{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 189,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 1.08417234214877,
      "learning_rate": 0.0,
      "loss": 0.5767,
      "step": 1
    },
    {
      "epoch": 0.032,
      "grad_norm": 1.0469008257052523,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.5511,
      "step": 2
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.983282752070103,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.4992,
      "step": 3
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.872051375279908,
      "learning_rate": 5e-06,
      "loss": 0.4061,
      "step": 4
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.893228824528603,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.4181,
      "step": 5
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.9220468625068179,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.4488,
      "step": 6
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.7934650361234915,
      "learning_rate": 1e-05,
      "loss": 0.412,
      "step": 7
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.5840477320156379,
      "learning_rate": 9.999336914672622e-06,
      "loss": 0.417,
      "step": 8
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.505453502147165,
      "learning_rate": 9.997347854104775e-06,
      "loss": 0.5068,
      "step": 9
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.5244034547886003,
      "learning_rate": 9.994033404481737e-06,
      "loss": 0.5052,
      "step": 10
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.43986559011579357,
      "learning_rate": 9.98939454258703e-06,
      "loss": 0.498,
      "step": 11
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.6155944923795194,
      "learning_rate": 9.98343263551454e-06,
      "loss": 0.4757,
      "step": 12
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.6010488091076704,
      "learning_rate": 9.97614944026565e-06,
      "loss": 0.4733,
      "step": 13
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.6021634931994316,
      "learning_rate": 9.967547103231432e-06,
      "loss": 0.4258,
      "step": 14
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.6482124300684173,
      "learning_rate": 9.957628159560088e-06,
      "loss": 0.5263,
      "step": 15
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.554249479130026,
      "learning_rate": 9.946395532409847e-06,
      "loss": 0.4806,
      "step": 16
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.5973792849680928,
      "learning_rate": 9.933852532087492e-06,
      "loss": 0.4736,
      "step": 17
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.41453038423395644,
      "learning_rate": 9.920002855072784e-06,
      "loss": 0.4289,
      "step": 18
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.4620366674199325,
      "learning_rate": 9.904850582929112e-06,
      "loss": 0.4864,
      "step": 19
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.35504897921565515,
      "learning_rate": 9.888400181100621e-06,
      "loss": 0.4219,
      "step": 20
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.31658139671010693,
      "learning_rate": 9.870656497596242e-06,
      "loss": 0.3972,
      "step": 21
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.3650004342330343,
      "learning_rate": 9.851624761560943e-06,
      "loss": 0.5571,
      "step": 22
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.3257963763381936,
      "learning_rate": 9.831310581734687e-06,
      "loss": 0.4769,
      "step": 23
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.325775920332389,
      "learning_rate": 9.809719944799512e-06,
      "loss": 0.4961,
      "step": 24
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.31671335015470503,
      "learning_rate": 9.786859213615222e-06,
