{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9999235532451648,
  "eval_steps": 500,
  "global_step": 1635,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006115740386820579,
      "grad_norm": 0.12052220602859784,
      "learning_rate": 6.0975609756097564e-06,
      "loss": 1.6245,
      "step": 1
    },
    {
      "epoch": 0.00305787019341029,
      "grad_norm": 0.11718955528750491,
      "learning_rate": 3.048780487804878e-05,
      "loss": 1.5875,
      "step": 5
    },
    {
      "epoch": 0.00611574038682058,
      "grad_norm": 0.07463826304526239,
      "learning_rate": 6.097560975609756e-05,
      "loss": 1.5734,
      "step": 10
    },
    {
      "epoch": 0.009173610580230869,
      "grad_norm": 0.07065399016948878,
      "learning_rate": 9.146341463414634e-05,
      "loss": 1.4926,
      "step": 15
    },
    {
      "epoch": 0.01223148077364116,
      "grad_norm": 0.06072873212977001,
      "learning_rate": 0.00012195121951219512,
      "loss": 1.458,
      "step": 20
    },
    {
      "epoch": 0.01528935096705145,
      "grad_norm": 0.0562127370758177,
      "learning_rate": 0.0001524390243902439,
      "loss": 1.4146,
      "step": 25
    },
    {
      "epoch": 0.018347221160461738,
      "grad_norm": 0.0369940258125185,
      "learning_rate": 0.00018292682926829268,
      "loss": 1.3727,
      "step": 30
    },
    {
      "epoch": 0.021405091353872027,
      "grad_norm": 0.03030856084221372,
      "learning_rate": 0.00021341463414634146,
      "loss": 1.3452,
      "step": 35
    },
    {
      "epoch": 0.02446296154728232,
      "grad_norm": 0.029052665253947514,
      "learning_rate": 0.00024390243902439024,
      "loss": 1.3062,
      "step": 40
    },
    {
      "epoch": 0.027520831740692607,
      "grad_norm": 0.027169249076678257,
      "learning_rate": 0.00027439024390243905,
      "loss": 1.3193,
      "step": 45
    },
    {
      "epoch": 0.0305787019341029,
      "grad_norm": 0.026308314290126287,
      "learning_rate": 0.0003048780487804878,
      "loss": 1.3059,
      "step": 50
    },
    {
      "epoch": 0.033636572127513184,
      "grad_norm": 0.02558312476230526,
      "learning_rate": 0.0003353658536585366,
      "loss": 1.2978,
      "step": 55
    },
    {
      "epoch": 0.036694442320923476,
      "grad_norm": 0.02366166156410773,
      "learning_rate": 0.00036585365853658537,
      "loss": 1.2835,
      "step": 60
    },
    {
      "epoch": 0.03975231251433377,
      "grad_norm": 0.023696910212749084,
      "learning_rate": 0.0003963414634146342,
      "loss": 1.2801,
      "step": 65
    },
    {
      "epoch": 0.04281018270774405,
      "grad_norm": 0.023961941292451862,
      "learning_rate": 0.0004268292682926829,
      "loss": 1.2862,
      "step": 70
    },
    {
      "epoch": 0.045868052901154345,
      "grad_norm": 0.026300989505884765,
      "learning_rate": 0.00045731707317073173,
      "loss": 1.2738,
      "step": 75
    },
    {
      "epoch": 0.04892592309456464,
      "grad_norm": 0.024085664746400153,
      "learning_rate": 0.0004878048780487805,
      "loss": 1.267,
      "step": 80
    },
    {
      "epoch": 0.05198379328797492,
      "grad_norm": 0.02400704254026435,
      "learning_rate": 0.0005182926829268293,
      "loss": 1.2687,
      "step": 85
    },
    {
      "epoch": 0.055041663481385214,
      "grad_norm": 0.028737409033153787,
      "learning_rate": 0.0005487804878048781,
      "loss": 1.248,
      "step": 90
    },
    {
      "epoch": 0.058099533674795506,
      "grad_norm": 0.033246208383736264,
      "learning_rate": 0.0005792682926829268,
      "loss": 1.2693,
      "step": 95
    },
    {
      "epoch": 0.0611574038682058,
      "grad_norm": 0.02684140817882857,
      "learning_rate": 0.0006097560975609756,
      "loss": 1.2562,
      "step": 100
    },
