{
  "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": 0.47873172315787393,
      "learning_rate": 0.0,
      "loss": 0.4393,
      "step": 1
    },
    {
      "epoch": 0.0256,
      "grad_norm": 0.515467090541731,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.4301,
      "step": 2
    },
    {
      "epoch": 0.0384,
      "grad_norm": 0.45415898637326074,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.4421,
      "step": 3
    },
    {
      "epoch": 0.0512,
      "grad_norm": 0.4931765663158739,
      "learning_rate": 1e-05,
      "loss": 0.4496,
      "step": 4
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.5208425203427642,
      "learning_rate": 9.995614150494293e-06,
      "loss": 0.4489,
      "step": 5
    },
    {
      "epoch": 0.0768,
      "grad_norm": 0.5118719865735493,
      "learning_rate": 9.982464296247523e-06,
      "loss": 0.4353,
      "step": 6
    },
    {
      "epoch": 0.0896,
      "grad_norm": 0.4620918613283098,
      "learning_rate": 9.960573506572391e-06,
      "loss": 0.4451,
      "step": 7
    },
    {
      "epoch": 0.1024,
      "grad_norm": 0.4897693428843195,
      "learning_rate": 9.929980185352525e-06,
      "loss": 0.4266,
      "step": 8
    },
    {
      "epoch": 0.1152,
      "grad_norm": 0.5281811277586651,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.4442,
      "step": 9
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.4842482139149718,
      "learning_rate": 9.842915805643156e-06,
      "loss": 0.4258,
      "step": 10
    },
    {
      "epoch": 0.1408,
      "grad_norm": 0.48200169586765984,
      "learning_rate": 9.786597487660336e-06,
      "loss": 0.4333,
      "step": 11
    },
    {
      "epoch": 0.1536,
      "grad_norm": 0.4553176945665744,
      "learning_rate": 9.721881851187406e-06,
      "loss": 0.4235,
      "step": 12
    },
    {
      "epoch": 0.1664,
      "grad_norm": 0.4536596781128087,
      "learning_rate": 9.648882429441258e-06,
      "loss": 0.4207,
      "step": 13
    },
    {
      "epoch": 0.1792,
      "grad_norm": 0.43591957791825053,
      "learning_rate": 9.567727288213005e-06,
      "loss": 0.4348,
      "step": 14
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.45424437451203825,
      "learning_rate": 9.478558801197065e-06,
      "loss": 0.4182,
      "step": 15
    },
    {
      "epoch": 0.2048,
      "grad_norm": 0.4439371237451927,
      "learning_rate": 9.381533400219319e-06,
      "loss": 0.4213,
      "step": 16
    },
    {
      "epoch": 0.2176,
      "grad_norm": 0.41164761148505485,
      "learning_rate": 9.276821300802535e-06,
      "loss": 0.4127,
      "step": 17
    },
    {
      "epoch": 0.2304,
      "grad_norm": 0.4093673203201909,
      "learning_rate": 9.164606203550498e-06,
      "loss": 0.4262,
      "step": 18
    },
    {
      "epoch": 0.2432,
      "grad_norm": 0.4144799012568144,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.432,
      "step": 19
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.4082644747468864,
      "learning_rate": 8.9184672866292e-06,
      "loss": 0.4209,
      "step": 20
    },
    {
      "epoch": 0.2688,
      "grad_norm": 0.4593895401140712,
      "learning_rate": 8.784975278258783e-06,
      "loss": 0.4246,
      "step": 21
    },
    {
      "epoch": 0.2816,
      "grad_norm": 0.3885794034551819,
      "learning_rate": 8.644843137107058e-06,
      "loss": 0.4121,
      "step": 22
    },
    {
      "epoch": 0.2944,
      "grad_norm": 0.39392238937848295,
      "learning_rate": 8.498316702566828e-06,
      "loss": 0.4232,
      "step": 23
    },
    {
      "epoch": 0.3072,
      "grad_norm": 0.3872486037058272,
      "learning_rate": 8.345653031794292e-06,
      "loss": 0.4141,
      "step": 24
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.39363127675958814,
      "learning_rate": 8.18711994874345e-06,
      "loss": 0.4107,
      "step": 25
    },
    {
      "epoch": 0.3328,
      "grad_norm": 0.37624153238475666,
      "learning_rate": 8.022995574311876e-06,
      "loss": 0.4271,
      "step": 26
    },
    {
      "epoch": 0.3456,
      "grad_norm": 0.3804093781367258,
      "learning_rate": 7.85356783842216e-06,
      "loss": 0.4219,
      "step": 27
