{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.029521166676507057,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 10.691952991485596,
      "epoch": 0.00029521166676507054,
      "grad_norm": 13.5,
      "learning_rate": 2e-06,
      "loss": 10.8063,
      "mean_token_accuracy": 0.00022093121660873293,
      "num_tokens": 9044.0,
      "step": 5
    },
    {
      "entropy": 10.691949939727783,
      "epoch": 0.0005904233335301411,
      "grad_norm": 12.3125,
      "learning_rate": 4.5e-06,
      "loss": 10.7746,
      "mean_token_accuracy": 0.00021052630618214607,
      "num_tokens": 20049.0,
      "step": 10
    },
    {
      "entropy": 10.691005229949951,
      "epoch": 0.0008856350002952116,
      "grad_norm": 10.5,
      "learning_rate": 7e-06,
      "loss": 10.5243,
      "mean_token_accuracy": 0.02576384658459574,
      "num_tokens": 30441.0,
      "step": 15
    },
    {
      "entropy": 10.681586647033692,
      "epoch": 0.0011808466670602822,
      "grad_norm": 6.03125,
      "learning_rate": 9.5e-06,
      "loss": 10.1811,
      "mean_token_accuracy": 0.04208611287176609,
      "num_tokens": 41245.0,
      "step": 20
    },
    {
      "entropy": 10.640601921081544,
      "epoch": 0.0014760583338253527,
      "grad_norm": 4.0625,
      "learning_rate": 1.2e-05,
      "loss": 9.9191,
      "mean_token_accuracy": 0.041578793339431284,
      "num_tokens": 51815.0,
      "step": 25
    },
    {
      "entropy": 10.59462308883667,
      "epoch": 0.0017712700005904232,
      "grad_norm": 3.203125,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 9.7236,
      "mean_token_accuracy": 0.046854367852211,
      "num_tokens": 62291.0,
      "step": 30
    },
    {
      "entropy": 10.566697216033935,
      "epoch": 0.002066481667355494,
      "grad_norm": 2.765625,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 9.6479,
      "mean_token_accuracy": 0.04647400453686714,
      "num_tokens": 72859.0,
      "step": 35
    },
    {
      "entropy": 10.56708059310913,
      "epoch": 0.0023616933341205643,
      "grad_norm": 2.609375,
      "learning_rate": 1.95e-05,
      "loss": 9.6398,
      "mean_token_accuracy": 0.04794426709413528,
      "num_tokens": 83349.0,
      "step": 40
    },
    {
      "entropy": 10.572033309936524,
      "epoch": 0.002656905000885635,
      "grad_norm": 2.46875,
      "learning_rate": 2.2e-05,
      "loss": 9.6101,
      "mean_token_accuracy": 0.04311534278094768,
      "num_tokens": 93550.0,
      "step": 45
    },
    {
      "entropy": 10.580781936645508,
      "epoch": 0.0029521166676507054,
      "grad_norm": 2.375,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.5518,
      "mean_token_accuracy": 0.0487774446606636,
      "num_tokens": 104354.0,
      "step": 50
    },
    {
      "entropy": 10.563411712646484,
      "epoch": 0.003247328334415776,
      "grad_norm": 2.296875,
      "learning_rate": 2.7e-05,
      "loss": 9.4688,
      "mean_token_accuracy": 0.05522352792322636,
      "num_tokens": 114901.0,
      "step": 55
    },
    {
      "entropy": 10.49093132019043,
      "epoch": 0.0035425400011808465,
      "grad_norm": 2.453125,
      "learning_rate": 2.95e-05,
      "loss": 9.3461,
      "mean_token_accuracy": 0.05991581827402115,
      "num_tokens": 125378.0,
      "step": 60
    },
    {
      "entropy": 10.3884859085083,
      "epoch": 0.0038377516679459172,
      "grad_norm": 2.28125,
      "learning_rate": 3.2e-05,
      "loss": 9.2938,
      "mean_token_accuracy": 0.05960136093199253,
      "num_tokens": 136074.0,
      "step": 65
    },
    {
      "entropy": 10.436979675292969,
      "epoch": 0.004132963334710988,
      "grad_norm": 2.21875,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.1677,
      "mean_token_accuracy": 0.06536128893494605,
      "num_tokens": 147517.0,
      "step": 70
    },
    {
      "entropy": 10.378404426574708,