    {
      "epoch": 0.06421527406161609,
      "grad_norm": 0.026557034480265206,
      "learning_rate": 0.0006402439024390244,
      "loss": 1.2286,
      "step": 105
    },
    {
      "epoch": 0.06727314425502637,
      "grad_norm": 0.025820861749653763,
      "learning_rate": 0.0006707317073170732,
      "loss": 1.2678,
      "step": 110
    },
    {
      "epoch": 0.07033101444843666,
      "grad_norm": 0.029846828731098105,
      "learning_rate": 0.0007012195121951219,
      "loss": 1.2335,
      "step": 115
    },
    {
      "epoch": 0.07338888464184695,
      "grad_norm": 0.03508112839172254,
      "learning_rate": 0.0007317073170731707,
      "loss": 1.2663,
      "step": 120
    },
    {
      "epoch": 0.07644675483525724,
      "grad_norm": 0.0352184112282257,
      "learning_rate": 0.0007621951219512195,
      "loss": 1.2399,
      "step": 125
    },
    {
      "epoch": 0.07950462502866754,
      "grad_norm": 0.03322649965458742,
      "learning_rate": 0.0007926829268292683,
      "loss": 1.2503,
      "step": 130
    },
    {
      "epoch": 0.08256249522207783,
      "grad_norm": 0.028514272146253784,
      "learning_rate": 0.000823170731707317,
      "loss": 1.2468,
      "step": 135
    },
    {
      "epoch": 0.0856203654154881,
      "grad_norm": 0.028671295675629906,
      "learning_rate": 0.0008536585365853659,
      "loss": 1.23,
      "step": 140
    },
    {
      "epoch": 0.0886782356088984,
      "grad_norm": 0.030269321761170552,
      "learning_rate": 0.0008841463414634147,
      "loss": 1.2296,
      "step": 145
    },
    {
      "epoch": 0.09173610580230869,
      "grad_norm": 0.02846427788729512,
      "learning_rate": 0.0009146341463414635,
      "loss": 1.2241,
      "step": 150
    },
    {
      "epoch": 0.09479397599571898,
      "grad_norm": 0.03975120343371244,
      "learning_rate": 0.0009451219512195122,
      "loss": 1.244,
      "step": 155
    },
    {
      "epoch": 0.09785184618912927,
      "grad_norm": 0.03216136084206205,
      "learning_rate": 0.000975609756097561,
      "loss": 1.2457,
      "step": 160
    },
    {
      "epoch": 0.10090971638253957,
      "grad_norm": 0.03152661590457252,
      "learning_rate": 0.000999998859712815,
      "loss": 1.2326,
      "step": 165
    },
    {
      "epoch": 0.10396758657594984,
      "grad_norm": 0.031922913335073945,
      "learning_rate": 0.0009999589502074485,
      "loss": 1.249,
      "step": 170
    },
    {
      "epoch": 0.10702545676936014,
      "grad_norm": 0.04658476708749259,
      "learning_rate": 0.0009998620315437507,
      "loss": 1.2447,
      "step": 175
    },
    {
      "epoch": 0.11008332696277043,
      "grad_norm": 0.03617623229838695,
      "learning_rate": 0.000999708114773132,
      "loss": 1.2419,
      "step": 180
    },
    {
      "epoch": 0.11314119715618072,
      "grad_norm": 0.03418014417549059,
      "learning_rate": 0.0009994972174463639,
      "loss": 1.2197,
      "step": 185
    },
    {
      "epoch": 0.11619906734959101,
      "grad_norm": 0.02577313047796619,
      "learning_rate": 0.0009992293636115793,
      "loss": 1.2334,
      "step": 190
    },
    {
      "epoch": 0.1192569375430013,
      "grad_norm": 0.026546715317612456,
      "learning_rate": 0.0009989045838115292,
      "loss": 1.2381,
      "step": 195
    },
    {
      "epoch": 0.1223148077364116,
      "grad_norm": 0.0326169458915842,
      "learning_rate": 0.0009985229150800998,
      "loss": 1.2143,
      "step": 200
    },
    {
      "epoch": 0.12537267792982187,
      "grad_norm": 0.03223237682583807,
      "learning_rate": 0.0009980844009380904,
      "loss": 1.231,
      "step": 205
    },
    {
      "epoch": 0.12843054812323218,
      "grad_norm": 0.029643352282643223,
      "learning_rate": 0.0009975890913882512,
      "loss": 1.2469,