      "loss": 0.4357,
      "step": 25
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.3281761016809856,
      "learning_rate": 9.762735125344227e-06,
      "loss": 0.4502,
      "step": 26
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.3554086729723955,
      "learning_rate": 9.737354789466068e-06,
      "loss": 0.4768,
      "step": 27
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.3865446724293106,
      "learning_rate": 9.710725685682222e-06,
      "loss": 0.4515,
      "step": 28
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.37003410749958987,
      "learning_rate": 9.682855661711803e-06,
      "loss": 0.4432,
      "step": 29
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.31180238962223594,
      "learning_rate": 9.653752930978794e-06,
      "loss": 0.463,
      "step": 30
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.3252391994136198,
      "learning_rate": 9.623426070191521e-06,
      "loss": 0.4087,
      "step": 31
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.31056365314104256,
      "learning_rate": 9.591884016815063e-06,
      "loss": 0.4254,
      "step": 32
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.32735595897929803,
      "learning_rate": 9.559136066437319e-06,
      "loss": 0.5447,
      "step": 33
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.3100995737340131,
      "learning_rate": 9.52519187002958e-06,
      "loss": 0.4321,
      "step": 34
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.2936011999974949,
      "learning_rate": 9.49006143110233e-06,
      "loss": 0.4156,
      "step": 35
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.29737459640312214,
      "learning_rate": 9.453755102757168e-06,
      "loss": 0.493,
      "step": 36
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.2728926853035778,
      "learning_rate": 9.4162835846357e-06,
      "loss": 0.4392,
      "step": 37
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.3272565049177079,
      "learning_rate": 9.377657919766307e-06,
      "loss": 0.491,
      "step": 38
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.2822226280837269,
      "learning_rate": 9.33788949130972e-06,
      "loss": 0.4266,
      "step": 39
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.3438862449071104,
      "learning_rate": 9.296990019204336e-06,
      "loss": 0.4819,
      "step": 40
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.3322076503353557,
      "learning_rate": 9.254971556712314e-06,
      "loss": 0.4597,
      "step": 41
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.3262451955412676,
      "learning_rate": 9.21184648686741e-06,
      "loss": 0.4891,
      "step": 42
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.27720763525504155,
      "learning_rate": 9.167627518825651e-06,
      "loss": 0.4262,
      "step": 43
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.291234979530001,
      "learning_rate": 9.122327684119883e-06,
      "loss": 0.3755,
      "step": 44
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.2910628070235976,
      "learning_rate": 9.075960332819314e-06,
      "loss": 0.4294,
      "step": 45
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.3184275314698029,
      "learning_rate": 9.028539129595199e-06,
      "loss": 0.5769,
      "step": 46
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.2722946981234995,
      "learning_rate": 8.980078049693785e-06,
      "loss": 0.4019,
      "step": 47
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.29789872299343384,
      "learning_rate": 8.930591374817757e-06,
      "loss": 0.4095,
      "step": 48
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.3287733650721115,
      "learning_rate": 8.88009368891734e-06,
      "loss": 0.5409,
      "step": 49
