{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1203659123736158,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001203659123736158,
      "grad_norm": 4.625,
      "learning_rate": 2.065577232275662e-05,
      "loss": 1.9427,
      "step": 5
    },
    {
      "epoch": 0.002407318247472316,
      "grad_norm": 3.90625,
      "learning_rate": 4.647548772620239e-05,
      "loss": 1.8343,
      "step": 10
    },
    {
      "epoch": 0.0036109773712084737,
      "grad_norm": 3.09375,
      "learning_rate": 7.229520312964818e-05,
      "loss": 1.7165,
      "step": 15
    },
    {
      "epoch": 0.004814636494944632,
      "grad_norm": 3.09375,
      "learning_rate": 9.811491853309394e-05,
      "loss": 1.5909,
      "step": 20
    },
    {
      "epoch": 0.00601829561868079,
      "grad_norm": 3.6875,
      "learning_rate": 0.00012393463393653973,
      "loss": 1.5327,
      "step": 25
    },
    {
      "epoch": 0.007221954742416947,
      "grad_norm": 3.0625,
      "learning_rate": 0.0001497543493399855,
      "loss": 1.4456,
      "step": 30
    },
    {
      "epoch": 0.008425613866153106,
      "grad_norm": 2.65625,
      "learning_rate": 0.00017557406474343128,
      "loss": 1.3967,
      "step": 35
    },
    {
      "epoch": 0.009629272989889264,
      "grad_norm": 2.90625,
      "learning_rate": 0.0001807379731713583,
      "loss": 1.3353,
      "step": 40
    },
    {
      "epoch": 0.010832932113625422,
      "grad_norm": 3.421875,
      "learning_rate": 0.00018073783239457288,
      "loss": 1.3252,
      "step": 45
    },
    {
      "epoch": 0.01203659123736158,
      "grad_norm": 2.875,
      "learning_rate": 0.00018073758332819127,
      "loss": 1.2706,
      "step": 50
    },
    {
      "epoch": 0.013240250361097737,
      "grad_norm": 3.015625,
      "learning_rate": 0.00018073722597261146,
      "loss": 1.2637,
      "step": 55
    },
    {
      "epoch": 0.014443909484833895,
      "grad_norm": 2.71875,
      "learning_rate": 0.00018073676032840438,
      "loss": 1.218,
      "step": 60
    },
    {
      "epoch": 0.015647568608570053,
      "grad_norm": 2.734375,
      "learning_rate": 0.00018073618639631402,
      "loss": 1.2207,
      "step": 65
    },
    {
      "epoch": 0.016851227732306212,
      "grad_norm": 2.765625,
      "learning_rate": 0.00018073550417725735,
      "loss": 1.1901,
      "step": 70
    },
    {
      "epoch": 0.018054886856042368,
      "grad_norm": 2.4375,
      "learning_rate": 0.0001807347136723244,
      "loss": 1.1795,
      "step": 75
    },
    {
      "epoch": 0.019258545979778528,
      "grad_norm": 2.65625,
      "learning_rate": 0.00018073381488277823,
      "loss": 1.1604,
      "step": 80
    },
    {
      "epoch": 0.020462205103514684,
      "grad_norm": 2.4375,
      "learning_rate": 0.00018073280781005481,
      "loss": 1.1633,
      "step": 85
    },
    {
      "epoch": 0.021665864227250843,
      "grad_norm": 2.671875,
      "learning_rate": 0.00018073169245576325,
      "loss": 1.1536,
      "step": 90
    },
    {
      "epoch": 0.022869523350987,
      "grad_norm": 2.4375,
      "learning_rate": 0.00018073046882168553,
      "loss": 1.1296,
      "step": 95
    },
    {
      "epoch": 0.02407318247472316,
      "grad_norm": 2.515625,
      "learning_rate": 0.00018072913690977675,
      "loss": 1.1209,
      "step": 100
    },
    {
