{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.45433893684688775,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.69198923110962,
      "epoch": 0.004543389368468878,
      "grad_norm": 14.25,
      "learning_rate": 2e-06,
      "loss": 10.8255,
      "mean_token_accuracy": 0.0,
      "num_tokens": 10131.0,
      "step": 5
    },
    {
      "entropy": 10.691961860656738,
      "epoch": 0.009086778736937756,
      "grad_norm": 13.9375,
      "learning_rate": 4.5e-06,
      "loss": 10.7543,
      "mean_token_accuracy": 0.00033454534714110195,
      "num_tokens": 20042.0,
      "step": 10
    },
    {
      "entropy": 10.690863990783692,
      "epoch": 0.013630168105406633,
      "grad_norm": 9.8125,
      "learning_rate": 7e-06,
      "loss": 10.5076,
      "mean_token_accuracy": 0.02908163322135806,
      "num_tokens": 30596.0,
      "step": 15
    },
    {
      "entropy": 10.680220794677734,
      "epoch": 0.01817355747387551,
      "grad_norm": 6.5625,
      "learning_rate": 9.5e-06,
      "loss": 10.1604,
      "mean_token_accuracy": 0.04479682110249996,
      "num_tokens": 40667.0,
      "step": 20
    },
    {
      "entropy": 10.61959457397461,
      "epoch": 0.02271694684234439,
      "grad_norm": 4.78125,
      "learning_rate": 1.2e-05,
      "loss": 9.8647,
      "mean_token_accuracy": 0.04831764362752437,
      "num_tokens": 51027.0,
      "step": 25
    },
    {
      "entropy": 10.559894180297851,
      "epoch": 0.027260336210813266,
      "grad_norm": 3.3125,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 9.7234,
      "mean_token_accuracy": 0.043796106800436975,
      "num_tokens": 61860.0,
      "step": 30
    },
    {
      "entropy": 10.580874252319337,
      "epoch": 0.03180372557928214,
      "grad_norm": 2.75,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 9.5845,
      "mean_token_accuracy": 0.042750259116292,
      "num_tokens": 72136.0,
      "step": 35
    },
    {
      "entropy": 10.5773193359375,
      "epoch": 0.03634711494775102,
      "grad_norm": 2.796875,
      "learning_rate": 1.95e-05,
      "loss": 9.561,
      "mean_token_accuracy": 0.0454920094460249,
      "num_tokens": 82611.0,
      "step": 40
    },
    {
      "entropy": 10.545099830627441,
      "epoch": 0.0408905043162199,
      "grad_norm": 2.71875,
      "learning_rate": 2.2e-05,
      "loss": 9.5763,
      "mean_token_accuracy": 0.04643099419772625,
      "num_tokens": 92722.0,
      "step": 45
    },
    {
      "entropy": 10.54197654724121,
      "epoch": 0.04543389368468878,
      "grad_norm": 2.578125,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.4838,
      "mean_token_accuracy": 0.051533405855298045,
      "num_tokens": 103258.0,
      "step": 50
    },
    {
      "entropy": 10.54912166595459,
      "epoch": 0.049977283053157656,
      "grad_norm": 2.59375,
      "learning_rate": 2.7e-05,
      "loss": 9.4581,
      "mean_token_accuracy": 0.050457367300987245,
      "num_tokens": 114277.0,
      "step": 55
    },
    {
      "entropy": 10.54041051864624,
      "epoch": 0.05452067242162653,
      "grad_norm": 2.59375,
      "learning_rate": 2.95e-05,
      "loss": 9.3354,
      "mean_token_accuracy": 0.06432176940143108,
      "num_tokens": 124098.0,
      "step": 60
    },
    {
      "entropy": 10.39171543121338,
      "epoch": 0.059064061790095414,
      "grad_norm": 2.640625,
      "learning_rate": 3.2e-05,
      "loss": 9.2163,