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.30019238586389524,
      "learning_rate": 8.828599873892351e-06,
      "loss": 0.4375,
      "step": 50
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.31598561474060005,
      "learning_rate": 8.776125105206433e-06,
      "loss": 0.4902,
      "step": 51
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.31172751963714107,
      "learning_rate": 8.722684847414771e-06,
      "loss": 0.5176,
      "step": 52
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.2807830457433651,
      "learning_rate": 8.668294849606626e-06,
      "loss": 0.4707,
      "step": 53
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.2960941109569259,
      "learning_rate": 8.612971140764e-06,
      "loss": 0.4283,
      "step": 54
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.3299368286152574,
      "learning_rate": 8.556730025037819e-06,
      "loss": 0.4088,
      "step": 55
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.26428803479637797,
      "learning_rate": 8.499588076943036e-06,
      "loss": 0.3912,
      "step": 56
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.3009234600421325,
      "learning_rate": 8.441562136474028e-06,
      "loss": 0.4067,
      "step": 57
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.3609455923426209,
      "learning_rate": 8.38266930414179e-06,
      "loss": 0.4898,
      "step": 58
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.31387386515515087,
      "learning_rate": 8.322926935934323e-06,
      "loss": 0.4282,
      "step": 59
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.2845268045281065,
      "learning_rate": 8.262352638201754e-06,
      "loss": 0.4841,
      "step": 60
    },
    {
      "epoch": 0.976,
      "grad_norm": 0.30381093535089976,
      "learning_rate": 8.200964262467658e-06,
      "loss": 0.5444,
      "step": 61
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.27310289060720006,
      "learning_rate": 8.13877990016813e-06,
      "loss": 0.341,
      "step": 62
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.27310289060720006,
      "learning_rate": 8.075817877320167e-06,
      "loss": 0.4322,
      "step": 63
    },
    {
      "epoch": 1.016,
      "grad_norm": 0.48420660950568,
      "learning_rate": 8.012096749120892e-06,
      "loss": 0.4956,
      "step": 64
    },
    {
      "epoch": 1.032,
      "grad_norm": 0.2856122575450543,
      "learning_rate": 7.947635294479262e-06,
      "loss": 0.3808,
      "step": 65
    },
    {
      "epoch": 1.048,
      "grad_norm": 0.2959094703912616,
      "learning_rate": 7.882452510481834e-06,
      "loss": 0.4794,
      "step": 66
    },
    {
      "epoch": 1.064,
      "grad_norm": 0.2587455831416144,
      "learning_rate": 7.81656760679424e-06,
      "loss": 0.4343,
      "step": 67
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.2789553742202286,
      "learning_rate": 7.75e-06,
      "loss": 0.4484,
      "step": 68
    },
    {
      "epoch": 1.096,
      "grad_norm": 0.3039866797711843,
      "learning_rate": 7.682769307878384e-06,
      "loss": 0.4165,
      "step": 69
    },
    {
      "epoch": 1.112,
      "grad_norm": 0.2588236721874104,
      "learning_rate": 7.614895343622941e-06,
      "loss": 0.4181,
      "step": 70
    },
    {
      "epoch": 1.1280000000000001,
      "grad_norm": 0.27938933998248044,
      "learning_rate": 7.546398110002477e-06,
      "loss": 0.4349,
      "step": 71
    },
    {
      "epoch": 1.144,
      "grad_norm": 0.30500409100487047,
      "learning_rate": 7.477297793466137e-06,
      "loss": 0.4195,
      "step": 72
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.2703316954052495,
      "learning_rate": 7.407614758194375e-06,
      "loss": 0.4593,
      "step": 73
    },
    {
      "epoch": 1.176,