      "epoch": 0.025276841598459315,
      "grad_norm": 2.515625,
      "learning_rate": 0.00018072769672216498,
      "loss": 1.0913,
      "step": 105
    },
    {
      "epoch": 0.026480500722195474,
      "grad_norm": 2.484375,
      "learning_rate": 0.0001807261482611512,
      "loss": 1.1271,
      "step": 110
    },
    {
      "epoch": 0.027684159845931634,
      "grad_norm": 2.71875,
      "learning_rate": 0.00018072449152920953,
      "loss": 1.1263,
      "step": 115
    },
    {
      "epoch": 0.02888781896966779,
      "grad_norm": 2.75,
      "learning_rate": 0.00018072272652898695,
      "loss": 1.0988,
      "step": 120
    },
    {
      "epoch": 0.03009147809340395,
      "grad_norm": 2.296875,
      "learning_rate": 0.0001807208532633035,
      "loss": 1.0511,
      "step": 125
    },
    {
      "epoch": 0.031295137217140105,
      "grad_norm": 2.890625,
      "learning_rate": 0.0001807188717351522,
      "loss": 1.1231,
      "step": 130
    },
    {
      "epoch": 0.03249879634087626,
      "grad_norm": 2.546875,
      "learning_rate": 0.00018071678194769898,
      "loss": 1.054,
      "step": 135
    },
    {
      "epoch": 0.033702455464612424,
      "grad_norm": 2.515625,
      "learning_rate": 0.0001807145839042828,
      "loss": 1.0571,
      "step": 140
    },
    {
      "epoch": 0.03490611458834858,
      "grad_norm": 2.703125,
      "learning_rate": 0.0001807122776084156,
      "loss": 1.0463,
      "step": 145
    },
    {
      "epoch": 0.036109773712084736,
      "grad_norm": 2.296875,
      "learning_rate": 0.00018070986306378223,
      "loss": 1.0482,
      "step": 150
    },
    {
      "epoch": 0.03731343283582089,
      "grad_norm": 2.375,
      "learning_rate": 0.00018070734027424048,
      "loss": 1.0518,
      "step": 155
    },
    {
      "epoch": 0.038517091959557055,
      "grad_norm": 2.25,
      "learning_rate": 0.00018070470924382115,
      "loss": 1.0772,
      "step": 160
    },
    {
      "epoch": 0.03972075108329321,
      "grad_norm": 2.140625,
      "learning_rate": 0.00018070196997672797,
      "loss": 1.0396,
      "step": 165
    },
    {
      "epoch": 0.04092441020702937,
      "grad_norm": 2.484375,
      "learning_rate": 0.00018069912247733758,
      "loss": 1.0425,
      "step": 170
    },
    {
      "epoch": 0.04212806933076553,
      "grad_norm": 2.0625,
      "learning_rate": 0.00018069616675019952,
      "loss": 1.034,
      "step": 175
    },
    {
      "epoch": 0.043331728454501686,
      "grad_norm": 2.265625,
      "learning_rate": 0.00018069310280003633,
      "loss": 1.0382,
      "step": 180
    },
    {
      "epoch": 0.04453538757823784,
      "grad_norm": 1.984375,
      "learning_rate": 0.00018068993063174337,
      "loss": 0.982,
      "step": 185
    },
    {
      "epoch": 0.045739046701974,
      "grad_norm": 2.515625,
      "learning_rate": 0.00018068665025038899,
      "loss": 1.0471,
      "step": 190
    },
    {
      "epoch": 0.04694270582571016,
      "grad_norm": 2.421875,
      "learning_rate": 0.00018068326166121437,
      "loss": 1.002,
      "step": 195
    },
    {
      "epoch": 0.04814636494944632,
      "grad_norm": 2.390625,
      "learning_rate": 0.00018067976486963364,
      "loss": 0.9909,
      "step": 200
    },
    {
      "epoch": 0.04935002407318247,
      "grad_norm": 1.921875,