      "mean_token_accuracy": 0.059896310418844224,
      "num_tokens": 133775.0,
      "step": 65
    },
    {
      "entropy": 10.376233863830567,
      "epoch": 0.06360745115856428,
      "grad_norm": 2.546875,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.1789,
      "mean_token_accuracy": 0.06541561521589756,
      "num_tokens": 144765.0,
      "step": 70
    },
    {
      "entropy": 10.435562705993652,
      "epoch": 0.06815084052703317,
      "grad_norm": 2.671875,
      "learning_rate": 3.7e-05,
      "loss": 9.0237,
      "mean_token_accuracy": 0.07151055298745632,
      "num_tokens": 154641.0,
      "step": 75
    },
    {
      "entropy": 10.328177547454834,
      "epoch": 0.07269422989550205,
      "grad_norm": 2.65625,
      "learning_rate": 3.95e-05,
      "loss": 8.9198,
      "mean_token_accuracy": 0.07580552473664284,
      "num_tokens": 164728.0,
      "step": 80
    },
    {
      "entropy": 10.30659589767456,
      "epoch": 0.07723761926397092,
      "grad_norm": 2.796875,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 8.8567,
      "mean_token_accuracy": 0.06854435540735722,
      "num_tokens": 174739.0,
      "step": 85
    },
    {
      "entropy": 10.201157188415527,
      "epoch": 0.0817810086324398,
      "grad_norm": 2.234375,
      "learning_rate": 4.45e-05,
      "loss": 8.7127,
      "mean_token_accuracy": 0.07744735479354858,
      "num_tokens": 184580.0,
      "step": 90
    },
    {
      "entropy": 10.151866340637207,
      "epoch": 0.08632439800090867,
      "grad_norm": 2.1875,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 8.6842,
      "mean_token_accuracy": 0.07533066719770432,
      "num_tokens": 195243.0,
      "step": 95
    },
    {
      "entropy": 10.13199291229248,
      "epoch": 0.09086778736937756,
      "grad_norm": 2.5,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 8.5675,
      "mean_token_accuracy": 0.08015098795294762,
      "num_tokens": 205751.0,
      "step": 100
    },
    {
      "entropy": 10.04837646484375,
      "epoch": 0.09541117673784644,
      "grad_norm": 2.21875,
      "learning_rate": 5.2e-05,
      "loss": 8.4086,
      "mean_token_accuracy": 0.07969476953148842,
      "num_tokens": 217283.0,
      "step": 105
    },
    {
      "entropy": 10.001432323455811,
      "epoch": 0.09995456610631531,
      "grad_norm": 1.9921875,
      "learning_rate": 5.45e-05,
      "loss": 8.3112,
      "mean_token_accuracy": 0.07908041924238204,
      "num_tokens": 226909.0,
      "step": 110
    },
    {
      "entropy": 9.96151065826416,
      "epoch": 0.10449795547478419,
      "grad_norm": 1.9375,
      "learning_rate": 5.7e-05,
      "loss": 8.2717,
      "mean_token_accuracy": 0.0716276228427887,
      "num_tokens": 237343.0,
      "step": 115
    },
    {
      "entropy": 9.76609468460083,
      "epoch": 0.10904134484325306,
      "grad_norm": 1.828125,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.0896,
      "mean_token_accuracy": 0.08059490025043488,
      "num_tokens": 246601.0,
      "step": 120
    },
    {
      "entropy": 9.774349784851074,
      "epoch": 0.11358473421172194,
      "grad_norm": 2.046875,
      "learning_rate": 6.2e-05,
      "loss": 7.9819,
      "mean_token_accuracy": 0.08241913989186286,
      "num_tokens": 256818.0,
      "step": 125
    },
    {
      "entropy": 9.546303367614746,
      "epoch": 0.11812812358019083,
      "grad_norm": 1.671875,
