{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.42973785990545765,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 7.491108751296997,
      "epoch": 0.004297378599054577,
      "grad_norm": 1.09375,
      "learning_rate": 2e-06,
      "loss": 7.3189,
      "mean_token_accuracy": 0.09141870960593224,
      "num_tokens": 10107.0,
      "step": 5
    },
    {
      "entropy": 7.515214681625366,
      "epoch": 0.008594757198109154,
      "grad_norm": 1.2890625,
      "learning_rate": 4.5e-06,
      "loss": 7.3203,
      "mean_token_accuracy": 0.09664802104234696,
      "num_tokens": 18391.0,
      "step": 10
    },
    {
      "entropy": 7.51798095703125,
      "epoch": 0.01289213579716373,
      "grad_norm": 1.1484375,
      "learning_rate": 7e-06,
      "loss": 7.3336,
      "mean_token_accuracy": 0.09290757700800896,
      "num_tokens": 27061.0,
      "step": 15
    },
    {
      "entropy": 7.496134233474732,
      "epoch": 0.017189514396218308,
      "grad_norm": 1.234375,
      "learning_rate": 9.5e-06,
      "loss": 7.3792,
      "mean_token_accuracy": 0.10020544826984405,
      "num_tokens": 36339.0,
      "step": 20
    },
    {
      "entropy": 7.491674518585205,
      "epoch": 0.021486892995272882,
      "grad_norm": 0.98828125,
      "learning_rate": 1.2e-05,
      "loss": 7.3608,
      "mean_token_accuracy": 0.09223981052637101,
      "num_tokens": 45770.0,
      "step": 25
    },
    {
      "entropy": 7.550447177886963,
      "epoch": 0.02578427159432746,
      "grad_norm": 1.1484375,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 7.3766,
      "mean_token_accuracy": 0.09226111099123954,
      "num_tokens": 54575.0,
      "step": 30
    },
    {
      "entropy": 7.5649909496307375,
      "epoch": 0.030081650193382038,
      "grad_norm": 0.9921875,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 7.4503,
      "mean_token_accuracy": 0.09087274968624115,
      "num_tokens": 66403.0,
      "step": 35
    },
    {
      "entropy": 7.568733358383179,
      "epoch": 0.034379028792436615,
      "grad_norm": 0.96484375,
      "learning_rate": 1.95e-05,
      "loss": 7.3758,
      "mean_token_accuracy": 0.09583879709243774,
      "num_tokens": 76510.0,
      "step": 40
    },
    {
      "entropy": 7.536895418167115,
      "epoch": 0.03867640739149119,
      "grad_norm": 1.0859375,
      "learning_rate": 2.2e-05,
      "loss": 7.2707,
      "mean_token_accuracy": 0.09973574429750443,
      "num_tokens": 84836.0,
      "step": 45
    },
    {
      "entropy": 7.539294195175171,
      "epoch": 0.042973785990545764,
      "grad_norm": 1.078125,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 7.2456,
      "mean_token_accuracy": 0.10200604945421218,
      "num_tokens": 93197.0,
      "step": 50
    },
    {
      "entropy": 7.543957090377807,
      "epoch": 0.047271164589600345,
      "grad_norm": 1.1640625,
      "learning_rate": 2.7e-05,
      "loss": 7.245,
      "mean_token_accuracy": 0.09889603033661842,
      "num_tokens": 101546.0,
      "step": 55
    },
    {
      "entropy": 7.518790864944458,
      "epoch": 0.05156854318865492,
      "grad_norm": 0.93359375,
      "learning_rate": 2.95e-05,
      "loss": 7.3185,
      "mean_token_accuracy": 0.0964392140507698,
      "num_tokens": 111703.0,
      "step": 60
    },
    {
      "entropy": 7.569249010086059,
      "epoch": 0.055865921787709494,
      "grad_norm": 1.0390625,
      "learning_rate": 3.2e-05,
      "loss": 7.2462,
      "mean_token_accuracy": 0.10106701627373696,
      "num_tokens": 119894.0,
      "step": 65
    },
    {
      "entropy": 7.529278564453125,
      "epoch": 0.060163300386764075,
      "grad_norm": 0.97265625,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 7.212,
      "mean_token_accuracy": 0.10316545292735099,
      "num_tokens": 128885.0,
      "step": 70
    },
    {
      "entropy": 7.5085443496704105,
      "epoch": 0.06446067898581866,