      "grad_norm": 0.29674738729978956,
      "learning_rate": 7.337369540097521e-06,
      "loss": 0.4018,
      "step": 74
    },
    {
      "epoch": 1.192,
      "grad_norm": 0.3434929792222651,
      "learning_rate": 7.266582840763774e-06,
      "loss": 0.4633,
      "step": 75
    },
    {
      "epoch": 1.208,
      "grad_norm": 0.32994268144478006,
      "learning_rate": 7.195275521358334e-06,
      "loss": 0.4982,
      "step": 76
    },
    {
      "epoch": 1.224,
      "grad_norm": 0.2751594270204829,
      "learning_rate": 7.123468596475526e-06,
      "loss": 0.4717,
      "step": 77
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.3277135583956103,
      "learning_rate": 7.051183227945703e-06,
      "loss": 0.3922,
      "step": 78
    },
    {
      "epoch": 1.256,
      "grad_norm": 0.3178890245565396,
      "learning_rate": 6.978440718598757e-06,
      "loss": 0.4359,
      "step": 79
    },
    {
      "epoch": 1.272,
      "grad_norm": 0.2936671959796726,
      "learning_rate": 6.905262505986076e-06,
      "loss": 0.4482,
      "step": 80
    },
    {
      "epoch": 1.288,
      "grad_norm": 0.30577342188899176,
      "learning_rate": 6.8316701560628015e-06,
      "loss": 0.3457,
      "step": 81
    },
    {
      "epoch": 1.304,
      "grad_norm": 0.25812738212578895,
      "learning_rate": 6.757685356832243e-06,
      "loss": 0.4501,
      "step": 82
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.31439500562242606,
      "learning_rate": 6.683329911954316e-06,
      "loss": 0.5262,
      "step": 83
    },
    {
      "epoch": 1.336,
      "grad_norm": 0.3508949566807093,
      "learning_rate": 6.608625734319917e-06,
      "loss": 0.3605,
      "step": 84
    },
    {
      "epoch": 1.3519999999999999,
      "grad_norm": 0.29111139241084,
      "learning_rate": 6.5335948395930815e-06,
      "loss": 0.4049,
      "step": 85
    },
    {
      "epoch": 1.3679999999999999,
      "grad_norm": 0.30291591445235805,
      "learning_rate": 6.458259339722871e-06,
      "loss": 0.4092,
      "step": 86
    },
    {
      "epoch": 1.384,
      "grad_norm": 0.29313552915613017,
      "learning_rate": 6.382641436426887e-06,
      "loss": 0.3528,
      "step": 87
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.2583754481347982,
      "learning_rate": 6.306763414648311e-06,
      "loss": 0.3559,
      "step": 88
    },
    {
      "epoch": 1.416,
      "grad_norm": 0.26863426430444226,
      "learning_rate": 6.230647635988437e-06,
      "loss": 0.4254,
      "step": 89
    },
    {
      "epoch": 1.432,
      "grad_norm": 0.3093298693816597,
      "learning_rate": 6.154316532116605e-06,
      "loss": 0.3579,
      "step": 90
    },
    {
      "epoch": 1.448,
      "grad_norm": 0.25998129570390127,
      "learning_rate": 6.0777925981594795e-06,
      "loss": 0.4028,
      "step": 91
    },
    {
      "epoch": 1.464,
      "grad_norm": 0.3033921125695614,
      "learning_rate": 6.00109838607164e-06,
      "loss": 0.3805,
      "step": 92
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.2904725832178519,
      "learning_rate": 5.924256497989411e-06,
      "loss": 0.4323,
      "step": 93
    },
    {
      "epoch": 1.496,
      "grad_norm": 0.30355923070799345,
      "learning_rate": 5.84728957956991e-06,
      "loss": 0.3297,
      "step": 94
    },
    {
      "epoch": 1.512,
      "grad_norm": 0.2705231290116716,
      "learning_rate": 5.770220313317269e-06,
      "loss": 0.4177,
      "step": 95
    },
    {
      "epoch": 1.528,
      "grad_norm": 0.337520528610411,
      "learning_rate": 5.693071411897996e-06,
      "loss": 0.3795,
      "step": 96
    },
    {
      "epoch": 1.544,
      "grad_norm": 0.2741225861592298,
      "learning_rate": 5.61586561144745e-06,
      "loss": 0.414,
      "step": 97