      "learning_rate": 6.450000000000001e-05,
      "loss": 7.792,
      "mean_token_accuracy": 0.08451972156763077,
      "num_tokens": 267157.0,
      "step": 130
    },
    {
      "entropy": 9.346164798736572,
      "epoch": 0.1226715129486597,
      "grad_norm": 1.5625,
      "learning_rate": 6.7e-05,
      "loss": 7.729,
      "mean_token_accuracy": 0.08054408058524132,
      "num_tokens": 277370.0,
      "step": 135
    },
    {
      "entropy": 9.197631072998046,
      "epoch": 0.12721490231712856,
      "grad_norm": 1.8125,
      "learning_rate": 6.950000000000001e-05,
      "loss": 7.6448,
      "mean_token_accuracy": 0.07991334870457649,
      "num_tokens": 287851.0,
      "step": 140
    },
    {
      "entropy": 8.952075290679932,
      "epoch": 0.13175829168559747,
      "grad_norm": 1.9765625,
      "learning_rate": 7.2e-05,
      "loss": 7.6049,
      "mean_token_accuracy": 0.08717379048466682,
      "num_tokens": 299043.0,
      "step": 145
    },
    {
      "entropy": 8.753842163085938,
      "epoch": 0.13630168105406634,
      "grad_norm": 1.390625,
      "learning_rate": 7.45e-05,
      "loss": 7.514,
      "mean_token_accuracy": 0.08479600548744201,
      "num_tokens": 308525.0,
      "step": 150
    },
    {
      "entropy": 8.543214130401612,
      "epoch": 0.14084507042253522,
      "grad_norm": 2.0625,
      "learning_rate": 7.7e-05,
      "loss": 7.3998,
      "mean_token_accuracy": 0.08677626475691795,
      "num_tokens": 318301.0,
      "step": 155
    },
    {
      "entropy": 8.366859912872314,
      "epoch": 0.1453884597910041,
      "grad_norm": 1.2578125,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.3808,
      "mean_token_accuracy": 0.08776860758662224,
      "num_tokens": 329599.0,
      "step": 160
    },
    {
      "entropy": 8.208882141113282,
      "epoch": 0.14993184915947297,
      "grad_norm": 1.4296875,
      "learning_rate": 8.2e-05,
      "loss": 7.2913,
      "mean_token_accuracy": 0.08820515275001525,
      "num_tokens": 339446.0,
      "step": 165
    },
    {
      "entropy": 8.189261150360107,
      "epoch": 0.15447523852794184,
      "grad_norm": 1.515625,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.361,
      "mean_token_accuracy": 0.08676841780543328,
      "num_tokens": 349579.0,
      "step": 170
    },
    {
      "entropy": 8.030198335647583,
      "epoch": 0.15901862789641072,
      "grad_norm": 1.3203125,
      "learning_rate": 8.7e-05,
      "loss": 7.2959,
      "mean_token_accuracy": 0.08807415291666984,
      "num_tokens": 359452.0,
      "step": 175
    },
    {
      "entropy": 7.909095239639282,
      "epoch": 0.1635620172648796,
      "grad_norm": 1.359375,
      "learning_rate": 8.95e-05,
      "loss": 7.2007,
      "mean_token_accuracy": 0.09265701398253441,
      "num_tokens": 369558.0,
      "step": 180
    },
    {
      "entropy": 7.885198545455933,
      "epoch": 0.16810540663334847,
      "grad_norm": 1.5234375,
      "learning_rate": 9.2e-05,
      "loss": 7.2374,
      "mean_token_accuracy": 0.09019400030374528,
      "num_tokens": 380458.0,
      "step": 185
    },
    {
      "entropy": 7.863682413101197,
      "epoch": 0.17264879600181735,
      "grad_norm": 1.3046875,
      "learning_rate": 9.45e-05,
      "loss": 7.2124,
      "mean_token_accuracy": 0.09065315276384353,
      "num_tokens": 390051.0,
      "step": 190
    },
    {
      "entropy": 7.756366014480591,
