "step": 58
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019596587095773495,
      "loss": 1.2951,
      "step": 59
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019578173241879872,
      "loss": 1.1108,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019559357507020162,
      "loss": 1.197,
      "step": 61
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019540140680664913,
      "loss": 1.0719,
      "step": 62
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019520523569113677,
      "loss": 1.1016,
      "step": 63
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001950050699546116,
      "loss": 1.2568,
      "step": 64
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019480091799562704,
      "loss": 1.1708,
      "step": 65
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019459278837999046,
      "loss": 1.2479,
      "step": 66
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019438068984040365,
      "loss": 1.2054,
      "step": 67
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019416463127609656,
      "loss": 1.2782,
      "step": 68
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019394462175245381,
      "loss": 1.2146,
      "step": 69
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019372067050063438,
      "loss": 1.2381,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019349278691718427,
      "loss": 1.0016,
      "step": 71
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019326098056364222,
      "loss": 0.9979,
      "step": 72
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019302526116613864,
      "loss": 1.2436,
      "step": 73
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019278563861498723,
      "loss": 1.269,
      "step": 74
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019254212296427044,
      "loss": 1.1738,
      "step": 75
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001922947244314172,
      "loss": 1.2086,
      "step": 76
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019204345339677442,
      "loss": 1.175,
      "step": 77
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019178832040317155,
      "loss": 1.2136,
      "step": 78
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019152933615547798,
      "loss": 1.1302,
      "step": 79
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019126651152015403,
      "loss": 1.2325,
      "step": 80
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019099985752479506,
      "loss": 0.9378,
      "step": 81
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019072938535766865,
      "loss": 1.0943,
      "step": 82
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001904551063672452,
      "loss": 1.1477,
      "step": 83
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019017703206172185,
      "loss": 1.2455,
      "step": 84
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018989517410853955,
      "loss": 1.2347,
      "step": 85
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018960954433389345,
      "loss": 1.4247,
      "step": 86
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018932015472223693,
      "loss": 1.0591,
      "step": 87
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001890270174157784,
      "loss": 1.417,
      "step": 88
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018873014471397224,
      "loss": 1.2822,
      "step": 89
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018842954907300236,
      "loss": 1.2454,
      "step": 90
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001881252431052599,
      "loss": 1.2658,
      "step": 91
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018781723957881372,
      "loss": 1.3752,
      "step": 92
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000187505551416875,
      "loss": 1.1369,
      "step": 93
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018719019169725472,
      "loss": 1.2625,
      "step": 94
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018687117365181512,
      "loss": 1.2937,
      "step": 95
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018654851066591448,
      "loss": 0.9782,
      "step": 96
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001862222162778454,
      "loss": 1.2066,
      "step": 97
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018589230417826697,
      "loss": 1.1922,
      "step": 98
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018555878820963013,
      "loss": 1.0794,
      "step": 99
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018522168236559695,
      "loss": 1.2692,
      "step": 100
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018488100079045344,
      "loss": 1.0703,
      "step": 101
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018453675777851627,
      "loss": 1.174,
      "step": 102
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001841889677735327,
      "loss": 1.1601,
      "step": 103
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018383764536807485,
      "loss": 1.1539,
      "step": 104
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018348280530292713,
      "loss": 1.0524,
      "step": 105
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001831244624664681,
      "loss": 1.1849,
      "step": 106
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001827626318940454,
      "loss": 1.2796,
      "step": 107
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018239732876734527,
      "loss": 1.0607,
      "step": 108
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018202856841375518,
      "loss": 1.1277,
      "step": 109
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001816563663057211,
      "loss": 1.1887,
      "step": 110
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000181280738060098,
      "loss": 1.0176,
      "step": 111
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.1298,
      "step": 112
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018051926634161282,
      "loss": 1.1681,
      "step": 113
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018013345481857903,
      "loss": 1.2057,
      "step": 114
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017974428105627208,
      "loss": 1.1583,
