{
  "log_history": [
    {
      "loss": 3.6021,
      "grad_norm": 4.66565465927124,
      "learning_rate": 1.8750000000000003e-06,
      "entropy": 2.4040649354457857,
      "num_tokens": 61199.0,
      "mean_token_accuracy": 0.4221017129719257,
      "epoch": 0.012626262626262626,
      "step": 10
    },
    {
      "loss": 3.3432,
      "grad_norm": 3.8161869049072266,
      "learning_rate": 3.958333333333333e-06,
      "entropy": 2.3836746215820312,
      "num_tokens": 122423.0,
      "mean_token_accuracy": 0.44042530804872515,
      "epoch": 0.025252525252525252,
      "step": 20
    },
    {
      "loss": 2.9033,
      "grad_norm": 3.8800699710845947,
      "learning_rate": 6.041666666666667e-06,
      "entropy": 2.355724626779556,
      "num_tokens": 182649.0,
      "mean_token_accuracy": 0.48426677361130716,
      "epoch": 0.03787878787878788,
      "step": 30
    },
    {
      "loss": 2.356,
      "grad_norm": 2.8217720985412598,
      "learning_rate": 8.125000000000001e-06,
      "entropy": 2.092331054806709,
      "num_tokens": 243049.0,
      "mean_token_accuracy": 0.5772452697157859,
      "epoch": 0.050505050505050504,
      "step": 40
    },
    {
      "loss": 1.8899,
      "grad_norm": 1.4623568058013916,
      "learning_rate": 9.993489583333334e-06,
      "entropy": 1.6766322344541549,
      "num_tokens": 304326.0,
      "mean_token_accuracy": 0.6480962842702865,
      "epoch": 0.06313131313131314,
      "step": 50
    },
    {
      "loss": 1.677,
      "grad_norm": 1.171562671661377,
      "learning_rate": 9.928385416666668e-06,
      "entropy": 1.5568815559148788,
      "num_tokens": 364866.0,
      "mean_token_accuracy": 0.6776855796575546,
      "epoch": 0.07575757575757576,
      "step": 60
    },
    {
      "loss": 1.5337,
      "grad_norm": 0.9904961585998535,
      "learning_rate": 9.863281250000001e-06,
      "entropy": 1.48199902176857,
      "num_tokens": 423478.0,
      "mean_token_accuracy": 0.697019773721695,
      "epoch": 0.08838383838383838,
      "step": 70
    },
    {
      "loss": 1.4953,
      "grad_norm": 0.9454260468482971,
      "learning_rate": 9.798177083333335e-06,
      "entropy": 1.497376424074173,
      "num_tokens": 483659.0,
      "mean_token_accuracy": 0.6976823702454567,
      "epoch": 0.10101010101010101,
      "step": 80
    },
    {
      "loss": 1.4356,
      "grad_norm": 0.8955270648002625,
      "learning_rate": 9.733072916666667e-06,
      "entropy": 1.4664768785238267,
      "num_tokens": 544453.0,
      "mean_token_accuracy": 0.7069446608424187,
      "epoch": 0.11363636363636363,
      "step": 90
    },
    {
      "loss": 1.4106,
      "grad_norm": 0.9242203235626221,
      "learning_rate": 9.66796875e-06,
      "entropy": 1.4269085675477982,
      "num_tokens": 604546.0,
      "mean_token_accuracy": 0.7122392952442169,
      "epoch": 0.12626262626262627,
      "step": 100
    },
    {
      "loss": 1.3487,
      "grad_norm": 0.8968560695648193,
      "learning_rate": 9.602864583333335e-06,
      "entropy": 1.4060751020908355,
      "num_tokens": 664860.0,
      "mean_token_accuracy": 0.7178552970290184,
      "epoch": 0.1388888888888889,
      "step": 110
    },
    {
      "loss": 1.3347,
      "grad_norm": 0.9047113656997681,
      "learning_rate": 9.537760416666667e-06,
      "entropy": 1.4018951296806335,
      "num_tokens": 725022.0,
      "mean_token_accuracy": 0.7208079636096955,
      "epoch": 0.15151515151515152,
      "step": 120
    },
    {
      "loss": 1.3155,
      "grad_norm": 0.8915444016456604,
      "learning_rate": 9.47265625e-06,
      "entropy": 1.3809731483459473,
      "num_tokens": 785586.0,
      "mean_token_accuracy": 0.7267520889639855,
      "epoch": 0.16414141414141414,
      "step": 130
    },
    {
      "loss": 1.3016,
      "grad_norm": 0.8574295043945312,
      "learning_rate": 9.407552083333334e-06,
      "entropy": 1.3699676394462585,
      "num_tokens": 845790.0,
      "mean_token_accuracy": 0.7266673430800438,
      "epoch": 0.17676767676767677,
      "step": 140
    },
    {
      "loss": 1.2823,
      "grad_norm": 0.8231800198554993,
      "learning_rate": 9.342447916666668e-06,
      "entropy": 1.3425012439489366,
      "num_tokens": 905842.0,
      "mean_token_accuracy": 0.7277117937803268,
      "epoch": 0.1893939393939394,
      "step": 150
    },
    {
      "loss": 1.2917,
      "grad_norm": 0.8166369795799255,
      "learning_rate": 9.277343750000001e-06,
      "entropy": 1.3314216613769532,
      "num_tokens": 966487.0,
      "mean_token_accuracy": 0.7278609350323677,
      "epoch": 0.20202020202020202,
      "step": 160
    },
    {
      "loss": 1.2481,
      "grad_norm": 0.7738587260246277,
      "learning_rate": 9.212239583333335e-06,
      "entropy": 1.30389544069767,
      "num_tokens": 1025558.0,
      "mean_token_accuracy": 0.7335339426994324,
      "epoch": 0.21464646464646464,
      "step": 170
    },
    {
      "loss": 1.2643,
      "grad_norm": 0.7718328833580017,
      "learning_rate": 9.147135416666667e-06,
      "entropy": 1.311449444293976,
      "num_tokens": 1086677.0,
      "mean_token_accuracy": 0.7285080313682556,
      "epoch": 0.22727272727272727,
      "step": 180
    },
    {
      "loss": 1.2641,
      "grad_norm": 0.7341915369033813,
      "learning_rate": 9.082031250000001e-06,
      "entropy": 1.3079361200332642,
      "num_tokens": 1147885.0,
      "mean_token_accuracy": 0.729550538957119,
      "epoch": 0.2398989898989899,
      "step": 190
    },
    {
      "loss": 1.2397,
      "grad_norm": 0.748540997505188,
      "learning_rate": 9.016927083333335e-06,
      "entropy": 1.2794219702482224,
      "num_tokens": 1207321.0,
      "mean_token_accuracy": 0.7351120054721832,
      "epoch": 0.25252525252525254,