      "epoch": 0.004428175001476058,
      "grad_norm": 2.34375,
      "learning_rate": 3.7e-05,
      "loss": 9.0427,
      "mean_token_accuracy": 0.07047605030238628,
      "num_tokens": 158398.0,
      "step": 75
    },
    {
      "entropy": 10.407978820800782,
      "epoch": 0.004723386668241129,
      "grad_norm": 2.359375,
      "learning_rate": 3.95e-05,
      "loss": 8.9631,
      "mean_token_accuracy": 0.07082438990473747,
      "num_tokens": 168721.0,
      "step": 80
    },
    {
      "entropy": 10.277961730957031,
      "epoch": 0.0050185983350062,
      "grad_norm": 2.453125,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 8.9505,
      "mean_token_accuracy": 0.06753718703985215,
      "num_tokens": 179053.0,
      "step": 85
    },
    {
      "entropy": 10.263121604919434,
      "epoch": 0.00531381000177127,
      "grad_norm": 2.1875,
      "learning_rate": 4.45e-05,
      "loss": 8.81,
      "mean_token_accuracy": 0.06845465488731861,
      "num_tokens": 189377.0,
      "step": 90
    },
    {
      "entropy": 10.137414455413818,
      "epoch": 0.0056090216685363405,
      "grad_norm": 2.078125,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 8.6659,
      "mean_token_accuracy": 0.08077330142259598,
      "num_tokens": 199316.0,
      "step": 95
    },
    {
      "entropy": 10.143539524078369,
      "epoch": 0.005904233335301411,
      "grad_norm": 2.03125,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 8.5703,
      "mean_token_accuracy": 0.07332179993391037,
      "num_tokens": 209735.0,
      "step": 100
    },
    {
      "entropy": 10.063137626647949,
      "epoch": 0.006199445002066482,
      "grad_norm": 1.9296875,
      "learning_rate": 5.2e-05,
      "loss": 8.5061,
      "mean_token_accuracy": 0.07544220425188541,
      "num_tokens": 220153.0,
      "step": 105
    },
    {
      "entropy": 10.078357124328614,
      "epoch": 0.006494656668831552,
      "grad_norm": 1.8359375,
      "learning_rate": 5.45e-05,
      "loss": 8.4012,
      "mean_token_accuracy": 0.07546676695346832,
      "num_tokens": 231226.0,
      "step": 110
    },
    {
      "entropy": 9.911471176147462,
      "epoch": 0.006789868335596623,
      "grad_norm": 1.8515625,
      "learning_rate": 5.7e-05,
      "loss": 8.2365,
      "mean_token_accuracy": 0.07300828918814659,
      "num_tokens": 241715.0,
      "step": 115
    },
    {
      "entropy": 9.870896339416504,
      "epoch": 0.007085080002361693,
      "grad_norm": 1.5859375,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.122,
      "mean_token_accuracy": 0.07934067547321319,
      "num_tokens": 253683.0,
      "step": 120
    },
    {
      "entropy": 9.708064746856689,
      "epoch": 0.007380291669126764,
      "grad_norm": 1.75,
      "learning_rate": 6.2e-05,
      "loss": 7.9982,
      "mean_token_accuracy": 0.07759345918893815,
      "num_tokens": 262863.0,
      "step": 125
    },
    {
      "entropy": 9.583840370178223,
      "epoch": 0.0076755033358918345,
      "grad_norm": 1.640625,
      "learning_rate": 6.450000000000001e-05,
      "loss": 7.9066,
      "mean_token_accuracy": 0.07621643394231796,
      "num_tokens": 273237.0,
      "step": 130
    },
    {
      "entropy": 9.455964183807373,
      "epoch": 0.007970715002656906,
      "grad_norm": 1.5390625,
      "learning_rate": 6.7e-05,
      "loss": 7.8192,
      "mean_token_accuracy": 0.0756739940494299,
      "num_tokens": 283772.0,
      "step": 135
    },
    {
      "entropy": 9.128956699371338,
      "epoch": 0.008265926669421976,
      "grad_norm": 1.5859375,
      "learning_rate": 6.950000000000001e-05,
      "loss": 7.686,
      "mean_token_accuracy": 0.08342597484588624,
      "num_tokens": 294776.0,
      "step": 140
    },
    {
      "entropy": 8.970587921142577,
      "epoch": 0.008561138336187046,
      "grad_norm": 1.453125,