      "step": 210
    },
    {
      "epoch": 0.13148841831664246,
      "grad_norm": 0.027522481255624117,
      "learning_rate": 0.0009970370429095794,
      "loss": 1.2062,
      "step": 215
    },
    {
      "epoch": 0.13454628851005274,
      "grad_norm": 0.033075124541469436,
      "learning_rate": 0.0009964283184508817,
      "loss": 1.224,
      "step": 220
    },
    {
      "epoch": 0.13760415870346304,
      "grad_norm": 0.027377314114451212,
      "learning_rate": 0.0009957629874235948,
      "loss": 1.2086,
      "step": 225
    },
    {
      "epoch": 0.14066202889687332,
      "grad_norm": 0.03090829597386635,
      "learning_rate": 0.000995041125693871,
      "loss": 1.217,
      "step": 230
    },
    {
      "epoch": 0.14371989909028363,
      "grad_norm": 0.035975979448955,
      "learning_rate": 0.0009942628155739275,
      "loss": 1.2133,
      "step": 235
    },
    {
      "epoch": 0.1467777692836939,
      "grad_norm": 0.029218388374324843,
      "learning_rate": 0.00099342814581266,
      "loss": 1.2056,
      "step": 240
    },
    {
      "epoch": 0.1498356394771042,
      "grad_norm": 0.028688837478414952,
      "learning_rate": 0.000992537211585524,
      "loss": 1.2145,
      "step": 245
    },
    {
      "epoch": 0.1528935096705145,
      "grad_norm": 0.0302429094788238,
      "learning_rate": 0.0009915901144836802,
      "loss": 1.2035,
      "step": 250
    },
    {
      "epoch": 0.15595137986392477,
      "grad_norm": 0.024901652208543252,
      "learning_rate": 0.000990586962502413,
      "loss": 1.2202,
      "step": 255
    },
    {
      "epoch": 0.15900925005733507,
      "grad_norm": 0.027892260766706888,
      "learning_rate": 0.0009895278700288131,
      "loss": 1.1807,
      "step": 260
    },
    {
      "epoch": 0.16206712025074535,
      "grad_norm": 0.03226968566991327,
      "learning_rate": 0.000988412957828737,
      "loss": 1.2072,
      "step": 265
    },
    {
      "epoch": 0.16512499044415566,
      "grad_norm": 0.03872574944189164,
      "learning_rate": 0.000987242353033034,
      "loss": 1.2037,
      "step": 270
    },
    {
      "epoch": 0.16818286063756593,
      "grad_norm": 0.033428446400930414,
      "learning_rate": 0.000986016189123051,
      "loss": 1.1912,
      "step": 275
    },
    {
      "epoch": 0.1712407308309762,
      "grad_norm": 0.0385131025139653,
      "learning_rate": 0.0009847346059154124,
      "loss": 1.2141,
      "step": 280
    },
    {
      "epoch": 0.17429860102438652,
      "grad_norm": 0.026232059261105282,
      "learning_rate": 0.0009833977495460754,
      "loss": 1.2019,
      "step": 285
    },
    {
      "epoch": 0.1773564712177968,
      "grad_norm": 0.024160196147301412,
      "learning_rate": 0.000982005772453668,
      "loss": 1.1787,
      "step": 290
    },
    {
      "epoch": 0.1804143414112071,
      "grad_norm": 0.022453529587095535,
      "learning_rate": 0.0009805588333621066,
      "loss": 1.1845,
      "step": 295
    },
    {
      "epoch": 0.18347221160461738,
      "grad_norm": 0.02720482538531544,
      "learning_rate": 0.0009790570972624964,
      "loss": 1.1738,
      "step": 300
    },
    {
      "epoch": 0.18653008179802769,
      "grad_norm": 0.02771296154155037,
      "learning_rate": 0.000977500735394318,
      "loss": 1.203,
      "step": 305
    },
    {
      "epoch": 0.18958795199143796,
      "grad_norm": 0.029629116640802273,
      "learning_rate": 0.0009758899252259019,
      "loss": 1.1867,
      "step": 310
    },
    {
      "epoch": 0.19264582218484824,
      "grad_norm": 0.024073515796522824,
      "learning_rate": 0.0009742248504341918,
      "loss": 1.1892,
      "step": 315
    },
    {
      "epoch": 0.19570369237825855,
      "grad_norm": 0.026256282210288567,
      "learning_rate": 0.0009725057008838005,
