{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0172413793103448,
  "eval_steps": 500,
  "global_step": 178,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2.5e-05,
      "loss": 1.8823,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 1.8925,
      "step": 2
    },
    {
      "epoch": 0.05,
      "learning_rate": 7.5e-05,
      "loss": 1.8355,
      "step": 3
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 1.8682,
      "step": 4
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000125,
      "loss": 1.6578,
      "step": 5
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00015,
      "loss": 1.7746,
      "step": 6
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000175,
      "loss": 1.7078,
      "step": 7
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.3556,
      "step": 8
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00022500000000000002,
      "loss": 1.785,
      "step": 9
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00025,
      "loss": 1.7491,
      "step": 10
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002499874839708436,
      "loss": 1.7576,
      "step": 11
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002499499383897902,
      "loss": 1.7944,
      "step": 12
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002498873707755852,
      "loss": 1.8368,
      "step": 13
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002497997936577979,
      "loss": 1.7509,
      "step": 14
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002496872245743125,
      "loss": 1.9833,
      "step": 15
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002495496860678158,
      "loss": 1.7853,
      "step": 16
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00024938720568128326,
      "loss": 1.7627,
      "step": 17
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002491998159524629,
      "loss": 1.7721,
      "step": 18
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002489875544073596,
      "loss": 1.6278,
      "step": 19
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00024875046355272046,
      "loss": 1.6963,
      "step": 20
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002484885908675223,
      "loss": 1.7123,
      "step": 21
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002482019887934636,
      "loss": 1.7719,
      "step": 22
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00024789071472446306,
      "loss": 1.8138,
      "step": 23
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00024755483099516584,
      "loss": 1.8235,
      "step": 24
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002471944048684608,
      "loss": 1.7845,
      "step": 25
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002468095085220104,
      "loss": 1.6665,
      "step": 26
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00024640021903379704,
      "loss": 1.6388,
      "step": 27
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00024596661836668736,
      "loss": 1.6817,
      "step": 28
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002455087933520188,
      "loss": 1.7617,
      "step": 29
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002450268356722112,
      "loss": 1.6921,
      "step": 30
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00024452084184240636,
      "loss": 1.6591,
      "step": 31
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00024399091319114082,
      "loss": 1.8172,
      "step": 32
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00024343715584005372,
      "loss": 1.7321,
      "step": 33
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00024285968068263553,
      "loss": 1.7617,
      "step": 34
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00024225860336202074,
      "loss": 1.7899,
      "step": 35
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00024163404424782967,
      "loss": 1.7486,
      "step": 36
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002409861284120637,
      "loss": 1.7422,
      "step": 37
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002403149856040586,
      "loss": 1.6344,
      "step": 38
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002396207502245017,
      "loss": 1.7174,
      "step": 39
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00023890356129851697,
      "loss": 1.7665,
      "step": 40
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00023816356244782462,
      "loss": 1.7379,
      "step": 41
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002374009018619796,
      "loss": 1.7206,
      "step": 42
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00023661573226869606,
      "loss": 1.6732,
      "step": 43
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00023580821090326233,
      "loss": 1.7475,
      "step": 44
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00023497849947705368,
      "loss": 1.7546,
      "step": 45
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00023412676414514853,
      "loss": 1.6588,
      "step": 46