      "learning_rate": 7.2e-05,
      "loss": 7.6361,
      "mean_token_accuracy": 0.07761476486921311,
      "num_tokens": 305244.0,
      "step": 145
    },
    {
      "entropy": 8.766981601715088,
      "epoch": 0.008856350002952117,
      "grad_norm": 1.328125,
      "learning_rate": 7.45e-05,
      "loss": 7.5218,
      "mean_token_accuracy": 0.08236418589949608,
      "num_tokens": 315175.0,
      "step": 150
    },
    {
      "entropy": 8.568089389801026,
      "epoch": 0.009151561669717187,
      "grad_norm": 1.328125,
      "learning_rate": 7.7e-05,
      "loss": 7.444,
      "mean_token_accuracy": 0.07824666872620582,
      "num_tokens": 326648.0,
      "step": 155
    },
    {
      "entropy": 8.377489757537841,
      "epoch": 0.009446773336482257,
      "grad_norm": 1.2421875,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.4133,
      "mean_token_accuracy": 0.07897001653909683,
      "num_tokens": 336905.0,
      "step": 160
    },
    {
      "entropy": 8.255996799468994,
      "epoch": 0.009741985003247328,
      "grad_norm": 1.3359375,
      "learning_rate": 8.2e-05,
      "loss": 7.3357,
      "mean_token_accuracy": 0.08415433838963508,
      "num_tokens": 348163.0,
      "step": 165
    },
    {
      "entropy": 8.156648921966553,
      "epoch": 0.0100371966700124,
      "grad_norm": 1.3359375,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.3681,
      "mean_token_accuracy": 0.08406007140874863,
      "num_tokens": 359420.0,
      "step": 170
    },
    {
      "entropy": 8.059180402755738,
      "epoch": 0.01033240833677747,
      "grad_norm": 1.328125,
      "learning_rate": 8.7e-05,
      "loss": 7.2938,
      "mean_token_accuracy": 0.08481760621070862,
      "num_tokens": 369712.0,
      "step": 175
    },
    {
      "entropy": 7.922717761993408,
      "epoch": 0.01062762000354254,
      "grad_norm": 1.234375,
      "learning_rate": 8.95e-05,
      "loss": 7.2317,
      "mean_token_accuracy": 0.08849364891648293,
      "num_tokens": 380413.0,
      "step": 180
    },
    {
      "entropy": 7.878174924850464,
      "epoch": 0.01092283167030761,
      "grad_norm": 1.3984375,
      "learning_rate": 9.2e-05,
      "loss": 7.2576,
      "mean_token_accuracy": 0.08616138696670532,
      "num_tokens": 391428.0,
      "step": 185
    },
    {
      "entropy": 7.907813787460327,
      "epoch": 0.011218043337072681,
      "grad_norm": 1.2109375,
      "learning_rate": 9.45e-05,
      "loss": 7.1902,
      "mean_token_accuracy": 0.08708868958055974,
      "num_tokens": 402383.0,
      "step": 190
    },
    {
      "entropy": 7.741433143615723,
      "epoch": 0.011513255003837751,
      "grad_norm": 1.4453125,
      "learning_rate": 9.7e-05,
      "loss": 7.2219,
      "mean_token_accuracy": 0.08469741642475129,
      "num_tokens": 412692.0,
      "step": 195
    },
    {
      "entropy": 7.7598718166351315,
      "epoch": 0.011808466670602822,
      "grad_norm": 1.640625,
      "learning_rate": 9.95e-05,
      "loss": 7.1954,
      "mean_token_accuracy": 0.08851397931575775,
      "num_tokens": 423175.0,
      "step": 200
    },
    {
      "entropy": 7.6599428176879885,
      "epoch": 0.012103678337367892,
      "grad_norm": 1.4609375,
      "learning_rate": 0.000102,
      "loss": 7.164,
      "mean_token_accuracy": 0.08638672009110451,
      "num_tokens": 433076.0,
      "step": 205
    },
    {
      "entropy": 7.721544361114502,
      "epoch": 0.012398890004132964,
      "grad_norm": 1.296875,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.1491,
      "mean_token_accuracy": 0.08772207424044609,
      "num_tokens": 443338.0,
      "step": 210
    },
    {
      "entropy": 7.719466781616211,
      "epoch": 0.012694101670898034,
      "grad_norm": 1.21875,
      "learning_rate": 0.000107,
      "loss": 7.0918,
      "mean_token_accuracy": 0.08484251573681831,
      "num_tokens": 453674.0,