      "epoch": 0.17719218537028622,
      "grad_norm": 1.5234375,
      "learning_rate": 9.7e-05,
      "loss": 7.1623,
      "mean_token_accuracy": 0.09404176101088524,
      "num_tokens": 400343.0,
      "step": 195
    },
    {
      "entropy": 7.77233304977417,
      "epoch": 0.18173557473875512,
      "grad_norm": 1.2734375,
      "learning_rate": 9.95e-05,
      "loss": 7.1858,
      "mean_token_accuracy": 0.09119251668453217,
      "num_tokens": 410004.0,
      "step": 200
    },
    {
      "entropy": 7.71948881149292,
      "epoch": 0.186278964107224,
      "grad_norm": 1.3203125,
      "learning_rate": 0.000102,
      "loss": 7.1628,
      "mean_token_accuracy": 0.08677014708518982,
      "num_tokens": 421286.0,
      "step": 205
    },
    {
      "entropy": 7.720707845687866,
      "epoch": 0.19082235347569287,
      "grad_norm": 1.0546875,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.1961,
      "mean_token_accuracy": 0.08782461136579514,
      "num_tokens": 432351.0,
      "step": 210
    },
    {
      "entropy": 7.727673149108886,
      "epoch": 0.19536574284416175,
      "grad_norm": 1.4609375,
      "learning_rate": 0.000107,
      "loss": 7.1924,
      "mean_token_accuracy": 0.09309446811676025,
      "num_tokens": 442843.0,
      "step": 215
    },
    {
      "entropy": 7.621369409561157,
      "epoch": 0.19990913221263062,
      "grad_norm": 1.3828125,
      "learning_rate": 0.0001095,
      "loss": 7.0629,
      "mean_token_accuracy": 0.09052515476942062,
      "num_tokens": 453370.0,
      "step": 220
    },
    {
      "entropy": 7.63883638381958,
      "epoch": 0.2044525215810995,
      "grad_norm": 1.4609375,
      "learning_rate": 0.000112,
      "loss": 7.2184,
      "mean_token_accuracy": 0.0872538447380066,
      "num_tokens": 464715.0,
      "step": 225
    },
    {
      "entropy": 7.644190263748169,
      "epoch": 0.20899591094956838,
      "grad_norm": 1.15625,
      "learning_rate": 0.0001145,
      "loss": 7.0549,
      "mean_token_accuracy": 0.0908614382147789,
      "num_tokens": 475086.0,
      "step": 230
    },
    {
      "entropy": 7.491489458084106,
      "epoch": 0.21353930031803725,
      "grad_norm": 1.171875,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.1148,
      "mean_token_accuracy": 0.10133155509829521,
      "num_tokens": 486088.0,
      "step": 235
    },
    {
      "entropy": 7.578480529785156,
      "epoch": 0.21808268968650613,
      "grad_norm": 1.4921875,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.0797,
      "mean_token_accuracy": 0.09119723215699196,
      "num_tokens": 496978.0,
      "step": 240
    },
    {
      "entropy": 7.449330139160156,
      "epoch": 0.222626079054975,
      "grad_norm": 1.09375,
      "learning_rate": 0.000122,
      "loss": 6.864,
      "mean_token_accuracy": 0.1022227019071579,
      "num_tokens": 507794.0,
      "step": 245
    },
    {
      "entropy": 7.454753732681274,
      "epoch": 0.22716946842344388,
      "grad_norm": 1.5078125,
      "learning_rate": 0.0001245,
      "loss": 7.0454,
      "mean_token_accuracy": 0.09052475318312644,
      "num_tokens": 517763.0,
      "step": 250
    },
    {
      "entropy": 7.496077680587769,
      "epoch": 0.23171285779191278,
      "grad_norm": 1.53125,
      "learning_rate": 0.000127,
      "loss": 6.9487,
      "mean_token_accuracy": 0.0943218432366848,
      "num_tokens": 527374.0,
      "step": 255
    },
    {