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.3099099396586251,
      "learning_rate": 5.538625664869393e-06,
      "loss": 0.3715,
      "step": 98
    },
    {
      "epoch": 1.576,
      "grad_norm": 0.28067657578779776,
      "learning_rate": 5.46137433513061e-06,
      "loss": 0.4295,
      "step": 99
    },
    {
      "epoch": 1.592,
      "grad_norm": 0.2290691740751286,
      "learning_rate": 5.384134388552552e-06,
      "loss": 0.3913,
      "step": 100
    },
    {
      "epoch": 1.608,
      "grad_norm": 0.292339568550721,
      "learning_rate": 5.306928588102005e-06,
      "loss": 0.4101,
      "step": 101
    },
    {
      "epoch": 1.624,
      "grad_norm": 0.26499794509502683,
      "learning_rate": 5.229779686682734e-06,
      "loss": 0.4146,
      "step": 102
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.3102018761949683,
      "learning_rate": 5.152710420430092e-06,
      "loss": 0.43,
      "step": 103
    },
    {
      "epoch": 1.6560000000000001,
      "grad_norm": 0.28357637434683114,
      "learning_rate": 5.0757435020105905e-06,
      "loss": 0.4247,
      "step": 104
    },
    {
      "epoch": 1.6720000000000002,
      "grad_norm": 0.2829919630781859,
      "learning_rate": 4.998901613928361e-06,
      "loss": 0.4038,
      "step": 105
    },
    {
      "epoch": 1.688,
      "grad_norm": 0.29284800214525813,
      "learning_rate": 4.922207401840521e-06,
      "loss": 0.3709,
      "step": 106
    },
    {
      "epoch": 1.704,
      "grad_norm": 0.3170342016576189,
      "learning_rate": 4.845683467883396e-06,
      "loss": 0.4447,
      "step": 107
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.3077243277320204,
      "learning_rate": 4.7693523640115646e-06,
      "loss": 0.3928,
      "step": 108
    },
    {
      "epoch": 1.736,
      "grad_norm": 0.2778878775122821,
      "learning_rate": 4.693236585351692e-06,
      "loss": 0.4175,
      "step": 109
    },
    {
      "epoch": 1.752,
      "grad_norm": 0.28795862892188867,
      "learning_rate": 4.617358563573114e-06,
      "loss": 0.3722,
      "step": 110
    },
    {
      "epoch": 1.768,
      "grad_norm": 0.25342664678922827,
      "learning_rate": 4.541740660277131e-06,
      "loss": 0.39,
      "step": 111
    },
    {
      "epoch": 1.784,
      "grad_norm": 0.29510553890778607,
      "learning_rate": 4.466405160406922e-06,
      "loss": 0.4833,
      "step": 112
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.2793848028342464,
      "learning_rate": 4.391374265680084e-06,
      "loss": 0.3726,
      "step": 113
    },
    {
      "epoch": 1.8159999999999998,
      "grad_norm": 0.3026649324366544,
      "learning_rate": 4.316670088045684e-06,
      "loss": 0.4718,
      "step": 114
    },
    {
      "epoch": 1.8319999999999999,
      "grad_norm": 0.27728466637557236,
      "learning_rate": 4.242314643167759e-06,
      "loss": 0.3371,
      "step": 115
    },
    {
      "epoch": 1.8479999999999999,
      "grad_norm": 0.3168390463410005,
      "learning_rate": 4.168329843937199e-06,
      "loss": 0.3784,
      "step": 116
    },
    {
      "epoch": 1.8639999999999999,
      "grad_norm": 0.23724238568345682,
      "learning_rate": 4.094737494013925e-06,
      "loss": 0.4107,
      "step": 117
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.3236361234128115,
      "learning_rate": 4.0215592814012435e-06,
      "loss": 0.4976,
      "step": 118
    },
    {
      "epoch": 1.896,
      "grad_norm": 0.30334182027072204,
      "learning_rate": 3.948816772054298e-06,
      "loss": 0.472,
      "step": 119
    },
    {
      "epoch": 1.912,
      "grad_norm": 0.2680853511924467,
      "learning_rate": 3.876531403524476e-06,
      "loss": 0.3274,
      "step": 120
    },
    {
      "epoch": 1.928,
      "grad_norm": 0.30193319196237894,
