{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9984,
  "eval_steps": 500,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0128,
      "grad_norm": 0.37097011587312084,
      "learning_rate": 0.0,
      "loss": 0.3901,
      "step": 1
    },
    {
      "epoch": 0.0256,
      "grad_norm": 0.436036081922528,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.3883,
      "step": 2
    },
    {
      "epoch": 0.0384,
      "grad_norm": 0.3573723071888369,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.3962,
      "step": 3
    },
    {
      "epoch": 0.0512,
      "grad_norm": 0.3518694774503068,
      "learning_rate": 1e-05,
      "loss": 0.3854,
      "step": 4
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.3595782263365104,
      "learning_rate": 9.995614150494293e-06,
      "loss": 0.3943,
      "step": 5
    },
    {
      "epoch": 0.0768,
      "grad_norm": 0.43911194680897103,
      "learning_rate": 9.982464296247523e-06,
      "loss": 0.3896,
      "step": 6
    },
    {
      "epoch": 0.0896,
      "grad_norm": 0.355130392515275,
      "learning_rate": 9.960573506572391e-06,
      "loss": 0.4013,
      "step": 7
    },
    {
      "epoch": 0.1024,
      "grad_norm": 0.40881173225252276,
      "learning_rate": 9.929980185352525e-06,
      "loss": 0.388,
      "step": 8
    },
    {
      "epoch": 0.1152,
      "grad_norm": 0.37811272957994063,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.3971,
      "step": 9
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.38683613267850125,
      "learning_rate": 9.842915805643156e-06,
      "loss": 0.3922,
      "step": 10
    },
    {
      "epoch": 0.1408,
      "grad_norm": 0.38548897546861477,
      "learning_rate": 9.786597487660336e-06,
      "loss": 0.3831,
      "step": 11
    },
    {
      "epoch": 0.1536,
      "grad_norm": 0.37692470678725043,
      "learning_rate": 9.721881851187406e-06,
      "loss": 0.37,
      "step": 12
    },
    {
      "epoch": 0.1664,
      "grad_norm": 0.33621506985048016,
      "learning_rate": 9.648882429441258e-06,
      "loss": 0.3819,
      "step": 13
    },
    {
      "epoch": 0.1792,
      "grad_norm": 0.37421498213131654,
      "learning_rate": 9.567727288213005e-06,
      "loss": 0.3819,
      "step": 14
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.36912595638250156,
      "learning_rate": 9.478558801197065e-06,
      "loss": 0.387,
      "step": 15
    },
    {
      "epoch": 0.2048,
      "grad_norm": 0.3666423355846176,
      "learning_rate": 9.381533400219319e-06,
      "loss": 0.3883,
      "step": 16
    },
    {
      "epoch": 0.2176,
      "grad_norm": 0.35046173350438564,
      "learning_rate": 9.276821300802535e-06,
      "loss": 0.3833,
      "step": 17
    },
    {
      "epoch": 0.2304,
      "grad_norm": 0.3368857977856999,
      "learning_rate": 9.164606203550498e-06,
      "loss": 0.3731,
      "step": 18
    },
    {
      "epoch": 0.2432,
      "grad_norm": 0.3733935656040606,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.377,
      "step": 19
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.3599861257574975,
      "learning_rate": 8.9184672866292e-06,
      "loss": 0.3755,
      "step": 20
    },
    {
      "epoch": 0.2688,
      "grad_norm": 0.3911421377175938,
      "learning_rate": 8.784975278258783e-06,
      "loss": 0.3924,
      "step": 21
    },
    {
      "epoch": 0.2816,
      "grad_norm": 0.3573971184913782,
      "learning_rate": 8.644843137107058e-06,
      "loss": 0.3776,
      "step": 22
    },
    {
      "epoch": 0.2944,
      "grad_norm": 0.3631940659643793,
      "learning_rate": 8.498316702566828e-06,
      "loss": 0.3793,
      "step": 23
    },
    {
      "epoch": 0.3072,
      "grad_norm": 0.3673181950680914,
      "learning_rate": 8.345653031794292e-06,
      "loss": 0.3723,
      "step": 24
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.3609017805032103,
      "learning_rate": 8.18711994874345e-06,
      "loss": 0.377,
      "step": 25
    },
    {
      "epoch": 0.3328,
      "grad_norm": 0.3613502421923999,
      "learning_rate": 8.022995574311876e-06,
      "loss": 0.3918,
      "step": 26
    },
    {
      "epoch": 0.3456,
      "grad_norm": 0.38481571972221584,
      "learning_rate": 7.85356783842216e-06,