      "entropy": 7.425622415542603,
      "epoch": 0.23625624716038165,
      "grad_norm": 1.390625,
      "learning_rate": 0.0001295,
      "loss": 7.0141,
      "mean_token_accuracy": 0.09675498828291892,
      "num_tokens": 537435.0,
      "step": 260
    },
    {
      "entropy": 7.358550405502319,
      "epoch": 0.24079963652885053,
      "grad_norm": 1.390625,
      "learning_rate": 0.000132,
      "loss": 6.978,
      "mean_token_accuracy": 0.09722853824496269,
      "num_tokens": 547236.0,
      "step": 265
    },
    {
      "entropy": 7.3646965503692625,
      "epoch": 0.2453430258973194,
      "grad_norm": 1.3671875,
      "learning_rate": 0.00013450000000000002,
      "loss": 6.954,
      "mean_token_accuracy": 0.09657247290015221,
      "num_tokens": 557130.0,
      "step": 270
    },
    {
      "entropy": 7.437637186050415,
      "epoch": 0.24988641526578828,
      "grad_norm": 1.28125,
      "learning_rate": 0.00013700000000000002,
      "loss": 6.968,
      "mean_token_accuracy": 0.09677831679582596,
      "num_tokens": 567482.0,
      "step": 275
    },
    {
      "entropy": 7.320119571685791,
      "epoch": 0.25442980463425713,
      "grad_norm": 1.3046875,
      "learning_rate": 0.0001395,
      "loss": 6.862,
      "mean_token_accuracy": 0.0923498347401619,
      "num_tokens": 577084.0,
      "step": 280
    },
    {
      "entropy": 7.309446048736572,
      "epoch": 0.25897319400272606,
      "grad_norm": 1.328125,
      "learning_rate": 0.00014199999999999998,
      "loss": 6.972,
      "mean_token_accuracy": 0.09742946326732635,
      "num_tokens": 587980.0,
      "step": 285
    },
    {
      "entropy": 7.299356460571289,
      "epoch": 0.26351658337119493,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0001445,
      "loss": 6.8505,
      "mean_token_accuracy": 0.10278590098023414,
      "num_tokens": 598989.0,
      "step": 290
    },
    {
      "entropy": 7.4622321128845215,
      "epoch": 0.2680599727396638,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000147,
      "loss": 7.0462,
      "mean_token_accuracy": 0.09367327913641929,
      "num_tokens": 608599.0,
      "step": 295
    },
    {
      "entropy": 7.311740112304688,
      "epoch": 0.2726033621081327,
      "grad_norm": 1.21875,
      "learning_rate": 0.0001495,
      "loss": 6.8489,
      "mean_token_accuracy": 0.09894169121980667,
      "num_tokens": 619267.0,
      "step": 300
    },
    {
      "entropy": 7.329383373260498,
      "epoch": 0.27714675147660156,
      "grad_norm": 1.2578125,
      "learning_rate": 0.000152,
      "loss": 7.0237,
      "mean_token_accuracy": 0.0995009183883667,
      "num_tokens": 629991.0,
      "step": 305
    },
    {
      "entropy": 7.334739446640015,
      "epoch": 0.28169014084507044,
      "grad_norm": 1.34375,
      "learning_rate": 0.00015450000000000001,
      "loss": 6.9751,
      "mean_token_accuracy": 0.09126680493354797,
      "num_tokens": 641311.0,
      "step": 310
    },
    {
      "entropy": 7.340094423294067,
      "epoch": 0.2862335302135393,
      "grad_norm": 0.953125,
      "learning_rate": 0.000157,
      "loss": 6.9349,
      "mean_token_accuracy": 0.0958991676568985,
      "num_tokens": 651812.0,
      "step": 315
    },
    {
      "entropy": 7.323620367050171,
      "epoch": 0.2907769195820082,
      "grad_norm": 1.203125,
      "learning_rate": 0.0001595,
      "loss": 6.8849,