      "step": 200
    },
    {
      "loss": 1.2489,
      "grad_norm": 0.7585553526878357,
      "learning_rate": 8.951822916666667e-06,
      "entropy": 1.294454461336136,
      "num_tokens": 1267837.0,
      "mean_token_accuracy": 0.7322148531675339,
      "epoch": 0.26515151515151514,
      "step": 210
    },
    {
      "loss": 1.2383,
      "grad_norm": 0.6937864422798157,
      "learning_rate": 8.88671875e-06,
      "entropy": 1.2862246632575989,
      "num_tokens": 1328436.0,
      "mean_token_accuracy": 0.7358245223760604,
      "epoch": 0.2777777777777778,
      "step": 220
    },
    {
      "loss": 1.2007,
      "grad_norm": 0.6792387366294861,
      "learning_rate": 8.821614583333334e-06,
      "entropy": 1.2531811505556107,
      "num_tokens": 1389877.0,
      "mean_token_accuracy": 0.7360369265079498,
      "epoch": 0.2904040404040404,
      "step": 230
    },
    {
      "loss": 1.2474,
      "grad_norm": 0.6865427494049072,
      "learning_rate": 8.756510416666666e-06,
      "entropy": 1.2815489560365676,
      "num_tokens": 1450927.0,
      "mean_token_accuracy": 0.7304804190993309,
      "epoch": 0.30303030303030304,
      "step": 240
    },
    {
      "loss": 1.2172,
      "grad_norm": 0.669840395450592,
      "learning_rate": 8.69140625e-06,
      "entropy": 1.2568059146404267,
      "num_tokens": 1511174.0,
      "mean_token_accuracy": 0.7385278165340423,
      "epoch": 0.31565656565656564,
      "step": 250
    },
    {
      "loss": 1.213,
      "grad_norm": 0.6434893012046814,
      "learning_rate": 8.626302083333334e-06,
      "entropy": 1.254868358373642,
      "num_tokens": 1570570.0,
      "mean_token_accuracy": 0.7380544006824493,
      "epoch": 0.3282828282828283,
      "step": 260
    },
    {
      "loss": 1.2116,
      "grad_norm": 0.6034978032112122,
      "learning_rate": 8.561197916666667e-06,
      "entropy": 1.2532441645860672,
      "num_tokens": 1630930.0,
      "mean_token_accuracy": 0.7382062628865242,
      "epoch": 0.3409090909090909,
      "step": 270
    },
    {
      "loss": 1.2313,
      "grad_norm": 0.6371450424194336,
      "learning_rate": 8.496093750000001e-06,
      "entropy": 1.2605280816555022,
      "num_tokens": 1692624.0,
      "mean_token_accuracy": 0.7328852489590645,
      "epoch": 0.35353535353535354,
      "step": 280
    },
    {
      "loss": 1.2195,
      "grad_norm": 0.6300278306007385,
      "learning_rate": 8.430989583333335e-06,
      "entropy": 1.248606452345848,
      "num_tokens": 1754213.0,
      "mean_token_accuracy": 0.7370449885725975,
      "epoch": 0.3661616161616162,
      "step": 290
    },
    {
      "loss": 1.1845,
      "grad_norm": 0.6430155634880066,
      "learning_rate": 8.365885416666667e-06,
      "entropy": 1.2246102809906005,
      "num_tokens": 1813841.0,
      "mean_token_accuracy": 0.7439196646213532,
      "epoch": 0.3787878787878788,
      "step": 300
    },
    {
      "loss": 1.1856,
      "grad_norm": 0.6395701766014099,
      "learning_rate": 8.30078125e-06,
      "entropy": 1.2188815206289292,
      "num_tokens": 1873568.0,
      "mean_token_accuracy": 0.7422183871269226,
      "epoch": 0.39141414141414144,
      "step": 310
    },
    {
      "loss": 1.1951,
      "grad_norm": 0.6168740391731262,
      "learning_rate": 8.235677083333334e-06,
      "entropy": 1.234528934955597,
      "num_tokens": 1935518.0,
      "mean_token_accuracy": 0.7380509555339814,
      "epoch": 0.40404040404040403,
      "step": 320
    },
    {
      "loss": 1.2078,
      "grad_norm": 0.611132800579071,
      "learning_rate": 8.170572916666666e-06,
      "entropy": 1.226365676522255,
      "num_tokens": 1995604.0,
      "mean_token_accuracy": 0.739974245429039,
      "epoch": 0.4166666666666667,
      "step": 330
    },
    {
      "loss": 1.1642,
      "grad_norm": 0.6103131771087646,
      "learning_rate": 8.10546875e-06,
      "entropy": 1.2132183194160462,
      "num_tokens": 2056484.0,
      "mean_token_accuracy": 0.7444137379527092,
      "epoch": 0.4292929292929293,
      "step": 340
    },
    {
      "loss": 1.2001,
      "grad_norm": 0.6188805103302002,
      "learning_rate": 8.040364583333334e-06,
      "entropy": 1.223158246278763,
      "num_tokens": 2118437.0,
      "mean_token_accuracy": 0.7385613292455673,
      "epoch": 0.44191919191919193,
      "step": 350
    },
    {
      "loss": 1.1848,
      "grad_norm": 0.6238694190979004,
      "learning_rate": 7.975260416666668e-06,
      "entropy": 1.2154075980186463,
      "num_tokens": 2179333.0,
      "mean_token_accuracy": 0.7404153689742088,
      "epoch": 0.45454545454545453,
      "step": 360
    },
    {
      "loss": 1.1597,
      "grad_norm": 0.6028566956520081,
      "learning_rate": 7.910156250000001e-06,
      "entropy": 1.197928261756897,
      "num_tokens": 2239604.0,
      "mean_token_accuracy": 0.7475010469555855,
      "epoch": 0.4671717171717172,
      "step": 370
    },
    {
      "loss": 1.1805,
      "grad_norm": 0.6569434404373169,
      "learning_rate": 7.845052083333335e-06,
      "entropy": 1.189855706691742,
      "num_tokens": 2300936.0,
      "mean_token_accuracy": 0.7427218139171601,
      "epoch": 0.4797979797979798,
      "step": 380
    },
    {
      "loss": 1.1759,
      "grad_norm": 0.6351733207702637,
      "learning_rate": 7.779947916666667e-06,
      "entropy": 1.2076493889093398,
      "num_tokens": 2361539.0,
      "mean_token_accuracy": 0.7408407002687454,
      "epoch": 0.49242424242424243,
      "step": 390
    },
    {
      "loss": 1.1874,
      "grad_norm": 0.6327986121177673,
      "learning_rate": 7.71484375e-06,
      "entropy": 1.2223081022500992,
      "num_tokens": 2422162.0,
      "mean_token_accuracy": 0.7407250568270684,
      "epoch": 0.5050505050505051,