      "step": 115
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001793517613836437,
      "loss": 1.0065,
      "step": 116
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017895591227003315,
      "loss": 1.1427,
      "step": 117
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017855675032447648,
      "loss": 1.0794,
      "step": 118
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017815429229500946,
      "loss": 0.8666,
      "step": 119
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017774855506796496,
      "loss": 1.1189,
      "step": 120
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001773395556672644,
      "loss": 0.9305,
      "step": 121
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017692731125370354,
      "loss": 1.114,
      "step": 122
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017651183912423228,
      "loss": 1.2557,
      "step": 123
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001760931567112291,
      "loss": 1.3754,
      "step": 124
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017567128158176953,
      "loss": 1.1994,
      "step": 125
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017524623143688902,
      "loss": 1.1867,
      "step": 126
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017481802411084042,
      "loss": 1.1963,
      "step": 127
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017438667757034546,
      "loss": 1.2005,
      "step": 128
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001739522099138411,
      "loss": 0.8968,
      "step": 129
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017351463937072004,
      "loss": 1.2357,
      "step": 130
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017307398430056593,
      "loss": 1.2491,
      "step": 131
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017263026319238301,
      "loss": 1.0971,
      "step": 132
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017218349466382023,
      "loss": 1.1475,
      "step": 133
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017173369746039025,
      "loss": 1.2107,
      "step": 134
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017128089045468294,
      "loss": 1.1637,
      "step": 135
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001708250926455733,
      "loss": 1.0868,
      "step": 136
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017036632315742462,
      "loss": 1.1642,
      "step": 137
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016990460123928575,
      "loss": 1.1791,
      "step": 138
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016943994626408363,
      "loss": 1.168,
      "step": 139
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016897237772781044,
      "loss": 1.0337,
      "step": 140
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016850191524870546,
      "loss": 1.0823,
      "step": 141
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016802857856643215,
      "loss": 1.1933,
      "step": 142
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016755238754124965,
      "loss": 1.1543,
      "step": 143
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016707336215317968,
      "loss": 1.3017,
      "step": 144
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016659152250116812,
      "loss": 1.1858,
      "step": 145
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016610688880224178,
      "loss": 1.202,
      "step": 146
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016561948139065996,
      "loss": 1.1246,
      "step": 147
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016512932071706152,
      "loss": 1.2125,
      "step": 148
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001646364273476067,
      "loss": 1.0142,
      "step": 149
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000164140821963114,
      "loss": 1.1634,
      "step": 150
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016364252535819282,
      "loss": 1.2093,
      "step": 151
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016314155844037074,
      "loss": 1.1758,
      "step": 152
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001626379422292162,
      "loss": 1.028,
      "step": 153
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001621316978554569,
      "loss": 1.2026,
      "step": 154
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016162284656009274,
      "loss": 1.143,
      "step": 155
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016111140969350503,
      "loss": 1.0423,
      "step": 156
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016059740871456036,
      "loss": 1.0494,
      "step": 157
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016008086518971037,
      "loss": 1.0948,
      "step": 158
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015956180079208682,
      "loss": 1.0134,
      "step": 159
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015904023730059228,
      "loss": 1.1691,
      "step": 160
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015851619659898623,
      "loss": 1.2238,
      "step": 161
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000157989700674967,
      "loss": 1.1941,
      "step": 162
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015746077161924905,
      "loss": 1.108,
      "step": 163
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015692943162463628,
      "loss": 1.0089,
      "step": 164
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015639570298509064,
      "loss": 1.1409,
      "step": 165
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015585960809479696,
      "loss": 1.1456,
      "step": 166
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015532116944722308,
      "loss": 0.9977,
      "step": 167
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001547804096341763,
      "loss": 1.1153,
      "step": 168
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015423735134485536,
      "loss": 1.1055,
      "step": 169
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001536920173648984,
      "loss": 1.1761,
      "step": 170
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015314443057542703,