      "step": 215
    },
    {
      "entropy": 7.642396736145019,
      "epoch": 0.012989313337663105,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0001095,
      "loss": 7.112,
      "mean_token_accuracy": 0.0881990872323513,
      "num_tokens": 464660.0,
      "step": 220
    },
    {
      "entropy": 7.623027515411377,
      "epoch": 0.013284525004428175,
      "grad_norm": 1.109375,
      "learning_rate": 0.000112,
      "loss": 7.135,
      "mean_token_accuracy": 0.08962138071656227,
      "num_tokens": 475478.0,
      "step": 225
    },
    {
      "entropy": 7.573812961578369,
      "epoch": 0.013579736671193245,
      "grad_norm": 1.328125,
      "learning_rate": 0.0001145,
      "loss": 7.0507,
      "mean_token_accuracy": 0.0912325844168663,
      "num_tokens": 486279.0,
      "step": 230
    },
    {
      "entropy": 7.559884262084961,
      "epoch": 0.013874948337958316,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.1265,
      "mean_token_accuracy": 0.08900480046868324,
      "num_tokens": 497947.0,
      "step": 235
    },
    {
      "entropy": 7.493877267837524,
      "epoch": 0.014170160004723386,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00011949999999999999,
      "loss": 6.948,
      "mean_token_accuracy": 0.09850702658295632,
      "num_tokens": 508492.0,
      "step": 240
    },
    {
      "entropy": 7.5359265327453615,
      "epoch": 0.014465371671488458,
      "grad_norm": 1.296875,
      "learning_rate": 0.000122,
      "loss": 7.034,
      "mean_token_accuracy": 0.09341262727975845,
      "num_tokens": 519231.0,
      "step": 245
    },
    {
      "entropy": 7.547327709197998,
      "epoch": 0.014760583338253528,
      "grad_norm": 1.5,
      "learning_rate": 0.0001245,
      "loss": 7.0388,
      "mean_token_accuracy": 0.08856186792254447,
      "num_tokens": 529936.0,
      "step": 250
    },
    {
      "entropy": 7.387069749832153,
      "epoch": 0.015055795005018599,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000127,
      "loss": 7.0339,
      "mean_token_accuracy": 0.09349972456693649,
      "num_tokens": 540315.0,
      "step": 255
    },
    {
      "entropy": 7.444060134887695,
      "epoch": 0.015351006671783669,
      "grad_norm": 1.203125,
      "learning_rate": 0.0001295,
      "loss": 6.9648,
      "mean_token_accuracy": 0.097850751131773,
      "num_tokens": 551587.0,
      "step": 260
    },
    {
      "entropy": 7.412183332443237,
      "epoch": 0.01564621833854874,
      "grad_norm": 1.234375,
      "learning_rate": 0.000132,
      "loss": 6.9316,
      "mean_token_accuracy": 0.09379192665219308,
      "num_tokens": 561857.0,
      "step": 265
    },
    {
      "entropy": 7.429265975952148,
      "epoch": 0.01594143000531381,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00013450000000000002,
      "loss": 6.9717,
      "mean_token_accuracy": 0.09063394144177436,
      "num_tokens": 571784.0,
      "step": 270
    },
    {
      "entropy": 7.434524583816528,
      "epoch": 0.01623664167207888,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.0056,
      "mean_token_accuracy": 0.09408731907606124,
      "num_tokens": 583475.0,
      "step": 275
    },
    {
      "entropy": 7.450810766220092,
      "epoch": 0.016531853338843952,
      "grad_norm": 1.203125,
      "learning_rate": 0.0001395,
      "loss": 6.9856,
      "mean_token_accuracy": 0.08944389000535011,
      "num_tokens": 594752.0,
      "step": 280
    },
    {
      "entropy": 7.2732994556427,
      "epoch": 0.016827065005609022,
      "grad_norm": 1.3125,
      "learning_rate": 0.00014199999999999998,
      "loss": 6.9268,
      "mean_token_accuracy": 0.09354007542133332,
      "num_tokens": 604459.0,
      "step": 285
    },
    {
      "entropy": 7.404242277145386,
      "epoch": 0.017122276672374093,
      "grad_norm": 1.3828125,
      "learning_rate": 0.0001445,