      "step": 400
    },
    {
      "loss": 1.1726,
      "grad_norm": 0.622104823589325,
      "learning_rate": 7.649739583333334e-06,
      "entropy": 1.2013412863016129,
      "num_tokens": 2483447.0,
      "mean_token_accuracy": 0.744242025911808,
      "epoch": 0.5176767676767676,
      "step": 410
    },
    {
      "loss": 1.1838,
      "grad_norm": 0.637651264667511,
      "learning_rate": 7.5846354166666665e-06,
      "entropy": 1.2116613179445266,
      "num_tokens": 2544848.0,
      "mean_token_accuracy": 0.7405030101537704,
      "epoch": 0.5303030303030303,
      "step": 420
    },
    {
      "loss": 1.1681,
      "grad_norm": 0.6252374649047852,
      "learning_rate": 7.51953125e-06,
      "entropy": 1.2024697184562683,
      "num_tokens": 2605232.0,
      "mean_token_accuracy": 0.7458183988928795,
      "epoch": 0.5429292929292929,
      "step": 430
    },
    {
      "loss": 1.1452,
      "grad_norm": 0.6502755284309387,
      "learning_rate": 7.454427083333334e-06,
      "entropy": 1.1797083109617232,
      "num_tokens": 2664276.0,
      "mean_token_accuracy": 0.7477341219782829,
      "epoch": 0.5555555555555556,
      "step": 440
    },
    {
      "loss": 1.1665,
      "grad_norm": 0.639979362487793,
      "learning_rate": 7.389322916666667e-06,
      "entropy": 1.1964200481772422,
      "num_tokens": 2724073.0,
      "mean_token_accuracy": 0.7431837096810341,
      "epoch": 0.5681818181818182,
      "step": 450
    },
    {
      "loss": 1.1529,
      "grad_norm": 0.6212354302406311,
      "learning_rate": 7.3242187500000006e-06,
      "entropy": 1.1795272737741471,
      "num_tokens": 2784262.0,
      "mean_token_accuracy": 0.7479098170995713,
      "epoch": 0.5808080808080808,
      "step": 460
    },
    {
      "loss": 1.1678,
      "grad_norm": 0.6528693437576294,
      "learning_rate": 7.259114583333334e-06,
      "entropy": 1.1908618807792664,
      "num_tokens": 2843804.0,
      "mean_token_accuracy": 0.745174677670002,
      "epoch": 0.5934343434343434,
      "step": 470
    },
    {
      "loss": 1.1565,
      "grad_norm": 0.639481246471405,
      "learning_rate": 7.194010416666667e-06,
      "entropy": 1.1862946093082427,
      "num_tokens": 2903408.0,
      "mean_token_accuracy": 0.7461866185069084,
      "epoch": 0.6060606060606061,
      "step": 480
    },
    {
      "loss": 1.1251,
      "grad_norm": 0.6332777142524719,
      "learning_rate": 7.128906250000001e-06,
      "entropy": 1.151743534207344,
      "num_tokens": 2963401.0,
      "mean_token_accuracy": 0.7535199671983719,
      "epoch": 0.6186868686868687,
      "step": 490
    },
    {
      "loss": 1.1407,
      "grad_norm": 0.5991836190223694,
      "learning_rate": 7.063802083333335e-06,
      "entropy": 1.1778477430343628,
      "num_tokens": 3023530.0,
      "mean_token_accuracy": 0.7491110354661942,
      "epoch": 0.6313131313131313,
      "step": 500
    },
    {
      "loss": 1.1724,
      "grad_norm": 0.6293458938598633,
      "learning_rate": 6.998697916666667e-06,
      "entropy": 1.2023035794496537,
      "num_tokens": 3085225.0,
      "mean_token_accuracy": 0.7405256554484367,
      "epoch": 0.6439393939393939,
      "step": 510
    },
    {
      "loss": 1.1604,
      "grad_norm": 0.6213802695274353,
      "learning_rate": 6.93359375e-06,
      "entropy": 1.1997334092855454,
      "num_tokens": 3145749.0,
      "mean_token_accuracy": 0.7435309410095214,
      "epoch": 0.6565656565656566,
      "step": 520
    },
    {
      "loss": 1.1381,
      "grad_norm": 0.6495156288146973,
      "learning_rate": 6.868489583333334e-06,
      "entropy": 1.1643184214830398,
      "num_tokens": 3205761.0,
      "mean_token_accuracy": 0.7496751576662064,
      "epoch": 0.6691919191919192,
      "step": 530
    },
    {
      "loss": 1.1563,
      "grad_norm": 0.6004510521888733,
      "learning_rate": 6.803385416666667e-06,
      "entropy": 1.1837532848119736,
      "num_tokens": 3267024.0,
      "mean_token_accuracy": 0.7447851061820984,
      "epoch": 0.6818181818181818,
      "step": 540
    },
    {
      "loss": 1.1776,
      "grad_norm": 0.607467532157898,
      "learning_rate": 6.738281250000001e-06,
      "entropy": 1.201677542924881,
      "num_tokens": 3329070.0,
      "mean_token_accuracy": 0.7406648993492126,
      "epoch": 0.6944444444444444,
      "step": 550
    },
    {
      "loss": 1.1298,
      "grad_norm": 0.6079947352409363,
      "learning_rate": 6.6731770833333345e-06,
      "entropy": 1.1659786373376846,
      "num_tokens": 3389505.0,
      "mean_token_accuracy": 0.7505511298775673,
      "epoch": 0.7070707070707071,
      "step": 560
    },
    {
      "loss": 1.144,
      "grad_norm": 0.6534572839736938,
      "learning_rate": 6.6080729166666665e-06,
      "entropy": 1.1714913487434386,
      "num_tokens": 3449834.0,
      "mean_token_accuracy": 0.7481625184416771,
      "epoch": 0.7196969696969697,
      "step": 570
    },
    {
      "loss": 1.139,
      "grad_norm": 0.5903164744377136,
      "learning_rate": 6.54296875e-06,
      "entropy": 1.1694963037967683,
      "num_tokens": 3510701.0,
      "mean_token_accuracy": 0.7476441130042076,
      "epoch": 0.7323232323232324,
      "step": 580
    },
    {
      "loss": 1.1422,
      "grad_norm": 0.6284182071685791,
      "learning_rate": 6.477864583333334e-06,
      "entropy": 1.1777653217315673,
      "num_tokens": 3570992.0,
      "mean_token_accuracy": 0.7490358456969262,
      "epoch": 0.7449494949494949,
      "step": 590
    },
    {
      "loss": 1.1336,
      "grad_norm": 0.6250146627426147,
      "learning_rate": 6.412760416666667e-06,
      "entropy": 1.1588268011808396,
      "num_tokens": 3631087.0,
      "mean_token_accuracy": 0.7504108369350433,
      "epoch": 0.7575757575757576,