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00023325317547305487,
      "loss": 1.7417,
      "step": 47
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00023235790840255328,
      "loss": 1.7224,
      "step": 48
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002314411422166639,
      "loss": 1.6476,
      "step": 49
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00023050306050374382,
      "loss": 1.73,
      "step": 50
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00022954385112072202,
      "loss": 1.6658,
      "step": 51
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00022856370615548027,
      "loss": 1.7046,
      "step": 52
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00022756282188838596,
      "loss": 1.7037,
      "step": 53
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00022654139875298573,
      "loss": 1.7166,
      "step": 54
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00022549964129586758,
      "loss": 1.7816,
      "step": 55
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00022443775813569874,
      "loss": 1.7556,
      "step": 56
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00022335596192144875,
      "loss": 1.7044,
      "step": 57
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00022225446928980495,
      "loss": 1.7183,
      "step": 58
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002211335008217896,
      "loss": 1.738,
      "step": 59
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00021999328099858717,
      "loss": 1.6217,
      "step": 60
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00021883403815659054,
      "loss": 1.5942,
      "step": 61
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00021765600444167505,
      "loss": 1.5313,
      "step": 62
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00021645941576270978,
      "loss": 1.6038,
      "step": 63
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00021524451174431556,
      "loss": 1.5116,
      "step": 64
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00021401153567887822,
      "loss": 1.5218,
      "step": 65
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00021276073447782786,
      "loss": 1.4994,
      "step": 66
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002114923586221933,
      "loss": 1.5652,
      "step": 67
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00021020666211244162,
      "loss": 1.5574,
      "step": 68
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00020890390241761286,
      "loss": 1.5671,
      "step": 69
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00020758434042376017,
      "loss": 1.4294,
      "step": 70
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00020624824038170583,
      "loss": 1.5317,
      "step": 71
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002048958698541231,
      "loss": 1.5671,
      "step": 72
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002035274996619553,
      "loss": 1.5256,
      "step": 73
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00020214340383018192,
      "loss": 1.5205,
      "step": 74
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00020074385953294352,
      "loss": 1.493,
      "step": 75
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00019932914703803584,
      "loss": 1.4958,
      "step": 76
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00019789954965078417,
      "loss": 1.498,
      "step": 77
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00019645535365730985,
      "loss": 1.4321,
      "step": 78
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00019499684826719944,
      "loss": 1.3947,
      "step": 79
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00019352432555558874,
      "loss": 1.4616,
      "step": 80
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001920380804046728,
      "loss": 1.4462,
      "step": 81
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00019053841044465398,
      "loss": 1.4964,
      "step": 82
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00018902561599413927,
      "loss": 1.5132,
      "step": 83
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001875,
      "loss": 1.4863,
      "step": 84
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00018596186797670432,
      "loss": 1.475,
      "step": 85
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00018441152794513625,
      "loss": 1.3819,
      "step": 86
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00018284929037091238,
      "loss": 1.4123,
      "step": 87
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00018127546810220915,
      "loss": 1.4385,
      "step": 88
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00017969037630711306,
      "loss": 1.4143,
      "step": 89
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.000178094332410506,
      "loss": 1.368,
      "step": 90
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001764876560304991,
      "loss": 1.4466,
      "step": 91
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00017487066891442703,
