{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9980022197558268,
  "eval_steps": 500,
  "global_step": 281,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 1.9832738637924194,
      "learning_rate": 1e-05,
      "loss": 0.5668,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.9458171129226685,
      "learning_rate": 1e-05,
      "loss": 0.527,
      "step": 2
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.8415082097053528,
      "learning_rate": 1e-05,
      "loss": 0.5078,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.839102029800415,
      "learning_rate": 1e-05,
      "loss": 0.5188,
      "step": 4
    },
    {
      "epoch": 0.02,
      "grad_norm": 2.0685036182403564,
      "learning_rate": 1e-05,
      "loss": 0.5227,
      "step": 5
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.8744383454322815,
      "learning_rate": 1e-05,
      "loss": 0.5149,
      "step": 6
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.6805229187011719,
      "learning_rate": 1e-05,
      "loss": 0.4921,
      "step": 7
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.070035696029663,
      "learning_rate": 1e-05,
      "loss": 0.4625,
      "step": 8
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.6167441010475159,
      "learning_rate": 1e-05,
      "loss": 0.4819,
      "step": 9
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.6767921447753906,
      "learning_rate": 1e-05,
      "loss": 0.4884,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.1164625883102417,
      "learning_rate": 1e-05,
      "loss": 0.4896,
      "step": 11
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.8692913055419922,
      "learning_rate": 1e-05,
      "loss": 0.4893,
      "step": 12
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.41812172532081604,
      "learning_rate": 1e-05,
      "loss": 0.493,
      "step": 13
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.49972113966941833,
      "learning_rate": 1e-05,
      "loss": 0.5021,
      "step": 14
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.5513176321983337,
      "learning_rate": 1e-05,
      "loss": 0.4859,
      "step": 15
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.7295736074447632,
      "learning_rate": 1e-05,
      "loss": 0.4439,
      "step": 16
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.45257988572120667,
      "learning_rate": 1e-05,
      "loss": 0.4719,
      "step": 17
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.535362720489502,
      "learning_rate": 1e-05,
      "loss": 0.4823,
      "step": 18
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.5812283158302307,
      "learning_rate": 1e-05,
      "loss": 0.4773,
      "step": 19
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.1126588582992554,
      "learning_rate": 1e-05,
      "loss": 0.4477,
      "step": 20
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.44774916768074036,
      "learning_rate": 1e-05,
      "loss": 0.4627,
      "step": 21
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.4647807478904724,
      "learning_rate": 1e-05,
      "loss": 0.4783,
      "step": 22
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.7982929944992065,
      "learning_rate": 1e-05,
      "loss": 0.4654,
      "step": 23
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.758514940738678,
      "learning_rate": 1e-05,
      "loss": 0.4453,
      "step": 24
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.47228220105171204,
      "learning_rate": 1e-05,
      "loss": 0.4799,
      "step": 25
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.5305970907211304,
      "learning_rate": 1e-05,
      "loss": 0.476,
      "step": 26
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.6885311603546143,
      "learning_rate": 1e-05,
      "loss": 0.4396,
      "step": 27
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.9302653074264526,
      "learning_rate": 1e-05,
      "loss": 0.4251,
      "step": 28
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.44655555486679077,
      "learning_rate": 1e-05,
      "loss": 0.4753,
      "step": 29
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.5989087820053101,
      "learning_rate": 1e-05,
      "loss": 0.4533,
      "step": 30
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.5649559497833252,
      "learning_rate": 1e-05,
      "loss": 0.4757,
      "step": 31
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.6152830719947815,
      "learning_rate": 1e-05,
      "loss": 0.4625,
      "step": 32
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.550224244594574,
      "learning_rate": 1e-05,
      "loss": 0.4634,
      "step": 33
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.6088584661483765,
      "learning_rate": 1e-05,
      "loss": 0.4617,
      "step": 34
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.7076464891433716,
      "learning_rate": 1e-05,
      "loss": 0.4538,
      "step": 35
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.5110942125320435,