      "step": 600
    },
    {
      "loss": 1.1534,
      "grad_norm": 0.6420578956604004,
      "learning_rate": 6.3476562500000006e-06,
      "entropy": 1.1890273630619048,
      "num_tokens": 3692871.0,
      "mean_token_accuracy": 0.7442372158169747,
      "epoch": 0.7702020202020202,
      "step": 610
    },
    {
      "loss": 1.1477,
      "grad_norm": 0.6156490445137024,
      "learning_rate": 6.282552083333334e-06,
      "entropy": 1.1817798465490341,
      "num_tokens": 3753671.0,
      "mean_token_accuracy": 0.7468263059854507,
      "epoch": 0.7828282828282829,
      "step": 620
    },
    {
      "loss": 1.139,
      "grad_norm": 0.6248748898506165,
      "learning_rate": 6.217447916666667e-06,
      "entropy": 1.1686612635850906,
      "num_tokens": 3813110.0,
      "mean_token_accuracy": 0.7478924334049225,
      "epoch": 0.7954545454545454,
      "step": 630
    },
    {
      "loss": 1.1118,
      "grad_norm": 0.6052266359329224,
      "learning_rate": 6.152343750000001e-06,
      "entropy": 1.1387953266501427,
      "num_tokens": 3873477.0,
      "mean_token_accuracy": 0.7538487210869789,
      "epoch": 0.8080808080808081,
      "step": 640
    },
    {
      "loss": 1.1108,
      "grad_norm": 0.6769536137580872,
      "learning_rate": 6.087239583333335e-06,
      "entropy": 1.1343814879655838,
      "num_tokens": 3932873.0,
      "mean_token_accuracy": 0.7548464313149452,
      "epoch": 0.8207070707070707,
      "step": 650
    },
    {
      "loss": 1.134,
      "grad_norm": 0.6545736789703369,
      "learning_rate": 6.022135416666667e-06,
      "entropy": 1.1686519652605056,
      "num_tokens": 3992754.0,
      "mean_token_accuracy": 0.7495195478200912,
      "epoch": 0.8333333333333334,
      "step": 660
    },
    {
      "loss": 1.1213,
      "grad_norm": 0.6192017793655396,
      "learning_rate": 5.95703125e-06,
      "entropy": 1.1596283346414566,
      "num_tokens": 4053540.0,
      "mean_token_accuracy": 0.7510297149419785,
      "epoch": 0.8459595959595959,
      "step": 670
    },
    {
      "loss": 1.1181,
      "grad_norm": 0.6520631909370422,
      "learning_rate": 5.891927083333334e-06,
      "entropy": 1.1484344542026519,
      "num_tokens": 4113582.0,
      "mean_token_accuracy": 0.751795919239521,
      "epoch": 0.8585858585858586,
      "step": 680
    },
    {
      "loss": 1.1204,
      "grad_norm": 0.6247655153274536,
      "learning_rate": 5.826822916666667e-06,
      "entropy": 1.1519750133156776,
      "num_tokens": 4174983.0,
      "mean_token_accuracy": 0.7506368085741997,
      "epoch": 0.8712121212121212,
      "step": 690
    },
    {
      "loss": 1.1191,
      "grad_norm": 0.620272159576416,
      "learning_rate": 5.761718750000001e-06,
      "entropy": 1.1486561581492425,
      "num_tokens": 4234465.0,
      "mean_token_accuracy": 0.7536391675472259,
      "epoch": 0.8838383838383839,
      "step": 700
    },
    {
      "loss": 1.1224,
      "grad_norm": 0.6308649182319641,
      "learning_rate": 5.6966145833333344e-06,
      "entropy": 1.1504923462867738,
      "num_tokens": 4295955.0,
      "mean_token_accuracy": 0.750646598637104,
      "epoch": 0.8964646464646465,
      "step": 710
    },
    {
      "loss": 1.1238,
      "grad_norm": 0.6629899740219116,
      "learning_rate": 5.6315104166666665e-06,
      "entropy": 1.1561898440122604,
      "num_tokens": 4357171.0,
      "mean_token_accuracy": 0.7507557719945908,
      "epoch": 0.9090909090909091,
      "step": 720
    },
    {
      "loss": 1.1038,
      "grad_norm": 0.5972346067428589,
      "learning_rate": 5.56640625e-06,
      "entropy": 1.1413449853658677,
      "num_tokens": 4417636.0,
      "mean_token_accuracy": 0.7554104939103127,
      "epoch": 0.9217171717171717,
      "step": 730
    },
    {
      "loss": 1.1005,
      "grad_norm": 0.6356479525566101,
      "learning_rate": 5.501302083333334e-06,
      "entropy": 1.1356119453907012,
      "num_tokens": 4477294.0,
      "mean_token_accuracy": 0.7565629109740257,
      "epoch": 0.9343434343434344,
      "step": 740
    },
    {
      "loss": 1.1225,
      "grad_norm": 0.6416464447975159,
      "learning_rate": 5.436197916666667e-06,
      "entropy": 1.1633600294589996,
      "num_tokens": 4537503.0,
      "mean_token_accuracy": 0.7515855401754379,
      "epoch": 0.946969696969697,
      "step": 750
    },
    {
      "loss": 1.1184,
      "grad_norm": 0.6126084327697754,
      "learning_rate": 5.3710937500000005e-06,
      "entropy": 1.1527763932943345,
      "num_tokens": 4598778.0,
      "mean_token_accuracy": 0.7526160582900048,
      "epoch": 0.9595959595959596,
      "step": 760
    },
    {
      "loss": 1.1144,
      "grad_norm": 0.6359922289848328,
      "learning_rate": 5.305989583333334e-06,
      "entropy": 1.1397768080234527,
      "num_tokens": 4658978.0,
      "mean_token_accuracy": 0.7548302739858628,
      "epoch": 0.9722222222222222,
      "step": 770
    },
    {
      "loss": 1.1213,
      "grad_norm": 0.6260409951210022,
      "learning_rate": 5.240885416666667e-06,
      "entropy": 1.1569962561130525,
      "num_tokens": 4720500.0,
      "mean_token_accuracy": 0.7512885302305221,
      "epoch": 0.9848484848484849,
      "step": 780
    },
    {
      "loss": 1.1227,
      "grad_norm": 0.6293452978134155,
      "learning_rate": 5.17578125e-06,
      "entropy": 1.1509152203798294,
      "num_tokens": 4781612.0,
      "mean_token_accuracy": 0.7519564241170883,
      "epoch": 0.9974747474747475,
      "step": 790
    },
    {
      "loss": 1.1034,
      "grad_norm": 0.664761483669281,
      "learning_rate": 5.110677083333334e-06,
      "entropy": 1.1399024561047555,
      "num_tokens": 4841359.0,
      "mean_token_accuracy": 0.7526706486940384,
      "epoch": 1.0101010101010102,