      "grad_norm": 0.9921875,
      "learning_rate": 3.7e-05,
      "loss": 7.3341,
      "mean_token_accuracy": 0.09605684131383896,
      "num_tokens": 138106.0,
      "step": 75
    },
    {
      "entropy": 7.545536041259766,
      "epoch": 0.06875805758487323,
      "grad_norm": 1.265625,
      "learning_rate": 3.95e-05,
      "loss": 7.2453,
      "mean_token_accuracy": 0.1033376321196556,
      "num_tokens": 146691.0,
      "step": 80
    },
    {
      "entropy": 7.557823944091797,
      "epoch": 0.0730554361839278,
      "grad_norm": 1.1171875,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 7.2809,
      "mean_token_accuracy": 0.10218598842620849,
      "num_tokens": 155792.0,
      "step": 85
    },
    {
      "entropy": 7.59003210067749,
      "epoch": 0.07735281478298238,
      "grad_norm": 0.9765625,
      "learning_rate": 4.45e-05,
      "loss": 7.358,
      "mean_token_accuracy": 0.09359859973192215,
      "num_tokens": 166944.0,
      "step": 90
    },
    {
      "entropy": 7.617101383209229,
      "epoch": 0.08165019338203695,
      "grad_norm": 1.046875,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 7.1989,
      "mean_token_accuracy": 0.1046324297785759,
      "num_tokens": 175303.0,
      "step": 95
    },
    {
      "entropy": 7.528326416015625,
      "epoch": 0.08594757198109153,
      "grad_norm": 1.0390625,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 7.2591,
      "mean_token_accuracy": 0.10362932458519936,
      "num_tokens": 184708.0,
      "step": 100
    },
    {
      "entropy": 7.538442516326905,
      "epoch": 0.09024495058014612,
      "grad_norm": 1.078125,
      "learning_rate": 5.2e-05,
      "loss": 7.2175,
      "mean_token_accuracy": 0.10121936872601509,
      "num_tokens": 193835.0,
      "step": 105
    },
    {
      "entropy": 7.487286758422852,
      "epoch": 0.09454232917920069,
      "grad_norm": 1.2265625,
      "learning_rate": 5.45e-05,
      "loss": 7.2608,
      "mean_token_accuracy": 0.10149957984685898,
      "num_tokens": 203344.0,
      "step": 110
    },
    {
      "entropy": 7.519776153564453,
      "epoch": 0.09883970777825526,
      "grad_norm": 1.0234375,
      "learning_rate": 5.7e-05,
      "loss": 7.365,
      "mean_token_accuracy": 0.090200637280941,
      "num_tokens": 213048.0,
      "step": 115
    },
    {
      "entropy": 7.641110944747925,
      "epoch": 0.10313708637730984,
      "grad_norm": 1.1484375,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 7.2283,
      "mean_token_accuracy": 0.10701292306184769,
      "num_tokens": 221784.0,
      "step": 120
    },
    {
      "entropy": 7.459906339645386,
      "epoch": 0.10743446497636441,
      "grad_norm": 1.15625,
      "learning_rate": 6.2e-05,
      "loss": 7.2232,
      "mean_token_accuracy": 0.0979800947010517,
      "num_tokens": 230971.0,
      "step": 125
    },
    {
      "entropy": 7.543297910690308,
      "epoch": 0.11173184357541899,
      "grad_norm": 1.1015625,
      "learning_rate": 6.450000000000001e-05,
      "loss": 7.1925,
      "mean_token_accuracy": 0.10740587189793586,
      "num_tokens": 240524.0,
      "step": 130
    },
    {
      "entropy": 7.5613665103912355,
      "epoch": 0.11602922217447358,
      "grad_norm": 0.984375,
      "learning_rate": 6.7e-05,
      "loss": 7.1644,
      "mean_token_accuracy": 0.10438360348343849,
      "num_tokens": 249220.0,
      "step": 135
    },
    {
      "entropy": 7.50055251121521,
      "epoch": 0.12032660077352815,
      "grad_norm": 1.1171875,
      "learning_rate": 6.950000000000001e-05,
      "loss": 7.2801,
      "mean_token_accuracy": 0.10291781276464462,
      "num_tokens": 258934.0,
      "step": 140
    },
    {
      "entropy": 7.580437517166137,
      "epoch": 0.12462397937258272,
      "grad_norm": 1.1171875,
      "learning_rate": 7.2e-05,
      "loss": 7.1981,
      "mean_token_accuracy": 0.10456435978412629,