      "learning_rate": 1e-05,
      "loss": 0.4279,
      "step": 36
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.9704209566116333,
      "learning_rate": 1e-05,
      "loss": 0.4765,
      "step": 37
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.5762418508529663,
      "learning_rate": 1e-05,
      "loss": 0.4633,
      "step": 38
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.6088821291923523,
      "learning_rate": 1e-05,
      "loss": 0.4441,
      "step": 39
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.6568654775619507,
      "learning_rate": 1e-05,
      "loss": 0.4464,
      "step": 40
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.5699493885040283,
      "learning_rate": 1e-05,
      "loss": 0.4626,
      "step": 41
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.4806917905807495,
      "learning_rate": 1e-05,
      "loss": 0.4769,
      "step": 42
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.5842737555503845,
      "learning_rate": 1e-05,
      "loss": 0.4506,
      "step": 43
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.7217497825622559,
      "learning_rate": 1e-05,
      "loss": 0.444,
      "step": 44
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.4894813597202301,
      "learning_rate": 1e-05,
      "loss": 0.473,
      "step": 45
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.4453926086425781,
      "learning_rate": 1e-05,
      "loss": 0.4619,
      "step": 46
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.7311206459999084,
      "learning_rate": 1e-05,
      "loss": 0.4492,
      "step": 47
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.1100599765777588,
      "learning_rate": 1e-05,
      "loss": 0.4111,
      "step": 48
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.5209776163101196,
      "learning_rate": 1e-05,
      "loss": 0.458,
      "step": 49
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.5144385099411011,
      "learning_rate": 1e-05,
      "loss": 0.4591,
      "step": 50
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.505511462688446,
      "learning_rate": 1e-05,
      "loss": 0.4557,
      "step": 51
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.8851682543754578,
      "learning_rate": 1e-05,
      "loss": 0.4229,
      "step": 52
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.43110543489456177,
      "learning_rate": 1e-05,
      "loss": 0.4799,
      "step": 53
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.7971346378326416,
      "learning_rate": 1e-05,
      "loss": 0.4519,
      "step": 54
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.8832608461380005,
      "learning_rate": 1e-05,
      "loss": 0.4339,
      "step": 55
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.1655290126800537,
      "learning_rate": 1e-05,
      "loss": 0.3927,
      "step": 56
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.42177918553352356,
      "learning_rate": 1e-05,
      "loss": 0.441,
      "step": 57
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.520730197429657,
      "learning_rate": 1e-05,
      "loss": 0.4636,
      "step": 58
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.585159420967102,
      "learning_rate": 1e-05,
      "loss": 0.4649,
      "step": 59
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.1990737915039062,
      "learning_rate": 1e-05,
      "loss": 0.4255,
      "step": 60
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.6422901749610901,
      "learning_rate": 1e-05,
      "loss": 0.4672,
      "step": 61
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.4904385507106781,
      "learning_rate": 1e-05,
      "loss": 0.4679,
      "step": 62
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.6044018864631653,
      "learning_rate": 1e-05,
      "loss": 0.4524,
      "step": 63
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.6931694746017456,
      "learning_rate": 1e-05,
      "loss": 0.4267,
      "step": 64
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.42534416913986206,
      "learning_rate": 1e-05,
      "loss": 0.4733,
      "step": 65
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.509138286113739,
      "learning_rate": 1e-05,
      "loss": 0.442,
      "step": 66
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.6317541003227234,
      "learning_rate": 1e-05,
      "loss": 0.4461,
      "step": 67
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.7053780555725098,
      "learning_rate": 1e-05,
      "loss": 0.4328,
      "step": 68
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.4144704043865204,
      "learning_rate": 1e-05,
      "loss": 0.4713,
      "step": 69
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.6023023724555969,
      "learning_rate": 1e-05,
      "loss": 0.4686,
      "step": 70
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.6286914348602295,
      "learning_rate": 1e-05,
      "loss": 0.43,
      "step": 71
    },
    {