      "learning_rate": 3.804724478641667e-06,
      "loss": 0.3816,
      "step": 121
    },
    {
      "epoch": 1.944,
      "grad_norm": 0.26693316547906853,
      "learning_rate": 3.733417159236228e-06,
      "loss": 0.3598,
      "step": 122
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.2717103343613883,
      "learning_rate": 3.6626304599024797e-06,
      "loss": 0.3841,
      "step": 123
    },
    {
      "epoch": 1.976,
      "grad_norm": 0.31425281419423284,
      "learning_rate": 3.592385241805628e-06,
      "loss": 0.4168,
      "step": 124
    },
    {
      "epoch": 1.992,
      "grad_norm": 0.25599583818936533,
      "learning_rate": 3.5227022065338623e-06,
      "loss": 0.4434,
      "step": 125
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.531221874086192,
      "learning_rate": 3.4536018899975255e-06,
      "loss": 0.3939,
      "step": 126
    },
    {
      "epoch": 2.016,
      "grad_norm": 0.26919931935198743,
      "learning_rate": 3.3851046563770617e-06,
      "loss": 0.3551,
      "step": 127
    },
    {
      "epoch": 2.032,
      "grad_norm": 0.2820331296888726,
      "learning_rate": 3.317230692121618e-06,
      "loss": 0.3248,
      "step": 128
    },
    {
      "epoch": 2.048,
      "grad_norm": 0.2560275313368148,
      "learning_rate": 3.2500000000000015e-06,
      "loss": 0.3168,
      "step": 129
    },
    {
      "epoch": 2.064,
      "grad_norm": 0.26575624913648593,
      "learning_rate": 3.1834323932057633e-06,
      "loss": 0.3388,
      "step": 130
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.2882413409588101,
      "learning_rate": 3.117547489518167e-06,
      "loss": 0.416,
      "step": 131
    },
    {
      "epoch": 2.096,
      "grad_norm": 0.26749471747908243,
      "learning_rate": 3.0523647055207393e-06,
      "loss": 0.4344,
      "step": 132
    },
    {
      "epoch": 2.112,
      "grad_norm": 0.2770415005714329,
      "learning_rate": 2.9879032508791096e-06,
      "loss": 0.4068,
      "step": 133
    },
    {
      "epoch": 2.128,
      "grad_norm": 0.25222155690032644,
      "learning_rate": 2.9241821226798338e-06,
      "loss": 0.3379,
      "step": 134
    },
    {
      "epoch": 2.144,
      "grad_norm": 0.292188926393636,
      "learning_rate": 2.86122009983187e-06,
      "loss": 0.3774,
      "step": 135
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.2898156735833746,
      "learning_rate": 2.799035737532344e-06,
      "loss": 0.3845,
      "step": 136
    },
    {
      "epoch": 2.176,
      "grad_norm": 0.27462927630805695,
      "learning_rate": 2.7376473617982456e-06,
      "loss": 0.3899,
      "step": 137
    },
    {
      "epoch": 2.192,
      "grad_norm": 0.28037858694245654,
      "learning_rate": 2.6770730640656784e-06,
      "loss": 0.4171,
      "step": 138
    },
    {
      "epoch": 2.208,
      "grad_norm": 0.2791430022438955,
      "learning_rate": 2.6173306958582125e-06,
      "loss": 0.3156,
      "step": 139
    },
    {
      "epoch": 2.224,
      "grad_norm": 0.29137935108000546,
      "learning_rate": 2.5584378635259733e-06,
      "loss": 0.3753,
      "step": 140
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.2593660029080348,
      "learning_rate": 2.5004119230569655e-06,
      "loss": 0.3766,
      "step": 141
    },
    {
      "epoch": 2.2560000000000002,
      "grad_norm": 0.2875413507661142,
      "learning_rate": 2.4432699749621813e-06,
      "loss": 0.3967,
      "step": 142
    },
    {
      "epoch": 2.2720000000000002,
      "grad_norm": 0.2931955054483654,
      "learning_rate": 2.387028859236002e-06,
      "loss": 0.3498,
      "step": 143
    },
    {
      "epoch": 2.288,
      "grad_norm": 0.26403010549011774,
      "learning_rate": 2.3317051503933743e-06,
      "loss": 0.3428,
      "step": 144
    },
    {
      "epoch": 2.304,