      "loss": 1.1895,
      "step": 320
    },
    {
      "epoch": 0.19876156257166883,
      "grad_norm": 0.027127167143907085,
      "learning_rate": 0.0009707326726053596,
      "loss": 1.1903,
      "step": 325
    },
    {
      "epoch": 0.20181943276507913,
      "grad_norm": 0.024066276808509948,
      "learning_rate": 0.0009689059677731673,
      "loss": 1.1732,
      "step": 330
    },
    {
      "epoch": 0.2048773029584894,
      "grad_norm": 0.03467571344471047,
      "learning_rate": 0.0009670257946821346,
      "loss": 1.1817,
      "step": 335
    },
    {
      "epoch": 0.2079351731518997,
      "grad_norm": 0.029277519444581707,
      "learning_rate": 0.0009650923677240338,
      "loss": 1.1949,
      "step": 340
    },
    {
      "epoch": 0.21099304334531,
      "grad_norm": 0.058400563521677724,
      "learning_rate": 0.0009631059073630522,
      "loss": 1.2189,
      "step": 345
    },
    {
      "epoch": 0.21405091353872027,
      "grad_norm": 0.035079123932762336,
      "learning_rate": 0.0009610666401106527,
      "loss": 1.183,
      "step": 350
    },
    {
      "epoch": 0.21710878373213058,
      "grad_norm": 0.027974026832942114,
      "learning_rate": 0.0009589747984997454,
      "loss": 1.1889,
      "step": 355
    },
    {
      "epoch": 0.22016665392554086,
      "grad_norm": 0.02669021024572584,
      "learning_rate": 0.0009568306210581728,
      "loss": 1.1787,
      "step": 360
    },
    {
      "epoch": 0.22322452411895116,
      "grad_norm": 0.02179715758089009,
      "learning_rate": 0.00095463435228151,
      "loss": 1.2111,
      "step": 365
    },
    {
      "epoch": 0.22628239431236144,
      "grad_norm": 0.02384963533856956,
      "learning_rate": 0.0009523862426051868,
      "loss": 1.1784,
      "step": 370
    },
    {
      "epoch": 0.22934026450577172,
      "grad_norm": 0.028747252177852817,
      "learning_rate": 0.00095008654837593,
      "loss": 1.1883,
      "step": 375
    },
    {
      "epoch": 0.23239813469918202,
      "grad_norm": 0.040361089898442656,
      "learning_rate": 0.0009477355318225334,
      "loss": 1.1769,
      "step": 380
    },
    {
      "epoch": 0.2354560048925923,
      "grad_norm": 0.02974537276209321,
      "learning_rate": 0.000945333461025956,
      "loss": 1.1765,
      "step": 385
    },
    {
      "epoch": 0.2385138750860026,
      "grad_norm": 0.02326511823628993,
      "learning_rate": 0.0009428806098887542,
      "loss": 1.1613,
      "step": 390
    },
    {
      "epoch": 0.24157174527941289,
      "grad_norm": 0.02788935788617548,
      "learning_rate": 0.0009403772581038481,
      "loss": 1.1885,
      "step": 395
    },
    {
      "epoch": 0.2446296154728232,
      "grad_norm": 0.02733650935761564,
      "learning_rate": 0.0009378236911226298,
      "loss": 1.1413,
      "step": 400
    },
    {
      "epoch": 0.24768748566623347,
      "grad_norm": 0.026735407407419445,
      "learning_rate": 0.0009352202001224133,
      "loss": 1.1689,
      "step": 405
    },
    {
      "epoch": 0.25074535585964375,
      "grad_norm": 0.02496495083042904,
      "learning_rate": 0.000932567081973233,
      "loss": 1.1766,
      "step": 410
    },
    {
      "epoch": 0.25380322605305405,
      "grad_norm": 0.022860603493433784,
      "learning_rate": 0.0009298646392039917,
      "loss": 1.1601,
      "step": 415
    },
    {
      "epoch": 0.25686109624646436,
      "grad_norm": 0.023001099418093644,
      "learning_rate": 0.0009271131799679638,
      "loss": 1.17,
      "step": 420
    },
    {
      "epoch": 0.2599189664398746,
      "grad_norm": 0.027817090057780446,
      "learning_rate": 0.0009243130180076583,
      "loss": 1.1614,
      "step": 425
    },
    {
      "epoch": 0.2629768366332849,
      "grad_norm": 0.024779365625928928,
      "learning_rate": 0.000921464472619042,