      "epoch": 0.26,
      "grad_norm": 1.7562507390975952,
      "learning_rate": 1e-05,
      "loss": 0.4354,
      "step": 72
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.4561932682991028,
      "learning_rate": 1e-05,
      "loss": 0.454,
      "step": 73
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.7432600855827332,
      "learning_rate": 1e-05,
      "loss": 0.4556,
      "step": 74
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.6152967810630798,
      "learning_rate": 1e-05,
      "loss": 0.4367,
      "step": 75
    },
    {
      "epoch": 0.27,
      "grad_norm": 1.1905455589294434,
      "learning_rate": 1e-05,
      "loss": 0.45,
      "step": 76
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.46641895174980164,
      "learning_rate": 1e-05,
      "loss": 0.4584,
      "step": 77
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5764038562774658,
      "learning_rate": 1e-05,
      "loss": 0.4461,
      "step": 78
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.5731326341629028,
      "learning_rate": 1e-05,
      "loss": 0.4566,
      "step": 79
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.9596810936927795,
      "learning_rate": 1e-05,
      "loss": 0.4488,
      "step": 80
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.42653772234916687,
      "learning_rate": 1e-05,
      "loss": 0.466,
      "step": 81
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.4516827464103699,
      "learning_rate": 1e-05,
      "loss": 0.4555,
      "step": 82
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.5996358394622803,
      "learning_rate": 1e-05,
      "loss": 0.444,
      "step": 83
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.9187763929367065,
      "learning_rate": 1e-05,
      "loss": 0.3769,
      "step": 84
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.4854133725166321,
      "learning_rate": 1e-05,
      "loss": 0.4711,
      "step": 85
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.4637454152107239,
      "learning_rate": 1e-05,
      "loss": 0.4636,
      "step": 86
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.5341816544532776,
      "learning_rate": 1e-05,
      "loss": 0.4358,
      "step": 87
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.7789736390113831,
      "learning_rate": 1e-05,
      "loss": 0.4088,
      "step": 88
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.3757864534854889,
      "learning_rate": 1e-05,
      "loss": 0.4654,
      "step": 89
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.5197014808654785,
      "learning_rate": 1e-05,
      "loss": 0.4434,
      "step": 90
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.5166840553283691,
      "learning_rate": 1e-05,
      "loss": 0.4474,
      "step": 91
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.6799307465553284,
      "learning_rate": 1e-05,
      "loss": 0.4435,
      "step": 92
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.49623581767082214,
      "learning_rate": 1e-05,
      "loss": 0.4636,
      "step": 93
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.5105348229408264,
      "learning_rate": 1e-05,
      "loss": 0.4297,
      "step": 94
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.5134614706039429,
      "learning_rate": 1e-05,
      "loss": 0.4345,
      "step": 95
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.6770723462104797,
      "learning_rate": 1e-05,
      "loss": 0.4181,
      "step": 96
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.580609917640686,
      "learning_rate": 1e-05,
      "loss": 0.4648,
      "step": 97
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.5286965370178223,
      "learning_rate": 1e-05,
      "loss": 0.4329,
      "step": 98
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.5784552693367004,
      "learning_rate": 1e-05,
      "loss": 0.4512,
      "step": 99
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.0502313375473022,
      "learning_rate": 1e-05,
      "loss": 0.4105,
      "step": 100
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.40381279587745667,
      "learning_rate": 1e-05,
      "loss": 0.4508,
      "step": 101
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.5827537775039673,
      "learning_rate": 1e-05,
      "loss": 0.4464,
      "step": 102
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.536665141582489,
      "learning_rate": 1e-05,
      "loss": 0.4382,
      "step": 103
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.6119434237480164,
      "learning_rate": 1e-05,
      "loss": 0.4246,
      "step": 104
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.3719892203807831,
      "learning_rate": 1e-05,
      "loss": 0.4596,
      "step": 105
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.4976269006729126,
      "learning_rate": 1e-05,
      "loss": 0.4563,
      "step": 106
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.6612491011619568,
      "learning_rate": 1e-05,