      "loss": 6.9605,
      "mean_token_accuracy": 0.09190556928515434,
      "num_tokens": 615477.0,
      "step": 290
    },
    {
      "entropy": 7.318359518051148,
      "epoch": 0.017417488339139163,
      "grad_norm": 1.2734375,
      "learning_rate": 0.000147,
      "loss": 6.9085,
      "mean_token_accuracy": 0.09038040712475777,
      "num_tokens": 626527.0,
      "step": 295
    },
    {
      "entropy": 7.3704808235168455,
      "epoch": 0.017712700005904233,
      "grad_norm": 1.109375,
      "learning_rate": 0.0001495,
      "loss": 6.9326,
      "mean_token_accuracy": 0.08688042685389519,
      "num_tokens": 638236.0,
      "step": 300
    },
    {
      "entropy": 7.292983913421631,
      "epoch": 0.018007911672669304,
      "grad_norm": 1.0625,
      "learning_rate": 0.000152,
      "loss": 6.9029,
      "mean_token_accuracy": 0.0930778980255127,
      "num_tokens": 648836.0,
      "step": 305
    },
    {
      "entropy": 7.261309051513672,
      "epoch": 0.018303123339434374,
      "grad_norm": 1.359375,
      "learning_rate": 0.00015450000000000001,
      "loss": 6.8546,
      "mean_token_accuracy": 0.09702132865786553,
      "num_tokens": 659610.0,
      "step": 310
    },
    {
      "entropy": 7.29406886100769,
      "epoch": 0.018598335006199444,
      "grad_norm": 1.0078125,
      "learning_rate": 0.000157,
      "loss": 6.9224,
      "mean_token_accuracy": 0.0894104540348053,
      "num_tokens": 671423.0,
      "step": 315
    },
    {
      "entropy": 7.343613338470459,
      "epoch": 0.018893546672964515,
      "grad_norm": 1.1796875,
      "learning_rate": 0.0001595,
      "loss": 6.8996,
      "mean_token_accuracy": 0.08960375934839249,
      "num_tokens": 682645.0,
      "step": 320
    },
    {
      "entropy": 7.207725191116333,
      "epoch": 0.019188758339729585,
      "grad_norm": 1.3203125,
      "learning_rate": 0.000162,
      "loss": 6.8131,
      "mean_token_accuracy": 0.09437809884548187,
      "num_tokens": 692315.0,
      "step": 325
    },
    {
      "entropy": 7.3380321025848385,
      "epoch": 0.019483970006494655,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00016450000000000001,
      "loss": 6.8965,
      "mean_token_accuracy": 0.09695785492658615,
      "num_tokens": 702973.0,
      "step": 330
    },
    {
      "entropy": 7.216346549987793,
      "epoch": 0.019779181673259726,
      "grad_norm": 1.1953125,
      "learning_rate": 0.00016700000000000002,
      "loss": 6.8629,
      "mean_token_accuracy": 0.0920400932431221,
      "num_tokens": 713787.0,
      "step": 335
    },
    {
      "entropy": 7.180256462097168,
      "epoch": 0.0200743933400248,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00016950000000000003,
      "loss": 6.7804,
      "mean_token_accuracy": 0.09937777146697044,
      "num_tokens": 725357.0,
      "step": 340
    },
    {
      "entropy": 7.094199705123901,
      "epoch": 0.02036960500678987,
      "grad_norm": 1.1875,
      "learning_rate": 0.00017199999999999998,
      "loss": 6.7488,
      "mean_token_accuracy": 0.10237349718809127,
      "num_tokens": 735003.0,
      "step": 345
    },
    {
      "entropy": 7.314488554000855,
      "epoch": 0.02066481667355494,
      "grad_norm": 1.2890625,
      "learning_rate": 0.00017449999999999999,
      "loss": 6.8222,
      "mean_token_accuracy": 0.09937268868088722,
      "num_tokens": 747278.0,
      "step": 350
    },
    {
      "entropy": 7.053475475311279,
      "epoch": 0.02096002834032001,
      "grad_norm": 1.3125,
      "learning_rate": 0.000177,
      "loss": 6.8199,
      "mean_token_accuracy": 0.0992422841489315,
      "num_tokens": 757974.0,
      "step": 355
    },
    {
      "entropy": 7.2850106716156,
      "epoch": 0.02125524000708508,
      "grad_norm": 1.265625,
      "learning_rate": 0.0001795,
      "loss": 6.8103,