      "mean_token_accuracy": 0.10023088753223419,
      "num_tokens": 662387.0,
      "step": 320
    },
    {
      "entropy": 7.2562236309051515,
      "epoch": 0.29532030895047706,
      "grad_norm": 1.375,
      "learning_rate": 0.000162,
      "loss": 6.8697,
      "mean_token_accuracy": 0.09553462415933608,
      "num_tokens": 673018.0,
      "step": 325
    },
    {
      "entropy": 7.216851282119751,
      "epoch": 0.29986369831894594,
      "grad_norm": 1.328125,
      "learning_rate": 0.00016450000000000001,
      "loss": 6.8094,
      "mean_token_accuracy": 0.09729016497731209,
      "num_tokens": 683192.0,
      "step": 330
    },
    {
      "entropy": 7.253824520111084,
      "epoch": 0.3044070876874148,
      "grad_norm": 1.5,
      "learning_rate": 0.00016700000000000002,
      "loss": 6.9097,
      "mean_token_accuracy": 0.10488839745521546,
      "num_tokens": 692747.0,
      "step": 335
    },
    {
      "entropy": 7.1223766803741455,
      "epoch": 0.3089504770558837,
      "grad_norm": 1.0625,
      "learning_rate": 0.00016950000000000003,
      "loss": 6.8912,
      "mean_token_accuracy": 0.09245335534214974,
      "num_tokens": 705109.0,
      "step": 340
    },
    {
      "entropy": 7.2870441436767575,
      "epoch": 0.31349386642435256,
      "grad_norm": 1.234375,
      "learning_rate": 0.00017199999999999998,
      "loss": 6.8193,
      "mean_token_accuracy": 0.09904048666357994,
      "num_tokens": 715658.0,
      "step": 345
    },
    {
      "entropy": 7.1810273170471195,
      "epoch": 0.31803725579282144,
      "grad_norm": 1.25,
      "learning_rate": 0.00017449999999999999,
      "loss": 6.8301,
      "mean_token_accuracy": 0.10451033040881157,
      "num_tokens": 724961.0,
      "step": 350
    },
    {
      "entropy": 7.068193769454956,
      "epoch": 0.3225806451612903,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000177,
      "loss": 6.7801,
      "mean_token_accuracy": 0.10440796837210656,
      "num_tokens": 735416.0,
      "step": 355
    },
    {
      "entropy": 7.2093346118927,
      "epoch": 0.3271240345297592,
      "grad_norm": 1.8046875,
      "learning_rate": 0.0001795,
      "loss": 6.8719,
      "mean_token_accuracy": 0.10421840399503708,
      "num_tokens": 745005.0,
      "step": 360
    },
    {
      "entropy": 7.2864179611206055,
      "epoch": 0.33166742389822806,
      "grad_norm": 1.328125,
      "learning_rate": 0.000182,
      "loss": 6.9046,
      "mean_token_accuracy": 0.10184969678521157,
      "num_tokens": 754743.0,
      "step": 365
    },
    {
      "entropy": 7.0180971145629885,
      "epoch": 0.33621081326669694,
      "grad_norm": 1.09375,
      "learning_rate": 0.0001845,
      "loss": 6.7603,
      "mean_token_accuracy": 0.10306568518280983,
      "num_tokens": 764897.0,
      "step": 370
    },
    {
      "entropy": 7.152372789382935,
      "epoch": 0.3407542026351658,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000187,
      "loss": 6.8267,
      "mean_token_accuracy": 0.09857897013425827,
      "num_tokens": 775302.0,
      "step": 375
    },
    {
      "entropy": 7.124710941314698,
      "epoch": 0.3452975920036347,
      "grad_norm": 1.28125,
      "learning_rate": 0.0001895,
      "loss": 6.7588,
      "mean_token_accuracy": 0.10548576042056083,
      "num_tokens": 785694.0,
      "step": 380
    },
    {
      "entropy": 7.054194736480713,
      "epoch": 0.34984098137210357,