      "loss": 0.4364,
      "step": 107
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.6775332093238831,
      "learning_rate": 1e-05,
      "loss": 0.4193,
      "step": 108
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.8782187700271606,
      "learning_rate": 1e-05,
      "loss": 0.4464,
      "step": 109
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.5137239694595337,
      "learning_rate": 1e-05,
      "loss": 0.4595,
      "step": 110
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.5837895274162292,
      "learning_rate": 1e-05,
      "loss": 0.4553,
      "step": 111
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.0835506916046143,
      "learning_rate": 1e-05,
      "loss": 0.4225,
      "step": 112
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.4510575234889984,
      "learning_rate": 1e-05,
      "loss": 0.4524,
      "step": 113
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.5319203734397888,
      "learning_rate": 1e-05,
      "loss": 0.4589,
      "step": 114
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.48096978664398193,
      "learning_rate": 1e-05,
      "loss": 0.4504,
      "step": 115
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.7882823944091797,
      "learning_rate": 1e-05,
      "loss": 0.4282,
      "step": 116
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.4668346643447876,
      "learning_rate": 1e-05,
      "loss": 0.4649,
      "step": 117
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.523875892162323,
      "learning_rate": 1e-05,
      "loss": 0.4399,
      "step": 118
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.7798515558242798,
      "learning_rate": 1e-05,
      "loss": 0.4293,
      "step": 119
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.6797575950622559,
      "learning_rate": 1e-05,
      "loss": 0.4334,
      "step": 120
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.372816801071167,
      "learning_rate": 1e-05,
      "loss": 0.4552,
      "step": 121
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.43806058168411255,
      "learning_rate": 1e-05,
      "loss": 0.4533,
      "step": 122
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.5015602111816406,
      "learning_rate": 1e-05,
      "loss": 0.452,
      "step": 123
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.8157485127449036,
      "learning_rate": 1e-05,
      "loss": 0.4266,
      "step": 124
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.5614244937896729,
      "learning_rate": 1e-05,
      "loss": 0.4498,
      "step": 125
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.5229978561401367,
      "learning_rate": 1e-05,
      "loss": 0.4435,
      "step": 126
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.5133040547370911,
      "learning_rate": 1e-05,
      "loss": 0.4365,
      "step": 127
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.9675442576408386,
      "learning_rate": 1e-05,
      "loss": 0.3885,
      "step": 128
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.3860965669155121,
      "learning_rate": 1e-05,
      "loss": 0.449,
      "step": 129
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.49970802664756775,
      "learning_rate": 1e-05,
      "loss": 0.43,
      "step": 130
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.5704831480979919,
      "learning_rate": 1e-05,
      "loss": 0.447,
      "step": 131
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.9462538361549377,
      "learning_rate": 1e-05,
      "loss": 0.4076,
      "step": 132
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.4560747742652893,
      "learning_rate": 1e-05,
      "loss": 0.449,
      "step": 133
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.4721296429634094,
      "learning_rate": 1e-05,
      "loss": 0.4324,
      "step": 134
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.5056577920913696,
      "learning_rate": 1e-05,
      "loss": 0.4406,
      "step": 135
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.5873216390609741,
      "learning_rate": 1e-05,
      "loss": 0.4111,
      "step": 136
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.3777410686016083,
      "learning_rate": 1e-05,
      "loss": 0.4656,
      "step": 137
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.4282991588115692,
      "learning_rate": 1e-05,
      "loss": 0.4189,
      "step": 138
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.4305042624473572,
      "learning_rate": 1e-05,
      "loss": 0.4523,
      "step": 139
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.6944953203201294,
      "learning_rate": 1e-05,
      "loss": 0.4284,
      "step": 140
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.4139988124370575,
      "learning_rate": 1e-05,
      "loss": 0.4431,
      "step": 141
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.5378341674804688,
      "learning_rate": 1e-05,
      "loss": 0.4527,
      "step": 142
