{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 284.2696901095738,
      "learning_rate": 2e-07,
      "loss": 7.1138,
      "step": 1
    },
    {
      "epoch": 0.02,
      "grad_norm": 280.0890600259792,
      "learning_rate": 4e-07,
      "loss": 6.8466,
      "step": 2
    },
    {
      "epoch": 0.03,
      "grad_norm": 296.98995011993617,
      "learning_rate": 6e-07,
      "loss": 6.8936,
      "step": 3
    },
    {
      "epoch": 0.04,
      "grad_norm": 284.92519297592935,
      "learning_rate": 8e-07,
      "loss": 7.1196,
      "step": 4
    },
    {
      "epoch": 0.05,
      "grad_norm": 296.67655171044885,
      "learning_rate": 1e-06,
      "loss": 6.7063,
      "step": 5
    },
    {
      "epoch": 0.06,
      "grad_norm": 281.91608332740634,
      "learning_rate": 9.99726628670463e-07,
      "loss": 6.028,
      "step": 6
    },
    {
      "epoch": 0.07,
      "grad_norm": 245.30165342232291,
      "learning_rate": 9.989068136093872e-07,
      "loss": 5.593,
      "step": 7
    },
    {
      "epoch": 0.08,
      "grad_norm": 171.71633417584104,
      "learning_rate": 9.975414512725056e-07,
      "loss": 4.1199,
      "step": 8
    },
    {
      "epoch": 0.09,
      "grad_norm": 153.69431185375615,
      "learning_rate": 9.956320346634875e-07,
      "loss": 3.8539,
      "step": 9
    },
    {
      "epoch": 0.1,
      "grad_norm": 138.4099703250891,
      "learning_rate": 9.931806517013612e-07,
      "loss": 3.364,
      "step": 10
    },
    {
      "epoch": 0.11,
      "grad_norm": 121.96592995402922,
      "learning_rate": 9.901899829374047e-07,
      "loss": 3.2359,
      "step": 11
    },
    {
      "epoch": 0.12,
      "grad_norm": 83.33555123373614,
      "learning_rate": 9.866632986240029e-07,
      "loss": 2.0694,
      "step": 12
    },
    {
      "epoch": 0.13,
      "grad_norm": 69.8343923660202,
      "learning_rate": 9.826044551386742e-07,
      "loss": 1.8041,
      "step": 13
    },
    {
      "epoch": 0.14,
      "grad_norm": 61.02444391130647,
      "learning_rate": 9.780178907671788e-07,
      "loss": 1.8221,
      "step": 14
    },
    {
      "epoch": 0.15,
      "grad_norm": 51.06086209218741,
      "learning_rate": 9.729086208503173e-07,
      "loss": 1.5577,
      "step": 15
    },
    {
      "epoch": 0.16,
      "grad_norm": 39.386178814833706,
      "learning_rate": 9.672822322997304e-07,
      "loss": 1.3898,
      "step": 16
    },
    {
      "epoch": 0.17,
      "grad_norm": 33.769199410950286,
      "learning_rate": 9.611448774886923e-07,
      "loss": 1.2839,
      "step": 17
    },
    {
      "epoch": 0.18,
      "grad_norm": 32.43709972193044,
      "learning_rate": 9.545032675245813e-07,
      "loss": 1.1126,
      "step": 18
    },
    {
      "epoch": 0.19,
      "grad_norm": 29.12905700014587,
      "learning_rate": 9.473646649103817e-07,
      "loss": 0.9637,
      "step": 19
    },
    {
      "epoch": 0.2,
      "grad_norm": 19.116333899951297,
      "learning_rate": 9.397368756032444e-07,
      "loss": 0.6976,
      "step": 20
    },
    {
      "epoch": 0.21,
      "grad_norm": 17.362547626796633,
      "learning_rate": 9.316282404787869e-07,
      "loss": 0.6686,
      "step": 21
    },
    {
      "epoch": 0.22,
      "grad_norm": 12.641692912258486,
      "learning_rate": 9.230476262104676e-07,
      "loss": 0.6055,
      "step": 22
    },
    {
      "epoch": 0.23,
      "grad_norm": 9.423373458222406,
      "learning_rate": 9.1400441557401e-07,
      "loss": 0.5312,
      "step": 23
    },
    {
      "epoch": 0.24,
      "grad_norm": 7.714449953085253,
      "learning_rate": 9.045084971874737e-07,
      "loss": 0.5334,
      "step": 24
    },
    {
      "epoch": 0.25,
      "grad_norm": 6.3626526485098545,
      "learning_rate": 8.945702546981968e-07,
      "loss": 0.5246,
      "step": 25
    },
    {
      "epoch": 0.26,
      "grad_norm": 5.787541205113461,
      "learning_rate": 8.842005554284295e-07,
      "loss": 0.4586,
      "step": 26