      "loss": 1.4604,
      "step": 92
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0001732436948744161,
      "loss": 1.4397,
      "step": 93
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001716070597225386,
      "loss": 1.4631,
      "step": 94
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.000169961091205567,
      "loss": 1.4424,
      "step": 95
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00016830611893934048,
      "loss": 1.4344,
      "step": 96
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0001666424743427572,
      "loss": 1.3999,
      "step": 97
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00016497049057140567,
      "loss": 1.3305,
      "step": 98
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00016329050245084795,
      "loss": 1.4365,
      "step": 99
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0001616028464095688,
      "loss": 1.4156,
      "step": 100
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015990786041160377,
      "loss": 1.4368,
      "step": 101
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015820588388885953,
      "loss": 1.3383,
      "step": 102
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015649725767314065,
      "loss": 1.4104,
      "step": 103
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001547823239278956,
      "loss": 1.4642,
      "step": 104
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00015306142607969655,
      "loss": 1.349,
      "step": 105
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001513349087494658,
      "loss": 1.3414,
      "step": 106
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014960311768346318,
      "loss": 1.4445,
      "step": 107
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00014786639968404833,
      "loss": 1.3416,
      "step": 108
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00014612510254023115,
      "loss": 1.3636,
      "step": 109
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014437957495802472,
      "loss": 1.4371,
      "step": 110
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00014263016649061492,
      "loss": 1.308,
      "step": 111
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00014087722746835985,
      "loss": 1.4221,
      "step": 112
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00013912110892863412,
      "loss": 1.3635,
      "step": 113
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013736216254553124,
      "loss": 1.4651,
      "step": 114
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013560074055943866,
      "loss": 1.4113,
      "step": 115
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013383719570649933,
      "loss": 1.4427,
      "step": 116
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013207188114797405,
      "loss": 1.4005,
      "step": 117
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00013030515039951854,
      "loss": 1.3678,
      "step": 118
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00012853735726038978,
      "loss": 1.3718,
      "step": 119
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00012676885574259528,
      "loss": 1.2768,
      "step": 120
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.000125,
      "loss": 1.2511,
      "step": 121
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00012323114425740475,
      "loss": 1.2024,
      "step": 122
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00012146264273961024,
      "loss": 1.2752,
      "step": 123
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00011969484960048149,
      "loss": 1.1877,
      "step": 124
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00011792811885202594,
      "loss": 1.129,
      "step": 125
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00011616280429350067,
      "loss": 1.1975,
      "step": 126
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0001143992594405614,
      "loss": 1.3163,
      "step": 127
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001126378374544688,
      "loss": 1.1691,
      "step": 128
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00011087889107136592,
      "loss": 1.2009,
      "step": 129
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00010912277253164016,
      "loss": 1.1294,
      "step": 130
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00010736983350938512,
      "loss": 1.2445,
      "step": 131
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00010562042504197526,
      "loss": 1.2484,
      "step": 132
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00010387489745976888,
      "loss": 1.1636,
      "step": 133
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00010213360031595167,
      "loss": 1.2341,
      "step": 134
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00010039688231653683,
      "loss": 1.16,
      "step": 135
    },
    {
      "epoch": 2.29,
      "learning_rate": 9.866509125053425e-05,
      "loss": 1.1895,
      "step": 136
    },
    {
      "epoch": 2.31,
      "learning_rate": 9.693857392030342e-05,