      "loss": 1.1769,
      "step": 171
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015259461395208628,
      "loss": 1.0164,
      "step": 172
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015204259056408046,
      "loss": 1.0465,
      "step": 173
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015148838357320537,
      "loss": 1.1404,
      "step": 174
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015093201623287631,
      "loss": 1.1634,
      "step": 175
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015037351188715265,
      "loss": 1.1184,
      "step": 176
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00014981289396975817,
      "loss": 1.0924,
      "step": 177
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014925018600309785,
      "loss": 0.9458,
      "step": 178
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014868541159727096,
      "loss": 1.2231,
      "step": 179
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014811859444908052,
      "loss": 1.0944,
      "step": 180
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014754975834103877,
      "loss": 1.1361,
      "step": 181
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014697892714036958,
      "loss": 1.002,
      "step": 182
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014640612479800686,
      "loss": 1.1042,
      "step": 183
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014583137534758967,
      "loss": 1.054,
      "step": 184
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014525470290445392,
      "loss": 1.1625,
      "step": 185
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014467613166462023,
      "loss": 1.2429,
      "step": 186
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014409568590377918,
      "loss": 1.1848,
      "step": 187
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014351338997627234,
      "loss": 1.3766,
      "step": 188
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014292926831407061,
      "loss": 1.2339,
      "step": 189
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014234334542574906,
      "loss": 1.1096,
      "step": 190
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014175564589545854,
      "loss": 1.1465,
      "step": 191
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001411661943818944,
      "loss": 1.2395,
      "step": 192
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014057501561726157,
      "loss": 1.0417,
      "step": 193
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001399821344062369,
      "loss": 1.3044,
      "step": 194
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013938757562492873,
      "loss": 0.991,
      "step": 195
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013879136421983266,
      "loss": 1.0881,
      "step": 196
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001381935252067852,
      "loss": 1.1961,
      "step": 197
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001375940836699139,
      "loss": 1.2466,
      "step": 198
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001369930647605852,
      "loss": 1.0601,
      "step": 199
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013639049369634876,
      "loss": 1.1748,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013578639575987958,
      "loss": 0.9668,
      "step": 201
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013518079629791724,
      "loss": 1.1252,
      "step": 202
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001345737207202023,
      "loss": 1.1977,
      "step": 203
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013396519449841005,
      "loss": 1.3469,
      "step": 204
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013335524316508208,
      "loss": 1.0968,
      "step": 205
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013274389231255466,
      "loss": 1.2344,
      "step": 206
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013213116759188523,
      "loss": 1.2466,
      "step": 207
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013151709471177588,
      "loss": 1.1162,
      "step": 208
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.0375,
      "step": 209
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013028500758979506,
      "loss": 1.1968,
      "step": 210
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012966704504383168,
      "loss": 1.2168,
      "step": 211
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012904783772807533,
      "loss": 1.1435,
      "step": 212
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012842741162322487,
      "loss": 1.1562,
      "step": 213
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012780579276111702,
      "loss": 1.0757,
      "step": 214
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001271830072236343,
      "loss": 1.2027,
      "step": 215
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001265590811416105,
      "loss": 1.168,
      "step": 216
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001259340406937345,
      "loss": 1.0693,
      "step": 217
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012530791210545162,
      "loss": 1.2123,
      "step": 218
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001246807216478634,
      "loss": 1.0348,
      "step": 219
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012405249563662537,
      "loss": 0.9382,
      "step": 220
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012342326043084266,
      "loss": 0.8843,
      "step": 221
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012279304243196436,
      "loss": 1.1019,
      "step": 222
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012216186808267546,
      "loss": 1.101,
      "step": 223
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001215297638657875,
      "loss": 1.0367,
      "step": 224
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012089675630312754,
      "loss": 1.1571,
      "step": 225
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012026287195442503,
      "loss": 1.1809,
      "step": 226
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011962813741619777,
      "loss": 1.077,
      "step": 227
