{
  "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": 10.69201593399048,
      "epoch": 0.00029521166676507054,
      "grad_norm": 12.6875,
      "learning_rate": 2e-06,
      "loss": 10.8334,
      "mean_token_accuracy": 0.0,
      "num_tokens": 10275.0,
      "step": 5
    },
    {
      "entropy": 10.691933250427246,
      "epoch": 0.0005904233335301411,
      "grad_norm": 13.1875,
      "learning_rate": 4.5e-06,
      "loss": 10.7937,
      "mean_token_accuracy": 0.0,
      "num_tokens": 22020.0,
      "step": 10
    },
    {
      "entropy": 10.691065883636474,
      "epoch": 0.0008856350002952116,
      "grad_norm": 9.5625,
      "learning_rate": 7e-06,
      "loss": 10.5174,
      "mean_token_accuracy": 0.021099633118137718,
      "num_tokens": 32612.0,
      "step": 15
    },
    {
      "entropy": 10.68113021850586,
      "epoch": 0.0011808466670602822,
      "grad_norm": 6.21875,
      "learning_rate": 9.5e-06,
      "loss": 10.1848,
      "mean_token_accuracy": 0.04274020157754421,
      "num_tokens": 43270.0,
      "step": 20
    },
    {
      "entropy": 10.621037483215332,
      "epoch": 0.0014760583338253527,
      "grad_norm": 3.84375,
      "learning_rate": 1.2e-05,
      "loss": 9.9202,
      "mean_token_accuracy": 0.04267438128590584,
      "num_tokens": 54178.0,
      "step": 25
    },
    {
      "entropy": 10.595892238616944,
      "epoch": 0.0017712700005904232,
      "grad_norm": 3.234375,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 9.7559,
      "mean_token_accuracy": 0.043279900401830676,
      "num_tokens": 64390.0,
      "step": 30
    },
    {
      "entropy": 10.602502059936523,
      "epoch": 0.002066481667355494,
      "grad_norm": 2.921875,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 9.6682,
      "mean_token_accuracy": 0.043131088465452196,
      "num_tokens": 73703.0,
      "step": 35
    },
    {
      "entropy": 10.59941120147705,
      "epoch": 0.0023616933341205643,
      "grad_norm": 2.6875,
      "learning_rate": 1.95e-05,
      "loss": 9.6023,
      "mean_token_accuracy": 0.04174515642225742,
      "num_tokens": 83463.0,
      "step": 40
    },
    {
      "entropy": 10.594866466522216,
      "epoch": 0.002656905000885635,
      "grad_norm": 2.515625,
      "learning_rate": 2.2e-05,
      "loss": 9.6097,
      "mean_token_accuracy": 0.04398317113518715,
      "num_tokens": 94129.0,
      "step": 45
    },
    {
      "entropy": 10.567664051055909,
      "epoch": 0.0029521166676507054,
      "grad_norm": 2.421875,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.558,
      "mean_token_accuracy": 0.043352384492754935,
      "num_tokens": 105482.0,
      "step": 50
    },
    {
      "entropy": 10.569747066497802,
      "epoch": 0.003247328334415776,
      "grad_norm": 2.453125,
      "learning_rate": 2.7e-05,
      "loss": 9.4562,
      "mean_token_accuracy": 0.043072767183184625,
      "num_tokens": 117342.0,
      "step": 55
    },
    {
      "entropy": 10.565975093841553,
      "epoch": 0.0035425400011808465,
      "grad_norm": 2.25,
      "learning_rate": 2.95e-05,
      "loss": 9.44,
      "mean_token_accuracy": 0.050405914708971974,
      "num_tokens": 127691.0,
      "step": 60
    },
    {
      "entropy": 10.458717250823975,
      "epoch": 0.0038377516679459172,
      "grad_norm": 2.46875,
      "learning_rate": 3.2e-05,
      "loss": 9.2492,
      "mean_token_accuracy": 0.05396741069853306,
      "num_tokens": 138186.0,
      "step": 65
    },
    {
      "entropy": 10.420860767364502,
      "epoch": 0.004132963334710988,
      "grad_norm": 2.28125,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.2326,
      "mean_token_accuracy": 0.06198026090860367,
      "num_tokens": 149578.0,
      "step": 70
    },
    {
      "entropy": 10.452775382995606,
      "epoch": 0.004428175001476058,
      "grad_norm": 2.21875,