      "num_tokens": 267680.0,
      "step": 145
    },
    {
      "entropy": 7.493255138397217,
      "epoch": 0.1289213579716373,
      "grad_norm": 1.1171875,
      "learning_rate": 7.45e-05,
      "loss": 7.2271,
      "mean_token_accuracy": 0.10516949817538261,
      "num_tokens": 276227.0,
      "step": 150
    },
    {
      "entropy": 7.456282997131348,
      "epoch": 0.1332187365706919,
      "grad_norm": 1.0859375,
      "learning_rate": 7.7e-05,
      "loss": 7.1356,
      "mean_token_accuracy": 0.10240317732095719,
      "num_tokens": 286342.0,
      "step": 155
    },
    {
      "entropy": 7.478529405593872,
      "epoch": 0.13751611516974646,
      "grad_norm": 1.15625,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.2034,
      "mean_token_accuracy": 0.10278507694602013,
      "num_tokens": 294994.0,
      "step": 160
    },
    {
      "entropy": 7.560914468765259,
      "epoch": 0.14181349376880104,
      "grad_norm": 1.15625,
      "learning_rate": 8.2e-05,
      "loss": 7.1728,
      "mean_token_accuracy": 0.10567683354020119,
      "num_tokens": 303882.0,
      "step": 165
    },
    {
      "entropy": 7.53267731666565,
      "epoch": 0.1461108723678556,
      "grad_norm": 1.09375,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.2185,
      "mean_token_accuracy": 0.10334216356277466,
      "num_tokens": 312515.0,
      "step": 170
    },
    {
      "entropy": 7.510133743286133,
      "epoch": 0.15040825096691018,
      "grad_norm": 1.3046875,
      "learning_rate": 8.7e-05,
      "loss": 7.1819,
      "mean_token_accuracy": 0.1053494967520237,
      "num_tokens": 320801.0,
      "step": 175
    },
    {
      "entropy": 7.564500951766968,
      "epoch": 0.15470562956596476,
      "grad_norm": 1.1796875,
      "learning_rate": 8.95e-05,
      "loss": 7.1958,
      "mean_token_accuracy": 0.10476180166006088,
      "num_tokens": 329382.0,
      "step": 180
    },
    {
      "entropy": 7.523471403121948,
      "epoch": 0.15900300816501933,
      "grad_norm": 1.125,
      "learning_rate": 9.2e-05,
      "loss": 7.1811,
      "mean_token_accuracy": 0.1035641834139824,
      "num_tokens": 337894.0,
      "step": 185
    },
    {
      "entropy": 7.490967750549316,
      "epoch": 0.1633003867640739,
      "grad_norm": 1.265625,
      "learning_rate": 9.45e-05,
      "loss": 7.1711,
      "mean_token_accuracy": 0.10333409234881401,
      "num_tokens": 346380.0,
      "step": 190
    },
    {
      "entropy": 7.575121831893921,
      "epoch": 0.16759776536312848,
      "grad_norm": 1.0234375,
      "learning_rate": 9.7e-05,
      "loss": 7.2686,
      "mean_token_accuracy": 0.09736321717500687,
      "num_tokens": 356305.0,
      "step": 195
    },
    {
      "entropy": 7.543933534622193,
      "epoch": 0.17189514396218306,
      "grad_norm": 1.203125,
      "learning_rate": 9.95e-05,
      "loss": 7.2081,
      "mean_token_accuracy": 0.10070987790822983,
      "num_tokens": 364899.0,
      "step": 200
    },
    {
      "entropy": 7.537495565414429,
      "epoch": 0.17619252256123766,
      "grad_norm": 1.1875,
      "learning_rate": 0.000102,
      "loss": 7.1983,
      "mean_token_accuracy": 0.10088053569197655,
      "num_tokens": 373663.0,
      "step": 205
    },
    {
      "entropy": 7.536725664138794,
      "epoch": 0.18048990116029223,
      "grad_norm": 1.328125,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.1549,
      "mean_token_accuracy": 0.10402223244309425,
      "num_tokens": 382730.0,
      "step": 210
    },
    {
      "entropy": 7.5419622421264645,
      "epoch": 0.1847872797593468,
      "grad_norm": 1.3203125,
      "learning_rate": 0.000107,
      "loss": 7.2121,
      "mean_token_accuracy": 0.09917423650622367,
      "num_tokens": 392676.0,
      "step": 215
    },
    {
      "entropy": 7.498674964904785,
      "epoch": 0.18908465835840138,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0001095,