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001189925793206357,
      "loss": 0.9586,
      "step": 228
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011835622433448361,
      "loss": 0.9559,
      "step": 229
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001177190991579223,
      "loss": 0.9069,
      "step": 230
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011708123052344804,
      "loss": 1.2167,
      "step": 231
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001164426451947513,
      "loss": 1.0831,
      "step": 232
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011580336996559343,
      "loss": 1.0083,
      "step": 233
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011516343165868279,
      "loss": 1.17,
      "step": 234
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011452285712454904,
      "loss": 1.0798,
      "step": 235
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011388167324041669,
      "loss": 1.1885,
      "step": 236
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011323990690907733,
      "loss": 1.1775,
      "step": 237
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011259758505776092,
      "loss": 1.3773,
      "step": 238
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001119547346370059,
      "loss": 1.0613,
      "step": 239
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011131138261952845,
      "loss": 1.1065,
      "step": 240
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011066755599909064,
      "loss": 1.1389,
      "step": 241
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011002328178936811,
      "loss": 1.1043,
      "step": 242
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010937858702281631,
      "loss": 1.2446,
      "step": 243
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001087334987495364,
      "loss": 0.8558,
      "step": 244
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010808804403614043,
      "loss": 1.1486,
      "step": 245
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001074422499646154,
      "loss": 1.1761,
      "step": 246
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010679614363118717,
      "loss": 0.9265,
      "step": 247
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001061497521451835,
      "loss": 1.2457,
      "step": 248
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010550310262789649,
      "loss": 1.1173,
      "step": 249
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010485622221144484,
      "loss": 1.0266,
      "step": 250
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010420913803763521,
      "loss": 1.2008,
      "step": 251
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010356187725682359,
      "loss": 0.9237,
      "step": 252
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010291446702677599,
      "loss": 1.1776,
      "step": 253
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000102266934511529,
      "loss": 0.9543,
      "step": 254
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010161930688025017,
      "loss": 0.908,
      "step": 255
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010097161130609773,
      "loss": 1.0167,
      "step": 256
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010032387496508089,
      "loss": 1.2062,
      "step": 257
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.967612503491914e-05,
      "loss": 1.0977,
      "step": 258
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.902838869390229e-05,
      "loss": 1.0898,
      "step": 259
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.838069311974986e-05,
      "loss": 1.1802,
      "step": 260
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.7733065488471e-05,
      "loss": 1.0734,
      "step": 261
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.708553297322406e-05,
      "loss": 1.2094,
      "step": 262
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.643812274317644e-05,
      "loss": 1.332,
      "step": 263
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.579086196236482e-05,
      "loss": 1.1703,
      "step": 264
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.514377778855521e-05,
      "loss": 0.9444,
      "step": 265
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.449689737210352e-05,
      "loss": 1.0035,
      "step": 266
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.385024785481654e-05,
      "loss": 1.2528,
      "step": 267
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.320385636881283e-05,
      "loss": 1.0786,
      "step": 268
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.255775003538462e-05,
      "loss": 1.1294,
      "step": 269
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.19119559638596e-05,
      "loss": 1.0809,
      "step": 270
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.126650125046361e-05,
      "loss": 1.079,
      "step": 271
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.062141297718371e-05,
      "loss": 1.1264,
      "step": 272
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.997671821063191e-05,
      "loss": 0.8984,
      "step": 273
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.933244400090937e-05,
      "loss": 1.0669,
      "step": 274
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.868861738047158e-05,
      "loss": 1.1277,
      "step": 275
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.804526536299413e-05,
      "loss": 1.0672,
      "step": 276
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.740241494223911e-05,
      "loss": 0.9704,
      "step": 277
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.676009309092272e-05,
      "loss": 1.2726,
      "step": 278
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.611832675958336e-05,
      "loss": 1.2471,
      "step": 279
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.5477142875451e-05,
      "loss": 0.8887,
      "step": 280
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.48365683413172e-05,
      "loss": 1.0268,
      "step": 281
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.419663003440657e-05,
      "loss": 1.133,
      "step": 282
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.355735480524874e-05,