      "learning_rate": 3.7e-05,
      "loss": 9.1186,
      "mean_token_accuracy": 0.06664705500006676,
      "num_tokens": 160139.0,
      "step": 75
    },
    {
      "entropy": 10.454645347595214,
      "epoch": 0.004723386668241129,
      "grad_norm": 2.296875,
      "learning_rate": 3.95e-05,
      "loss": 9.037,
      "mean_token_accuracy": 0.06905781887471676,
      "num_tokens": 170768.0,
      "step": 80
    },
    {
      "entropy": 10.332771587371827,
      "epoch": 0.0050185983350062,
      "grad_norm": 2.3125,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 8.8423,
      "mean_token_accuracy": 0.07480080313980579,
      "num_tokens": 180702.0,
      "step": 85
    },
    {
      "entropy": 10.249947929382325,
      "epoch": 0.00531381000177127,
      "grad_norm": 2.328125,
      "learning_rate": 4.45e-05,
      "loss": 8.7738,
      "mean_token_accuracy": 0.07588593885302544,
      "num_tokens": 191188.0,
      "step": 90
    },
    {
      "entropy": 10.206402206420899,
      "epoch": 0.0056090216685363405,
      "grad_norm": 3.609375,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 8.6866,
      "mean_token_accuracy": 0.07205914407968521,
      "num_tokens": 201094.0,
      "step": 95
    },
    {
      "entropy": 10.155156707763672,
      "epoch": 0.005904233335301411,
      "grad_norm": 3.046875,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 8.5626,
      "mean_token_accuracy": 0.076263627409935,
      "num_tokens": 211718.0,
      "step": 100
    },
    {
      "entropy": 10.151510620117188,
      "epoch": 0.006199445002066482,
      "grad_norm": 2.25,
      "learning_rate": 5.2e-05,
      "loss": 8.4394,
      "mean_token_accuracy": 0.07763982266187668,
      "num_tokens": 221446.0,
      "step": 105
    },
    {
      "entropy": 10.075346565246582,
      "epoch": 0.006494656668831552,
      "grad_norm": 1.84375,
      "learning_rate": 5.45e-05,
      "loss": 8.4619,
      "mean_token_accuracy": 0.07559167668223381,
      "num_tokens": 232848.0,
      "step": 110
    },
    {
      "entropy": 10.015703201293945,
      "epoch": 0.006789868335596623,
      "grad_norm": 1.8046875,
      "learning_rate": 5.7e-05,
      "loss": 8.3798,
      "mean_token_accuracy": 0.0727357666939497,
      "num_tokens": 244008.0,
      "step": 115
    },
    {
      "entropy": 9.909519577026368,
      "epoch": 0.007085080002361693,
      "grad_norm": 1.6171875,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.1771,
      "mean_token_accuracy": 0.08037759214639664,
      "num_tokens": 256211.0,
      "step": 120
    },
    {
      "entropy": 9.780295848846436,
      "epoch": 0.007380291669126764,
      "grad_norm": 1.6171875,
      "learning_rate": 6.2e-05,
      "loss": 8.1207,
      "mean_token_accuracy": 0.07622570730745792,
      "num_tokens": 266688.0,
      "step": 125
    },
    {
      "entropy": 9.564407634735108,
      "epoch": 0.0076755033358918345,
      "grad_norm": 1.4609375,
      "learning_rate": 6.450000000000001e-05,
      "loss": 7.9156,
      "mean_token_accuracy": 0.07875195294618606,
      "num_tokens": 276930.0,
      "step": 130
    },
    {
      "entropy": 9.403815078735352,
      "epoch": 0.007970715002656906,
      "grad_norm": 1.5546875,
      "learning_rate": 6.7e-05,
      "loss": 7.7559,
      "mean_token_accuracy": 0.08111081309616566,
      "num_tokens": 287508.0,
      "step": 135
    },
    {
      "entropy": 9.18376874923706,
      "epoch": 0.008265926669421976,
      "grad_norm": 1.4609375,
      "learning_rate": 6.950000000000001e-05,
      "loss": 7.6109,
      "mean_token_accuracy": 0.08215704038739205,
      "num_tokens": 298021.0,
      "step": 140
    },
    {
      "entropy": 8.89451036453247,
      "epoch": 0.008561138336187046,
      "grad_norm": 1.1875,
      "learning_rate": 7.2e-05,
      "loss": 7.5483,