      "loss": 7.1809,
      "mean_token_accuracy": 0.09803537428379058,
      "num_tokens": 401050.0,
      "step": 220
    },
    {
      "entropy": 7.47620153427124,
      "epoch": 0.19338203695745596,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000112,
      "loss": 7.1693,
      "mean_token_accuracy": 0.10769422501325607,
      "num_tokens": 410009.0,
      "step": 225
    },
    {
      "entropy": 7.477664566040039,
      "epoch": 0.19767941555651053,
      "grad_norm": 1.015625,
      "learning_rate": 0.0001145,
      "loss": 7.1813,
      "mean_token_accuracy": 0.1022846557199955,
      "num_tokens": 419302.0,
      "step": 230
    },
    {
      "entropy": 7.504415702819824,
      "epoch": 0.2019767941555651,
      "grad_norm": 1.28125,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.0897,
      "mean_token_accuracy": 0.11041160002350807,
      "num_tokens": 427296.0,
      "step": 235
    },
    {
      "entropy": 7.440302228927612,
      "epoch": 0.20627417275461968,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.2172,
      "mean_token_accuracy": 0.10320142880082131,
      "num_tokens": 436368.0,
      "step": 240
    },
    {
      "entropy": 7.594078588485718,
      "epoch": 0.21057155135367425,
      "grad_norm": 1.140625,
      "learning_rate": 0.000122,
      "loss": 7.1116,
      "mean_token_accuracy": 0.10851684138178826,
      "num_tokens": 445535.0,
      "step": 245
    },
    {
      "entropy": 7.354097700119018,
      "epoch": 0.21486892995272883,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0001245,
      "loss": 7.1184,
      "mean_token_accuracy": 0.10696499496698379,
      "num_tokens": 454769.0,
      "step": 250
    },
    {
      "entropy": 7.493505668640137,
      "epoch": 0.2191663085517834,
      "grad_norm": 1.28125,
      "learning_rate": 0.000127,
      "loss": 7.1528,
      "mean_token_accuracy": 0.10274568796157837,
      "num_tokens": 463975.0,
      "step": 255
    },
    {
      "entropy": 7.474530839920044,
      "epoch": 0.22346368715083798,
      "grad_norm": 1.25,
      "learning_rate": 0.0001295,
      "loss": 7.1706,
      "mean_token_accuracy": 0.10459161475300789,
      "num_tokens": 472899.0,
      "step": 260
    },
    {
      "entropy": 7.493699789047241,
      "epoch": 0.22776106574989258,
      "grad_norm": 1.15625,
      "learning_rate": 0.000132,
      "loss": 7.1087,
      "mean_token_accuracy": 0.10158660039305686,
      "num_tokens": 481556.0,
      "step": 265
    },
    {
      "entropy": 7.483793687820435,
      "epoch": 0.23205844434894715,
      "grad_norm": 1.1875,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.1274,
      "mean_token_accuracy": 0.10895142033696174,
      "num_tokens": 490253.0,
      "step": 270
    },
    {
      "entropy": 7.462975406646729,
      "epoch": 0.23635582294800173,
      "grad_norm": 1.3671875,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.1663,
      "mean_token_accuracy": 0.10515937954187393,
      "num_tokens": 498444.0,
      "step": 275
    },
    {
      "entropy": 7.426873064041137,
      "epoch": 0.2406532015470563,
      "grad_norm": 1.09375,
      "learning_rate": 0.0001395,
      "loss": 7.093,
      "mean_token_accuracy": 0.11008984223008156,
      "num_tokens": 508330.0,
      "step": 280
    },
    {
      "entropy": 7.484303283691406,
      "epoch": 0.24495058014611087,
      "grad_norm": 1.1875,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.2074,
      "mean_token_accuracy": 0.10344811007380486,
      "num_tokens": 517900.0,
      "step": 285
    },
    {
      "entropy": 7.455639600753784,
      "epoch": 0.24924795874516545,
      "grad_norm": 1.28125,
      "learning_rate": 0.0001445,
      "loss": 7.1342,
      "mean_token_accuracy": 0.10256287604570388,
      "num_tokens": 527808.0,
      "step": 290
    },
    {
      "entropy": 7.514905118942261,
      "epoch": 0.25354533734422,