      "grad_norm": 0.2777071852283896,
      "learning_rate": 2.2773151525852313e-06,
      "loss": 0.3777,
      "step": 145
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.29111968942296174,
      "learning_rate": 2.223874894793569e-06,
      "loss": 0.4267,
      "step": 146
    },
    {
      "epoch": 2.336,
      "grad_norm": 0.30801800316293676,
      "learning_rate": 2.17140012610765e-06,
      "loss": 0.3731,
      "step": 147
    },
    {
      "epoch": 2.352,
      "grad_norm": 0.2950618309605883,
      "learning_rate": 2.119906311082662e-06,
      "loss": 0.4385,
      "step": 148
    },
    {
      "epoch": 2.368,
      "grad_norm": 0.24715278994212442,
      "learning_rate": 2.069408625182244e-06,
      "loss": 0.3629,
      "step": 149
    },
    {
      "epoch": 2.384,
      "grad_norm": 0.2742573979067362,
      "learning_rate": 2.019921950306216e-06,
      "loss": 0.381,
      "step": 150
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.28689018960107904,
      "learning_rate": 1.9714608704048036e-06,
      "loss": 0.4096,
      "step": 151
    },
    {
      "epoch": 2.416,
      "grad_norm": 0.2624247476439798,
      "learning_rate": 1.924039667180687e-06,
      "loss": 0.3014,
      "step": 152
    },
    {
      "epoch": 2.432,
      "grad_norm": 0.269857690537919,
      "learning_rate": 1.8776723158801188e-06,
      "loss": 0.3713,
      "step": 153
    },
    {
      "epoch": 2.448,
      "grad_norm": 0.3457149846408549,
      "learning_rate": 1.8323724811743495e-06,
      "loss": 0.4165,
      "step": 154
    },
    {
      "epoch": 2.464,
      "grad_norm": 0.31737427991855693,
      "learning_rate": 1.78815351313259e-06,
      "loss": 0.4442,
      "step": 155
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.3148729894178642,
      "learning_rate": 1.7450284432876873e-06,
      "loss": 0.4802,
      "step": 156
    },
    {
      "epoch": 2.496,
      "grad_norm": 0.26484117644858995,
      "learning_rate": 1.7030099807956649e-06,
      "loss": 0.3706,
      "step": 157
    },
    {
      "epoch": 2.512,
      "grad_norm": 0.2923543941519516,
      "learning_rate": 1.6621105086902822e-06,
      "loss": 0.3906,
      "step": 158
    },
    {
      "epoch": 2.528,
      "grad_norm": 0.2787856319176262,
      "learning_rate": 1.6223420802336933e-06,
      "loss": 0.3995,
      "step": 159
    },
    {
      "epoch": 2.544,
      "grad_norm": 0.2648560287594022,
      "learning_rate": 1.5837164153643014e-06,
      "loss": 0.3437,
      "step": 160
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.28029815338389324,
      "learning_rate": 1.5462448972428334e-06,
      "loss": 0.4114,
      "step": 161
    },
    {
      "epoch": 2.576,
      "grad_norm": 0.32764654451552816,
      "learning_rate": 1.5099385688976695e-06,
      "loss": 0.4176,
      "step": 162
    },
    {
      "epoch": 2.592,
      "grad_norm": 0.26653675081715944,
      "learning_rate": 1.474808129970421e-06,
      "loss": 0.4394,
      "step": 163
    },
    {
      "epoch": 2.608,
      "grad_norm": 0.30303023697633824,
      "learning_rate": 1.4408639335626823e-06,
      "loss": 0.446,
      "step": 164
    },
    {
      "epoch": 2.624,
      "grad_norm": 0.30230020169875327,
      "learning_rate": 1.4081159831849395e-06,
      "loss": 0.3978,
      "step": 165
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.3069707267289378,
      "learning_rate": 1.3765739298084792e-06,
      "loss": 0.3623,
      "step": 166
    },
    {
      "epoch": 2.656,
      "grad_norm": 0.27712650857341004,
      "learning_rate": 1.346247069021208e-06,
      "loss": 0.3382,
      "step": 167
    },
    {
      "epoch": 2.672,
      "grad_norm": 0.2699015904710055,
      "learning_rate": 1.3171443382881993e-06,
      "loss": 0.4117,
      "step": 168
    },