      "loss": 1.0977,
      "step": 283
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.291876947655196e-05,
      "loss": 0.9636,
      "step": 284
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.228090084207774e-05,
      "loss": 0.8884,
      "step": 285
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.16437756655164e-05,
      "loss": 1.1231,
      "step": 286
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.100742067936431e-05,
      "loss": 1.0584,
      "step": 287
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.037186258380226e-05,
      "loss": 1.0427,
      "step": 288
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.973712804557501e-05,
      "loss": 1.0874,
      "step": 289
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.91032436968725e-05,
      "loss": 1.0463,
      "step": 290
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.847023613421251e-05,
      "loss": 1.1485,
      "step": 291
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.78381319173246e-05,
      "loss": 0.9406,
      "step": 292
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.72069575680357e-05,
      "loss": 1.1498,
      "step": 293
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.657673956915735e-05,
      "loss": 1.1227,
      "step": 294
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.594750436337467e-05,
      "loss": 1.2052,
      "step": 295
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.531927835213656e-05,
      "loss": 1.2671,
      "step": 296
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.469208789454838e-05,
      "loss": 0.9186,
      "step": 297
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.40659593062655e-05,
      "loss": 1.0966,
      "step": 298
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.344091885838948e-05,
      "loss": 1.2277,
      "step": 299
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.281699277636572e-05,
      "loss": 1.0399,
      "step": 300
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.2194207238883e-05,
      "loss": 1.0553,
      "step": 301
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.157258837677514e-05,
      "loss": 1.2325,
      "step": 302
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.095216227192467e-05,
      "loss": 1.1877,
      "step": 303
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.033295495616834e-05,
      "loss": 1.0895,
      "step": 304
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.971499241020495e-05,
      "loss": 1.1126,
      "step": 305
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.1778,
      "step": 306
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.848290528822416e-05,
      "loss": 1.0256,
      "step": 307
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.786883240811479e-05,
      "loss": 1.2018,
      "step": 308
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.725610768744534e-05,
      "loss": 1.0068,
      "step": 309
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.664475683491796e-05,
      "loss": 0.9965,
      "step": 310
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.603480550158995e-05,
      "loss": 1.0319,
      "step": 311
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.542627927979771e-05,
      "loss": 0.9029,
      "step": 312
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.481920370208274e-05,
      "loss": 1.0431,
      "step": 313
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.42136042401204e-05,
      "loss": 0.9684,
      "step": 314
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.360950630365126e-05,
      "loss": 1.0175,
      "step": 315
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.300693523941482e-05,
      "loss": 1.1331,
      "step": 316
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.24059163300861e-05,
      "loss": 1.2773,
      "step": 317
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.180647479321485e-05,
      "loss": 1.0293,
      "step": 318
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.120863578016735e-05,
      "loss": 1.1619,
      "step": 319
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.061242437507131e-05,
      "loss": 0.7395,
      "step": 320
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.00178655937631e-05,
      "loss": 1.0401,
      "step": 321
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.942498438273849e-05,
      "loss": 1.0951,
      "step": 322
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.883380561810563e-05,
      "loss": 1.0268,
      "step": 323
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.82443541045415e-05,
      "loss": 1.047,
      "step": 324
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.765665457425102e-05,
      "loss": 0.8275,
      "step": 325
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.707073168592942e-05,
      "loss": 0.9986,
      "step": 326
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.648661002372768e-05,
      "loss": 0.9283,
      "step": 327
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.590431409622081e-05,
      "loss": 0.8529,
      "step": 328
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.532386833537977e-05,
      "loss": 1.07,
      "step": 329
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.474529709554612e-05,
      "loss": 1.1059,
      "step": 330
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.416862465241033e-05,
      "loss": 1.3235,
      "step": 331
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.3593875201993174e-05,
      "loss": 1.2318,
      "step": 332
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.302107285963045e-05,
      "loss": 0.907,
      "step": 333
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.245024165896126e-05,
      "loss": 1.0178,
      "step": 334
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.1881405550919493e-05,
      "loss": 0.9352,
      "step": 335
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.1314588402729044e-05,
      "loss": 0.9356,
      "step": 336
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.074981399690218e-05,
      "loss": 0.8162,
      "step": 337
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.018710603024187e-05,
      "loss": 1.1338,
      "step": 338