      "mean_token_accuracy": 0.0828169234097004,
      "num_tokens": 308301.0,
      "step": 145
    },
    {
      "entropy": 8.718179512023926,
      "epoch": 0.008856350002952117,
      "grad_norm": 1.734375,
      "learning_rate": 7.45e-05,
      "loss": 7.4558,
      "mean_token_accuracy": 0.07895909734070301,
      "num_tokens": 319321.0,
      "step": 150
    },
    {
      "entropy": 8.486823749542236,
      "epoch": 0.009151561669717187,
      "grad_norm": 1.3125,
      "learning_rate": 7.7e-05,
      "loss": 7.5026,
      "mean_token_accuracy": 0.07978610247373581,
      "num_tokens": 330926.0,
      "step": 155
    },
    {
      "entropy": 8.353065967559814,
      "epoch": 0.009446773336482257,
      "grad_norm": 1.1953125,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.3196,
      "mean_token_accuracy": 0.08807190880179405,
      "num_tokens": 341133.0,
      "step": 160
    },
    {
      "entropy": 8.217400360107423,
      "epoch": 0.009741985003247328,
      "grad_norm": 1.40625,
      "learning_rate": 8.2e-05,
      "loss": 7.3374,
      "mean_token_accuracy": 0.08286328092217446,
      "num_tokens": 351897.0,
      "step": 165
    },
    {
      "entropy": 8.153849840164185,
      "epoch": 0.0100371966700124,
      "grad_norm": 1.1796875,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.3121,
      "mean_token_accuracy": 0.08045563325285912,
      "num_tokens": 362644.0,
      "step": 170
    },
    {
      "entropy": 8.020972394943238,
      "epoch": 0.01033240833677747,
      "grad_norm": 1.3515625,
      "learning_rate": 8.7e-05,
      "loss": 7.3254,
      "mean_token_accuracy": 0.08039250746369361,
      "num_tokens": 373902.0,
      "step": 175
    },
    {
      "entropy": 7.979048109054565,
      "epoch": 0.01062762000354254,
      "grad_norm": 1.453125,
      "learning_rate": 8.95e-05,
      "loss": 7.2138,
      "mean_token_accuracy": 0.09198684617877007,
      "num_tokens": 384828.0,
      "step": 180
    },
    {
      "entropy": 7.852319145202637,
      "epoch": 0.01092283167030761,
      "grad_norm": 1.375,
      "learning_rate": 9.2e-05,
      "loss": 7.227,
      "mean_token_accuracy": 0.08049636781215667,
      "num_tokens": 395103.0,
      "step": 185
    },
    {
      "entropy": 7.785118961334229,
      "epoch": 0.011218043337072681,
      "grad_norm": 1.3359375,
      "learning_rate": 9.45e-05,
      "loss": 7.1629,
      "mean_token_accuracy": 0.09020237326622009,
      "num_tokens": 405283.0,
      "step": 190
    },
    {
      "entropy": 7.803817939758301,
      "epoch": 0.011513255003837751,
      "grad_norm": 1.53125,
      "learning_rate": 9.7e-05,
      "loss": 7.1458,
      "mean_token_accuracy": 0.08684369623661041,
      "num_tokens": 416005.0,
      "step": 195
    },
    {
      "entropy": 7.734343099594116,
      "epoch": 0.011808466670602822,
      "grad_norm": 1.28125,
      "learning_rate": 9.95e-05,
      "loss": 7.1475,
      "mean_token_accuracy": 0.08818956762552262,
      "num_tokens": 426547.0,
      "step": 200
    },
    {
      "entropy": 7.702443599700928,
      "epoch": 0.012103678337367892,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000102,
      "loss": 7.0801,
      "mean_token_accuracy": 0.09228792935609817,
      "num_tokens": 436262.0,
      "step": 205
    },
    {
      "entropy": 7.663109302520752,
      "epoch": 0.012398890004132964,
      "grad_norm": 1.578125,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.101,
      "mean_token_accuracy": 0.08728625029325485,
      "num_tokens": 446899.0,
      "step": 210
    },
    {
      "entropy": 7.67796368598938,
      "epoch": 0.012694101670898034,
      "grad_norm": 1.140625,
      "learning_rate": 0.000107,
      "loss": 7.1407,
      "mean_token_accuracy": 0.08986683264374733,
      "num_tokens": 458224.0,
      "step": 215
    },
    {
      "entropy": 7.675721073150635,