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.5123686790466309,
      "learning_rate": 1e-05,
      "loss": 0.4361,
      "step": 143
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.7670745849609375,
      "learning_rate": 1e-05,
      "loss": 0.4221,
      "step": 144
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.7429537773132324,
      "learning_rate": 1e-05,
      "loss": 0.438,
      "step": 145
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.5465981960296631,
      "learning_rate": 1e-05,
      "loss": 0.4515,
      "step": 146
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.5833389163017273,
      "learning_rate": 1e-05,
      "loss": 0.4331,
      "step": 147
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.8879693746566772,
      "learning_rate": 1e-05,
      "loss": 0.4137,
      "step": 148
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.40366512537002563,
      "learning_rate": 1e-05,
      "loss": 0.4505,
      "step": 149
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.775814414024353,
      "learning_rate": 1e-05,
      "loss": 0.4291,
      "step": 150
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.5580259561538696,
      "learning_rate": 1e-05,
      "loss": 0.4311,
      "step": 151
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.0347977876663208,
      "learning_rate": 1e-05,
      "loss": 0.4054,
      "step": 152
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.4463992714881897,
      "learning_rate": 1e-05,
      "loss": 0.4631,
      "step": 153
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5559613108634949,
      "learning_rate": 1e-05,
      "loss": 0.4339,
      "step": 154
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.4996100068092346,
      "learning_rate": 1e-05,
      "loss": 0.4522,
      "step": 155
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.639824390411377,
      "learning_rate": 1e-05,
      "loss": 0.432,
      "step": 156
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.38671043515205383,
      "learning_rate": 1e-05,
      "loss": 0.4665,
      "step": 157
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.4905610978603363,
      "learning_rate": 1e-05,
      "loss": 0.4532,
      "step": 158
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.6270061731338501,
      "learning_rate": 1e-05,
      "loss": 0.4406,
      "step": 159
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.789944589138031,
      "learning_rate": 1e-05,
      "loss": 0.3897,
      "step": 160
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.83070969581604,
      "learning_rate": 1e-05,
      "loss": 0.4747,
      "step": 161
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.4273388087749481,
      "learning_rate": 1e-05,
      "loss": 0.4414,
      "step": 162
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.5557335019111633,
      "learning_rate": 1e-05,
      "loss": 0.4322,
      "step": 163
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.5714684724807739,
      "learning_rate": 1e-05,
      "loss": 0.4293,
      "step": 164
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.3697482645511627,
      "learning_rate": 1e-05,
      "loss": 0.4584,
      "step": 165
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.45178842544555664,
      "learning_rate": 1e-05,
      "loss": 0.4481,
      "step": 166
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.5978602170944214,
      "learning_rate": 1e-05,
      "loss": 0.4082,
      "step": 167
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.6311948895454407,
      "learning_rate": 1e-05,
      "loss": 0.422,
      "step": 168
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3639450669288635,
      "learning_rate": 1e-05,
      "loss": 0.4388,
      "step": 169
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.49596938490867615,
      "learning_rate": 1e-05,
      "loss": 0.4453,
      "step": 170
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.49753278493881226,
      "learning_rate": 1e-05,
      "loss": 0.4276,
      "step": 171
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.770423948764801,
      "learning_rate": 1e-05,
      "loss": 0.4273,
      "step": 172
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.43721652030944824,
      "learning_rate": 1e-05,
      "loss": 0.4556,
      "step": 173
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.44143715500831604,
      "learning_rate": 1e-05,
      "loss": 0.4579,
      "step": 174
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.6291133165359497,
      "learning_rate": 1e-05,
      "loss": 0.4237,
      "step": 175
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.909862220287323,
      "learning_rate": 1e-05,
      "loss": 0.3763,
      "step": 176
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.43771499395370483,
      "learning_rate": 1e-05,
      "loss": 0.4402,
      "step": 177
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.5810952186584473,
      "learning_rate": 1e-05,