      "loss": 1.1744,
      "step": 430
    },
    {
      "epoch": 0.2660347068266952,
      "grad_norm": 0.02415651195912707,
      "learning_rate": 0.0009185678686151322,
      "loss": 1.1579,
      "step": 435
    },
    {
      "epoch": 0.2690925770201055,
      "grad_norm": 0.022815366652922293,
      "learning_rate": 0.0009156235362889584,
      "loss": 1.1745,
      "step": 440
    },
    {
      "epoch": 0.2721504472135158,
      "grad_norm": 0.021130481291703748,
      "learning_rate": 0.0009126318113758999,
      "loss": 1.1607,
      "step": 445
    },
    {
      "epoch": 0.2752083174069261,
      "grad_norm": 0.026167022396722542,
      "learning_rate": 0.0009095930350154026,
      "loss": 1.1874,
      "step": 450
    },
    {
      "epoch": 0.2782661876003364,
      "grad_norm": 0.03886381769784487,
      "learning_rate": 0.0009065075537120796,
      "loss": 1.1896,
      "step": 455
    },
    {
      "epoch": 0.28132405779374664,
      "grad_norm": 0.03341109366532242,
      "learning_rate": 0.0009033757192962004,
      "loss": 1.1575,
      "step": 460
    },
    {
      "epoch": 0.28438192798715695,
      "grad_norm": 0.03306894493562745,
      "learning_rate": 0.0009001978888835723,
      "loss": 1.1452,
      "step": 465
    },
    {
      "epoch": 0.28743979818056725,
      "grad_norm": 0.02506155876387002,
      "learning_rate": 0.0008969744248348192,
      "loss": 1.1589,
      "step": 470
    },
    {
      "epoch": 0.2904976683739775,
      "grad_norm": 0.025436594808100562,
      "learning_rate": 0.0008937056947140625,
      "loss": 1.188,
      "step": 475
    },
    {
      "epoch": 0.2935555385673878,
      "grad_norm": 0.023518916924014855,
      "learning_rate": 0.0008903920712470089,
      "loss": 1.1513,
      "step": 480
    },
    {
      "epoch": 0.2966134087607981,
      "grad_norm": 0.025275737643640807,
      "learning_rate": 0.0008870339322784491,
      "loss": 1.1646,
      "step": 485
    },
    {
      "epoch": 0.2996712789542084,
      "grad_norm": 0.02705678175117531,
      "learning_rate": 0.0008836316607291732,
      "loss": 1.1468,
      "step": 490
    },
    {
      "epoch": 0.30272914914761867,
      "grad_norm": 0.03300749247554839,
      "learning_rate": 0.0008801856445523064,
      "loss": 1.1593,
      "step": 495
    },
    {
      "epoch": 0.305787019341029,
      "grad_norm": 0.03070807591397227,
      "learning_rate": 0.0008766962766890733,
      "loss": 1.1494,
      "step": 500
    },
    {
      "epoch": 0.3088448895344393,
      "grad_norm": 0.03171884578840513,
      "learning_rate": 0.0008731639550239895,
      "loss": 1.1549,
      "step": 505
    },
    {
      "epoch": 0.31190275972784953,
      "grad_norm": 0.026683099702115617,
      "learning_rate": 0.0008695890823394938,
      "loss": 1.1599,
      "step": 510
    },
    {
      "epoch": 0.31496062992125984,
      "grad_norm": 0.02544573139035867,
      "learning_rate": 0.0008659720662700183,
      "loss": 1.14,
      "step": 515
    },
    {
      "epoch": 0.31801850011467014,
      "grad_norm": 0.022400712579356837,
      "learning_rate": 0.0008623133192555081,
      "loss": 1.1631,
      "step": 520
    },
    {
      "epoch": 0.3210763703080804,
      "grad_norm": 0.021516644941970493,
      "learning_rate": 0.0008586132584943902,
      "loss": 1.1414,
      "step": 525
    },
    {
      "epoch": 0.3241342405014907,
      "grad_norm": 0.022140987842416558,
      "learning_rate": 0.0008548723058960033,
      "loss": 1.1514,
      "step": 530
    },
    {
      "epoch": 0.327192110694901,
      "grad_norm": 0.02141121718297312,
      "learning_rate": 0.0008510908880324864,
      "loss": 1.1496,
      "step": 535
    },
    {
      "epoch": 0.3302499808883113,
      "grad_norm": 0.0230067385747688,