      "epoch": 0.012989313337663105,
      "grad_norm": 1.2109375,
      "learning_rate": 0.0001095,
      "loss": 7.0746,
      "mean_token_accuracy": 0.08677861616015434,
      "num_tokens": 469306.0,
      "step": 220
    },
    {
      "entropy": 7.5801355838775635,
      "epoch": 0.013284525004428175,
      "grad_norm": 1.6953125,
      "learning_rate": 0.000112,
      "loss": 7.0774,
      "mean_token_accuracy": 0.0875390887260437,
      "num_tokens": 478685.0,
      "step": 225
    },
    {
      "entropy": 7.611648845672607,
      "epoch": 0.013579736671193245,
      "grad_norm": 1.296875,
      "learning_rate": 0.0001145,
      "loss": 7.0051,
      "mean_token_accuracy": 0.09632268622517585,
      "num_tokens": 489376.0,
      "step": 230
    },
    {
      "entropy": 7.525375843048096,
      "epoch": 0.013874948337958316,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.0117,
      "mean_token_accuracy": 0.0921477772295475,
      "num_tokens": 500260.0,
      "step": 235
    },
    {
      "entropy": 7.426083660125732,
      "epoch": 0.014170160004723386,
      "grad_norm": 1.265625,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.0023,
      "mean_token_accuracy": 0.09566814824938774,
      "num_tokens": 511953.0,
      "step": 240
    },
    {
      "entropy": 7.632671928405761,
      "epoch": 0.014465371671488458,
      "grad_norm": 1.3359375,
      "learning_rate": 0.000122,
      "loss": 7.1873,
      "mean_token_accuracy": 0.08889849931001663,
      "num_tokens": 523055.0,
      "step": 245
    },
    {
      "entropy": 7.509737873077393,
      "epoch": 0.014760583338253528,
      "grad_norm": 1.296875,
      "learning_rate": 0.0001245,
      "loss": 6.9947,
      "mean_token_accuracy": 0.09188270270824432,
      "num_tokens": 534337.0,
      "step": 250
    },
    {
      "entropy": 7.46486268043518,
      "epoch": 0.015055795005018599,
      "grad_norm": 1.421875,
      "learning_rate": 0.000127,
      "loss": 6.9868,
      "mean_token_accuracy": 0.09533577933907508,
      "num_tokens": 545189.0,
      "step": 255
    },
    {
      "entropy": 7.538589096069336,
      "epoch": 0.015351006671783669,
      "grad_norm": 1.1875,
      "learning_rate": 0.0001295,
      "loss": 7.0231,
      "mean_token_accuracy": 0.09476621299982071,
      "num_tokens": 555506.0,
      "step": 260
    },
    {
      "entropy": 7.462624025344849,
      "epoch": 0.01564621833854874,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000132,
      "loss": 6.9308,
      "mean_token_accuracy": 0.0939927913248539,
      "num_tokens": 565936.0,
      "step": 265
    },
    {
      "entropy": 7.461940479278565,
      "epoch": 0.01594143000531381,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.033,
      "mean_token_accuracy": 0.09217713922262191,
      "num_tokens": 575691.0,
      "step": 270
    },
    {
      "entropy": 7.481535339355469,
      "epoch": 0.01623664167207888,
      "grad_norm": 1.2265625,
      "learning_rate": 0.00013700000000000002,
      "loss": 6.9921,
      "mean_token_accuracy": 0.09237621873617172,
      "num_tokens": 586170.0,
      "step": 275
    },
    {
      "entropy": 7.461501359939575,
      "epoch": 0.016531853338843952,
      "grad_norm": 1.453125,
      "learning_rate": 0.0001395,
      "loss": 6.9755,
      "mean_token_accuracy": 0.09221490249037742,
      "num_tokens": 596458.0,
      "step": 280
    },
    {
      "entropy": 7.365391731262207,
      "epoch": 0.016827065005609022,
      "grad_norm": 1.125,
      "learning_rate": 0.00014199999999999998,
      "loss": 6.9201,
      "mean_token_accuracy": 0.08767134547233582,
      "num_tokens": 606214.0,
      "step": 285
    },
    {
      "entropy": 7.444003868103027,
      "epoch": 0.017122276672374093,
      "grad_norm": 1.4296875,
      "learning_rate": 0.0001445,
      "loss": 6.9609,