      "learning_rate": 0.00018067615988123374,
      "loss": 0.9895,
      "step": 205
    },
    {
      "epoch": 0.05055368319691863,
      "grad_norm": 1.921875,
      "learning_rate": 0.00018067244670177452,
      "loss": 0.9895,
      "step": 210
    },
    {
      "epoch": 0.05175734232065479,
      "grad_norm": 2.4375,
      "learning_rate": 0.00018066862533718873,
      "loss": 0.9932,
      "step": 215
    },
    {
      "epoch": 0.05296100144439095,
      "grad_norm": 2.0625,
      "learning_rate": 0.0001806646957935819,
      "loss": 0.9931,
      "step": 220
    },
    {
      "epoch": 0.054164660568127104,
      "grad_norm": 2.28125,
      "learning_rate": 0.00018066065807723243,
      "loss": 0.9888,
      "step": 225
    },
    {
      "epoch": 0.05536831969186327,
      "grad_norm": 2.21875,
      "learning_rate": 0.00018065651219459158,
      "loss": 0.9817,
      "step": 230
    },
    {
      "epoch": 0.05657197881559942,
      "grad_norm": 2.234375,
      "learning_rate": 0.00018065225815228335,
      "loss": 0.9572,
      "step": 235
    },
    {
      "epoch": 0.05777563793933558,
      "grad_norm": 2.09375,
      "learning_rate": 0.00018064789595710468,
      "loss": 0.9525,
      "step": 240
    },
    {
      "epoch": 0.058979297063071735,
      "grad_norm": 2.09375,
      "learning_rate": 0.00018064342561602522,
      "loss": 0.9726,
      "step": 245
    },
    {
      "epoch": 0.0601829561868079,
      "grad_norm": 2.21875,
      "learning_rate": 0.00018063884713618737,
      "loss": 0.9637,
      "step": 250
    },
    {
      "epoch": 0.061386615310544054,
      "grad_norm": 2.203125,
      "learning_rate": 0.00018063416052490648,
      "loss": 0.9902,
      "step": 255
    },
    {
      "epoch": 0.06259027443428021,
      "grad_norm": 2.1875,
      "learning_rate": 0.00018062936578967044,
      "loss": 0.9271,
      "step": 260
    },
    {
      "epoch": 0.06379393355801637,
      "grad_norm": 2.375,
      "learning_rate": 0.00018062446293814008,
      "loss": 0.9563,
      "step": 265
    },
    {
      "epoch": 0.06499759268175252,
      "grad_norm": 2.171875,
      "learning_rate": 0.0001806194519781489,
      "loss": 0.9442,
      "step": 270
    },
    {
      "epoch": 0.06620125180548869,
      "grad_norm": 2.078125,
      "learning_rate": 0.00018061433291770306,
      "loss": 0.945,
      "step": 275
    },
    {
      "epoch": 0.06740491092922485,
      "grad_norm": 2.328125,
      "learning_rate": 0.00018060910576498158,
      "loss": 0.9385,
      "step": 280
    },
    {
      "epoch": 0.068608570052961,
      "grad_norm": 2.296875,
      "learning_rate": 0.0001806037705283361,
      "loss": 0.9244,
      "step": 285
    },
    {
      "epoch": 0.06981222917669716,
      "grad_norm": 2.234375,
      "learning_rate": 0.0001805983272162909,
      "loss": 0.926,
      "step": 290
    },
    {
      "epoch": 0.07101588830043332,
      "grad_norm": 2.40625,
      "learning_rate": 0.00018059277583754304,
      "loss": 0.9232,
      "step": 295
    },
    {
      "epoch": 0.07221954742416947,
      "grad_norm": 2.09375,
      "learning_rate": 0.00018058711640096223,
      "loss": 0.8977,
      "step": 300
    },
    {
      "epoch": 0.07342320654790563,
      "grad_norm": 2.125,
      "learning_rate": 0.00018058134891559078,
      "loss": 0.9126,
      "step": 305
    },