      "step": 800
    },
    {
      "loss": 1.0857,
      "grad_norm": 0.5934865474700928,
      "learning_rate": 5.045572916666667e-06,
      "entropy": 1.120214229822159,
      "num_tokens": 4901016.0,
      "mean_token_accuracy": 0.7593594208359719,
      "epoch": 1.0227272727272727,
      "step": 810
    },
    {
      "loss": 1.1165,
      "grad_norm": 0.6040735840797424,
      "learning_rate": 4.98046875e-06,
      "entropy": 1.1430341199040412,
      "num_tokens": 4961646.0,
      "mean_token_accuracy": 0.7525988414883613,
      "epoch": 1.0353535353535352,
      "step": 820
    },
    {
      "loss": 1.0851,
      "grad_norm": 0.6277610063552856,
      "learning_rate": 4.915364583333333e-06,
      "entropy": 1.1245349109172822,
      "num_tokens": 5022365.0,
      "mean_token_accuracy": 0.7577921718358993,
      "epoch": 1.047979797979798,
      "step": 830
    },
    {
      "loss": 1.0813,
      "grad_norm": 0.6260582804679871,
      "learning_rate": 4.850260416666667e-06,
      "entropy": 1.1204675793647767,
      "num_tokens": 5081972.0,
      "mean_token_accuracy": 0.7580071151256561,
      "epoch": 1.0606060606060606,
      "step": 840
    },
    {
      "loss": 1.0922,
      "grad_norm": 0.6023226976394653,
      "learning_rate": 4.785156250000001e-06,
      "entropy": 1.1222782507538795,
      "num_tokens": 5142184.0,
      "mean_token_accuracy": 0.7566258609294891,
      "epoch": 1.0732323232323233,
      "step": 850
    },
    {
      "loss": 1.0994,
      "grad_norm": 0.6206791996955872,
      "learning_rate": 4.7200520833333336e-06,
      "entropy": 1.1227335944771766,
      "num_tokens": 5203020.0,
      "mean_token_accuracy": 0.7540625646710396,
      "epoch": 1.0858585858585859,
      "step": 860
    },
    {
      "loss": 1.0958,
      "grad_norm": 0.6301055550575256,
      "learning_rate": 4.654947916666667e-06,
      "entropy": 1.1352888554334641,
      "num_tokens": 5263291.0,
      "mean_token_accuracy": 0.7562039017677307,
      "epoch": 1.0984848484848484,
      "step": 870
    },
    {
      "loss": 1.0793,
      "grad_norm": 0.6210020780563354,
      "learning_rate": 4.58984375e-06,
      "entropy": 1.1120088309049607,
      "num_tokens": 5323972.0,
      "mean_token_accuracy": 0.7590557768940925,
      "epoch": 1.1111111111111112,
      "step": 880
    },
    {
      "loss": 1.0717,
      "grad_norm": 0.6332690715789795,
      "learning_rate": 4.524739583333334e-06,
      "entropy": 1.0996666207909584,
      "num_tokens": 5383911.0,
      "mean_token_accuracy": 0.7615471586585045,
      "epoch": 1.1237373737373737,
      "step": 890
    },
    {
      "loss": 1.1027,
      "grad_norm": 0.6505516767501831,
      "learning_rate": 4.459635416666668e-06,
      "entropy": 1.127107810974121,
      "num_tokens": 5445417.0,
      "mean_token_accuracy": 0.7562421515583992,
      "epoch": 1.1363636363636362,
      "step": 900
    },
    {
      "loss": 1.0879,
      "grad_norm": 0.6406158804893494,
      "learning_rate": 4.3945312500000005e-06,
      "entropy": 1.129740473628044,
      "num_tokens": 5505455.0,
      "mean_token_accuracy": 0.7587148532271385,
      "epoch": 1.148989898989899,
      "step": 910
    },
    {
      "loss": 1.0752,
      "grad_norm": 0.6297397613525391,
      "learning_rate": 4.329427083333333e-06,
      "entropy": 1.1167259424924851,
      "num_tokens": 5565311.0,
      "mean_token_accuracy": 0.7604142814874649,
      "epoch": 1.1616161616161615,
      "step": 920
    },
    {
      "loss": 1.0686,
      "grad_norm": 0.6490073204040527,
      "learning_rate": 4.264322916666667e-06,
      "entropy": 1.1037891641259194,
      "num_tokens": 5625358.0,
      "mean_token_accuracy": 0.7610052570700645,
      "epoch": 1.1742424242424243,
      "step": 930
    },
    {
      "loss": 1.0868,
      "grad_norm": 0.6366387009620667,
      "learning_rate": 4.19921875e-06,
      "entropy": 1.1061881184577942,
      "num_tokens": 5686421.0,
      "mean_token_accuracy": 0.7574937298893929,
      "epoch": 1.1868686868686869,
      "step": 940
    },
    {
      "loss": 1.0694,
      "grad_norm": 0.6556055545806885,
      "learning_rate": 4.134114583333334e-06,
      "entropy": 1.1124324068427085,
      "num_tokens": 5745891.0,
      "mean_token_accuracy": 0.7602224007248879,
      "epoch": 1.1994949494949494,
      "step": 950
    },
    {
      "loss": 1.081,
      "grad_norm": 0.6404849886894226,
      "learning_rate": 4.0690104166666675e-06,
      "entropy": 1.1175200879573821,
      "num_tokens": 5806078.0,
      "mean_token_accuracy": 0.7568994402885437,
      "epoch": 1.2121212121212122,
      "step": 960
    },
    {
      "loss": 1.0791,
      "grad_norm": 0.6227584481239319,
      "learning_rate": 4.00390625e-06,
      "entropy": 1.1186978340148925,
      "num_tokens": 5866369.0,
      "mean_token_accuracy": 0.759756401181221,
      "epoch": 1.2247474747474747,
      "step": 970
    },
    {
      "loss": 1.0937,
      "grad_norm": 0.6616361141204834,
      "learning_rate": 3.938802083333333e-06,
      "entropy": 1.122128139436245,
      "num_tokens": 5926217.0,
      "mean_token_accuracy": 0.7582718566060066,
      "epoch": 1.2373737373737375,
      "step": 980
    },
    {
      "loss": 1.0978,
      "grad_norm": 0.6384168267250061,
      "learning_rate": 3.873697916666667e-06,
      "entropy": 1.122861033678055,
      "num_tokens": 5987666.0,
      "mean_token_accuracy": 0.7549964562058449,
      "epoch": 1.25,
      "step": 990
    },
    {
      "loss": 1.0952,
      "grad_norm": 0.6038117408752441,
      "learning_rate": 3.8085937500000002e-06,
      "entropy": 1.1277505576610565,
      "num_tokens": 6048708.0,
      "mean_token_accuracy": 0.755272176861763,
      "epoch": 1.2626262626262625,
