{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0035058401453755047,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.8430669089591743e-05,
      "grad_norm": 10.995234489440918,
      "learning_rate": 6e-06,
      "loss": 36.76142578125,
      "step": 10
    },
    {
      "epoch": 0.00011686133817918349,
      "grad_norm": 10.91879653930664,
      "learning_rate": 1.2666666666666668e-05,
      "loss": 36.63887023925781,
      "step": 20
    },
    {
      "epoch": 0.00017529200726877522,
      "grad_norm": 12.004676818847656,
      "learning_rate": 1.9333333333333333e-05,
      "loss": 36.38578491210937,
      "step": 30
    },
    {
      "epoch": 0.00023372267635836697,
      "grad_norm": 11.3691987991333,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 36.06534118652344,
      "step": 40
    },
    {
      "epoch": 0.0002921533454479587,
      "grad_norm": 13.08530044555664,
      "learning_rate": 3.266666666666667e-05,
      "loss": 35.64937744140625,
      "step": 50
    },
    {
      "epoch": 0.00035058401453755045,
      "grad_norm": 13.18602180480957,
      "learning_rate": 3.933333333333333e-05,
      "loss": 35.051446533203126,
      "step": 60
    },
    {
      "epoch": 0.0004090146836271422,
      "grad_norm": 13.574982643127441,
      "learning_rate": 4.600000000000001e-05,
      "loss": 34.180169677734376,
      "step": 70
    },
    {
      "epoch": 0.00046744535271673395,
      "grad_norm": 14.570645332336426,
      "learning_rate": 5.266666666666666e-05,
      "loss": 33.2185546875,
      "step": 80
    },
    {
      "epoch": 0.0005258760218063257,
      "grad_norm": 16.55890464782715,
      "learning_rate": 5.9333333333333343e-05,
      "loss": 32.12116394042969,
      "step": 90
    },
    {
      "epoch": 0.0005843066908959174,
      "grad_norm": 17.331336975097656,
      "learning_rate": 6.6e-05,
      "loss": 30.47571716308594,
      "step": 100
    },
    {
      "epoch": 0.0006427373599855092,
      "grad_norm": 14.68326187133789,
      "learning_rate": 7.266666666666667e-05,
      "loss": 28.728692626953126,
      "step": 110
    },
    {
      "epoch": 0.0007011680290751009,
      "grad_norm": 18.396814346313477,
      "learning_rate": 7.933333333333334e-05,
      "loss": 26.857958984375,
      "step": 120
    },
    {
      "epoch": 0.0007595986981646927,
      "grad_norm": 16.36812973022461,
      "learning_rate": 8.6e-05,
      "loss": 25.132843017578125,
      "step": 130
    },
    {
      "epoch": 0.0008180293672542844,
      "grad_norm": 21.44991111755371,
      "learning_rate": 9.266666666666666e-05,
      "loss": 23.530233764648436,
      "step": 140
    },
    {
      "epoch": 0.0008764600363438762,
      "grad_norm": 22.47516632080078,
      "learning_rate": 9.933333333333334e-05,
      "loss": 22.332640075683592,
      "step": 150
    },
    {
      "epoch": 0.0009348907054334679,
      "grad_norm": 22.053213119506836,
      "learning_rate": 0.00010600000000000002,
      "loss": 21.743748474121094,
      "step": 160
    },
    {
      "epoch": 0.0009933213745230596,
      "grad_norm": 26.53052520751953,
      "learning_rate": 0.00011266666666666668,
      "loss": 20.7405029296875,
      "step": 170
    },
    {
      "epoch": 0.0010517520436126514,
      "grad_norm": 37.71436309814453,
      "learning_rate": 0.00011933333333333334,
      "loss": 19.994790649414064,
      "step": 180
    },
    {
      "epoch": 0.001110182712702243,
      "grad_norm": 33.68248748779297,
      "learning_rate": 0.000126,
      "loss": 19.59712371826172,
      "step": 190
    },
    {
      "epoch": 0.001168613381791835,
      "grad_norm": 29.311405181884766,
      "learning_rate": 0.00013266666666666667,
      "loss": 19.54248809814453,
