{
  "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": 10.742573165893555,
      "epoch": 0.00029521166676507054,
      "grad_norm": 4.96875,
      "learning_rate": 2e-06,
      "loss": 10.7764,
      "mean_token_accuracy": 0.00011173184029757976,
      "num_tokens": 10275.0,
      "step": 5
    },
    {
      "entropy": 10.74255199432373,
      "epoch": 0.0005904233335301411,
      "grad_norm": 5.4375,
      "learning_rate": 4.5e-06,
      "loss": 10.7784,
      "mean_token_accuracy": 0.00011086474405601621,
      "num_tokens": 22020.0,
      "step": 10
    },
    {
      "entropy": 10.742577171325683,
      "epoch": 0.0008856350002952116,
      "grad_norm": 5.09375,
      "learning_rate": 7e-06,
      "loss": 10.7479,
      "mean_token_accuracy": 0.0,
      "num_tokens": 32612.0,
      "step": 15
    },
    {
      "entropy": 10.742585563659668,
      "epoch": 0.0011808466670602822,
      "grad_norm": 5.125,
      "learning_rate": 9.5e-06,
      "loss": 10.692,
      "mean_token_accuracy": 0.0002895977755542845,
      "num_tokens": 43270.0,
      "step": 20
    },
    {
      "entropy": 10.74253044128418,
      "epoch": 0.0014760583338253527,
      "grad_norm": 4.34375,
      "learning_rate": 1.2e-05,
      "loss": 10.5945,
      "mean_token_accuracy": 0.0037050600280053914,
      "num_tokens": 54178.0,
      "step": 25
    },
    {
      "entropy": 10.742242050170898,
      "epoch": 0.0017712700005904232,
      "grad_norm": 4.15625,
      "learning_rate": 1.4500000000000002e-05,
      "loss": 10.4602,
      "mean_token_accuracy": 0.02422279641032219,
      "num_tokens": 64390.0,
      "step": 30
    },
    {
      "entropy": 10.741262912750244,
      "epoch": 0.002066481667355494,
      "grad_norm": 3.3125,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 10.2806,
      "mean_token_accuracy": 0.041601650416851044,
      "num_tokens": 73703.0,
      "step": 35
    },
    {
      "entropy": 10.738601016998292,
      "epoch": 0.0023616933341205643,
      "grad_norm": 2.625,
      "learning_rate": 1.95e-05,
      "loss": 10.1485,
      "mean_token_accuracy": 0.04163007400929928,
      "num_tokens": 83463.0,
      "step": 40
    },
    {
      "entropy": 10.734784793853759,
      "epoch": 0.002656905000885635,
      "grad_norm": 2.265625,
      "learning_rate": 2.2e-05,
      "loss": 10.0675,
      "mean_token_accuracy": 0.04389659091830254,
      "num_tokens": 94129.0,
      "step": 45
    },
    {
      "entropy": 10.73138256072998,
      "epoch": 0.0029521166676507054,
      "grad_norm": 2.109375,
      "learning_rate": 2.4500000000000003e-05,
      "loss": 9.9969,
      "mean_token_accuracy": 0.043133416399359706,
      "num_tokens": 105482.0,
      "step": 50
    },
    {
      "entropy": 10.729689979553223,
      "epoch": 0.003247328334415776,
      "grad_norm": 2.0625,
      "learning_rate": 2.7e-05,
      "loss": 9.9129,
      "mean_token_accuracy": 0.04309733100235462,
      "num_tokens": 117342.0,
      "step": 55
    },
    {
      "entropy": 10.728583812713623,
      "epoch": 0.0035425400011808465,
      "grad_norm": 1.859375,
      "learning_rate": 2.95e-05,
      "loss": 9.8878,
      "mean_token_accuracy": 0.04118645377457142,
      "num_tokens": 127691.0,
      "step": 60
    },
    {
      "entropy": 10.727480697631837,
      "epoch": 0.0038377516679459172,
      "grad_norm": 1.90625,
      "learning_rate": 3.2e-05,