      "step": 1000
    },
    {
      "loss": 1.078,
      "grad_norm": 0.6418159604072571,
      "learning_rate": 3.7434895833333336e-06,
      "entropy": 1.1120157346129418,
      "num_tokens": 6109652.0,
      "mean_token_accuracy": 0.7594122514128685,
      "epoch": 1.2752525252525253,
      "step": 1010
    },
    {
      "loss": 1.0688,
      "grad_norm": 0.6218425035476685,
      "learning_rate": 3.6783854166666673e-06,
      "entropy": 1.101425115764141,
      "num_tokens": 6169125.0,
      "mean_token_accuracy": 0.7604865297675133,
      "epoch": 1.2878787878787878,
      "step": 1020
    },
    {
      "loss": 1.0581,
      "grad_norm": 0.6429149508476257,
      "learning_rate": 3.61328125e-06,
      "entropy": 1.1007713869214057,
      "num_tokens": 6230303.0,
      "mean_token_accuracy": 0.7621071562170982,
      "epoch": 1.3005050505050506,
      "step": 1030
    },
    {
      "loss": 1.0715,
      "grad_norm": 0.6489748358726501,
      "learning_rate": 3.5481770833333335e-06,
      "entropy": 1.1094096556305886,
      "num_tokens": 6291396.0,
      "mean_token_accuracy": 0.7599423810839653,
      "epoch": 1.3131313131313131,
      "step": 1040
    },
    {
      "loss": 1.0584,
      "grad_norm": 0.6485461592674255,
      "learning_rate": 3.483072916666667e-06,
      "entropy": 1.0827289715409278,
      "num_tokens": 6351579.0,
      "mean_token_accuracy": 0.7630694910883904,
      "epoch": 1.3257575757575757,
      "step": 1050
    },
    {
      "loss": 1.0764,
      "grad_norm": 0.6261104941368103,
      "learning_rate": 3.41796875e-06,
      "entropy": 1.114325873553753,
      "num_tokens": 6411662.0,
      "mean_token_accuracy": 0.7585488513112069,
      "epoch": 1.3383838383838385,
      "step": 1060
    },
    {
      "loss": 1.0902,
      "grad_norm": 0.6522034406661987,
      "learning_rate": 3.3528645833333334e-06,
      "entropy": 1.1271554425358772,
      "num_tokens": 6473505.0,
      "mean_token_accuracy": 0.7562535598874092,
      "epoch": 1.351010101010101,
      "step": 1070
    },
    {
      "loss": 1.065,
      "grad_norm": 0.6176674962043762,
      "learning_rate": 3.287760416666667e-06,
      "entropy": 1.1013643085956573,
      "num_tokens": 6533580.0,
      "mean_token_accuracy": 0.763075165450573,
      "epoch": 1.3636363636363638,
      "step": 1080
    },
    {
      "loss": 1.0596,
      "grad_norm": 0.6540253758430481,
      "learning_rate": 3.2226562500000004e-06,
      "entropy": 1.098090337216854,
      "num_tokens": 6593481.0,
      "mean_token_accuracy": 0.7616770043969154,
      "epoch": 1.3762626262626263,
      "step": 1090
    },
    {
      "loss": 1.0861,
      "grad_norm": 0.6754550933837891,
      "learning_rate": 3.1575520833333333e-06,
      "entropy": 1.1176372200250626,
      "num_tokens": 6653967.0,
      "mean_token_accuracy": 0.7573029339313507,
      "epoch": 1.3888888888888888,
      "step": 1100
    },
    {
      "loss": 1.0573,
      "grad_norm": 0.6022531986236572,
      "learning_rate": 3.092447916666667e-06,
      "entropy": 1.1040414482355119,
      "num_tokens": 6714685.0,
      "mean_token_accuracy": 0.7612267225980759,
      "epoch": 1.4015151515151514,
      "step": 1110
    },
    {
      "loss": 1.0637,
      "grad_norm": 0.6621010303497314,
      "learning_rate": 3.0273437500000003e-06,
      "entropy": 1.0926991075277328,
      "num_tokens": 6774659.0,
      "mean_token_accuracy": 0.7612977519631385,
      "epoch": 1.4141414141414141,
      "step": 1120
    },
    {
      "loss": 1.0701,
      "grad_norm": 0.62503981590271,
      "learning_rate": 2.962239583333333e-06,
      "entropy": 1.1095534324645997,
      "num_tokens": 6834579.0,
      "mean_token_accuracy": 0.7618053883314133,
      "epoch": 1.4267676767676767,
      "step": 1130
    },
    {
      "loss": 1.0747,
      "grad_norm": 0.6527109742164612,
      "learning_rate": 2.897135416666667e-06,
      "entropy": 1.117809349298477,
      "num_tokens": 6894074.0,
      "mean_token_accuracy": 0.759482853114605,
      "epoch": 1.4393939393939394,
      "step": 1140
    },
    {
      "loss": 1.0607,
      "grad_norm": 0.6720954775810242,
      "learning_rate": 2.8320312500000002e-06,
      "entropy": 1.1005077749490737,
      "num_tokens": 6953870.0,
      "mean_token_accuracy": 0.7621246844530105,
      "epoch": 1.452020202020202,
      "step": 1150
    },
    {
      "loss": 1.0884,
      "grad_norm": 0.658524215221405,
      "learning_rate": 2.7669270833333335e-06,
      "entropy": 1.1236482918262483,
      "num_tokens": 7014553.0,
      "mean_token_accuracy": 0.7560836613178253,
      "epoch": 1.4646464646464645,
      "step": 1160
    },
    {
      "loss": 1.0659,
      "grad_norm": 0.6261802911758423,
      "learning_rate": 2.7018229166666673e-06,
      "entropy": 1.1116504594683647,
      "num_tokens": 7076291.0,
      "mean_token_accuracy": 0.7597616642713547,
      "epoch": 1.4772727272727273,
      "step": 1170
    },
    {
      "loss": 1.0524,
      "grad_norm": 0.6310375332832336,
      "learning_rate": 2.63671875e-06,
      "entropy": 1.073892480134964,
      "num_tokens": 7137305.0,
      "mean_token_accuracy": 0.7628733053803444,
      "epoch": 1.4898989898989898,
      "step": 1180
    },
    {
      "loss": 1.0679,
      "grad_norm": 0.638482391834259,
      "learning_rate": 2.5716145833333334e-06,
      "entropy": 1.0975843235850333,
      "num_tokens": 7198239.0,
      "mean_token_accuracy": 0.7603248566389084,
      "epoch": 1.5025252525252526,
      "step": 1190
    },
    {
      "loss": 1.0666,
      "grad_norm": 0.640065610408783,
      "learning_rate": 2.506510416666667e-06,
      "entropy": 1.0986508697271347,
      "num_tokens": 7257847.0,
      "mean_token_accuracy": 0.7622530281543731,