      "step": 200
    },
    {
      "epoch": 0.0012270440508814267,
      "grad_norm": 27.571697235107422,
      "learning_rate": 0.00013933333333333335,
      "loss": 18.915852355957032,
      "step": 210
    },
    {
      "epoch": 0.0012854747199710183,
      "grad_norm": 50.6077880859375,
      "learning_rate": 0.000146,
      "loss": 18.705543518066406,
      "step": 220
    },
    {
      "epoch": 0.0013439053890606102,
      "grad_norm": 24.939199447631836,
      "learning_rate": 0.00015266666666666667,
      "loss": 19.156636047363282,
      "step": 230
    },
    {
      "epoch": 0.0014023360581502018,
      "grad_norm": 28.88422393798828,
      "learning_rate": 0.00015933333333333332,
      "loss": 17.941325378417968,
      "step": 240
    },
    {
      "epoch": 0.0014607667272397936,
      "grad_norm": 32.721168518066406,
      "learning_rate": 0.000166,
      "loss": 17.255938720703124,
      "step": 250
    },
    {
      "epoch": 0.0015191973963293855,
      "grad_norm": 44.036075592041016,
      "learning_rate": 0.00017266666666666667,
      "loss": 17.748182678222655,
      "step": 260
    },
    {
      "epoch": 0.001577628065418977,
      "grad_norm": 30.866708755493164,
      "learning_rate": 0.00017933333333333332,
      "loss": 17.471981811523438,
      "step": 270
    },
    {
      "epoch": 0.001636058734508569,
      "grad_norm": 58.11023712158203,
      "learning_rate": 0.00018600000000000002,
      "loss": 17.05304870605469,
      "step": 280
    },
    {
      "epoch": 0.0016944894035981605,
      "grad_norm": 94.0334243774414,
      "learning_rate": 0.0001926666666666667,
      "loss": 16.84721221923828,
      "step": 290
    },
    {
      "epoch": 0.0017529200726877523,
      "grad_norm": 75.26679992675781,
      "learning_rate": 0.00019933333333333334,
      "loss": 16.655764770507812,
      "step": 300
    },
    {
      "epoch": 0.0018113507417773442,
      "grad_norm": NaN,
      "learning_rate": 0.00019999999996000412,
      "loss": 17.352436828613282,
      "step": 310
    },
    {
      "epoch": 0.0018697814108669358,
      "grad_norm": NaN,
      "learning_rate": 0.00019999999982174674,
      "loss": 17.325209045410155,
      "step": 320
    },
    {
      "epoch": 0.0019282120799565276,
      "grad_norm": 421.18212890625,
      "learning_rate": 0.00019999999958473402,
      "loss": 17.76262512207031,
      "step": 330
    },
    {
      "epoch": 0.0019866427490461192,
      "grad_norm": Infinity,
      "learning_rate": 0.00019999999924896604,
      "loss": 17.62756805419922,
      "step": 340
    },
    {
      "epoch": 0.002045073418135711,
      "grad_norm": 128304.0234375,
      "learning_rate": 0.00019999999881444277,
      "loss": 18.896243286132812,
      "step": 350
    },
    {
      "epoch": 0.002103504087225303,
      "grad_norm": 1544019.375,
      "learning_rate": 0.00019999999828116422,
      "loss": 19.169711303710937,
      "step": 360
    },
    {
      "epoch": 0.0021619347563148947,
      "grad_norm": 2917.049072265625,
      "learning_rate": 0.00019999999764913037,
      "loss": 19.900315856933595,
      "step": 370
    },
    {
      "epoch": 0.002220365425404486,
      "grad_norm": 507.0084533691406,
      "learning_rate": 0.00019999999691834125,
      "loss": 20.770042419433594,
      "step": 380
    },
    {
      "epoch": 0.002278796094494078,
      "grad_norm": 6932.96435546875,
      "learning_rate": 0.00019999999608879683,
      "loss": 21.493869018554687,
      "step": 390
    },
    {
      "epoch": 0.00233722676358367,
      "grad_norm": 711.9380493164062,
      "learning_rate": 0.00019999999516049713,
      "loss": 21.287228393554688,
      "step": 400
    },
    {
      "epoch": 0.0023956574326732616,