      "grad_norm": 1.2265625,
      "learning_rate": 0.000192,
      "loss": 6.72,
      "mean_token_accuracy": 0.11008026450872421,
      "num_tokens": 795045.0,
      "step": 385
    },
    {
      "entropy": 7.09068751335144,
      "epoch": 0.35438437074057244,
      "grad_norm": 1.265625,
      "learning_rate": 0.0001945,
      "loss": 6.781,
      "mean_token_accuracy": 0.10049664527177811,
      "num_tokens": 805579.0,
      "step": 390
    },
    {
      "entropy": 7.095667552947998,
      "epoch": 0.35892776010904137,
      "grad_norm": 1.109375,
      "learning_rate": 0.00019700000000000002,
      "loss": 6.6838,
      "mean_token_accuracy": 0.10740630999207497,
      "num_tokens": 816743.0,
      "step": 395
    },
    {
      "entropy": 7.093503808975219,
      "epoch": 0.36347114947751025,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00019950000000000002,
      "loss": 6.8234,
      "mean_token_accuracy": 0.09930850043892861,
      "num_tokens": 827217.0,
      "step": 400
    },
    {
      "entropy": 7.012804555892944,
      "epoch": 0.3680145388459791,
      "grad_norm": 1.2265625,
      "learning_rate": 0.000202,
      "loss": 6.6731,
      "mean_token_accuracy": 0.10424429401755334,
      "num_tokens": 837555.0,
      "step": 405
    },
    {
      "entropy": 7.039196920394898,
      "epoch": 0.372557928214448,
      "grad_norm": 1.3203125,
      "learning_rate": 0.00020449999999999998,
      "loss": 6.7459,
      "mean_token_accuracy": 0.10508461520075799,
      "num_tokens": 846726.0,
      "step": 410
    },
    {
      "entropy": 7.120304107666016,
      "epoch": 0.3771013175829169,
      "grad_norm": 1.1015625,
      "learning_rate": 0.000207,
      "loss": 6.7475,
      "mean_token_accuracy": 0.10223370566964149,
      "num_tokens": 856535.0,
      "step": 415
    },
    {
      "entropy": 7.005828332901001,
      "epoch": 0.38164470695138575,
      "grad_norm": 1.125,
      "learning_rate": 0.0002095,
      "loss": 6.8069,
      "mean_token_accuracy": 0.09859322756528854,
      "num_tokens": 866973.0,
      "step": 420
    },
    {
      "entropy": 7.085656690597534,
      "epoch": 0.3861880963198546,
      "grad_norm": 1.2734375,
      "learning_rate": 0.000212,
      "loss": 6.7415,
      "mean_token_accuracy": 0.1009980633854866,
      "num_tokens": 877873.0,
      "step": 425
    },
    {
      "entropy": 7.018812036514282,
      "epoch": 0.3907314856883235,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0002145,
      "loss": 6.7335,
      "mean_token_accuracy": 0.10494705140590668,
      "num_tokens": 887135.0,
      "step": 430
    },
    {
      "entropy": 7.096279811859131,
      "epoch": 0.3952748750567924,
      "grad_norm": 1.1640625,
      "learning_rate": 0.00021700000000000002,
      "loss": 6.7514,
      "mean_token_accuracy": 0.10019353330135346,
      "num_tokens": 897206.0,
      "step": 435
    },
    {
      "entropy": 7.024485397338867,
      "epoch": 0.39981826442526125,
      "grad_norm": 1.234375,
      "learning_rate": 0.0002195,
      "loss": 6.7353,
      "mean_token_accuracy": 0.10563584491610527,
      "num_tokens": 906808.0,
      "step": 440
    },
    {
      "entropy": 6.898047828674317,
      "epoch": 0.4043616537937301,
      "grad_norm": 1.265625,
      "learning_rate": 0.000222,
      "loss": 6.6422,
      "mean_token_accuracy": 0.11458711996674538,
      "num_tokens": 917177.0,
      "step": 445
    },
    {