      "loss": 9.7761,
      "mean_token_accuracy": 0.04004005677998066,
      "num_tokens": 138186.0,
      "step": 65
    },
    {
      "entropy": 10.725414276123047,
      "epoch": 0.004132963334710988,
      "grad_norm": 1.9375,
      "learning_rate": 3.4500000000000005e-05,
      "loss": 9.7581,
      "mean_token_accuracy": 0.0433019045740366,
      "num_tokens": 149578.0,
      "step": 70
    },
    {
      "entropy": 10.720968532562257,
      "epoch": 0.004428175001476058,
      "grad_norm": 1.9140625,
      "learning_rate": 3.7e-05,
      "loss": 9.6737,
      "mean_token_accuracy": 0.04341540932655334,
      "num_tokens": 160139.0,
      "step": 75
    },
    {
      "entropy": 10.71543197631836,
      "epoch": 0.004723386668241129,
      "grad_norm": 1.90625,
      "learning_rate": 3.95e-05,
      "loss": 9.6176,
      "mean_token_accuracy": 0.042911310121417044,
      "num_tokens": 170768.0,
      "step": 80
    },
    {
      "entropy": 10.708538818359376,
      "epoch": 0.0050185983350062,
      "grad_norm": 1.984375,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 9.5004,
      "mean_token_accuracy": 0.04607887454330921,
      "num_tokens": 180702.0,
      "step": 85
    },
    {
      "entropy": 10.699075031280518,
      "epoch": 0.00531381000177127,
      "grad_norm": 1.9921875,
      "learning_rate": 4.45e-05,
      "loss": 9.4474,
      "mean_token_accuracy": 0.04201225638389587,
      "num_tokens": 191188.0,
      "step": 90
    },
    {
      "entropy": 10.691750621795654,
      "epoch": 0.0056090216685363405,
      "grad_norm": 1.90625,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 9.381,
      "mean_token_accuracy": 0.03792413603514433,
      "num_tokens": 201094.0,
      "step": 95
    },
    {
      "entropy": 10.6837984085083,
      "epoch": 0.005904233335301411,
      "grad_norm": 1.8984375,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 9.2614,
      "mean_token_accuracy": 0.04629642106592655,
      "num_tokens": 211718.0,
      "step": 100
    },
    {
      "entropy": 10.667647075653075,
      "epoch": 0.006199445002066482,
      "grad_norm": 1.8828125,
      "learning_rate": 5.2e-05,
      "loss": 9.1409,
      "mean_token_accuracy": 0.05333527401089668,
      "num_tokens": 221446.0,
      "step": 105
    },
    {
      "entropy": 10.640782737731934,
      "epoch": 0.006494656668831552,
      "grad_norm": 1.7578125,
      "learning_rate": 5.45e-05,
      "loss": 9.1093,
      "mean_token_accuracy": 0.05261831916868687,
      "num_tokens": 232848.0,
      "step": 110
    },
    {
      "entropy": 10.602476406097413,
      "epoch": 0.006789868335596623,
      "grad_norm": 1.75,
      "learning_rate": 5.7e-05,
      "loss": 9.0166,
      "mean_token_accuracy": 0.05226000994443893,
      "num_tokens": 244008.0,
      "step": 115
    },
    {
      "entropy": 10.5585186958313,
      "epoch": 0.007085080002361693,
      "grad_norm": 1.7265625,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 8.8449,
      "mean_token_accuracy": 0.05914722830057144,
      "num_tokens": 256211.0,
      "step": 120
    },
    {
      "entropy": 10.501475620269776,
      "epoch": 0.007380291669126764,
      "grad_norm": 1.671875,
      "learning_rate": 6.2e-05,
      "loss": 8.7664,
      "mean_token_accuracy": 0.05910652950406074,
      "num_tokens": 266688.0,
      "step": 125
    },
    {
      "entropy": 10.426000499725342,