      "grad_norm": 2512.957275390625,
      "learning_rate": 0.00019999999413344217,
      "loss": 20.687088012695312,
      "step": 410
    },
    {
      "epoch": 0.0024540881017628535,
      "grad_norm": 245.29962158203125,
      "learning_rate": 0.0001999999930076319,
      "loss": 19.545924377441406,
      "step": 420
    },
    {
      "epoch": 0.002512518770852445,
      "grad_norm": 873.497314453125,
      "learning_rate": 0.00019999999178306637,
      "loss": 19.846446228027343,
      "step": 430
    },
    {
      "epoch": 0.0025709494399420367,
      "grad_norm": 273.556884765625,
      "learning_rate": 0.00019999999045974555,
      "loss": 19.4821044921875,
      "step": 440
    },
    {
      "epoch": 0.0026293801090316285,
      "grad_norm": 105.1680679321289,
      "learning_rate": 0.00019999998903766944,
      "loss": 18.83043212890625,
      "step": 450
    },
    {
      "epoch": 0.0026878107781212203,
      "grad_norm": 19779.220703125,
      "learning_rate": 0.00019999998751683804,
      "loss": 18.68498992919922,
      "step": 460
    },
    {
      "epoch": 0.002746241447210812,
      "grad_norm": 379.18695068359375,
      "learning_rate": 0.0001999999858972514,
      "loss": 17.952909851074217,
      "step": 470
    },
    {
      "epoch": 0.0028046721163004036,
      "grad_norm": 982.7449340820312,
      "learning_rate": 0.00019999998417890945,
      "loss": 18.662619018554686,
      "step": 480
    },
    {
      "epoch": 0.0028631027853899954,
      "grad_norm": 264.763671875,
      "learning_rate": 0.00019999998236181225,
      "loss": 18.683988952636717,
      "step": 490
    },
    {
      "epoch": 0.0029215334544795872,
      "grad_norm": 1355.505126953125,
      "learning_rate": 0.0001999999804459598,
      "loss": 18.34948272705078,
      "step": 500
    },
    {
      "epoch": 0.002979964123569179,
      "grad_norm": 106.23206329345703,
      "learning_rate": 0.00019999997843135202,
      "loss": 18.03973388671875,
      "step": 510
    },
    {
      "epoch": 0.003038394792658771,
      "grad_norm": 135.76995849609375,
      "learning_rate": 0.00019999997631798904,
      "loss": 18.432786560058595,
      "step": 520
    },
    {
      "epoch": 0.0030968254617483623,
      "grad_norm": 683.4022216796875,
      "learning_rate": 0.00019999997410587078,
      "loss": 19.00628662109375,
      "step": 530
    },
    {
      "epoch": 0.003155256130837954,
      "grad_norm": 1766.309814453125,
      "learning_rate": 0.00019999997179499722,
      "loss": 18.93055877685547,
      "step": 540
    },
    {
      "epoch": 0.003213686799927546,
      "grad_norm": 12474.607421875,
      "learning_rate": 0.0001999999693853684,
      "loss": 19.35320129394531,
      "step": 550
    },
    {
      "epoch": 0.003272117469017138,
      "grad_norm": 14713.984375,
      "learning_rate": 0.00019999996687698437,
      "loss": 19.091952514648437,
      "step": 560
    },
    {
      "epoch": 0.0033305481381067296,
      "grad_norm": 37941.45703125,
      "learning_rate": 0.00019999996426984504,
      "loss": 18.91400604248047,
      "step": 570
    },
    {
      "epoch": 0.003388978807196321,
      "grad_norm": 40131.44140625,
      "learning_rate": 0.0001999999615639505,
      "loss": 19.18461456298828,
      "step": 580
    },
    {
      "epoch": 0.003447409476285913,
      "grad_norm": 4507.1064453125,
      "learning_rate": 0.00019999995875930068,
      "loss": 19.337628173828126,
      "step": 590
    },
    {
      "epoch": 0.0035058401453755047,
      "grad_norm": 69082.234375,
      "learning_rate": 0.00019999995585589562,
      "loss": 19.456033325195314,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4809098082475008.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}