      "loss": 0.4359,
      "step": 178
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.48108798265457153,
      "learning_rate": 1e-05,
      "loss": 0.4488,
      "step": 179
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.7238831520080566,
      "learning_rate": 1e-05,
      "loss": 0.4207,
      "step": 180
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.4471929371356964,
      "learning_rate": 1e-05,
      "loss": 0.4391,
      "step": 181
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.46182355284690857,
      "learning_rate": 1e-05,
      "loss": 0.4405,
      "step": 182
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5112327337265015,
      "learning_rate": 1e-05,
      "loss": 0.4404,
      "step": 183
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.7985268235206604,
      "learning_rate": 1e-05,
      "loss": 0.3994,
      "step": 184
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.4040653705596924,
      "learning_rate": 1e-05,
      "loss": 0.451,
      "step": 185
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.4301965832710266,
      "learning_rate": 1e-05,
      "loss": 0.4472,
      "step": 186
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.6474922895431519,
      "learning_rate": 1e-05,
      "loss": 0.4331,
      "step": 187
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.8670556545257568,
      "learning_rate": 1e-05,
      "loss": 0.4318,
      "step": 188
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.5550181269645691,
      "learning_rate": 1e-05,
      "loss": 0.4618,
      "step": 189
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.44763821363449097,
      "learning_rate": 1e-05,
      "loss": 0.4515,
      "step": 190
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.5281996726989746,
      "learning_rate": 1e-05,
      "loss": 0.4094,
      "step": 191
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.6521373987197876,
      "learning_rate": 1e-05,
      "loss": 0.4202,
      "step": 192
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.4100494682788849,
      "learning_rate": 1e-05,
      "loss": 0.4454,
      "step": 193
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.5752792954444885,
      "learning_rate": 1e-05,
      "loss": 0.4488,
      "step": 194
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.6012833118438721,
      "learning_rate": 1e-05,
      "loss": 0.4329,
      "step": 195
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.6597912311553955,
      "learning_rate": 1e-05,
      "loss": 0.4157,
      "step": 196
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.4282044768333435,
      "learning_rate": 1e-05,
      "loss": 0.434,
      "step": 197
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.5571615099906921,
      "learning_rate": 1e-05,
      "loss": 0.4482,
      "step": 198
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.5163079500198364,
      "learning_rate": 1e-05,
      "loss": 0.4304,
      "step": 199
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.8305063843727112,
      "learning_rate": 1e-05,
      "loss": 0.4022,
      "step": 200
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.4464957118034363,
      "learning_rate": 1e-05,
      "loss": 0.4503,
      "step": 201
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.46648305654525757,
      "learning_rate": 1e-05,
      "loss": 0.4489,
      "step": 202
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.6516060829162598,
      "learning_rate": 1e-05,
      "loss": 0.4342,
      "step": 203
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.6265027523040771,
      "learning_rate": 1e-05,
      "loss": 0.4175,
      "step": 204
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.4391736686229706,
      "learning_rate": 1e-05,
      "loss": 0.4586,
      "step": 205
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.4877251386642456,
      "learning_rate": 1e-05,
      "loss": 0.4369,
      "step": 206
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.5316377282142639,
      "learning_rate": 1e-05,
      "loss": 0.4319,
      "step": 207
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.0411840677261353,
      "learning_rate": 1e-05,
      "loss": 0.4256,
      "step": 208
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.5061484575271606,
      "learning_rate": 1e-05,
      "loss": 0.4319,
      "step": 209
    },
    {
      "epoch": 0.75,
      "grad_norm": 2.133131980895996,
      "learning_rate": 1e-05,
      "loss": 0.4485,
      "step": 210
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.5447837114334106,
      "learning_rate": 1e-05,
      "loss": 0.4416,
      "step": 211
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.7947729825973511,
      "learning_rate": 1e-05,
      "loss": 0.4075,
      "step": 212
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.44168147444725037,
      "learning_rate": 1e-05,
      "loss": 0.4526,
      "step": 213