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.962648811284738e-05,
      "loss": 1.0577,
      "step": 339
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.9067983767123736e-05,
      "loss": 1.2962,
      "step": 340
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.851161642679466e-05,
      "loss": 1.1202,
      "step": 341
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.795740943591955e-05,
      "loss": 0.9954,
      "step": 342
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.74053860479137e-05,
      "loss": 1.0711,
      "step": 343
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.6855569424572955e-05,
      "loss": 0.8067,
      "step": 344
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.630798263510162e-05,
      "loss": 1.1629,
      "step": 345
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.5762648655144666e-05,
      "loss": 1.0221,
      "step": 346
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.5219590365823714e-05,
      "loss": 1.1386,
      "step": 347
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.467883055277695e-05,
      "loss": 0.9104,
      "step": 348
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.414039190520308e-05,
      "loss": 1.0861,
      "step": 349
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.360429701490934e-05,
      "loss": 1.2544,
      "step": 350
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.307056837536373e-05,
      "loss": 1.0977,
      "step": 351
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.253922838075095e-05,
      "loss": 1.0201,
      "step": 352
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.2010299325033034e-05,
      "loss": 1.0682,
      "step": 353
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.1483803401013796e-05,
      "loss": 0.9791,
      "step": 354
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.0959762699407766e-05,
      "loss": 1.2229,
      "step": 355
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.043819920791322e-05,
      "loss": 1.1814,
      "step": 356
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.991913481028965e-05,
      "loss": 1.0074,
      "step": 357
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.940259128543967e-05,
      "loss": 0.953,
      "step": 358
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.8888590306494974e-05,
      "loss": 1.2351,
      "step": 359
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.8377153439907266e-05,
      "loss": 1.1869,
      "step": 360
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.786830214454315e-05,
      "loss": 1.124,
      "step": 361
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.736205777078381e-05,
      "loss": 0.8072,
      "step": 362
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.6858441559629306e-05,
      "loss": 0.8998,
      "step": 363
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.63574746418072e-05,
      "loss": 1.0842,
      "step": 364
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.585917803688603e-05,
      "loss": 0.7244,
      "step": 365
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.5363572652393326e-05,
      "loss": 1.0099,
      "step": 366
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.487067928293848e-05,
      "loss": 1.1167,
      "step": 367
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.4380518609340076e-05,
      "loss": 1.3043,
      "step": 368
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.389311119775828e-05,
      "loss": 0.9831,
      "step": 369
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.340847749883191e-05,
      "loss": 1.2556,
      "step": 370
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.292663784682036e-05,
      "loss": 1.1075,
      "step": 371
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.2447612458750365e-05,
      "loss": 0.7925,
      "step": 372
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.197142143356787e-05,
      "loss": 1.0794,
      "step": 373
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.149808475129452e-05,
      "loss": 0.9456,
      "step": 374
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.102762227218957e-05,
      "loss": 1.0697,
      "step": 375
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.056005373591637e-05,
      "loss": 1.031,
      "step": 376
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0095398760714267e-05,
      "loss": 0.94,
      "step": 377
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9633676842575387e-05,
      "loss": 0.9163,
      "step": 378
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9174907354426696e-05,
      "loss": 1.1313,
      "step": 379
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8719109545317103e-05,
      "loss": 0.9787,
      "step": 380
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8266302539609745e-05,
      "loss": 1.0568,
      "step": 381
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.7816505336179798e-05,
      "loss": 1.0352,
      "step": 382
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.736973680761702e-05,
      "loss": 0.955,
      "step": 383
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6926015699434072e-05,
      "loss": 0.9809,
      "step": 384
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6485360629279987e-05,
      "loss": 1.024,
      "step": 385
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6047790086158952e-05,
      "loss": 1.2458,
      "step": 386
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5613322429654574e-05,
      "loss": 0.9735,
      "step": 387
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.5181975889159615e-05,
      "loss": 1.0485,
      "step": 388
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.475376856311097e-05,
      "loss": 0.888,
      "step": 389
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.432871841823047e-05,
      "loss": 1.0219,
      "step": 390
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3906843288770886e-05,
      "loss": 1.1039,
      "step": 391
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3488160875767717e-05,
      "loss": 0.7981,
      "step": 392
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.307268874629649e-05,
      "loss": 1.0341,