      "grad_norm": 1.21875,
      "learning_rate": 0.000147,
      "loss": 7.1506,
      "mean_token_accuracy": 0.10260518342256546,
      "num_tokens": 536931.0,
      "step": 295
    },
    {
      "entropy": 7.504227924346924,
      "epoch": 0.2578427159432746,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0001495,
      "loss": 7.1732,
      "mean_token_accuracy": 0.10155779272317886,
      "num_tokens": 545758.0,
      "step": 300
    },
    {
      "entropy": 7.49675178527832,
      "epoch": 0.26214009454232917,
      "grad_norm": 1.203125,
      "learning_rate": 0.000152,
      "loss": 7.1899,
      "mean_token_accuracy": 0.10567427054047585,
      "num_tokens": 555165.0,
      "step": 305
    },
    {
      "entropy": 7.394629907608032,
      "epoch": 0.2664374731413838,
      "grad_norm": 1.234375,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.0983,
      "mean_token_accuracy": 0.10148947015404701,
      "num_tokens": 564719.0,
      "step": 310
    },
    {
      "entropy": 7.432728815078735,
      "epoch": 0.2707348517404383,
      "grad_norm": 1.2578125,
      "learning_rate": 0.000157,
      "loss": 7.0682,
      "mean_token_accuracy": 0.10739247426390648,
      "num_tokens": 573572.0,
      "step": 315
    },
    {
      "entropy": 7.586349010467529,
      "epoch": 0.2750322303394929,
      "grad_norm": 1.421875,
      "learning_rate": 0.0001595,
      "loss": 7.2456,
      "mean_token_accuracy": 0.10255748108029365,
      "num_tokens": 581497.0,
      "step": 320
    },
    {
      "entropy": 7.318369674682617,
      "epoch": 0.27932960893854747,
      "grad_norm": 1.21875,
      "learning_rate": 0.000162,
      "loss": 7.1311,
      "mean_token_accuracy": 0.10708568394184112,
      "num_tokens": 591107.0,
      "step": 325
    },
    {
      "entropy": 7.487468528747558,
      "epoch": 0.28362698753760207,
      "grad_norm": 1.1484375,
      "learning_rate": 0.00016450000000000001,
      "loss": 7.1639,
      "mean_token_accuracy": 0.10406824648380279,
      "num_tokens": 600241.0,
      "step": 330
    },
    {
      "entropy": 7.458619403839111,
      "epoch": 0.2879243661366566,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00016700000000000002,
      "loss": 7.0833,
      "mean_token_accuracy": 0.10933952927589416,
      "num_tokens": 608697.0,
      "step": 335
    },
    {
      "entropy": 7.387399578094483,
      "epoch": 0.2922217447357112,
      "grad_norm": 1.28125,
      "learning_rate": 0.00016950000000000003,
      "loss": 7.0767,
      "mean_token_accuracy": 0.11132601723074913,
      "num_tokens": 617275.0,
      "step": 340
    },
    {
      "entropy": 7.476171684265137,
      "epoch": 0.29651912333476577,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00017199999999999998,
      "loss": 7.1697,
      "mean_token_accuracy": 0.1055254265666008,
      "num_tokens": 626644.0,
      "step": 345
    },
    {
      "entropy": 7.3781880855560305,
      "epoch": 0.30081650193382037,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00017449999999999999,
      "loss": 7.067,
      "mean_token_accuracy": 0.10572395622730255,
      "num_tokens": 635110.0,
      "step": 350
    },
    {
      "entropy": 7.468985176086425,
      "epoch": 0.30511388053287497,
      "grad_norm": 1.1875,
      "learning_rate": 0.000177,
      "loss": 7.2351,
      "mean_token_accuracy": 0.10162713378667831,
      "num_tokens": 644746.0,
      "step": 355
    },
    {
      "entropy": 7.523141098022461,
      "epoch": 0.3094112591319295,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0001795,
      "loss": 7.1415,
      "mean_token_accuracy": 0.10366995185613632,
      "num_tokens": 654281.0,
      "step": 360
    },
    {
      "entropy": 7.358317518234253,
      "epoch": 0.3137086377309841,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000182,
      "loss": 7.1342,
      "mean_token_accuracy": 0.1051877960562706,