      "epoch": 0.0076755033358918345,
      "grad_norm": 1.5625,
      "learning_rate": 6.450000000000001e-05,
      "loss": 8.57,
      "mean_token_accuracy": 0.0610476765781641,
      "num_tokens": 276930.0,
      "step": 130
    },
    {
      "entropy": 10.339440727233887,
      "epoch": 0.007970715002656906,
      "grad_norm": 1.625,
      "learning_rate": 6.7e-05,
      "loss": 8.4277,
      "mean_token_accuracy": 0.07068866156041623,
      "num_tokens": 287508.0,
      "step": 135
    },
    {
      "entropy": 10.240792846679687,
      "epoch": 0.008265926669421976,
      "grad_norm": 1.546875,
      "learning_rate": 6.950000000000001e-05,
      "loss": 8.2713,
      "mean_token_accuracy": 0.07111315764486789,
      "num_tokens": 298021.0,
      "step": 140
    },
    {
      "entropy": 10.135569763183593,
      "epoch": 0.008561138336187046,
      "grad_norm": 1.3828125,
      "learning_rate": 7.2e-05,
      "loss": 8.1726,
      "mean_token_accuracy": 0.07181189507246018,
      "num_tokens": 308301.0,
      "step": 145
    },
    {
      "entropy": 9.984276580810548,
      "epoch": 0.008856350002952117,
      "grad_norm": 1.375,
      "learning_rate": 7.45e-05,
      "loss": 8.0427,
      "mean_token_accuracy": 0.06862774454057216,
      "num_tokens": 319321.0,
      "step": 150
    },
    {
      "entropy": 9.829378795623779,
      "epoch": 0.009151561669717187,
      "grad_norm": 1.25,
      "learning_rate": 7.7e-05,
      "loss": 8.0055,
      "mean_token_accuracy": 0.07413771599531174,
      "num_tokens": 330926.0,
      "step": 155
    },
    {
      "entropy": 9.623138332366944,
      "epoch": 0.009446773336482257,
      "grad_norm": 1.125,
      "learning_rate": 7.950000000000001e-05,
      "loss": 7.7929,
      "mean_token_accuracy": 0.07890797778964043,
      "num_tokens": 341133.0,
      "step": 160
    },
    {
      "entropy": 9.416749095916748,
      "epoch": 0.009741985003247328,
      "grad_norm": 1.28125,
      "learning_rate": 8.2e-05,
      "loss": 7.7407,
      "mean_token_accuracy": 0.07391801774501801,
      "num_tokens": 351897.0,
      "step": 165
    },
    {
      "entropy": 9.196506309509278,
      "epoch": 0.0100371966700124,
      "grad_norm": 0.96875,
      "learning_rate": 8.450000000000001e-05,
      "loss": 7.6663,
      "mean_token_accuracy": 0.07125836983323097,
      "num_tokens": 362644.0,
      "step": 170
    },
    {
      "entropy": 8.932462692260742,
      "epoch": 0.01033240833677747,
      "grad_norm": 0.9296875,
      "learning_rate": 8.7e-05,
      "loss": 7.628,
      "mean_token_accuracy": 0.07178853973746299,
      "num_tokens": 373902.0,
      "step": 175
    },
    {
      "entropy": 8.703715133666993,
      "epoch": 0.01062762000354254,
      "grad_norm": 0.87890625,
      "learning_rate": 8.95e-05,
      "loss": 7.4958,
      "mean_token_accuracy": 0.08398130461573601,
      "num_tokens": 384828.0,
      "step": 180
    },
    {
      "entropy": 8.474815559387206,
      "epoch": 0.01092283167030761,
      "grad_norm": 0.8359375,
      "learning_rate": 9.2e-05,
      "loss": 7.4684,
      "mean_token_accuracy": 0.07413811013102531,
      "num_tokens": 395103.0,
      "step": 185
    },
    {
      "entropy": 8.360427570343017,
      "epoch": 0.011218043337072681,
      "grad_norm": 0.8515625,
      "learning_rate": 9.45e-05,
      "loss": 7.374,
      "mean_token_accuracy": 0.08157729879021644,