    },
    {
      "epoch": 0.27,
      "grad_norm": 5.217072482502457,
      "learning_rate": 8.734107384920769e-07,
      "loss": 0.514,
      "step": 27
    },
    {
      "epoch": 0.28,
      "grad_norm": 5.69075014149454,
      "learning_rate": 8.622126023955445e-07,
      "loss": 0.469,
      "step": 28
    },
    {
      "epoch": 0.29,
      "grad_norm": 5.767332317747505,
      "learning_rate": 8.506183921362442e-07,
      "loss": 0.4928,
      "step": 29
    },
    {
      "epoch": 0.3,
      "grad_norm": 5.29694390512729,
      "learning_rate": 8.386407858128706e-07,
      "loss": 0.416,
      "step": 30
    },
    {
      "epoch": 0.31,
      "grad_norm": 5.4751365453564524,
      "learning_rate": 8.262928807620843e-07,
      "loss": 0.4065,
      "step": 31
    },
    {
      "epoch": 0.32,
      "grad_norm": 4.210968327443881,
      "learning_rate": 8.135881792367685e-07,
      "loss": 0.4302,
      "step": 32
    },
    {
      "epoch": 0.33,
      "grad_norm": 4.889628663080109,
      "learning_rate": 8.005405736415125e-07,
      "loss": 0.475,
      "step": 33
    },
    {
      "epoch": 0.34,
      "grad_norm": 5.01223684022235,
      "learning_rate": 7.871643313414718e-07,
      "loss": 0.4418,
      "step": 34
    },
    {
      "epoch": 0.35,
      "grad_norm": 4.362633576491621,
      "learning_rate": 7.734740790612136e-07,
      "loss": 0.4074,
      "step": 35
    },
    {
      "epoch": 0.36,
      "grad_norm": 3.9179637860680874,
      "learning_rate": 7.594847868906076e-07,
      "loss": 0.4006,
      "step": 36
    },
    {
      "epoch": 0.37,
      "grad_norm": 3.8386018601431067,
      "learning_rate": 7.452117519152541e-07,
      "loss": 0.4099,
      "step": 37
    },
    {
      "epoch": 0.38,
      "grad_norm": 4.465384708590031,
      "learning_rate": 7.306705814893439e-07,
      "loss": 0.4258,
      "step": 38
    },
    {
      "epoch": 0.39,
      "grad_norm": 4.869675336079214,
      "learning_rate": 7.158771761692464e-07,
      "loss": 0.4066,
      "step": 39
    },
    {
      "epoch": 0.4,
      "grad_norm": 4.6892092384872255,
      "learning_rate": 7.008477123264847e-07,
      "loss": 0.4272,
      "step": 40
    },
    {
      "epoch": 0.41,
      "grad_norm": 4.282400513219925,
      "learning_rate": 6.855986244591103e-07,
      "loss": 0.4166,
      "step": 41
    },
    {
      "epoch": 0.42,
      "grad_norm": 4.44179530817891,
      "learning_rate": 6.701465872208216e-07,
      "loss": 0.3928,
      "step": 42
    },
    {
      "epoch": 0.43,
      "grad_norm": 4.753857420255081,
      "learning_rate": 6.545084971874736e-07,
      "loss": 0.4291,
      "step": 43
    },
    {
      "epoch": 0.44,
      "grad_norm": 5.121989871402109,
      "learning_rate": 6.387014543809223e-07,
      "loss": 0.3841,
      "step": 44
    },
    {
      "epoch": 0.45,
      "grad_norm": 4.306307235348373,
      "learning_rate": 6.227427435703995e-07,
      "loss": 0.3897,
      "step": 45
    },
    {
      "epoch": 0.46,
      "grad_norm": 4.1819998879575095,
      "learning_rate": 6.066498153718734e-07,
      "loss": 0.3938,
      "step": 46
    },
    {
      "epoch": 0.47,
      "grad_norm": 3.9858764933030493,
      "learning_rate": 5.90440267166055e-07,
      "loss": 0.3722,
      "step": 47
    },
    {
      "epoch": 0.48,
      "grad_norm": 3.768016055450793,
      "learning_rate": 5.741318238559209e-07,
      "loss": 0.4295,
      "step": 48
    },
    {
      "epoch": 0.49,
      "grad_norm": 4.155664350209782,
      "learning_rate": 5.577423184847931e-07,
      "loss": 0.3834,
      "step": 49
    },
    {
      "epoch": 0.5,
      "grad_norm": 3.79515186565417,
      "learning_rate": 5.412896727361662e-07,
      "loss": 0.3391,
      "step": 50
    },
    {
      "epoch": 0.51,
      "grad_norm": 3.4230723188666476,
      "learning_rate": 5.247918773366111e-07,
      "loss": 0.3942,
      "step": 51
    },
    {
      "epoch": 0.52,
      "grad_norm": 3.0931484903099773,