      "mean_token_accuracy": 0.09952985718846322,
      "num_tokens": 767584.0,
      "step": 360
    },
    {
      "entropy": 7.131100606918335,
      "epoch": 0.02155045167385015,
      "grad_norm": 1.2421875,
      "learning_rate": 0.000182,
      "loss": 6.7109,
      "mean_token_accuracy": 0.09645930156111718,
      "num_tokens": 777397.0,
      "step": 365
    },
    {
      "entropy": 7.148231458663941,
      "epoch": 0.02184566334061522,
      "grad_norm": 1.171875,
      "learning_rate": 0.0001845,
      "loss": 6.7905,
      "mean_token_accuracy": 0.09331258609890938,
      "num_tokens": 788227.0,
      "step": 370
    },
    {
      "entropy": 7.114551830291748,
      "epoch": 0.02214087500738029,
      "grad_norm": 1.0703125,
      "learning_rate": 0.000187,
      "loss": 6.7458,
      "mean_token_accuracy": 0.09811887294054031,
      "num_tokens": 799168.0,
      "step": 375
    },
    {
      "entropy": 7.097161912918091,
      "epoch": 0.022436086674145362,
      "grad_norm": 1.1796875,
      "learning_rate": 0.0001895,
      "loss": 6.7355,
      "mean_token_accuracy": 0.10040534660220146,
      "num_tokens": 810199.0,
      "step": 380
    },
    {
      "entropy": 7.139192867279053,
      "epoch": 0.022731298340910432,
      "grad_norm": 1.3515625,
      "learning_rate": 0.000192,
      "loss": 6.7409,
      "mean_token_accuracy": 0.09671718701720237,
      "num_tokens": 822391.0,
      "step": 385
    },
    {
      "entropy": 7.088096618652344,
      "epoch": 0.023026510007675503,
      "grad_norm": 1.15625,
      "learning_rate": 0.0001945,
      "loss": 6.8565,
      "mean_token_accuracy": 0.09625174552202224,
      "num_tokens": 834350.0,
      "step": 390
    },
    {
      "entropy": 7.0904669761657715,
      "epoch": 0.023321721674440573,
      "grad_norm": 1.0625,
      "learning_rate": 0.00019700000000000002,
      "loss": 6.7523,
      "mean_token_accuracy": 0.09790571630001069,
      "num_tokens": 845709.0,
      "step": 395
    },
    {
      "entropy": 6.981272554397583,
      "epoch": 0.023616933341205643,
      "grad_norm": 1.375,
      "learning_rate": 0.00019950000000000002,
      "loss": 6.7085,
      "mean_token_accuracy": 0.10158270671963691,
      "num_tokens": 855092.0,
      "step": 400
    },
    {
      "entropy": 7.02293906211853,
      "epoch": 0.023912145007970714,
      "grad_norm": 1.21875,
      "learning_rate": 0.000202,
      "loss": 6.7193,
      "mean_token_accuracy": 0.08962539583444595,
      "num_tokens": 865943.0,
      "step": 405
    },
    {
      "entropy": 7.03565149307251,
      "epoch": 0.024207356674735784,
      "grad_norm": 1.1171875,
      "learning_rate": 0.00020449999999999998,
      "loss": 6.647,
      "mean_token_accuracy": 0.09619486778974533,
      "num_tokens": 876649.0,
      "step": 410
    },
    {
      "entropy": 6.996511030197143,
      "epoch": 0.024502568341500858,
      "grad_norm": 1.265625,
      "learning_rate": 0.000207,
      "loss": 6.6861,
      "mean_token_accuracy": 0.10710784569382667,
      "num_tokens": 886221.0,
      "step": 415
    },
    {
      "entropy": 7.017127513885498,
      "epoch": 0.024797780008265928,
      "grad_norm": 1.1796875,
      "learning_rate": 0.0002095,
      "loss": 6.7047,
      "mean_token_accuracy": 0.10007574260234833,
      "num_tokens": 896234.0,
      "step": 420
    },
    {
      "entropy": 6.983069896697998,
      "epoch": 0.025092991675031,
      "grad_norm": 1.375,
      "learning_rate": 0.000212,
      "loss": 6.6479,
      "mean_token_accuracy": 0.09976074621081352,
      "num_tokens": 907198.0,
      "step": 425
    },
    {
      "entropy": 6.8837158203125,
      "epoch": 0.02538820334179607,
      "grad_norm": 1.09375,
      "learning_rate": 0.0002145,
      "loss": 6.702,
      "mean_token_accuracy": 0.10629369989037514,
      "num_tokens": 917579.0,
      "step": 430
    },
    {