      "loss": 0.3798,
      "step": 27
    },
    {
      "epoch": 0.3584,
      "grad_norm": 0.33712257754498065,
      "learning_rate": 7.679133974894984e-06,
      "loss": 0.3798,
      "step": 28
    },
    {
      "epoch": 0.3712,
      "grad_norm": 0.3295851624866036,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.366,
      "step": 29
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.3478890116495374,
      "learning_rate": 7.31648017559931e-06,
      "loss": 0.3815,
      "step": 30
    },
    {
      "epoch": 0.3968,
      "grad_norm": 0.3376828863420035,
      "learning_rate": 7.128896457825364e-06,
      "loss": 0.3798,
      "step": 31
    },
    {
      "epoch": 0.4096,
      "grad_norm": 0.3614567558661752,
      "learning_rate": 6.9375779322605154e-06,
      "loss": 0.3785,
      "step": 32
    },
    {
      "epoch": 0.4224,
      "grad_norm": 0.3538444335842918,
      "learning_rate": 6.7428602366090764e-06,
      "loss": 0.3855,
      "step": 33
    },
    {
      "epoch": 0.4352,
      "grad_norm": 0.37946895332136865,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.3733,
      "step": 34
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.3547101815519377,
      "learning_rate": 6.344599103076329e-06,
      "loss": 0.3757,
      "step": 35
    },
    {
      "epoch": 0.4608,
      "grad_norm": 0.3494781242267413,
      "learning_rate": 6.141754350553279e-06,
      "loss": 0.3845,
      "step": 36
    },
    {
      "epoch": 0.4736,
      "grad_norm": 0.3486921256646317,
      "learning_rate": 5.936906572928625e-06,
      "loss": 0.3828,
      "step": 37
    },
    {
      "epoch": 0.4864,
      "grad_norm": 0.3661895332981024,
      "learning_rate": 5.730415142812059e-06,
      "loss": 0.3631,
      "step": 38
    },
    {
      "epoch": 0.4992,
      "grad_norm": 0.3726525512431902,
      "learning_rate": 5.522642316338268e-06,
      "loss": 0.3873,
      "step": 39
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.37122955449932626,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 0.3741,
      "step": 40
    },
    {
      "epoch": 0.5248,
      "grad_norm": 0.35890087584823,
      "learning_rate": 5.1047120994167855e-06,
      "loss": 0.3736,
      "step": 41
    },
    {
      "epoch": 0.5376,
      "grad_norm": 0.4124738032066601,
      "learning_rate": 4.895287900583216e-06,
      "loss": 0.3735,
      "step": 42
    },
    {
      "epoch": 0.5504,
      "grad_norm": 0.3586662859958761,
      "learning_rate": 4.686047402353433e-06,
      "loss": 0.3719,
      "step": 43
    },
    {
      "epoch": 0.5632,
      "grad_norm": 0.3481223264106508,
      "learning_rate": 4.477357683661734e-06,
      "loss": 0.3715,
      "step": 44
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.35910735606242167,
      "learning_rate": 4.269584857187942e-06,
      "loss": 0.3671,
      "step": 45
    },
    {
      "epoch": 0.5888,
      "grad_norm": 0.3761516933625998,
      "learning_rate": 4.063093427071376e-06,
      "loss": 0.3739,
      "step": 46
    },
    {
      "epoch": 0.6016,
      "grad_norm": 0.3499083653449883,
      "learning_rate": 3.8582456494467214e-06,
      "loss": 0.3739,
      "step": 47
    },
    {
      "epoch": 0.6144,
      "grad_norm": 0.40616031275072645,
      "learning_rate": 3.655400896923672e-06,
      "loss": 0.374,
      "step": 48
    },
    {
      "epoch": 0.6272,
      "grad_norm": 0.371910271626943,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.3675,
      "step": 49
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.3794108439198809,
      "learning_rate": 3.2571397633909252e-06,
      "loss": 0.3772,
      "step": 50
    },
    {
      "epoch": 0.6528,
      "grad_norm": 0.34353956116020024,
      "learning_rate": 3.0624220677394854e-06,
      "loss": 0.366,
      "step": 51
    },
    {
      "epoch": 0.6656,
      "grad_norm": 0.3738102880959614,
      "learning_rate": 2.871103542174637e-06,
      "loss": 0.3802,
      "step": 52
    },
    {
      "epoch": 0.6784,
      "grad_norm": 0.37822364987600077,
      "learning_rate": 2.683519824400693e-06,
      "loss": 0.3741,
      "step": 53
    },
    {
      "epoch": 0.6912,
      "grad_norm": 0.36706891104650813,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.3788,