      "learning_rate": 5.082669723831793e-07,
      "loss": 0.3848,
      "step": 52
    },
    {
      "epoch": 0.53,
      "grad_norm": 4.693387026086119,
      "learning_rate": 4.917330276168208e-07,
      "loss": 0.385,
      "step": 53
    },
    {
      "epoch": 0.54,
      "grad_norm": 3.531161429609241,
      "learning_rate": 4.752081226633888e-07,
      "loss": 0.3694,
      "step": 54
    },
    {
      "epoch": 0.55,
      "grad_norm": 3.696655191494645,
      "learning_rate": 4.5871032726383385e-07,
      "loss": 0.3615,
      "step": 55
    },
    {
      "epoch": 0.56,
      "grad_norm": 3.798666905310865,
      "learning_rate": 4.4225768151520694e-07,
      "loss": 0.3257,
      "step": 56
    },
    {
      "epoch": 0.57,
      "grad_norm": 3.595957261529934,
      "learning_rate": 4.258681761440789e-07,
      "loss": 0.351,
      "step": 57
    },
    {
      "epoch": 0.58,
      "grad_norm": 3.443958917780827,
      "learning_rate": 4.095597328339452e-07,
      "loss": 0.3964,
      "step": 58
    },
    {
      "epoch": 0.59,
      "grad_norm": 4.222996925336396,
      "learning_rate": 3.9335018462812664e-07,
      "loss": 0.3783,
      "step": 59
    },
    {
      "epoch": 0.6,
      "grad_norm": 4.141091647019225,
      "learning_rate": 3.772572564296004e-07,
      "loss": 0.3617,
      "step": 60
    },
    {
      "epoch": 0.61,
      "grad_norm": 4.207602140662548,
      "learning_rate": 3.612985456190778e-07,
      "loss": 0.3997,
      "step": 61
    },
    {
      "epoch": 0.62,
      "grad_norm": 3.4580694579960918,
      "learning_rate": 3.454915028125263e-07,
      "loss": 0.3582,
      "step": 62
    },
    {
      "epoch": 0.63,
      "grad_norm": 3.422220201677041,
      "learning_rate": 3.2985341277917846e-07,
      "loss": 0.3804,
      "step": 63
    },
    {
      "epoch": 0.64,
      "grad_norm": 3.273283148367399,
      "learning_rate": 3.1440137554088953e-07,
      "loss": 0.3646,
      "step": 64
    },
    {
      "epoch": 0.65,
      "grad_norm": 3.099164792571154,
      "learning_rate": 2.9915228767351535e-07,
      "loss": 0.3387,
      "step": 65
    },
    {
      "epoch": 0.66,
      "grad_norm": 3.6768199519226314,
      "learning_rate": 2.841228238307536e-07,
      "loss": 0.3839,
      "step": 66
    },
    {
      "epoch": 0.67,
      "grad_norm": 3.684496636177031,
      "learning_rate": 2.6932941851065615e-07,
      "loss": 0.3635,
      "step": 67
    },
    {
      "epoch": 0.68,
      "grad_norm": 2.8715160468944236,
      "learning_rate": 2.547882480847461e-07,
      "loss": 0.3905,
      "step": 68
    },
    {
      "epoch": 0.69,
      "grad_norm": 4.542266866557925,
      "learning_rate": 2.4051521310939254e-07,
      "loss": 0.3666,
      "step": 69
    },
    {
      "epoch": 0.7,
      "grad_norm": 3.721830078063186,
      "learning_rate": 2.2652592093878665e-07,
      "loss": 0.3317,
      "step": 70
    },
    {
      "epoch": 0.71,
      "grad_norm": 3.7314666594735724,
      "learning_rate": 2.128356686585282e-07,
      "loss": 0.3231,
      "step": 71
    },
    {
      "epoch": 0.72,
      "grad_norm": 3.283124086872181,
      "learning_rate": 1.9945942635848745e-07,
      "loss": 0.3447,
      "step": 72
    },
    {
      "epoch": 0.73,
      "grad_norm": 3.9554685048457183,
      "learning_rate": 1.8641182076323148e-07,
      "loss": 0.3284,
      "step": 73
    },
    {
      "epoch": 0.74,
      "grad_norm": 3.8402484907207435,
      "learning_rate": 1.7370711923791564e-07,
      "loss": 0.3591,
      "step": 74
    },
    {
      "epoch": 0.75,
      "grad_norm": 3.4683454793599884,
      "learning_rate": 1.6135921418712955e-07,
      "loss": 0.3444,
      "step": 75
    },
    {
      "epoch": 0.76,
      "grad_norm": 3.837469581874028,
      "learning_rate": 1.493816078637557e-07,
      "loss": 0.4039,
      "step": 76
    },
    {
      "epoch": 0.77,
      "grad_norm": 3.498682351133943,
      "learning_rate": 1.3778739760445552e-07,