      "num_tokens": 405283.0,
      "step": 190
    },
    {
      "entropy": 8.21293478012085,
      "epoch": 0.011513255003837751,
      "grad_norm": 0.96484375,
      "learning_rate": 9.7e-05,
      "loss": 7.3468,
      "mean_token_accuracy": 0.0755577202886343,
      "num_tokens": 416005.0,
      "step": 195
    },
    {
      "entropy": 8.12078037261963,
      "epoch": 0.011808466670602822,
      "grad_norm": 0.828125,
      "learning_rate": 9.95e-05,
      "loss": 7.3518,
      "mean_token_accuracy": 0.08057705461978912,
      "num_tokens": 426547.0,
      "step": 200
    },
    {
      "entropy": 8.019514322280884,
      "epoch": 0.012103678337367892,
      "grad_norm": 1.1328125,
      "learning_rate": 0.000102,
      "loss": 7.2823,
      "mean_token_accuracy": 0.08034192845225334,
      "num_tokens": 436262.0,
      "step": 205
    },
    {
      "entropy": 7.997368812561035,
      "epoch": 0.012398890004132964,
      "grad_norm": 1.0390625,
      "learning_rate": 0.00010449999999999999,
      "loss": 7.3018,
      "mean_token_accuracy": 0.07936789095401764,
      "num_tokens": 446899.0,
      "step": 210
    },
    {
      "entropy": 7.968120145797729,
      "epoch": 0.012694101670898034,
      "grad_norm": 0.9140625,
      "learning_rate": 0.000107,
      "loss": 7.3322,
      "mean_token_accuracy": 0.07839082404971123,
      "num_tokens": 458224.0,
      "step": 215
    },
    {
      "entropy": 8.01854157447815,
      "epoch": 0.012989313337663105,
      "grad_norm": 0.92578125,
      "learning_rate": 0.0001095,
      "loss": 7.2688,
      "mean_token_accuracy": 0.0764270156621933,
      "num_tokens": 469306.0,
      "step": 220
    },
    {
      "entropy": 7.9349792957305905,
      "epoch": 0.013284525004428175,
      "grad_norm": 1.1796875,
      "learning_rate": 0.000112,
      "loss": 7.2614,
      "mean_token_accuracy": 0.08024230971932411,
      "num_tokens": 478685.0,
      "step": 225
    },
    {
      "entropy": 7.891508388519287,
      "epoch": 0.013579736671193245,
      "grad_norm": 0.9140625,
      "learning_rate": 0.0001145,
      "loss": 7.1822,
      "mean_token_accuracy": 0.0861165277659893,
      "num_tokens": 489376.0,
      "step": 230
    },
    {
      "entropy": 7.872423553466797,
      "epoch": 0.013874948337958316,
      "grad_norm": 0.9453125,
      "learning_rate": 0.00011700000000000001,
      "loss": 7.1724,
      "mean_token_accuracy": 0.08608285039663315,
      "num_tokens": 500260.0,
      "step": 235
    },
    {
      "entropy": 7.763920402526855,
      "epoch": 0.014170160004723386,
      "grad_norm": 0.953125,
      "learning_rate": 0.00011949999999999999,
      "loss": 7.1567,
      "mean_token_accuracy": 0.08700917065143585,
      "num_tokens": 511953.0,
      "step": 240
    },
    {
      "entropy": 7.8764701843261715,
      "epoch": 0.014465371671488458,
      "grad_norm": 0.91796875,
      "learning_rate": 0.000122,
      "loss": 7.3427,
      "mean_token_accuracy": 0.07973492071032524,
      "num_tokens": 523055.0,
      "step": 245
    },
    {
      "entropy": 7.788686466217041,
      "epoch": 0.014760583338253528,
      "grad_norm": 0.9453125,
      "learning_rate": 0.0001245,
      "loss": 7.1424,
      "mean_token_accuracy": 0.0809820182621479,
      "num_tokens": 534337.0,
      "step": 250
    },
    {
      "entropy": 7.773524141311645,
      "epoch": 0.015055795005018599,