    },
    {
      "epoch": 0.3584,
      "grad_norm": 0.36913249533104836,
      "learning_rate": 7.679133974894984e-06,
      "loss": 0.4128,
      "step": 28
    },
    {
      "epoch": 0.3712,
      "grad_norm": 0.37520342957735603,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.403,
      "step": 29
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.4036337371652964,
      "learning_rate": 7.31648017559931e-06,
      "loss": 0.4143,
      "step": 30
    },
    {
      "epoch": 0.3968,
      "grad_norm": 0.5699162854300589,
      "learning_rate": 7.128896457825364e-06,
      "loss": 0.4181,
      "step": 31
    },
    {
      "epoch": 0.4096,
      "grad_norm": 0.38901177355221755,
      "learning_rate": 6.9375779322605154e-06,
      "loss": 0.4334,
      "step": 32
    },
    {
      "epoch": 0.4224,
      "grad_norm": 0.39470410100606806,
      "learning_rate": 6.7428602366090764e-06,
      "loss": 0.4234,
      "step": 33
    },
    {
      "epoch": 0.4352,
      "grad_norm": 0.36489342907645733,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.4085,
      "step": 34
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.42072792696973443,
      "learning_rate": 6.344599103076329e-06,
      "loss": 0.4127,
      "step": 35
    },
    {
      "epoch": 0.4608,
      "grad_norm": 0.3623627693094219,
      "learning_rate": 6.141754350553279e-06,
      "loss": 0.4023,
      "step": 36
    },
    {
      "epoch": 0.4736,
      "grad_norm": 0.3729221845549037,
      "learning_rate": 5.936906572928625e-06,
      "loss": 0.4114,
      "step": 37
    },
    {
      "epoch": 0.4864,
      "grad_norm": 0.3837141909325611,
      "learning_rate": 5.730415142812059e-06,
      "loss": 0.4096,
      "step": 38
    },
    {
      "epoch": 0.4992,
      "grad_norm": 0.37746036917459397,
      "learning_rate": 5.522642316338268e-06,
      "loss": 0.4245,
      "step": 39
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.36691718532900464,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 0.4112,
      "step": 40
    },
    {
      "epoch": 0.5248,
      "grad_norm": 0.36390767214109315,
      "learning_rate": 5.1047120994167855e-06,
      "loss": 0.4037,
      "step": 41
    },
    {
      "epoch": 0.5376,
      "grad_norm": 0.43125513418612005,
      "learning_rate": 4.895287900583216e-06,
      "loss": 0.4083,
      "step": 42
    },
    {
      "epoch": 0.5504,
      "grad_norm": 0.3477846184326069,
      "learning_rate": 4.686047402353433e-06,
      "loss": 0.4122,
      "step": 43
    },
    {
      "epoch": 0.5632,
      "grad_norm": 0.34969362225455913,
      "learning_rate": 4.477357683661734e-06,
      "loss": 0.4043,
      "step": 44
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.35707239532750956,
      "learning_rate": 4.269584857187942e-06,
      "loss": 0.4127,
      "step": 45
    },
    {
      "epoch": 0.5888,
      "grad_norm": 0.3702993256011211,
      "learning_rate": 4.063093427071376e-06,
      "loss": 0.4053,
      "step": 46
    },
    {
      "epoch": 0.6016,
      "grad_norm": 0.33772426618846585,
      "learning_rate": 3.8582456494467214e-06,
      "loss": 0.4007,
      "step": 47
    },
    {
      "epoch": 0.6144,
      "grad_norm": 0.40624534074941954,
      "learning_rate": 3.655400896923672e-06,
      "loss": 0.408,
      "step": 48
    },
    {
      "epoch": 0.6272,
      "grad_norm": 0.3397306182337386,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.4144,
      "step": 49
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.3623116071261053,
      "learning_rate": 3.2571397633909252e-06,
      "loss": 0.4107,
      "step": 50
    },
    {
      "epoch": 0.6528,
      "grad_norm": 0.3468094093176239,
      "learning_rate": 3.0624220677394854e-06,
      "loss": 0.3995,
      "step": 51
    },
    {
      "epoch": 0.6656,
      "grad_norm": 0.35334981741550653,
      "learning_rate": 2.871103542174637e-06,
      "loss": 0.4233,
      "step": 52
    },
    {
      "epoch": 0.6784,
      "grad_norm": 0.3842932906412869,
      "learning_rate": 2.683519824400693e-06,
      "loss": 0.4051,
      "step": 53
    },
    {
      "epoch": 0.6912,
      "grad_norm": 0.3802867937618585,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.4195,