      "entropy": 6.959504508972168,
      "epoch": 0.408905043162199,
      "grad_norm": 1.265625,
      "learning_rate": 0.0002245,
      "loss": 6.6907,
      "mean_token_accuracy": 0.10576008260250092,
      "num_tokens": 927229.0,
      "step": 450
    },
    {
      "entropy": 7.006360816955566,
      "epoch": 0.4134484325306679,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.6812,
      "mean_token_accuracy": 0.11021844074130058,
      "num_tokens": 937832.0,
      "step": 455
    },
    {
      "entropy": 6.870974111557007,
      "epoch": 0.41799182189913675,
      "grad_norm": 1.21875,
      "learning_rate": 0.00022950000000000002,
      "loss": 6.6064,
      "mean_token_accuracy": 0.10718697234988213,
      "num_tokens": 948038.0,
      "step": 460
    },
    {
      "entropy": 7.002683067321778,
      "epoch": 0.4225352112676056,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00023200000000000003,
      "loss": 6.7181,
      "mean_token_accuracy": 0.10097691044211388,
      "num_tokens": 957924.0,
      "step": 465
    },
    {
      "entropy": 6.933505868911743,
      "epoch": 0.4270786006360745,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00023449999999999998,
      "loss": 6.6792,
      "mean_token_accuracy": 0.10600680485367775,
      "num_tokens": 968497.0,
      "step": 470
    },
    {
      "entropy": 6.915420055389404,
      "epoch": 0.4316219900045434,
      "grad_norm": 1.125,
      "learning_rate": 0.000237,
      "loss": 6.6043,
      "mean_token_accuracy": 0.11050590574741363,
      "num_tokens": 978878.0,
      "step": 475
    },
    {
      "entropy": 6.828244590759278,
      "epoch": 0.43616537937301225,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0002395,
      "loss": 6.7024,
      "mean_token_accuracy": 0.10729977861046791,
      "num_tokens": 989984.0,
      "step": 480
    },
    {
      "entropy": 6.974292421340943,
      "epoch": 0.4407087687414811,
      "grad_norm": 1.125,
      "learning_rate": 0.000242,
      "loss": 6.6266,
      "mean_token_accuracy": 0.1099898062646389,
      "num_tokens": 1000254.0,
      "step": 485
    },
    {
      "entropy": 6.815394496917724,
      "epoch": 0.44525215810995,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0002445,
      "loss": 6.687,
      "mean_token_accuracy": 0.10523343607783317,
      "num_tokens": 1010697.0,
      "step": 490
    },
    {
      "entropy": 7.067700672149658,
      "epoch": 0.4497955474784189,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000247,
      "loss": 6.7775,
      "mean_token_accuracy": 0.10482538044452668,
      "num_tokens": 1020892.0,
      "step": 495
    },
    {
      "entropy": 6.969514179229736,
      "epoch": 0.45433893684688775,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0002495,
      "loss": 6.6552,
      "mean_token_accuracy": 0.11519927084445954,
      "num_tokens": 1030380.0,
      "step": 500
    },
    {
      "epoch": 0.45433893684688775,
      "eval_entropy": 6.938153394432955,
      "eval_loss": 6.763866901397705,
      "eval_mean_token_accuracy": 0.10726368882974913,
      "eval_num_tokens": 1030380.0,
      "eval_runtime": 2.6364,
      "eval_samples_per_second": 1302.937,
      "eval_steps_per_second": 163.104,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 11000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 1490466908160000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}