      "grad_norm": 0.96875,
      "learning_rate": 0.000127,
      "loss": 7.1488,
      "mean_token_accuracy": 0.08801065608859063,
      "num_tokens": 545189.0,
      "step": 255
    },
    {
      "entropy": 7.762392187118531,
      "epoch": 0.015351006671783669,
      "grad_norm": 0.859375,
      "learning_rate": 0.0001295,
      "loss": 7.1789,
      "mean_token_accuracy": 0.08976453244686126,
      "num_tokens": 555506.0,
      "step": 260
    },
    {
      "entropy": 7.752877712249756,
      "epoch": 0.01564621833854874,
      "grad_norm": 0.84765625,
      "learning_rate": 0.000132,
      "loss": 7.0892,
      "mean_token_accuracy": 0.08789646476507187,
      "num_tokens": 565936.0,
      "step": 265
    },
    {
      "entropy": 7.730583906173706,
      "epoch": 0.01594143000531381,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00013450000000000002,
      "loss": 7.1826,
      "mean_token_accuracy": 0.08930487185716629,
      "num_tokens": 575691.0,
      "step": 270
    },
    {
      "entropy": 7.710203313827515,
      "epoch": 0.01623664167207888,
      "grad_norm": 0.9765625,
      "learning_rate": 0.00013700000000000002,
      "loss": 7.1496,
      "mean_token_accuracy": 0.08626075237989425,
      "num_tokens": 586170.0,
      "step": 275
    },
    {
      "entropy": 7.728785562515259,
      "epoch": 0.016531853338843952,
      "grad_norm": 1.2265625,
      "learning_rate": 0.0001395,
      "loss": 7.1356,
      "mean_token_accuracy": 0.08597519621253014,
      "num_tokens": 596458.0,
      "step": 280
    },
    {
      "entropy": 7.711720895767212,
      "epoch": 0.016827065005609022,
      "grad_norm": 0.94921875,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.0549,
      "mean_token_accuracy": 0.08382375612854957,
      "num_tokens": 606214.0,
      "step": 285
    },
    {
      "entropy": 7.6635658740997314,
      "epoch": 0.017122276672374093,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0001445,
      "loss": 7.1085,
      "mean_token_accuracy": 0.08702588006854058,
      "num_tokens": 617074.0,
      "step": 290
    },
    {
      "entropy": 7.613530492782592,
      "epoch": 0.017417488339139163,
      "grad_norm": 1.03125,
      "learning_rate": 0.000147,
      "loss": 7.1582,
      "mean_token_accuracy": 0.0854655608534813,
      "num_tokens": 628057.0,
      "step": 295
    },
    {
      "entropy": 7.640975618362427,
      "epoch": 0.017712700005904233,
      "grad_norm": 0.95703125,
      "learning_rate": 0.0001495,
      "loss": 7.0762,
      "mean_token_accuracy": 0.0919909045100212,
      "num_tokens": 638150.0,
      "step": 300
    },
    {
      "entropy": 7.644310426712036,
      "epoch": 0.018007911672669304,
      "grad_norm": 1.03125,
      "learning_rate": 0.000152,
      "loss": 6.9574,
      "mean_token_accuracy": 0.09665790945291519,
      "num_tokens": 648377.0,
      "step": 305
    },
    {
      "entropy": 7.570417594909668,
      "epoch": 0.018303123339434374,
      "grad_norm": 0.89453125,
      "learning_rate": 0.00015450000000000001,
      "loss": 7.0219,
      "mean_token_accuracy": 0.09368904307484627,
      "num_tokens": 658777.0,
      "step": 310
    },
    {
      "entropy": 7.5545618534088135,
      "epoch": 0.018598335006199444,
      "grad_norm": 1.078125,
      "learning_rate": 0.000157,
      "loss": 7.1283,
      "mean_token_accuracy": 0.08728318810462951,