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 2.125,
      "learning_rate": 0.00018057547339064362,
      "loss": 0.9649,
      "step": 310
    },
    {
      "epoch": 0.07583052479537795,
      "grad_norm": 2.265625,
      "learning_rate": 0.00018056948983550834,
      "loss": 0.8945,
      "step": 315
    },
    {
      "epoch": 0.07703418391911411,
      "grad_norm": 2.203125,
      "learning_rate": 0.00018056339825974518,
      "loss": 0.9023,
      "step": 320
    },
    {
      "epoch": 0.07823784304285027,
      "grad_norm": 1.9375,
      "learning_rate": 0.00018055719867308685,
      "loss": 0.907,
      "step": 325
    },
    {
      "epoch": 0.07944150216658642,
      "grad_norm": 2.046875,
      "learning_rate": 0.00018055089108543872,
      "loss": 0.9306,
      "step": 330
    },
    {
      "epoch": 0.08064516129032258,
      "grad_norm": 2.359375,
      "learning_rate": 0.00018054447550687873,
      "loss": 0.9115,
      "step": 335
    },
    {
      "epoch": 0.08184882041405873,
      "grad_norm": 2.03125,
      "learning_rate": 0.00018053795194765732,
      "loss": 0.909,
      "step": 340
    },
    {
      "epoch": 0.08305247953779489,
      "grad_norm": 2.171875,
      "learning_rate": 0.00018053132041819745,
      "loss": 0.8878,
      "step": 345
    },
    {
      "epoch": 0.08425613866153106,
      "grad_norm": 1.90625,
      "learning_rate": 0.00018052458092909456,
      "loss": 0.9281,
      "step": 350
    },
    {
      "epoch": 0.08545979778526722,
      "grad_norm": 2.15625,
      "learning_rate": 0.00018051773349111671,
      "loss": 0.9012,
      "step": 355
    },
    {
      "epoch": 0.08666345690900337,
      "grad_norm": 1.7890625,
      "learning_rate": 0.00018051077811520431,
      "loss": 0.9071,
      "step": 360
    },
    {
      "epoch": 0.08786711603273953,
      "grad_norm": 2.0625,
      "learning_rate": 0.00018050371481247027,
      "loss": 0.9063,
      "step": 365
    },
    {
      "epoch": 0.08907077515647568,
      "grad_norm": 1.859375,
      "learning_rate": 0.00018049654359419994,
      "loss": 0.903,
      "step": 370
    },
    {
      "epoch": 0.09027443428021184,
      "grad_norm": 2.09375,
      "learning_rate": 0.00018048926447185106,
      "loss": 0.9166,
      "step": 375
    },
    {
      "epoch": 0.091478093403948,
      "grad_norm": 1.8359375,
      "learning_rate": 0.00018048187745705387,
      "loss": 0.8833,
      "step": 380
    },
    {
      "epoch": 0.09268175252768417,
      "grad_norm": 2.125,
      "learning_rate": 0.00018047438256161086,
      "loss": 0.8981,
      "step": 385
    },
    {
      "epoch": 0.09388541165142032,
      "grad_norm": 2.03125,
      "learning_rate": 0.00018046677979749698,
      "loss": 0.8898,
      "step": 390
    },
    {
      "epoch": 0.09508907077515648,
      "grad_norm": 1.9609375,
      "learning_rate": 0.00018045906917685947,
      "loss": 0.8837,
      "step": 395
    },
    {
      "epoch": 0.09629272989889263,
      "grad_norm": 2.015625,
      "learning_rate": 0.000180451250712018,
      "loss": 0.8803,
      "step": 400
    },
    {
      "epoch": 0.09749638902262879,
      "grad_norm": 1.8984375,
      "learning_rate": 0.00018044332441546437,
      "loss": 0.8851,
      "step": 405
    },
    {
      "epoch": 0.09870004814636495,
      "grad_norm": 1.9453125,
      "learning_rate": 0.00018043529029986285,