      "num_tokens": 663174.0,
      "step": 365
    },
    {
      "entropy": 7.420715570449829,
      "epoch": 0.31800601633003867,
      "grad_norm": 1.15625,
      "learning_rate": 0.0001845,
      "loss": 7.0567,
      "mean_token_accuracy": 0.1060252383351326,
      "num_tokens": 672178.0,
      "step": 370
    },
    {
      "entropy": 7.440627765655518,
      "epoch": 0.32230339492909327,
      "grad_norm": 1.171875,
      "learning_rate": 0.000187,
      "loss": 7.0829,
      "mean_token_accuracy": 0.10851024910807609,
      "num_tokens": 681323.0,
      "step": 375
    },
    {
      "entropy": 7.312611055374146,
      "epoch": 0.3266007735281478,
      "grad_norm": 1.03125,
      "learning_rate": 0.0001895,
      "loss": 7.0134,
      "mean_token_accuracy": 0.1070731021463871,
      "num_tokens": 690461.0,
      "step": 380
    },
    {
      "entropy": 7.485116195678711,
      "epoch": 0.3308981521272024,
      "grad_norm": 1.5390625,
      "learning_rate": 0.000192,
      "loss": 7.038,
      "mean_token_accuracy": 0.10665726512670518,
      "num_tokens": 699199.0,
      "step": 385
    },
    {
      "entropy": 7.286711549758911,
      "epoch": 0.33519553072625696,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0001945,
      "loss": 7.0332,
      "mean_token_accuracy": 0.11690814569592475,
      "num_tokens": 707949.0,
      "step": 390
    },
    {
      "entropy": 7.411632871627807,
      "epoch": 0.33949290932531156,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00019700000000000002,
      "loss": 7.0682,
      "mean_token_accuracy": 0.10877912119030952,
      "num_tokens": 715752.0,
      "step": 395
    },
    {
      "entropy": 7.451524162292481,
      "epoch": 0.3437902879243661,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00019950000000000002,
      "loss": 7.0304,
      "mean_token_accuracy": 0.11193935424089432,
      "num_tokens": 724416.0,
      "step": 400
    },
    {
      "entropy": 7.3398294925689695,
      "epoch": 0.3480876665234207,
      "grad_norm": 1.34375,
      "learning_rate": 0.000202,
      "loss": 7.0979,
      "mean_token_accuracy": 0.10706080496311188,
      "num_tokens": 733116.0,
      "step": 405
    },
    {
      "entropy": 7.373892545700073,
      "epoch": 0.3523850451224753,
      "grad_norm": 1.328125,
      "learning_rate": 0.00020449999999999998,
      "loss": 7.0823,
      "mean_token_accuracy": 0.10571770668029785,
      "num_tokens": 742093.0,
      "step": 410
    },
    {
      "entropy": 7.35628867149353,
      "epoch": 0.35668242372152986,
      "grad_norm": 1.2578125,
      "learning_rate": 0.000207,
      "loss": 7.0485,
      "mean_token_accuracy": 0.11085971966385841,
      "num_tokens": 750402.0,
      "step": 415
    },
    {
      "entropy": 7.272590160369873,
      "epoch": 0.36097980232058446,
      "grad_norm": 1.1796875,
      "learning_rate": 0.0002095,
      "loss": 7.0175,
      "mean_token_accuracy": 0.11432302817702293,
      "num_tokens": 760961.0,
      "step": 420
    },
    {
      "entropy": 7.479759454727173,
      "epoch": 0.365277180919639,
      "grad_norm": 1.203125,
      "learning_rate": 0.000212,
      "loss": 7.1296,
      "mean_token_accuracy": 0.10654517561197281,
      "num_tokens": 770554.0,
      "step": 425
    },
    {
      "entropy": 7.259108257293701,
      "epoch": 0.3695745595186936,
      "grad_norm": 1.3671875,
      "learning_rate": 0.0002145,
      "loss": 7.0763,
      "mean_token_accuracy": 0.11016570776700974,
      "num_tokens": 779172.0,
      "step": 430
    },
    {
      "entropy": 7.46284122467041,
      "epoch": 0.37387193811774816,
      "grad_norm": 1.1875,
      "learning_rate": 0.00021700000000000002,
      "loss": 7.1502,
      "mean_token_accuracy": 0.10204855352640152,
      "num_tokens": 788040.0,
      "step": 435
    },
    {
      "entropy": 7.377580165863037,
      "epoch": 0.37816931671680276,
      "grad_norm": 1.2890625,