      "num_tokens": 669105.0,
      "step": 315
    },
    {
      "entropy": 7.581419992446899,
      "epoch": 0.018893546672964515,
      "grad_norm": 0.8671875,
      "learning_rate": 0.0001595,
      "loss": 6.9931,
      "mean_token_accuracy": 0.08857197985053063,
      "num_tokens": 679294.0,
      "step": 320
    },
    {
      "entropy": 7.5300342559814455,
      "epoch": 0.019188758339729585,
      "grad_norm": 0.8125,
      "learning_rate": 0.000162,
      "loss": 6.9576,
      "mean_token_accuracy": 0.09436112716794014,
      "num_tokens": 690495.0,
      "step": 325
    },
    {
      "entropy": 7.517716407775879,
      "epoch": 0.019483970006494655,
      "grad_norm": 0.86328125,
      "learning_rate": 0.00016450000000000001,
      "loss": 6.979,
      "mean_token_accuracy": 0.09718031734228134,
      "num_tokens": 701002.0,
      "step": 330
    },
    {
      "entropy": 7.48517951965332,
      "epoch": 0.019779181673259726,
      "grad_norm": 0.97265625,
      "learning_rate": 0.00016700000000000002,
      "loss": 6.8828,
      "mean_token_accuracy": 0.09275271818041801,
      "num_tokens": 711488.0,
      "step": 335
    },
    {
      "entropy": 7.405734252929688,
      "epoch": 0.0200743933400248,
      "grad_norm": 0.984375,
      "learning_rate": 0.00016950000000000003,
      "loss": 6.9022,
      "mean_token_accuracy": 0.09012737646698951,
      "num_tokens": 722637.0,
      "step": 340
    },
    {
      "entropy": 7.489488410949707,
      "epoch": 0.02036960500678987,
      "grad_norm": 0.88671875,
      "learning_rate": 0.00017199999999999998,
      "loss": 6.9705,
      "mean_token_accuracy": 0.09417287185788155,
      "num_tokens": 733212.0,
      "step": 345
    },
    {
      "entropy": 7.45473804473877,
      "epoch": 0.02066481667355494,
      "grad_norm": 1.390625,
      "learning_rate": 0.00017449999999999999,
      "loss": 6.9008,
      "mean_token_accuracy": 0.09309542924165726,
      "num_tokens": 743602.0,
      "step": 350
    },
    {
      "entropy": 7.441885089874267,
      "epoch": 0.02096002834032001,
      "grad_norm": 1.15625,
      "learning_rate": 0.000177,
      "loss": 6.9506,
      "mean_token_accuracy": 0.09587474688887596,
      "num_tokens": 754094.0,
      "step": 355
    },
    {
      "entropy": 7.430218076705932,
      "epoch": 0.02125524000708508,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0001795,
      "loss": 6.8964,
      "mean_token_accuracy": 0.09253331273794174,
      "num_tokens": 763823.0,
      "step": 360
    },
    {
      "entropy": 7.417900943756104,
      "epoch": 0.02155045167385015,
      "grad_norm": 1.2109375,
      "learning_rate": 0.000182,
      "loss": 6.8424,
      "mean_token_accuracy": 0.09944578483700753,
      "num_tokens": 774128.0,
      "step": 365
    },
    {
      "entropy": 7.384387731552124,
      "epoch": 0.02184566334061522,
      "grad_norm": 1.1484375,
      "learning_rate": 0.0001845,
      "loss": 6.913,
      "mean_token_accuracy": 0.09629636481404305,
      "num_tokens": 784292.0,
      "step": 370
    },
    {
      "entropy": 7.428071117401123,
      "epoch": 0.02214087500738029,
      "grad_norm": 0.921875,
      "learning_rate": 0.000187,
      "loss": 6.896,
      "mean_token_accuracy": 0.09847814217209816,
      "num_tokens": 795437.0,
      "step": 375
    },
    {
      "entropy": 7.368625783920288,
      "epoch": 0.022436086674145362,