      "step": 54
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.3588338232340778,
      "learning_rate": 2.320866025105016e-06,
      "loss": 0.3667,
      "step": 55
    },
    {
      "epoch": 0.7168,
      "grad_norm": 0.33982756078396936,
      "learning_rate": 2.146432161577842e-06,
      "loss": 0.3821,
      "step": 56
    },
    {
      "epoch": 0.7296,
      "grad_norm": 0.36237403858150463,
      "learning_rate": 1.977004425688126e-06,
      "loss": 0.3685,
      "step": 57
    },
    {
      "epoch": 0.7424,
      "grad_norm": 0.3719691838281121,
      "learning_rate": 1.8128800512565514e-06,
      "loss": 0.3831,
      "step": 58
    },
    {
      "epoch": 0.7552,
      "grad_norm": 0.35429659891005705,
      "learning_rate": 1.6543469682057105e-06,
      "loss": 0.3739,
      "step": 59
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.3813493534067349,
      "learning_rate": 1.5016832974331725e-06,
      "loss": 0.3698,
      "step": 60
    },
    {
      "epoch": 0.7808,
      "grad_norm": 0.3735560509373922,
      "learning_rate": 1.3551568628929434e-06,
      "loss": 0.3665,
      "step": 61
    },
    {
      "epoch": 0.7936,
      "grad_norm": 0.37382203270208175,
      "learning_rate": 1.2150247217412186e-06,
      "loss": 0.3724,
      "step": 62
    },
    {
      "epoch": 0.8064,
      "grad_norm": 0.33800288133345135,
      "learning_rate": 1.0815327133708015e-06,
      "loss": 0.3769,
      "step": 63
    },
    {
      "epoch": 0.8192,
      "grad_norm": 0.36053969319846985,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.3726,
      "step": 64
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.35040639123035566,
      "learning_rate": 8.353937964495029e-07,
      "loss": 0.3642,
      "step": 65
    },
    {
      "epoch": 0.8448,
      "grad_norm": 0.34119689441540785,
      "learning_rate": 7.23178699197467e-07,
      "loss": 0.3742,
      "step": 66
    },
    {
      "epoch": 0.8576,
      "grad_norm": 0.32780736669039207,
      "learning_rate": 6.184665997806832e-07,
      "loss": 0.3753,
      "step": 67
    },
    {
      "epoch": 0.8704,
      "grad_norm": 0.37224717916806577,
      "learning_rate": 5.214411988029355e-07,
      "loss": 0.3766,
      "step": 68
    },
    {
      "epoch": 0.8832,
      "grad_norm": 0.38019197202708854,
      "learning_rate": 4.322727117869951e-07,
      "loss": 0.3673,
      "step": 69
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.360040865272652,
      "learning_rate": 3.511175705587433e-07,
      "loss": 0.3698,
      "step": 70
    },
    {
      "epoch": 0.9088,
      "grad_norm": 0.3475714599209027,
      "learning_rate": 2.7811814881259503e-07,
      "loss": 0.3712,
      "step": 71
    },
    {
      "epoch": 0.9216,
      "grad_norm": 0.36964857656525896,
      "learning_rate": 2.134025123396638e-07,
      "loss": 0.3713,
      "step": 72
    },
    {
      "epoch": 0.9344,
      "grad_norm": 0.3687330614589881,
      "learning_rate": 1.5708419435684463e-07,
      "loss": 0.3765,
      "step": 73
    },
    {
      "epoch": 0.9472,
      "grad_norm": 0.3594661514184954,
      "learning_rate": 1.0926199633097156e-07,
      "loss": 0.3729,
      "step": 74
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.35786708238296827,
      "learning_rate": 7.001981464747565e-08,
      "loss": 0.3724,
      "step": 75
    },
    {
      "epoch": 0.9728,
      "grad_norm": 0.3894878194119222,
      "learning_rate": 3.9426493427611177e-08,
      "loss": 0.3677,
      "step": 76
    },
    {
      "epoch": 0.9856,
      "grad_norm": 0.38808691171122667,
      "learning_rate": 1.753570375247815e-08,
      "loss": 0.3738,
      "step": 77
    },
    {
      "epoch": 0.9984,
      "grad_norm": 0.36037714569951623,
      "learning_rate": 4.385849505708084e-09,
      "loss": 0.3667,
      "step": 78
    },
    {
      "epoch": 0.9984,
      "step": 78,
      "total_flos": 116872787132416.0,
      "train_loss": 0.3777111012202043,
      "train_runtime": 903.3304,
      "train_samples_per_second": 11.07,
      "train_steps_per_second": 0.086
    }
  ],
  "logging_steps": 1,
  "max_steps": 78,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 116872787132416.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}