      "mean_token_accuracy": 0.09265968054533005,
      "num_tokens": 617074.0,
      "step": 290
    },
    {
      "entropy": 7.425234937667847,
      "epoch": 0.017417488339139163,
      "grad_norm": 1.3125,
      "learning_rate": 0.000147,
      "loss": 6.998,
      "mean_token_accuracy": 0.08931455463171005,
      "num_tokens": 628057.0,
      "step": 295
    },
    {
      "entropy": 7.338685989379883,
      "epoch": 0.017712700005904233,
      "grad_norm": 1.1171875,
      "learning_rate": 0.0001495,
      "loss": 6.9406,
      "mean_token_accuracy": 0.09267161414027214,
      "num_tokens": 638150.0,
      "step": 300
    },
    {
      "entropy": 7.352516222000122,
      "epoch": 0.018007911672669304,
      "grad_norm": 1.25,
      "learning_rate": 0.000152,
      "loss": 6.8101,
      "mean_token_accuracy": 0.10107955634593964,
      "num_tokens": 648377.0,
      "step": 305
    },
    {
      "entropy": 7.305817174911499,
      "epoch": 0.018303123339434374,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00015450000000000001,
      "loss": 6.8875,
      "mean_token_accuracy": 0.09907981753349304,
      "num_tokens": 658777.0,
      "step": 310
    },
    {
      "entropy": 7.311208295822143,
      "epoch": 0.018598335006199444,
      "grad_norm": 1.2734375,
      "learning_rate": 0.000157,
      "loss": 6.9908,
      "mean_token_accuracy": 0.09044492170214653,
      "num_tokens": 669105.0,
      "step": 315
    },
    {
      "entropy": 7.355552816390992,
      "epoch": 0.018893546672964515,
      "grad_norm": 1.109375,
      "learning_rate": 0.0001595,
      "loss": 6.8608,
      "mean_token_accuracy": 0.09483690708875656,
      "num_tokens": 679294.0,
      "step": 320
    },
    {
      "entropy": 7.222180414199829,
      "epoch": 0.019188758339729585,
      "grad_norm": 1.125,
      "learning_rate": 0.000162,
      "loss": 6.829,
      "mean_token_accuracy": 0.09829319342970848,
      "num_tokens": 690495.0,
      "step": 325
    },
    {
      "entropy": 7.220251893997192,
      "epoch": 0.019483970006494655,
      "grad_norm": 1.1640625,
      "learning_rate": 0.00016450000000000001,
      "loss": 6.8432,
      "mean_token_accuracy": 0.09830230325460435,
      "num_tokens": 701002.0,
      "step": 330
    },
    {
      "entropy": 7.257207536697388,
      "epoch": 0.019779181673259726,
      "grad_norm": 1.40625,
      "learning_rate": 0.00016700000000000002,
      "loss": 6.753,
      "mean_token_accuracy": 0.09737947657704353,
      "num_tokens": 711488.0,
      "step": 335
    },
    {
      "entropy": 7.091268253326416,
      "epoch": 0.0200743933400248,
      "grad_norm": 1.203125,
      "learning_rate": 0.00016950000000000003,
      "loss": 6.7863,
      "mean_token_accuracy": 0.09428932666778564,
      "num_tokens": 722637.0,
      "step": 340
    },
    {
      "entropy": 7.228825855255127,
      "epoch": 0.02036960500678987,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00017199999999999998,
      "loss": 6.8498,
      "mean_token_accuracy": 0.09802942052483558,
      "num_tokens": 733212.0,
      "step": 345
    },
    {
      "entropy": 7.253208494186401,
      "epoch": 0.02066481667355494,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00017449999999999999,
      "loss": 6.7639,
      "mean_token_accuracy": 0.09950084388256072,
      "num_tokens": 743602.0,
      "step": 350
    },
    {
      "entropy": 7.207983446121216,
      "epoch": 0.02096002834032001,
      "grad_norm": 1.59375,
      "learning_rate": 0.000177,
      "loss": 6.8151,
      "mean_token_accuracy": 0.09879285991191863,
      "num_tokens": 754094.0,
      "step": 355
    },
    {
      "entropy": 7.099168062210083,
      "epoch": 0.02125524000708508,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0001795,
      "loss": 6.7724,
      "mean_token_accuracy": 0.09406139552593232,