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.4681871235370636,
      "learning_rate": 1e-05,
      "loss": 0.4384,
      "step": 214
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.568696141242981,
      "learning_rate": 1e-05,
      "loss": 0.4309,
      "step": 215
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.676292896270752,
      "learning_rate": 1e-05,
      "loss": 0.3851,
      "step": 216
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.42382004857063293,
      "learning_rate": 1e-05,
      "loss": 0.4657,
      "step": 217
    },
    {
      "epoch": 0.77,
      "grad_norm": 1.7760436534881592,
      "learning_rate": 1e-05,
      "loss": 0.4471,
      "step": 218
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.570806622505188,
      "learning_rate": 1e-05,
      "loss": 0.4307,
      "step": 219
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.913851261138916,
      "learning_rate": 1e-05,
      "loss": 0.4132,
      "step": 220
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.4583609700202942,
      "learning_rate": 1e-05,
      "loss": 0.4508,
      "step": 221
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.5516847968101501,
      "learning_rate": 1e-05,
      "loss": 0.4521,
      "step": 222
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.526192843914032,
      "learning_rate": 1e-05,
      "loss": 0.4473,
      "step": 223
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.852449357509613,
      "learning_rate": 1e-05,
      "loss": 0.4297,
      "step": 224
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.8044112920761108,
      "learning_rate": 1e-05,
      "loss": 0.4392,
      "step": 225
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.4642798602581024,
      "learning_rate": 1e-05,
      "loss": 0.4188,
      "step": 226
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.5552318692207336,
      "learning_rate": 1e-05,
      "loss": 0.4447,
      "step": 227
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.7442976832389832,
      "learning_rate": 1e-05,
      "loss": 0.404,
      "step": 228
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.5462561845779419,
      "learning_rate": 1e-05,
      "loss": 0.4434,
      "step": 229
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.4776632785797119,
      "learning_rate": 1e-05,
      "loss": 0.4487,
      "step": 230
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.8107818365097046,
      "learning_rate": 1e-05,
      "loss": 0.4256,
      "step": 231
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.7552162408828735,
      "learning_rate": 1e-05,
      "loss": 0.4116,
      "step": 232
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.5497348308563232,
      "learning_rate": 1e-05,
      "loss": 0.4397,
      "step": 233
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.5682913661003113,
      "learning_rate": 1e-05,
      "loss": 0.4432,
      "step": 234
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.6614949703216553,
      "learning_rate": 1e-05,
      "loss": 0.4408,
      "step": 235
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.8305519223213196,
      "learning_rate": 1e-05,
      "loss": 0.4217,
      "step": 236
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.42773041129112244,
      "learning_rate": 1e-05,
      "loss": 0.4517,
      "step": 237
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.771364688873291,
      "learning_rate": 1e-05,
      "loss": 0.4258,
      "step": 238
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.7548272013664246,
      "learning_rate": 1e-05,
      "loss": 0.4329,
      "step": 239
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.673877477645874,
      "learning_rate": 1e-05,
      "loss": 0.4241,
      "step": 240
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.42514756321907043,
      "learning_rate": 1e-05,
      "loss": 0.45,
      "step": 241
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.48240309953689575,
      "learning_rate": 1e-05,
      "loss": 0.4253,
      "step": 242
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.5749714970588684,
      "learning_rate": 1e-05,
      "loss": 0.4459,
      "step": 243
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.6530050039291382,
      "learning_rate": 1e-05,
      "loss": 0.412,
      "step": 244
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.690308690071106,
      "learning_rate": 1e-05,
      "loss": 0.4205,
      "step": 245
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.40998125076293945,
      "learning_rate": 1e-05,
      "loss": 0.4478,
      "step": 246
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.586068332195282,
      "learning_rate": 1e-05,
      "loss": 0.4115,
      "step": 247
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.6974151730537415,
      "learning_rate": 1e-05,
      "loss": 0.3864,
      "step": 248
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.4335140883922577,
      "learning_rate": 1e-05,