      "loss": 1.1355,
      "step": 137
    },
    {
      "epoch": 2.33,
      "learning_rate": 9.52176760721044e-05,
      "loss": 1.0434,
      "step": 138
    },
    {
      "epoch": 2.34,
      "learning_rate": 9.350274232685938e-05,
      "loss": 1.1358,
      "step": 139
    },
    {
      "epoch": 2.36,
      "learning_rate": 9.179411611114049e-05,
      "loss": 1.0848,
      "step": 140
    },
    {
      "epoch": 2.38,
      "learning_rate": 9.009213958839625e-05,
      "loss": 1.1591,
      "step": 141
    },
    {
      "epoch": 2.4,
      "learning_rate": 8.839715359043121e-05,
      "loss": 1.2907,
      "step": 142
    },
    {
      "epoch": 2.41,
      "learning_rate": 8.670949754915208e-05,
      "loss": 1.1806,
      "step": 143
    },
    {
      "epoch": 2.43,
      "learning_rate": 8.502950942859435e-05,
      "loss": 1.1443,
      "step": 144
    },
    {
      "epoch": 2.45,
      "learning_rate": 8.33575256572428e-05,
      "loss": 1.0913,
      "step": 145
    },
    {
      "epoch": 2.47,
      "learning_rate": 8.169388106065959e-05,
      "loss": 1.0982,
      "step": 146
    },
    {
      "epoch": 2.48,
      "learning_rate": 8.003890879443303e-05,
      "loss": 1.0401,
      "step": 147
    },
    {
      "epoch": 2.5,
      "learning_rate": 7.839294027746143e-05,
      "loss": 1.1177,
      "step": 148
    },
    {
      "epoch": 2.52,
      "learning_rate": 7.675630512558389e-05,
      "loss": 1.0619,
      "step": 149
    },
    {
      "epoch": 2.53,
      "learning_rate": 7.512933108557296e-05,
      "loss": 1.0004,
      "step": 150
    },
    {
      "epoch": 2.55,
      "learning_rate": 7.351234396950094e-05,
      "loss": 1.169,
      "step": 151
    },
    {
      "epoch": 2.57,
      "learning_rate": 7.190566758949402e-05,
      "loss": 1.0743,
      "step": 152
    },
    {
      "epoch": 2.59,
      "learning_rate": 7.030962369288702e-05,
      "loss": 1.1376,
      "step": 153
    },
    {
      "epoch": 2.6,
      "learning_rate": 6.872453189779081e-05,
      "loss": 1.1071,
      "step": 154
    },
    {
      "epoch": 2.62,
      "learning_rate": 6.715070962908766e-05,
      "loss": 1.053,
      "step": 155
    },
    {
      "epoch": 2.64,
      "learning_rate": 6.558847205486374e-05,
      "loss": 1.0751,
      "step": 156
    },
    {
      "epoch": 2.66,
      "learning_rate": 6.403813202329571e-05,
      "loss": 1.0028,
      "step": 157
    },
    {
      "epoch": 2.67,
      "learning_rate": 6.250000000000003e-05,
      "loss": 1.0816,
      "step": 158
    },
    {
      "epoch": 2.69,
      "learning_rate": 6.0974384005860736e-05,
      "loss": 1.1124,
      "step": 159
    },
    {
      "epoch": 2.71,
      "learning_rate": 5.9461589555346056e-05,
      "loss": 1.0811,
      "step": 160
    },
    {
      "epoch": 2.72,
      "learning_rate": 5.7961919595327204e-05,
      "loss": 1.0916,
      "step": 161
    },
    {
      "epoch": 2.74,
      "learning_rate": 5.647567444441129e-05,
      "loss": 1.0218,
      "step": 162
    },
    {
      "epoch": 2.76,
      "learning_rate": 5.500315173280059e-05,
      "loss": 1.0776,
      "step": 163
    },
    {
      "epoch": 2.78,
      "learning_rate": 5.354464634269017e-05,
      "loss": 1.0637,
      "step": 164
    },
    {
      "epoch": 2.79,
      "learning_rate": 5.210045034921583e-05,
      "loss": 1.0057,
      "step": 165
    },
    {
      "epoch": 2.81,
      "learning_rate": 5.0670852961964176e-05,
      "loss": 1.09,
      "step": 166
    },
    {
      "epoch": 2.83,
      "learning_rate": 4.925614046705648e-05,
      "loss": 1.0644,
      "step": 167
    },
    {
      "epoch": 2.84,
      "learning_rate": 4.785659616981813e-05,
      "loss": 0.9983,
      "step": 168
    },
    {
      "epoch": 2.86,
      "learning_rate": 4.64725003380447e-05,
      "loss": 1.0903,
      "step": 169
    },
    {
      "epoch": 2.88,
      "learning_rate": 4.510413014587692e-05,
      "loss": 1.051,
      "step": 170
    },
    {
      "epoch": 2.9,
      "learning_rate": 4.375175961829415e-05,
      "loss": 1.0629,
      "step": 171
    },
    {
      "epoch": 2.91,
      "learning_rate": 4.2415659576239844e-05,
      "loss": 1.0092,
      "step": 172
    },
    {
      "epoch": 2.93,
      "learning_rate": 4.109609758238714e-05,
      "loss": 1.1383,
      "step": 173
    },
    {
      "epoch": 2.95,
      "learning_rate": 3.979333788755842e-05,
      "loss": 1.1097,
      "step": 174
    },
    {
      "epoch": 2.97,
      "learning_rate": 3.850764137780674e-05,
      "loss": 1.1173,
      "step": 175
    },
    {
      "epoch": 2.98,
      "learning_rate": 3.723926552217219e-05,
      "loss": 1.085,
      "step": 176
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.598846432112182e-05,
      "loss": 1.0868,
      "step": 177
    },
    {
      "epoch": 3.02,
      "learning_rate": 3.475548825568445e-05,
      "loss": 1.0675,
      "step": 178
    }
  ],
  "logging_steps": 1,
  "max_steps": 232,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 1.5793187263900287e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}