      "num_tokens": 763823.0,
      "step": 360
    },
    {
      "entropy": 7.163098907470703,
      "epoch": 0.02155045167385015,
      "grad_norm": 1.25,
      "learning_rate": 0.000182,
      "loss": 6.7096,
      "mean_token_accuracy": 0.10476447790861129,
      "num_tokens": 774128.0,
      "step": 365
    },
    {
      "entropy": 7.131285381317139,
      "epoch": 0.02184566334061522,
      "grad_norm": 1.375,
      "learning_rate": 0.0001845,
      "loss": 6.7883,
      "mean_token_accuracy": 0.09998859390616417,
      "num_tokens": 784292.0,
      "step": 370
    },
    {
      "entropy": 7.133191156387329,
      "epoch": 0.02214087500738029,
      "grad_norm": 1.125,
      "learning_rate": 0.000187,
      "loss": 6.7794,
      "mean_token_accuracy": 0.09937844276428223,
      "num_tokens": 795437.0,
      "step": 375
    },
    {
      "entropy": 7.124974298477173,
      "epoch": 0.022436086674145362,
      "grad_norm": 1.1875,
      "learning_rate": 0.0001895,
      "loss": 6.687,
      "mean_token_accuracy": 0.10222809389233589,
      "num_tokens": 806543.0,
      "step": 380
    },
    {
      "entropy": 7.1218994140625,
      "epoch": 0.022731298340910432,
      "grad_norm": 1.34375,
      "learning_rate": 0.000192,
      "loss": 6.843,
      "mean_token_accuracy": 0.09876690059900284,
      "num_tokens": 817179.0,
      "step": 385
    },
    {
      "entropy": 7.118319416046143,
      "epoch": 0.023026510007675503,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0001945,
      "loss": 6.7608,
      "mean_token_accuracy": 0.10439011678099633,
      "num_tokens": 826749.0,
      "step": 390
    },
    {
      "entropy": 7.08788104057312,
      "epoch": 0.023321721674440573,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00019700000000000002,
      "loss": 6.798,
      "mean_token_accuracy": 0.09762646481394768,
      "num_tokens": 838807.0,
      "step": 395
    },
    {
      "entropy": 7.131559801101685,
      "epoch": 0.023616933341205643,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00019950000000000002,
      "loss": 6.7766,
      "mean_token_accuracy": 0.10133634880185127,
      "num_tokens": 849651.0,
      "step": 400
    },
    {
      "entropy": 7.159732913970947,
      "epoch": 0.023912145007970714,
      "grad_norm": 1.28125,
      "learning_rate": 0.000202,
      "loss": 6.8434,
      "mean_token_accuracy": 0.09272509887814522,
      "num_tokens": 859753.0,
      "step": 405
    },
    {
      "entropy": 7.0073809146881105,
      "epoch": 0.024207356674735784,
      "grad_norm": 1.1875,
      "learning_rate": 0.00020449999999999998,
      "loss": 6.7134,
      "mean_token_accuracy": 0.10226179882884026,
      "num_tokens": 869904.0,
      "step": 410
    },
    {
      "entropy": 6.957417392730713,
      "epoch": 0.024502568341500858,
      "grad_norm": 1.0390625,
      "learning_rate": 0.000207,
      "loss": 6.73,
      "mean_token_accuracy": 0.10192711651325226,
      "num_tokens": 880948.0,
      "step": 415
    },
    {
      "entropy": 7.170308446884155,
      "epoch": 0.024797780008265928,
      "grad_norm": 1.046875,
      "learning_rate": 0.0002095,
      "loss": 6.7966,
      "mean_token_accuracy": 0.09502052217721939,
      "num_tokens": 892331.0,
      "step": 420
    },
    {
      "entropy": 6.980013370513916,
      "epoch": 0.025092991675031,
      "grad_norm": 1.21875,
      "learning_rate": 0.000212,
      "loss": 6.628,
      "mean_token_accuracy": 0.1050586886703968,
      "num_tokens": 901691.0,
      "step": 425
    },
    {
      "entropy": 7.007831001281739,
      "epoch": 0.02538820334179607,
      "grad_norm": 1.1875,
      "learning_rate": 0.0002145,
      "loss": 6.6769,
      "mean_token_accuracy": 0.10150302425026894,
      "num_tokens": 912495.0,
      "step": 430
    },
    {
      "entropy": 7.010691833496094,