      "grad_norm": 1.0078125,
      "learning_rate": 0.0001895,
      "loss": 6.8038,
      "mean_token_accuracy": 0.09553659558296204,
      "num_tokens": 806543.0,
      "step": 380
    },
    {
      "entropy": 7.34774341583252,
      "epoch": 0.022731298340910432,
      "grad_norm": 1.1484375,
      "learning_rate": 0.000192,
      "loss": 6.9575,
      "mean_token_accuracy": 0.09456263706088067,
      "num_tokens": 817179.0,
      "step": 385
    },
    {
      "entropy": 7.4415544986724855,
      "epoch": 0.023026510007675503,
      "grad_norm": 0.94921875,
      "learning_rate": 0.0001945,
      "loss": 6.8667,
      "mean_token_accuracy": 0.09976130351424217,
      "num_tokens": 826749.0,
      "step": 390
    },
    {
      "entropy": 7.363486337661743,
      "epoch": 0.023321721674440573,
      "grad_norm": 1.109375,
      "learning_rate": 0.00019700000000000002,
      "loss": 6.8927,
      "mean_token_accuracy": 0.0938490979373455,
      "num_tokens": 838807.0,
      "step": 395
    },
    {
      "entropy": 7.37176923751831,
      "epoch": 0.023616933341205643,
      "grad_norm": 0.99609375,
      "learning_rate": 0.00019950000000000002,
      "loss": 6.8827,
      "mean_token_accuracy": 0.09748194366693497,
      "num_tokens": 849651.0,
      "step": 400
    },
    {
      "entropy": 7.367251443862915,
      "epoch": 0.023912145007970714,
      "grad_norm": 1.0234375,
      "learning_rate": 0.000202,
      "loss": 6.934,
      "mean_token_accuracy": 0.09160904809832573,
      "num_tokens": 859753.0,
      "step": 405
    },
    {
      "entropy": 7.345250177383423,
      "epoch": 0.024207356674735784,
      "grad_norm": 0.90625,
      "learning_rate": 0.00020449999999999998,
      "loss": 6.8134,
      "mean_token_accuracy": 0.10118522644042968,
      "num_tokens": 869904.0,
      "step": 410
    },
    {
      "entropy": 7.267154836654663,
      "epoch": 0.024502568341500858,
      "grad_norm": 0.88671875,
      "learning_rate": 0.000207,
      "loss": 6.8152,
      "mean_token_accuracy": 0.09964827746152878,
      "num_tokens": 880948.0,
      "step": 415
    },
    {
      "entropy": 7.350914382934571,
      "epoch": 0.024797780008265928,
      "grad_norm": 0.94921875,
      "learning_rate": 0.0002095,
      "loss": 6.8961,
      "mean_token_accuracy": 0.09352625384926797,
      "num_tokens": 892331.0,
      "step": 420
    },
    {
      "entropy": 7.300309419631958,
      "epoch": 0.025092991675031,
      "grad_norm": 1.09375,
      "learning_rate": 0.000212,
      "loss": 6.731,
      "mean_token_accuracy": 0.10073179304599762,
      "num_tokens": 901691.0,
      "step": 425
    },
    {
      "entropy": 7.247861719131469,
      "epoch": 0.02538820334179607,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0002145,
      "loss": 6.7662,
      "mean_token_accuracy": 0.0965045303106308,
      "num_tokens": 912495.0,
      "step": 430
    },
    {
      "entropy": 7.235934734344482,
      "epoch": 0.02568341500856114,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00021700000000000002,
      "loss": 6.7406,
      "mean_token_accuracy": 0.10061677768826485,
      "num_tokens": 923420.0,
      "step": 435
    },
    {
      "entropy": 7.153478145599365,
      "epoch": 0.02597862667532621,
      "grad_norm": 0.94140625,
      "learning_rate": 0.0002195,
      "loss": 6.7327,
      "mean_token_accuracy": 0.10134619474411011,