      "learning_rate": 0.0002195,
      "loss": 7.0556,
      "mean_token_accuracy": 0.10719484761357308,
      "num_tokens": 796786.0,
      "step": 440
    },
    {
      "entropy": 7.2963978290557865,
      "epoch": 0.3824666953158573,
      "grad_norm": 1.25,
      "learning_rate": 0.000222,
      "loss": 7.0257,
      "mean_token_accuracy": 0.11093981638550758,
      "num_tokens": 805520.0,
      "step": 445
    },
    {
      "entropy": 7.230100870132446,
      "epoch": 0.3867640739149119,
      "grad_norm": 1.453125,
      "learning_rate": 0.0002245,
      "loss": 6.9865,
      "mean_token_accuracy": 0.10948721244931221,
      "num_tokens": 814939.0,
      "step": 450
    },
    {
      "entropy": 7.344197130203247,
      "epoch": 0.39106145251396646,
      "grad_norm": 1.4296875,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.9985,
      "mean_token_accuracy": 0.11251249313354492,
      "num_tokens": 823862.0,
      "step": 455
    },
    {
      "entropy": 7.369870948791504,
      "epoch": 0.39535883111302106,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00022950000000000002,
      "loss": 7.0169,
      "mean_token_accuracy": 0.10975069999694824,
      "num_tokens": 832820.0,
      "step": 460
    },
    {
      "entropy": 7.322132015228272,
      "epoch": 0.39965620971207566,
      "grad_norm": 1.4140625,
      "learning_rate": 0.00023200000000000003,
      "loss": 7.0044,
      "mean_token_accuracy": 0.11229758933186532,
      "num_tokens": 841538.0,
      "step": 465
    },
    {
      "entropy": 7.337738561630249,
      "epoch": 0.4039535883111302,
      "grad_norm": 1.15625,
      "learning_rate": 0.00023449999999999998,
      "loss": 7.1229,
      "mean_token_accuracy": 0.10578583925962448,
      "num_tokens": 851123.0,
      "step": 470
    },
    {
      "entropy": 7.333683729171753,
      "epoch": 0.4082509669101848,
      "grad_norm": 1.3125,
      "learning_rate": 0.000237,
      "loss": 7.0822,
      "mean_token_accuracy": 0.1119972050189972,
      "num_tokens": 860357.0,
      "step": 475
    },
    {
      "entropy": 7.331111764907837,
      "epoch": 0.41254834550923936,
      "grad_norm": 1.28125,
      "learning_rate": 0.0002395,
      "loss": 6.9903,
      "mean_token_accuracy": 0.11009360924363136,
      "num_tokens": 869980.0,
      "step": 480
    },
    {
      "entropy": 7.231062650680542,
      "epoch": 0.41684572410829396,
      "grad_norm": 1.171875,
      "learning_rate": 0.000242,
      "loss": 6.9683,
      "mean_token_accuracy": 0.11301724538207054,
      "num_tokens": 878250.0,
      "step": 485
    },
    {
      "entropy": 7.38806791305542,
      "epoch": 0.4211431027073485,
      "grad_norm": 1.2890625,
      "learning_rate": 0.0002445,
      "loss": 7.0717,
      "mean_token_accuracy": 0.10711101293563843,
      "num_tokens": 887624.0,
      "step": 490
    },
    {
      "entropy": 7.216950559616089,
      "epoch": 0.4254404813064031,
      "grad_norm": 1.265625,
      "learning_rate": 0.000247,
      "loss": 7.0432,
      "mean_token_accuracy": 0.11447345688939095,
      "num_tokens": 897120.0,
      "step": 495
    },
    {
      "entropy": 7.223309516906738,
      "epoch": 0.42973785990545765,
      "grad_norm": 1.15625,
      "learning_rate": 0.0002495,
      "loss": 7.0009,
      "mean_token_accuracy": 0.11249879151582717,
      "num_tokens": 906215.0,
      "step": 500
    },
    {
      "epoch": 0.42973785990545765,
      "eval_entropy": 7.237139492421536,
      "eval_loss": 7.02439546585083,
      "eval_mean_token_accuracy": 0.11452774357822565,
      "eval_num_tokens": 906215.0,
      "eval_runtime": 2.6841,
      "eval_samples_per_second": 1322.226,
      "eval_steps_per_second": 165.418,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 11630,
  "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": 1378388957184000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}