      "loss": 0.8997,
      "step": 410
    },
    {
      "epoch": 0.0999037072701011,
      "grad_norm": 1.9140625,
      "learning_rate": 0.00018042714837804985,
      "loss": 0.8991,
      "step": 415
    },
    {
      "epoch": 0.10110736639383726,
      "grad_norm": 2.03125,
      "learning_rate": 0.0001804188986630341,
      "loss": 0.8939,
      "step": 420
    },
    {
      "epoch": 0.10231102551757343,
      "grad_norm": 2.203125,
      "learning_rate": 0.00018041054116799653,
      "loss": 0.8914,
      "step": 425
    },
    {
      "epoch": 0.10351468464130958,
      "grad_norm": 2.1875,
      "learning_rate": 0.00018040207590629026,
      "loss": 0.8398,
      "step": 430
    },
    {
      "epoch": 0.10471834376504574,
      "grad_norm": 1.8203125,
      "learning_rate": 0.0001803935028914406,
      "loss": 0.8818,
      "step": 435
    },
    {
      "epoch": 0.1059220028887819,
      "grad_norm": 1.953125,
      "learning_rate": 0.00018038482213714508,
      "loss": 0.8518,
      "step": 440
    },
    {
      "epoch": 0.10712566201251805,
      "grad_norm": 2.09375,
      "learning_rate": 0.00018037603365727323,
      "loss": 0.8874,
      "step": 445
    },
    {
      "epoch": 0.10832932113625421,
      "grad_norm": 1.921875,
      "learning_rate": 0.00018036713746586689,
      "loss": 0.8923,
      "step": 450
    },
    {
      "epoch": 0.10953298025999036,
      "grad_norm": 1.7109375,
      "learning_rate": 0.00018035813357713984,
      "loss": 0.8945,
      "step": 455
    },
    {
      "epoch": 0.11073663938372653,
      "grad_norm": 1.71875,
      "learning_rate": 0.00018034902200547796,
      "loss": 0.857,
      "step": 460
    },
    {
      "epoch": 0.11194029850746269,
      "grad_norm": 2.015625,
      "learning_rate": 0.00018033980276543928,
      "loss": 0.8514,
      "step": 465
    },
    {
      "epoch": 0.11314395763119885,
      "grad_norm": 1.703125,
      "learning_rate": 0.0001803304758717537,
      "loss": 0.8674,
      "step": 470
    },
    {
      "epoch": 0.114347616754935,
      "grad_norm": 1.96875,
      "learning_rate": 0.00018032104133932326,
      "loss": 0.9035,
      "step": 475
    },
    {
      "epoch": 0.11555127587867116,
      "grad_norm": 1.7734375,
      "learning_rate": 0.00018031149918322191,
      "loss": 0.8484,
      "step": 480
    },
    {
      "epoch": 0.11675493500240731,
      "grad_norm": 1.9140625,
      "learning_rate": 0.0001803018494186956,
      "loss": 0.8609,
      "step": 485
    },
    {
      "epoch": 0.11795859412614347,
      "grad_norm": 1.875,
      "learning_rate": 0.0001802920920611621,
      "loss": 0.8008,
      "step": 490
    },
    {
      "epoch": 0.11916225324987964,
      "grad_norm": 1.7890625,
      "learning_rate": 0.00018028222712621126,
      "loss": 0.8406,
      "step": 495
    },
    {
      "epoch": 0.1203659123736158,
      "grad_norm": 2.03125,
      "learning_rate": 0.00018027225462960463,
      "loss": 0.8552,
      "step": 500
    },
    {
      "epoch": 0.1203659123736158,
      "eval_loss": 0.7584288716316223,
      "eval_runtime": 2.397,
      "eval_samples_per_second": 83.437,
      "eval_steps_per_second": 83.437,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 12462,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2542017536e+16,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}