      "step": 393
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.266044433273562e-05,
      "loss": 1.2271,
      "step": 394
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2251444932035094e-05,
      "loss": 0.9574,
      "step": 395
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.184570770499056e-05,
      "loss": 1.145,
      "step": 396
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1443249675523536e-05,
      "loss": 0.9001,
      "step": 397
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.1044087729966856e-05,
      "loss": 1.2492,
      "step": 398
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0648238616356332e-05,
      "loss": 1.2757,
      "step": 399
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.025571894372794e-05,
      "loss": 0.9874,
      "step": 400
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9866545181421013e-05,
      "loss": 1.2184,
      "step": 401
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9480733658387175e-05,
      "loss": 1.1349,
      "step": 402
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.9653,
      "step": 403
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.871926193990202e-05,
      "loss": 1.2276,
      "step": 404
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8343633694278895e-05,
      "loss": 1.1803,
      "step": 405
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7971431586244815e-05,
      "loss": 1.0849,
      "step": 406
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7602671232654754e-05,
      "loss": 0.994,
      "step": 407
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.723736810595461e-05,
      "loss": 1.2073,
      "step": 408
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6875537533531948e-05,
      "loss": 0.985,
      "step": 409
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.65171946970729e-05,
      "loss": 1.1621,
      "step": 410
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6162354631925204e-05,
      "loss": 0.643,
      "step": 411
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5811032226467305e-05,
      "loss": 1.0069,
      "step": 412
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5463242221483743e-05,
      "loss": 1.2104,
      "step": 413
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5118999209546559e-05,
      "loss": 1.2341,
      "step": 414
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4778317634403083e-05,
      "loss": 1.1068,
      "step": 415
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.444121179036989e-05,
      "loss": 1.0403,
      "step": 416
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4107695821733025e-05,
      "loss": 1.3551,
      "step": 417
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3777783722154603e-05,
      "loss": 1.0249,
      "step": 418
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3451489334085554e-05,
      "loss": 1.0825,
      "step": 419
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3128826348184887e-05,
      "loss": 1.0339,
      "step": 420
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2809808302745297e-05,
      "loss": 0.9929,
      "step": 421
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2494448583125018e-05,
      "loss": 1.0914,
      "step": 422
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.218276042118629e-05,
      "loss": 0.9416,
      "step": 423
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1874756894740135e-05,
      "loss": 1.129,
      "step": 424
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1570450926997655e-05,
      "loss": 1.0151,
      "step": 425
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1269855286027797e-05,
      "loss": 0.8199,
      "step": 426
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0972982584221592e-05,
      "loss": 1.1032,
      "step": 427
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.067984527776309e-05,
      "loss": 1.0803,
      "step": 428
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0390455666106547e-05,
      "loss": 1.1913,
      "step": 429
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.010482589146048e-05,
      "loss": 0.7645,
      "step": 430
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.822967938278171e-06,
      "loss": 1.0084,
      "step": 431
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.544893632754814e-06,
      "loss": 1.0602,
      "step": 432
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.270614642331376e-06,
      "loss": 1.0323,
      "step": 433
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.000142475204964e-06,
      "loss": 1.1445,
      "step": 434
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.733488479845997e-06,
      "loss": 1.1864,
      "step": 435
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.470663844522052e-06,
      "loss": 1.219,
      "step": 436
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.21167959682848e-06,
      "loss": 0.9414,
      "step": 437
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.956546603225601e-06,
      "loss": 1.096,
      "step": 438
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.705275568582848e-06,
      "loss": 1.1988,
      "step": 439
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.457877035729588e-06,
      "loss": 0.7263,
      "step": 440
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.21436138501278e-06,
      "loss": 1.1411,
      "step": 441
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.974738833861383e-06,
      "loss": 0.8643,
      "step": 442
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.739019436357774e-06,
      "loss": 1.0981,
      "step": 443
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.507213082815744e-06,
      "loss": 1.0246,
      "step": 444
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.2793294993656494e-06,
      "loss": 1.1948,
      "step": 445
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.055378247546218e-06,
      "loss": 0.9333,
      "step": 446
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.835368723903456e-06,
      "loss": 1.0208,
      "step": 447
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.6193101595963585e-06,
      "loss": 0.9535,
      "step": 448