      "epoch": 1.5151515151515151,
      "step": 1200
    },
    {
      "loss": 1.0587,
      "grad_norm": 0.6437165141105652,
      "learning_rate": 2.44140625e-06,
      "entropy": 1.0971406906843186,
      "num_tokens": 7317615.0,
      "mean_token_accuracy": 0.7623877748847008,
      "epoch": 1.5277777777777777,
      "step": 1210
    },
    {
      "loss": 1.0569,
      "grad_norm": 0.6590547561645508,
      "learning_rate": 2.3763020833333338e-06,
      "entropy": 1.1032136514782906,
      "num_tokens": 7377946.0,
      "mean_token_accuracy": 0.7616146191954613,
      "epoch": 1.5404040404040404,
      "step": 1220
    },
    {
      "loss": 1.0616,
      "grad_norm": 0.6317723989486694,
      "learning_rate": 2.3111979166666667e-06,
      "entropy": 1.0922824308276176,
      "num_tokens": 7438666.0,
      "mean_token_accuracy": 0.7611089378595353,
      "epoch": 1.553030303030303,
      "step": 1230
    },
    {
      "loss": 1.0725,
      "grad_norm": 0.66637122631073,
      "learning_rate": 2.2460937500000004e-06,
      "entropy": 1.1092566132545472,
      "num_tokens": 7499747.0,
      "mean_token_accuracy": 0.7594954133033752,
      "epoch": 1.5656565656565657,
      "step": 1240
    },
    {
      "loss": 1.074,
      "grad_norm": 0.6520881652832031,
      "learning_rate": 2.1809895833333337e-06,
      "entropy": 1.111878876388073,
      "num_tokens": 7561004.0,
      "mean_token_accuracy": 0.7558068126440048,
      "epoch": 1.5782828282828283,
      "step": 1250
    },
    {
      "loss": 1.0844,
      "grad_norm": 0.6495437622070312,
      "learning_rate": 2.1158854166666666e-06,
      "entropy": 1.1105972841382026,
      "num_tokens": 7622115.0,
      "mean_token_accuracy": 0.7563070356845856,
      "epoch": 1.5909090909090908,
      "step": 1260
    },
    {
      "loss": 1.0649,
      "grad_norm": 0.6420316696166992,
      "learning_rate": 2.0507812500000003e-06,
      "entropy": 1.0932338371872903,
      "num_tokens": 7682210.0,
      "mean_token_accuracy": 0.7622412323951722,
      "epoch": 1.6035353535353534,
      "step": 1270
    },
    {
      "loss": 1.0427,
      "grad_norm": 0.6192623972892761,
      "learning_rate": 1.9856770833333336e-06,
      "entropy": 1.0919055327773095,
      "num_tokens": 7742745.0,
      "mean_token_accuracy": 0.7657591253519058,
      "epoch": 1.6161616161616161,
      "step": 1280
    },
    {
      "loss": 1.0701,
      "grad_norm": 0.6355161666870117,
      "learning_rate": 1.920572916666667e-06,
      "entropy": 1.1026942864060403,
      "num_tokens": 7802902.0,
      "mean_token_accuracy": 0.7609635755419731,
      "epoch": 1.628787878787879,
      "step": 1290
    },
    {
      "loss": 1.0789,
      "grad_norm": 0.6254522800445557,
      "learning_rate": 1.8554687500000002e-06,
      "entropy": 1.1140723824501038,
      "num_tokens": 7863576.0,
      "mean_token_accuracy": 0.7592580512166023,
      "epoch": 1.6414141414141414,
      "step": 1300
    },
    {
      "loss": 1.0714,
      "grad_norm": 0.633172333240509,
      "learning_rate": 1.7903645833333335e-06,
      "entropy": 1.108394268155098,
      "num_tokens": 7925518.0,
      "mean_token_accuracy": 0.7598690986633301,
      "epoch": 1.654040404040404,
      "step": 1310
    },
    {
      "loss": 1.0701,
      "grad_norm": 0.6279735565185547,
      "learning_rate": 1.7252604166666668e-06,
      "entropy": 1.1097407966852189,
      "num_tokens": 7987388.0,
      "mean_token_accuracy": 0.7611567705869675,
      "epoch": 1.6666666666666665,
      "step": 1320
    },
    {
      "loss": 1.0786,
      "grad_norm": 0.6425778269767761,
      "learning_rate": 1.6601562500000001e-06,
      "entropy": 1.1071213275194167,
      "num_tokens": 8048853.0,
      "mean_token_accuracy": 0.7576610520482063,
      "epoch": 1.6792929292929293,
      "step": 1330
    },
    {
      "loss": 1.0604,
      "grad_norm": 0.666192889213562,
      "learning_rate": 1.5950520833333336e-06,
      "entropy": 1.0931925728917122,
      "num_tokens": 8108967.0,
      "mean_token_accuracy": 0.7616572439670563,
      "epoch": 1.691919191919192,
      "step": 1340
    },
    {
      "loss": 1.0769,
      "grad_norm": 0.6348255276679993,
      "learning_rate": 1.5299479166666667e-06,
      "entropy": 1.0973364993929864,
      "num_tokens": 8169700.0,
      "mean_token_accuracy": 0.7596119627356529,
      "epoch": 1.7045454545454546,
      "step": 1350
    },
    {
      "loss": 1.0731,
      "grad_norm": 0.6510699391365051,
      "learning_rate": 1.46484375e-06,
      "entropy": 1.1137071400880814,
      "num_tokens": 8229676.0,
      "mean_token_accuracy": 0.7593250289559365,
      "epoch": 1.7171717171717171,
      "step": 1360
    },
    {
      "loss": 1.069,
      "grad_norm": 0.6622318625450134,
      "learning_rate": 1.3997395833333335e-06,
      "entropy": 1.1052428260445595,
      "num_tokens": 8289396.0,
      "mean_token_accuracy": 0.7627501472830772,
      "epoch": 1.7297979797979797,
      "step": 1370
    },
    {
      "loss": 1.0506,
      "grad_norm": 0.6430277824401855,
      "learning_rate": 1.3346354166666666e-06,
      "entropy": 1.0989198789000512,
      "num_tokens": 8351152.0,
      "mean_token_accuracy": 0.7634323209524154,
      "epoch": 1.7424242424242424,
      "step": 1380
    },
    {
      "loss": 1.0505,
      "grad_norm": 0.639707088470459,
      "learning_rate": 1.2695312500000002e-06,
      "entropy": 1.0913211867213248,
      "num_tokens": 8411357.0,
      "mean_token_accuracy": 0.763850274682045,
      "epoch": 1.7550505050505052,
      "step": 1390
    },
    {
      "loss": 1.0756,
      "grad_norm": 0.680479109287262,
      "learning_rate": 1.2044270833333335e-06,
      "entropy": 1.1044820442795753,
      "num_tokens": 8471975.0,
      "mean_token_accuracy": 0.7598197475075722,