      "num_tokens": 933598.0,
      "step": 440
    },
    {
      "entropy": 7.279621028900147,
      "epoch": 0.02627383834209128,
      "grad_norm": 1.1953125,
      "learning_rate": 0.000222,
      "loss": 6.8611,
      "mean_token_accuracy": 0.09994317889213562,
      "num_tokens": 943229.0,
      "step": 445
    },
    {
      "entropy": 7.256894063949585,
      "epoch": 0.02656905000885635,
      "grad_norm": 1.0390625,
      "learning_rate": 0.0002245,
      "loss": 6.7288,
      "mean_token_accuracy": 0.09972334206104279,
      "num_tokens": 954425.0,
      "step": 450
    },
    {
      "entropy": 7.333712911605835,
      "epoch": 0.02686426167562142,
      "grad_norm": 1.1328125,
      "learning_rate": 0.00022700000000000002,
      "loss": 6.8322,
      "mean_token_accuracy": 0.10051686838269233,
      "num_tokens": 965516.0,
      "step": 455
    },
    {
      "entropy": 7.109683799743652,
      "epoch": 0.02715947334238649,
      "grad_norm": 0.90234375,
      "learning_rate": 0.00022950000000000002,
      "loss": 6.7124,
      "mean_token_accuracy": 0.10072791278362274,
      "num_tokens": 976469.0,
      "step": 460
    },
    {
      "entropy": 7.249271726608276,
      "epoch": 0.02745468500915156,
      "grad_norm": 1.046875,
      "learning_rate": 0.00023200000000000003,
      "loss": 6.8029,
      "mean_token_accuracy": 0.09443021714687347,
      "num_tokens": 986946.0,
      "step": 465
    },
    {
      "entropy": 7.233931303024292,
      "epoch": 0.02774989667591663,
      "grad_norm": 1.015625,
      "learning_rate": 0.00023449999999999998,
      "loss": 6.6988,
      "mean_token_accuracy": 0.10011776387691498,
      "num_tokens": 997101.0,
      "step": 470
    },
    {
      "entropy": 7.123860883712768,
      "epoch": 0.0280451083426817,
      "grad_norm": 1.0703125,
      "learning_rate": 0.000237,
      "loss": 6.8063,
      "mean_token_accuracy": 0.09995891153812408,
      "num_tokens": 1007866.0,
      "step": 475
    },
    {
      "entropy": 7.302121591567993,
      "epoch": 0.028340320009446772,
      "grad_norm": 1.15625,
      "learning_rate": 0.0002395,
      "loss": 6.8209,
      "mean_token_accuracy": 0.09563429430127143,
      "num_tokens": 1019377.0,
      "step": 480
    },
    {
      "entropy": 7.214538860321045,
      "epoch": 0.028635531676211842,
      "grad_norm": 0.97265625,
      "learning_rate": 0.000242,
      "loss": 6.7985,
      "mean_token_accuracy": 0.10173870101571084,
      "num_tokens": 1031278.0,
      "step": 485
    },
    {
      "entropy": 7.053379869461059,
      "epoch": 0.028930743342976916,
      "grad_norm": 0.94140625,
      "learning_rate": 0.0002445,
      "loss": 6.609,
      "mean_token_accuracy": 0.10857169032096863,
      "num_tokens": 1041663.0,
      "step": 490
    },
    {
      "entropy": 7.141558599472046,
      "epoch": 0.029225955009741986,
      "grad_norm": 1.0078125,
      "learning_rate": 0.000247,
      "loss": 6.68,
      "mean_token_accuracy": 0.10325370877981185,
      "num_tokens": 1052286.0,
      "step": 495
    },
    {
      "entropy": 7.082495021820068,
      "epoch": 0.029521166676507057,
      "grad_norm": 1.1953125,
      "learning_rate": 0.0002495,
      "loss": 6.7424,
      "mean_token_accuracy": 0.10430480614304542,
      "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": 228077211156480.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}