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.407211620009544e-06,
      "loss": 0.9038,
      "step": 449
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.199082004372957e-06,
      "loss": 1.0561,
      "step": 450
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.994930045388413e-06,
      "loss": 1.0509,
      "step": 451
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.794764308863242e-06,
      "loss": 1.0753,
      "step": 452
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.5985931933508754e-06,
      "loss": 0.9812,
      "step": 453
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.406424929798403e-06,
      "loss": 1.0773,
      "step": 454
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.2182675812012965e-06,
      "loss": 0.9144,
      "step": 455
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.034129042265066e-06,
      "loss": 1.1081,
      "step": 456
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.854017039074009e-06,
      "loss": 1.0401,
      "step": 457
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.6779391287670494e-06,
      "loss": 1.0266,
      "step": 458
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.5059026992206647e-06,
      "loss": 0.9342,
      "step": 459
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.3379149687388867e-06,
      "loss": 1.1004,
      "step": 460
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.1739829857504234e-06,
      "loss": 1.1163,
      "step": 461
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.014113628512982e-06,
      "loss": 1.0274,
      "step": 462
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8583136048245697e-06,
      "loss": 1.1967,
      "step": 463
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.706589451742181e-06,
      "loss": 1.2187,
      "step": 464
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.5589475353073988e-06,
      "loss": 0.946,
      "step": 465
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.415394050279318e-06,
      "loss": 0.8931,
      "step": 466
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.2759350198746976e-06,
      "loss": 1.0036,
      "step": 467
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1405762955151176e-06,
      "loss": 1.1022,
      "step": 468
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.009323556581566e-06,
      "loss": 0.9233,
      "step": 469
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.882182310176095e-06,
      "loss": 1.1482,
      "step": 470
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7591578908907724e-06,
      "loss": 1.0461,
      "step": 471
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.6402554605838172e-06,
      "loss": 0.9742,
      "step": 472
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5254800081630826e-06,
      "loss": 1.0997,
      "step": 473
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4148363493766802e-06,
      "loss": 0.9499,
      "step": 474
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.30832912661093e-06,
      "loss": 0.857,
      "step": 475
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2059628086956044e-06,
      "loss": 0.9575,
      "step": 476
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1077416907163574e-06,
      "loss": 1.0901,
      "step": 477
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0136698938346011e-06,
      "loss": 0.9817,
      "step": 478
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.237513651145225e-07,
      "loss": 0.9251,
      "step": 479
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.379898773574924e-07,
      "loss": 0.901,
      "step": 480
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.563890289437825e-07,
      "loss": 0.9311,
      "step": 481
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.78952243681541e-07,
      "loss": 0.9309,
      "step": 482
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.056827706632185e-07,
      "loss": 0.9619,
      "step": 483
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.365836841291438e-07,
      "loss": 0.983,
      "step": 484
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.7165788333860536e-07,
      "loss": 1.0906,
      "step": 485
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.1090809244814785e-07,
      "loss": 1.1527,
      "step": 486
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.543368603973529e-07,
      "loss": 0.8958,
      "step": 487
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.019465608018024e-07,
      "loss": 1.1326,
      "step": 488
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.537393918535358e-07,
      "loss": 1.0768,
      "step": 489
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.0971737622883515e-07,
      "loss": 0.8094,
      "step": 490
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.6988236100329292e-07,
      "loss": 1.167,
      "step": 491
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3423601757436287e-07,
      "loss": 0.8562,
      "step": 492
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0277984159122733e-07,
      "loss": 0.7308,
      "step": 493
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.551515289203615e-08,
      "loss": 0.9788,
      "step": 494
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.2443095448506674e-08,
      "loss": 1.0888,
      "step": 495
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.356463731798432e-08,
      "loss": 1.0148,
      "step": 496
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.888057060274173e-08,
      "loss": 1.0185,
      "step": 497
    },
    {
      "epoch": 1.0,
      "learning_rate": 8.391511416816489e-09,
      "loss": 1.0111,
      "step": 498
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.0978998601206556e-09,
      "loss": 0.9629,
      "step": 499
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.0114,
      "step": 500
    },
    {
      "epoch": 1.0,
      "step": 500,
      "total_flos": 3.720056178265293e+16,
      "train_loss": 1.1111255639791489,
      "train_runtime": 1258.8356,
      "train_samples_per_second": 1.589,
      "train_steps_per_second": 0.397
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 3.720056178265293e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}