      "epoch": 0.02568341500856114,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00021700000000000002,
      "loss": 6.636,
      "mean_token_accuracy": 0.1017840936779976,
      "num_tokens": 923420.0,
      "step": 435
    },
    {
      "entropy": 6.8785758972167965,
      "epoch": 0.02597862667532621,
      "grad_norm": 1.1875,
      "learning_rate": 0.0002195,
      "loss": 6.6396,
      "mean_token_accuracy": 0.09978873506188393,
      "num_tokens": 933598.0,
      "step": 440
    },
    {
      "entropy": 6.98797607421875,
      "epoch": 0.02627383834209128,
      "grad_norm": 1.3046875,
      "learning_rate": 0.000222,
      "loss": 6.7659,
      "mean_token_accuracy": 0.1045355699956417,
      "num_tokens": 943229.0,
      "step": 445
    },
    {
      "entropy": 6.983278131484985,
      "epoch": 0.02656905000885635,
      "grad_norm": 1.0625,
      "learning_rate": 0.0002245,
      "loss": 6.6247,
      "mean_token_accuracy": 0.10298437029123306,
      "num_tokens": 954425.0,
      "step": 450
    },
    {
      "entropy": 7.073006629943848,
      "epoch": 0.02686426167562142,
      "grad_norm": 1.3359375,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.745,
      "mean_token_accuracy": 0.10184216126799583,
      "num_tokens": 965516.0,
      "step": 455
    },
    {
      "entropy": 6.900727653503418,
      "epoch": 0.02715947334238649,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00022950000000000002,
      "loss": 6.6285,
      "mean_token_accuracy": 0.10302256718277931,
      "num_tokens": 976469.0,
      "step": 460
    },
    {
      "entropy": 6.955856561660767,
      "epoch": 0.02745468500915156,
      "grad_norm": 1.140625,
      "learning_rate": 0.00023200000000000003,
      "loss": 6.7139,
      "mean_token_accuracy": 0.09732916429638863,
      "num_tokens": 986946.0,
      "step": 465
    },
    {
      "entropy": 6.982401418685913,
      "epoch": 0.02774989667591663,
      "grad_norm": 1.1796875,
      "learning_rate": 0.00023449999999999998,
      "loss": 6.612,
      "mean_token_accuracy": 0.10779485702514649,
      "num_tokens": 997101.0,
      "step": 470
    },
    {
      "entropy": 6.9505868434906,
      "epoch": 0.0280451083426817,
      "grad_norm": 1.2890625,
      "learning_rate": 0.000237,
      "loss": 6.7346,
      "mean_token_accuracy": 0.10266673490405083,
      "num_tokens": 1007866.0,
      "step": 475
    },
    {
      "entropy": 7.019359874725342,
      "epoch": 0.028340320009446772,
      "grad_norm": 1.3203125,
      "learning_rate": 0.0002395,
      "loss": 6.7355,
      "mean_token_accuracy": 0.09643693268299103,
      "num_tokens": 1019377.0,
      "step": 480
    },
    {
      "entropy": 6.936902332305908,
      "epoch": 0.028635531676211842,
      "grad_norm": 1.28125,
      "learning_rate": 0.000242,
      "loss": 6.7267,
      "mean_token_accuracy": 0.09898768290877343,
      "num_tokens": 1031278.0,
      "step": 485
    },
    {
      "entropy": 6.772035408020019,
      "epoch": 0.028930743342976916,
      "grad_norm": 1.25,
      "learning_rate": 0.0002445,
      "loss": 6.5192,
      "mean_token_accuracy": 0.1116688534617424,
      "num_tokens": 1041663.0,
      "step": 490
    },
    {
      "entropy": 6.908066129684448,
      "epoch": 0.029225955009741986,
      "grad_norm": 1.203125,
      "learning_rate": 0.000247,
      "loss": 6.5969,
      "mean_token_accuracy": 0.10450899600982666,
      "num_tokens": 1052286.0,
      "step": 495
    },
    {
      "entropy": 6.807862234115601,
      "epoch": 0.029521166676507057,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0002495,
      "loss": 6.6629,
      "mean_token_accuracy": 0.10684632584452629,
      "num_tokens": 1061945.0,
      "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": 1538340507648000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}