      "epoch": 1.7676767676767677,
      "step": 1400
    },
    {
      "loss": 1.048,
      "grad_norm": 0.651622474193573,
      "learning_rate": 1.1393229166666668e-06,
      "entropy": 1.0821994885802269,
      "num_tokens": 8532480.0,
      "mean_token_accuracy": 0.7638402819633484,
      "epoch": 1.7803030303030303,
      "step": 1410
    },
    {
      "loss": 1.0545,
      "grad_norm": 0.6294305920600891,
      "learning_rate": 1.07421875e-06,
      "entropy": 1.0933044001460075,
      "num_tokens": 8593538.0,
      "mean_token_accuracy": 0.7633207753300667,
      "epoch": 1.7929292929292928,
      "step": 1420
    },
    {
      "loss": 1.065,
      "grad_norm": 0.6396600008010864,
      "learning_rate": 1.0091145833333334e-06,
      "entropy": 1.1002878457307816,
      "num_tokens": 8654446.0,
      "mean_token_accuracy": 0.7610213488340378,
      "epoch": 1.8055555555555556,
      "step": 1430
    },
    {
      "loss": 1.079,
      "grad_norm": 0.6585692167282104,
      "learning_rate": 9.440104166666668e-07,
      "entropy": 1.1098253890872,
      "num_tokens": 8715305.0,
      "mean_token_accuracy": 0.7590781077742577,
      "epoch": 1.8181818181818183,
      "step": 1440
    },
    {
      "loss": 1.0555,
      "grad_norm": 0.6637106537818909,
      "learning_rate": 8.789062500000001e-07,
      "entropy": 1.0894212126731873,
      "num_tokens": 8775351.0,
      "mean_token_accuracy": 0.7621971383690834,
      "epoch": 1.8308080808080809,
      "step": 1450
    },
    {
      "loss": 1.0464,
      "grad_norm": 0.6491685509681702,
      "learning_rate": 8.138020833333334e-07,
      "entropy": 1.0821923539042473,
      "num_tokens": 8836131.0,
      "mean_token_accuracy": 0.7639922067523003,
      "epoch": 1.8434343434343434,
      "step": 1460
    },
    {
      "loss": 1.0682,
      "grad_norm": 0.6781795024871826,
      "learning_rate": 7.486979166666668e-07,
      "entropy": 1.1058385655283929,
      "num_tokens": 8896334.0,
      "mean_token_accuracy": 0.7595004603266716,
      "epoch": 1.856060606060606,
      "step": 1470
    },
    {
      "loss": 1.0625,
      "grad_norm": 0.652746319770813,
      "learning_rate": 6.835937500000001e-07,
      "entropy": 1.0934822604060173,
      "num_tokens": 8956948.0,
      "mean_token_accuracy": 0.7614723727107048,
      "epoch": 1.8686868686868687,
      "step": 1480
    },
    {
      "loss": 1.0677,
      "grad_norm": 0.6350075006484985,
      "learning_rate": 6.184895833333334e-07,
      "entropy": 1.0955146595835685,
      "num_tokens": 9017330.0,
      "mean_token_accuracy": 0.75977371186018,
      "epoch": 1.8813131313131313,
      "step": 1490
    },
    {
      "loss": 1.0778,
      "grad_norm": 0.6651970744132996,
      "learning_rate": 5.533854166666667e-07,
      "entropy": 1.1074895232915878,
      "num_tokens": 9077561.0,
      "mean_token_accuracy": 0.7592803448438644,
      "epoch": 1.893939393939394,
      "step": 1500
    },
    {
      "loss": 1.0517,
      "grad_norm": 0.6216638684272766,
      "learning_rate": 4.8828125e-07,
      "entropy": 1.088778705894947,
      "num_tokens": 9137424.0,
      "mean_token_accuracy": 0.7628024965524673,
      "epoch": 1.9065656565656566,
      "step": 1510
    },
    {
      "loss": 1.0657,
      "grad_norm": 0.6801443099975586,
      "learning_rate": 4.2317708333333337e-07,
      "entropy": 1.0963940545916557,
      "num_tokens": 9198465.0,
      "mean_token_accuracy": 0.7611119478940964,
      "epoch": 1.9191919191919191,
      "step": 1520
    },
    {
      "loss": 1.0657,
      "grad_norm": 0.6482690572738647,
      "learning_rate": 3.5807291666666667e-07,
      "entropy": 1.107513566315174,
      "num_tokens": 9258486.0,
      "mean_token_accuracy": 0.7620691254734993,
      "epoch": 1.9318181818181817,
      "step": 1530
    },
    {
      "loss": 1.0758,
      "grad_norm": 0.6314805746078491,
      "learning_rate": 2.9296875000000003e-07,
      "entropy": 1.1056584566831589,
      "num_tokens": 9319619.0,
      "mean_token_accuracy": 0.7584919854998589,
      "epoch": 1.9444444444444444,
      "step": 1540
    },
    {
      "loss": 1.0745,
      "grad_norm": 0.6383644938468933,
      "learning_rate": 2.2786458333333333e-07,
      "entropy": 1.1117310538887977,
      "num_tokens": 9380350.0,
      "mean_token_accuracy": 0.7591810420155525,
      "epoch": 1.9570707070707072,
      "step": 1550
    },
    {
      "loss": 1.0557,
      "grad_norm": 0.6331989169120789,
      "learning_rate": 1.627604166666667e-07,
      "entropy": 1.0970366701483727,
      "num_tokens": 9441627.0,
      "mean_token_accuracy": 0.7604442983865738,
      "epoch": 1.9696969696969697,
      "step": 1560
    },
    {
      "loss": 1.0546,
      "grad_norm": 0.6618102192878723,
      "learning_rate": 9.765625e-08,
      "entropy": 1.0917240902781487,
      "num_tokens": 9501728.0,
      "mean_token_accuracy": 0.7638352930545806,
      "epoch": 1.9823232323232323,
      "step": 1570
    },
    {
      "loss": 1.0615,
      "grad_norm": 0.6413847804069519,
      "learning_rate": 3.2552083333333335e-08,
      "entropy": 1.096452857553959,
      "num_tokens": 9562238.0,
      "mean_token_accuracy": 0.7619210347533226,
      "epoch": 1.9949494949494948,
      "step": 1580
    },
    {
      "train_runtime": 50353.3546,
      "train_samples_per_second": 1.006,
      "train_steps_per_second": 0.031,
      "total_flos": 5.4295385739381965e+17,
      "train_loss": 1.1876104943680041,
      "entropy": 1.1173381134867668,
      "num_tokens": 9585534.0,
      "mean_token_accuracy": 0.7577789686620235,
      "epoch": 2.0,
      "step": 1584
    }
  ],
  "best_metric": null,
  "best_model_checkpoint": null,
  "global_step": 1584,
  "num_train_epochs": 2
}