      "entropy": 6.978274822235107,
      "epoch": 0.02568341500856114,
      "grad_norm": 1.09375,
      "learning_rate": 0.00021700000000000002,
      "loss": 6.6347,
      "mean_token_accuracy": 0.10065946727991104,
      "num_tokens": 928763.0,
      "step": 435
    },
    {
      "entropy": 6.867664194107055,
      "epoch": 0.02597862667532621,
      "grad_norm": 1.234375,
      "learning_rate": 0.0002195,
      "loss": 6.6455,
      "mean_token_accuracy": 0.1076437845826149,
      "num_tokens": 939383.0,
      "step": 440
    },
    {
      "entropy": 7.063400411605835,
      "epoch": 0.02627383834209128,
      "grad_norm": 1.234375,
      "learning_rate": 0.000222,
      "loss": 6.7118,
      "mean_token_accuracy": 0.09779355004429817,
      "num_tokens": 949967.0,
      "step": 445
    },
    {
      "entropy": 6.977987289428711,
      "epoch": 0.02656905000885635,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0002245,
      "loss": 6.7177,
      "mean_token_accuracy": 0.09856124073266984,
      "num_tokens": 960438.0,
      "step": 450
    },
    {
      "entropy": 6.9721705436706545,
      "epoch": 0.02686426167562142,
      "grad_norm": 1.2265625,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.678,
      "mean_token_accuracy": 0.1020229034125805,
      "num_tokens": 971771.0,
      "step": 455
    },
    {
      "entropy": 7.0487203121185305,
      "epoch": 0.02715947334238649,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00022950000000000002,
      "loss": 6.7437,
      "mean_token_accuracy": 0.09785925075411797,
      "num_tokens": 982431.0,
      "step": 460
    },
    {
      "entropy": 6.8306797504425045,
      "epoch": 0.02745468500915156,
      "grad_norm": 1.3125,
      "learning_rate": 0.00023200000000000003,
      "loss": 6.69,
      "mean_token_accuracy": 0.09700809046626091,
      "num_tokens": 992763.0,
      "step": 465
    },
    {
      "entropy": 6.909020566940308,
      "epoch": 0.02774989667591663,
      "grad_norm": 1.265625,
      "learning_rate": 0.00023449999999999998,
      "loss": 6.6022,
      "mean_token_accuracy": 0.107904601842165,
      "num_tokens": 1002977.0,
      "step": 470
    },
    {
      "entropy": 6.922635841369629,
      "epoch": 0.0280451083426817,
      "grad_norm": 1.21875,
      "learning_rate": 0.000237,
      "loss": 6.6653,
      "mean_token_accuracy": 0.10020340532064438,
      "num_tokens": 1014211.0,
      "step": 475
    },
    {
      "entropy": 6.923598337173462,
      "epoch": 0.028340320009446772,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0002395,
      "loss": 6.6715,
      "mean_token_accuracy": 0.10355789959430695,
      "num_tokens": 1025625.0,
      "step": 480
    },
    {
      "entropy": 6.909690856933594,
      "epoch": 0.028635531676211842,
      "grad_norm": 1.0859375,
      "learning_rate": 0.000242,
      "loss": 6.686,
      "mean_token_accuracy": 0.10261352136731147,
      "num_tokens": 1036430.0,
      "step": 485
    },
    {
      "entropy": 6.986854982376099,
      "epoch": 0.028930743342976916,
      "grad_norm": 0.9921875,
      "learning_rate": 0.0002445,
      "loss": 6.7083,
      "mean_token_accuracy": 0.10415773317217827,
      "num_tokens": 1047246.0,
      "step": 490
    },
    {
      "entropy": 6.8165546417236325,
      "epoch": 0.029225955009741986,
      "grad_norm": 1.0625,
      "learning_rate": 0.000247,
      "loss": 6.5998,
      "mean_token_accuracy": 0.10099067613482475,
      "num_tokens": 1057004.0,
      "step": 495
    },
    {
      "entropy": 6.876231527328491,
      "epoch": 0.029521166676507057,
      "grad_norm": 1.171875,
      "learning_rate": 0.0002495,
      "loss": 6.6397,
      "mean_token_accuracy": 0.1102587789297104,
      "num_tokens": 1067224.0,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1555553120256000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}