      "step": 54
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.34507984308007367,
      "learning_rate": 2.320866025105016e-06,
      "loss": 0.4069,
      "step": 55
    },
    {
      "epoch": 0.7168,
      "grad_norm": 0.35634061010002965,
      "learning_rate": 2.146432161577842e-06,
      "loss": 0.401,
      "step": 56
    },
    {
      "epoch": 0.7296,
      "grad_norm": 0.36971727084999223,
      "learning_rate": 1.977004425688126e-06,
      "loss": 0.4089,
      "step": 57
    },
    {
      "epoch": 0.7424,
      "grad_norm": 0.3757664285781387,
      "learning_rate": 1.8128800512565514e-06,
      "loss": 0.4126,
      "step": 58
    },
    {
      "epoch": 0.7552,
      "grad_norm": 0.35039775799504175,
      "learning_rate": 1.6543469682057105e-06,
      "loss": 0.4131,
      "step": 59
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.3467894857268479,
      "learning_rate": 1.5016832974331725e-06,
      "loss": 0.4085,
      "step": 60
    },
    {
      "epoch": 0.7808,
      "grad_norm": 0.3755855396568688,
      "learning_rate": 1.3551568628929434e-06,
      "loss": 0.4008,
      "step": 61
    },
    {
      "epoch": 0.7936,
      "grad_norm": 0.3617494070999663,
      "learning_rate": 1.2150247217412186e-06,
      "loss": 0.4126,
      "step": 62
    },
    {
      "epoch": 0.8064,
      "grad_norm": 0.36584150079037564,
      "learning_rate": 1.0815327133708015e-06,
      "loss": 0.404,
      "step": 63
    },
    {
      "epoch": 0.8192,
      "grad_norm": 0.34541478556277005,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.4065,
      "step": 64
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.369607095142407,
      "learning_rate": 8.353937964495029e-07,
      "loss": 0.4116,
      "step": 65
    },
    {
      "epoch": 0.8448,
      "grad_norm": 0.3659407758862279,
      "learning_rate": 7.23178699197467e-07,
      "loss": 0.4148,
      "step": 66
    },
    {
      "epoch": 0.8576,
      "grad_norm": 0.34102332072690505,
      "learning_rate": 6.184665997806832e-07,
      "loss": 0.4092,
      "step": 67
    },
    {
      "epoch": 0.8704,
      "grad_norm": 0.36059884811292736,
      "learning_rate": 5.214411988029355e-07,
      "loss": 0.4167,
      "step": 68
    },
    {
      "epoch": 0.8832,
      "grad_norm": 0.3490168735870933,
      "learning_rate": 4.322727117869951e-07,
      "loss": 0.4216,
      "step": 69
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.3852693892536214,
      "learning_rate": 3.511175705587433e-07,
      "loss": 0.407,
      "step": 70
    },
    {
      "epoch": 0.9088,
      "grad_norm": 0.35323744614740593,
      "learning_rate": 2.7811814881259503e-07,
      "loss": 0.415,
      "step": 71
    },
    {
      "epoch": 0.9216,
      "grad_norm": 0.35756904195209555,
      "learning_rate": 2.134025123396638e-07,
      "loss": 0.4015,
      "step": 72
    },
    {
      "epoch": 0.9344,
      "grad_norm": 0.3577334516530848,
      "learning_rate": 1.5708419435684463e-07,
      "loss": 0.3999,
      "step": 73
    },
    {
      "epoch": 0.9472,
      "grad_norm": 0.36369247596159854,
      "learning_rate": 1.0926199633097156e-07,
      "loss": 0.4044,
      "step": 74
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.37737890379183897,
      "learning_rate": 7.001981464747565e-08,
      "loss": 0.4088,
      "step": 75
    },
    {
      "epoch": 0.9728,
      "grad_norm": 0.34452940493015555,
      "learning_rate": 3.9426493427611177e-08,
      "loss": 0.3989,
      "step": 76
    },
    {
      "epoch": 0.9856,
      "grad_norm": 0.3760025011133086,
      "learning_rate": 1.753570375247815e-08,
      "loss": 0.4109,
      "step": 77
    },
    {
      "epoch": 0.9984,
      "grad_norm": 0.38685082213633215,
      "learning_rate": 4.385849505708084e-09,
      "loss": 0.405,
      "step": 78
    },
    {
      "epoch": 0.9984,
      "step": 78,
      "total_flos": 119279810772992.0,
      "train_loss": 0.41637224493882596,
      "train_runtime": 907.1839,
      "train_samples_per_second": 11.023,
      "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": 119279810772992.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}