      "loss": 0.4669,
      "step": 249
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.44653356075286865,
      "learning_rate": 1e-05,
      "loss": 0.4139,
      "step": 250
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.750583291053772,
      "learning_rate": 1e-05,
      "loss": 0.4152,
      "step": 251
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.7355042099952698,
      "learning_rate": 1e-05,
      "loss": 0.4149,
      "step": 252
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.5112454295158386,
      "learning_rate": 1e-05,
      "loss": 0.4444,
      "step": 253
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.7759450674057007,
      "learning_rate": 1e-05,
      "loss": 0.4474,
      "step": 254
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.6432544589042664,
      "learning_rate": 1e-05,
      "loss": 0.4555,
      "step": 255
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.723268985748291,
      "learning_rate": 1e-05,
      "loss": 0.3851,
      "step": 256
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.4089478850364685,
      "learning_rate": 1e-05,
      "loss": 0.447,
      "step": 257
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.5243247747421265,
      "learning_rate": 1e-05,
      "loss": 0.4565,
      "step": 258
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.776333212852478,
      "learning_rate": 1e-05,
      "loss": 0.4145,
      "step": 259
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.4910255968570709,
      "learning_rate": 1e-05,
      "loss": 0.4163,
      "step": 260
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.46245935559272766,
      "learning_rate": 1e-05,
      "loss": 0.4669,
      "step": 261
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.5398200154304504,
      "learning_rate": 1e-05,
      "loss": 0.4321,
      "step": 262
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.8473610281944275,
      "learning_rate": 1e-05,
      "loss": 0.3985,
      "step": 263
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.8328168988227844,
      "learning_rate": 1e-05,
      "loss": 0.3997,
      "step": 264
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.5752345323562622,
      "learning_rate": 1e-05,
      "loss": 0.4513,
      "step": 265
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.45842844247817993,
      "learning_rate": 1e-05,
      "loss": 0.4268,
      "step": 266
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.5272755026817322,
      "learning_rate": 1e-05,
      "loss": 0.4205,
      "step": 267
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.6478350758552551,
      "learning_rate": 1e-05,
      "loss": 0.417,
      "step": 268
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.4239070415496826,
      "learning_rate": 1e-05,
      "loss": 0.4369,
      "step": 269
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.48916614055633545,
      "learning_rate": 1e-05,
      "loss": 0.443,
      "step": 270
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.6267674565315247,
      "learning_rate": 1e-05,
      "loss": 0.4152,
      "step": 271
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.5838894844055176,
      "learning_rate": 1e-05,
      "loss": 0.4177,
      "step": 272
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.40867578983306885,
      "learning_rate": 1e-05,
      "loss": 0.445,
      "step": 273
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.6627911925315857,
      "learning_rate": 1e-05,
      "loss": 0.4379,
      "step": 274
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.5618704557418823,
      "learning_rate": 1e-05,
      "loss": 0.4188,
      "step": 275
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.64666748046875,
      "learning_rate": 1e-05,
      "loss": 0.4159,
      "step": 276
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.5590734481811523,
      "learning_rate": 1e-05,
      "loss": 0.4416,
      "step": 277
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.4989932179450989,
      "learning_rate": 1e-05,
      "loss": 0.4428,
      "step": 278
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.6639497876167297,
      "learning_rate": 1e-05,
      "loss": 0.4064,
      "step": 279
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.6805359125137329,
      "learning_rate": 1e-05,
      "loss": 0.4119,
      "step": 280
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6433411836624146,
      "learning_rate": 1e-05,
      "loss": 0.4374,
      "step": 281
    },
    {
      "epoch": 1.0,
      "step": 281,
      "total_flos": 423312888037376.0,
      "train_loss": 0.44328434908517317,
      "train_runtime": 88939.3662,
      "train_samples_per_second": 0.051,
      "train_steps_per_second": 0.003
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 281,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 30,
  "total_flos": 423312888037376.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}