    {
      "epoch": 2.6879999999999997,
      "grad_norm": 0.29159348133947205,
      "learning_rate": 1.2892743143177793e-06,
      "loss": 0.3288,
      "step": 169
    },
    {
      "epoch": 2.7039999999999997,
      "grad_norm": 0.24614166945136878,
      "learning_rate": 1.262645210533934e-06,
      "loss": 0.4084,
      "step": 170
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.2758825153172464,
      "learning_rate": 1.2372648746557742e-06,
      "loss": 0.3513,
      "step": 171
    },
    {
      "epoch": 2.7359999999999998,
      "grad_norm": 0.29799910395406354,
      "learning_rate": 1.213140786384779e-06,
      "loss": 0.386,
      "step": 172
    },
    {
      "epoch": 2.752,
      "grad_norm": 0.32545648563171126,
      "learning_rate": 1.190280055200489e-06,
      "loss": 0.4041,
      "step": 173
    },
    {
      "epoch": 2.768,
      "grad_norm": 0.28037781950139645,
      "learning_rate": 1.1686894182653137e-06,
      "loss": 0.4193,
      "step": 174
    },
    {
      "epoch": 2.784,
      "grad_norm": 0.269297811870558,
      "learning_rate": 1.1483752384390583e-06,
      "loss": 0.3404,
      "step": 175
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.2621451208629847,
      "learning_rate": 1.1293435024037592e-06,
      "loss": 0.4476,
      "step": 176
    },
    {
      "epoch": 2.816,
      "grad_norm": 0.2840465963543336,
      "learning_rate": 1.1115998188993788e-06,
      "loss": 0.3689,
      "step": 177
    },
    {
      "epoch": 2.832,
      "grad_norm": 0.30328731810375564,
      "learning_rate": 1.09514941707089e-06,
      "loss": 0.4219,
      "step": 178
    },
    {
      "epoch": 2.848,
      "grad_norm": 0.28062525330655147,
      "learning_rate": 1.0799971449272174e-06,
      "loss": 0.3932,
      "step": 179
    },
    {
      "epoch": 2.864,
      "grad_norm": 0.28452098866262326,
      "learning_rate": 1.0661474679125096e-06,
      "loss": 0.4198,
      "step": 180
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.29354727351428,
      "learning_rate": 1.0536044675901534e-06,
      "loss": 0.3813,
      "step": 181
    },
    {
      "epoch": 2.896,
      "grad_norm": 0.3093060506201193,
      "learning_rate": 1.0423718404399139e-06,
      "loss": 0.4137,
      "step": 182
    },
    {
      "epoch": 2.912,
      "grad_norm": 0.2536429694083317,
      "learning_rate": 1.0324528967685698e-06,
      "loss": 0.4057,
      "step": 183
    },
    {
      "epoch": 2.928,
      "grad_norm": 0.278656315909379,
      "learning_rate": 1.0238505597343494e-06,
      "loss": 0.3078,
      "step": 184
    },
    {
      "epoch": 2.944,
      "grad_norm": 0.26173005919140585,
      "learning_rate": 1.0165673644854601e-06,
      "loss": 0.4326,
      "step": 185
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.29711263236623364,
      "learning_rate": 1.0106054574129717e-06,
      "loss": 0.4436,
      "step": 186
    },
    {
      "epoch": 2.976,
      "grad_norm": 0.2412655286518132,
      "learning_rate": 1.0059665955182629e-06,
      "loss": 0.3899,
      "step": 187
    },
    {
      "epoch": 2.992,
      "grad_norm": 0.2744645092683126,
      "learning_rate": 1.0026521458952265e-06,
      "loss": 0.3335,
      "step": 188
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.2744645092683126,
      "learning_rate": 1.0006630853273791e-06,
      "loss": 0.395,
      "step": 189
    },
    {
      "epoch": 3.0,
      "step": 189,
      "total_flos": 1.847238457911296e+16,
      "train_loss": 0.4201909417197818,
      "train_runtime": 1415.4735,
      "train_samples_per_second": 2.119,
      "train_steps_per_second": 0.134
    }
  ],
  "logging_steps": 1,
  "max_steps": 189,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.847238457911296e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}