      "loss": 0.3203,
      "step": 77
    },
    {
      "epoch": 0.78,
      "grad_norm": 4.16268013662858,
      "learning_rate": 1.2658926150792322e-07,
      "loss": 0.3715,
      "step": 78
    },
    {
      "epoch": 0.79,
      "grad_norm": 3.404009699611626,
      "learning_rate": 1.1579944457157059e-07,
      "loss": 0.3226,
      "step": 79
    },
    {
      "epoch": 0.8,
      "grad_norm": 3.8135862465406904,
      "learning_rate": 1.0542974530180327e-07,
      "loss": 0.3627,
      "step": 80
    },
    {
      "epoch": 0.81,
      "grad_norm": 3.3969260525552616,
      "learning_rate": 9.549150281252632e-08,
      "loss": 0.3646,
      "step": 81
    },
    {
      "epoch": 0.82,
      "grad_norm": 2.9007273599583057,
      "learning_rate": 8.599558442598998e-08,
      "loss": 0.3506,
      "step": 82
    },
    {
      "epoch": 0.83,
      "grad_norm": 2.8266227536670523,
      "learning_rate": 7.695237378953224e-08,
      "loss": 0.3471,
      "step": 83
    },
    {
      "epoch": 0.84,
      "grad_norm": 2.8680227347397893,
      "learning_rate": 6.837175952121304e-08,
      "loss": 0.3362,
      "step": 84
    },
    {
      "epoch": 0.85,
      "grad_norm": 3.017390726560224,
      "learning_rate": 6.026312439675551e-08,
      "loss": 0.354,
      "step": 85
    },
    {
      "epoch": 0.86,
      "grad_norm": 2.75220355066635,
      "learning_rate": 5.263533508961826e-08,
      "loss": 0.3589,
      "step": 86
    },
    {
      "epoch": 0.87,
      "grad_norm": 2.5609091595597784,
      "learning_rate": 4.549673247541874e-08,
      "loss": 0.3209,
      "step": 87
    },
    {
      "epoch": 0.88,
      "grad_norm": 3.366788037939117,
      "learning_rate": 3.8855122511307626e-08,
      "loss": 0.3707,
      "step": 88
    },
    {
      "epoch": 0.89,
      "grad_norm": 2.998733006487237,
      "learning_rate": 3.271776770026963e-08,
      "loss": 0.3314,
      "step": 89
    },
    {
      "epoch": 0.9,
      "grad_norm": 3.38338292899199,
      "learning_rate": 2.7091379149682682e-08,
      "loss": 0.3634,
      "step": 90
    },
    {
      "epoch": 0.91,
      "grad_norm": 3.62894701397729,
      "learning_rate": 2.1982109232821176e-08,
      "loss": 0.3762,
      "step": 91
    },
    {
      "epoch": 0.92,
      "grad_norm": 3.6241096556456243,
      "learning_rate": 1.7395544861325718e-08,
      "loss": 0.3393,
      "step": 92
    },
    {
      "epoch": 0.93,
      "grad_norm": 3.681150537295675,
      "learning_rate": 1.3336701375997127e-08,
      "loss": 0.3408,
      "step": 93
    },
    {
      "epoch": 0.94,
      "grad_norm": 3.573864183770881,
      "learning_rate": 9.810017062595321e-09,
      "loss": 0.3388,
      "step": 94
    },
    {
      "epoch": 0.95,
      "grad_norm": 3.1628676346413824,
      "learning_rate": 6.819348298638839e-09,
      "loss": 0.3396,
      "step": 95
    },
    {
      "epoch": 0.96,
      "grad_norm": 4.253309468483455,
      "learning_rate": 4.367965336512403e-09,
      "loss": 0.3292,
      "step": 96
    },
    {
      "epoch": 0.97,
      "grad_norm": 3.3389999287279166,
      "learning_rate": 2.458548727494292e-09,
      "loss": 0.3415,
      "step": 97
    },
    {
      "epoch": 0.98,
      "grad_norm": 3.0295989312166327,
      "learning_rate": 1.0931863906127325e-09,
      "loss": 0.3261,
      "step": 98
    },
    {
      "epoch": 0.99,
      "grad_norm": 2.9789770023523388,
      "learning_rate": 2.733713295369755e-10,
      "loss": 0.3191,
      "step": 99
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.6932194833157013,
      "learning_rate": 0.0,
      "loss": 0.355,
      "step": 100
    },
    {
      "epoch": 1.0,
      "step": 100,
      "total_flos": 6384023396352.0,
      "train_loss": 1.047203412950039,
      "train_runtime": 2682.144,
      "train_samples_per_second": 9.545,
      "train_steps_per_second": 0.037
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6384023396352.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}