      "learning_rate": 0.000847269436090139,
      "loss": 1.1565,
      "step": 540
    },
    {
      "epoch": 0.33330785108172156,
      "grad_norm": 0.026857409244505942,
      "learning_rate": 0.0008434083858202541,
      "loss": 1.1541,
      "step": 545
    },
    {
      "epoch": 0.33636572127513187,
      "grad_norm": 0.031962019558439914,
      "learning_rate": 0.0008395081774894297,
      "loss": 1.1369,
      "step": 550
    },
    {
      "epoch": 0.3394235914685422,
      "grad_norm": 0.025328863714439345,
      "learning_rate": 0.0008355692558293664,
      "loss": 1.1462,
      "step": 555
    },
    {
      "epoch": 0.3424814616619524,
      "grad_norm": 0.02322136360750488,
      "learning_rate": 0.0008315920699861561,
      "loss": 1.1364,
      "step": 560
    },
    {
      "epoch": 0.34553933185536273,
      "grad_norm": 0.023916932106576035,
      "learning_rate": 0.0008275770734690669,
      "loss": 1.1376,
      "step": 565
    },
    {
      "epoch": 0.34859720204877304,
      "grad_norm": 0.027655600181262414,
      "learning_rate": 0.0008235247240988294,
      "loss": 1.1433,
      "step": 570
    },
    {
      "epoch": 0.35165507224218334,
      "grad_norm": 0.01944294724363515,
      "learning_rate": 0.0008194354839554344,
      "loss": 1.1422,
      "step": 575
    },
    {
      "epoch": 0.3547129424355936,
      "grad_norm": 0.024586207516548813,
      "learning_rate": 0.0008153098193254413,
      "loss": 1.1481,
      "step": 580
    },
    {
      "epoch": 0.3577708126290039,
      "grad_norm": 0.02722431056639769,
      "learning_rate": 0.0008111482006488091,
      "loss": 1.1479,
      "step": 585
    },
    {
      "epoch": 0.3608286828224142,
      "grad_norm": 0.021338457814223475,
      "learning_rate": 0.0008069511024652537,
      "loss": 1.1444,
      "step": 590
    },
    {
      "epoch": 0.36388655301582445,
      "grad_norm": 0.025185341202656784,
      "learning_rate": 0.0008027190033601363,
      "loss": 1.1301,
      "step": 595
    },
    {
      "epoch": 0.36694442320923476,
      "grad_norm": 0.020971837960705533,
      "learning_rate": 0.000798452385909892,
      "loss": 1.1431,
      "step": 600
    },
    {
      "epoch": 0.37000229340264507,
      "grad_norm": 0.02495043534094607,
      "learning_rate": 0.0007941517366270032,
      "loss": 1.1356,
      "step": 605
    },
    {
      "epoch": 0.37306016359605537,
      "grad_norm": 0.025056486993634036,
      "learning_rate": 0.0007898175459045224,
      "loss": 1.1529,
      "step": 610
    },
    {
      "epoch": 0.3761180337894656,
      "grad_norm": 0.02276962025168977,
      "learning_rate": 0.0007854503079601551,
      "loss": 1.1236,
      "step": 615
    },
    {
      "epoch": 0.37917590398287593,
      "grad_norm": 0.021078280161330308,
      "learning_rate": 0.0007810505207799046,
      "loss": 1.137,
      "step": 620
    },
    {
      "epoch": 0.38223377417628623,
      "grad_norm": 0.02117005306879687,
      "learning_rate": 0.000776618686061288,
      "loss": 1.1449,
      "step": 625
    },
    {
      "epoch": 0.3852916443696965,
      "grad_norm": 0.024567794869791014,
      "learning_rate": 0.0007721553091561288,
      "loss": 1.139,
      "step": 630
    },
    {
      "epoch": 0.3883495145631068,
      "grad_norm": 0.019473444654760176,
      "learning_rate": 0.000767660899012933,
      "loss": 1.1386,
      "step": 635
    },
    {
      "epoch": 0.3914073847565171,
      "grad_norm": 0.022412121303153214,
      "learning_rate": 0.0007631359681188544,
      "loss": 1.1368,
      "step": 640
    },
    {
      "epoch": 0.3944652549499274,
      "grad_norm": 0.022050962340279187,
      "learning_rate": 0.000758581032441257,
      "loss": 1.1223,
      "step": 645
    },
    {
      "epoch": 0.39752312514333765,
      "grad_norm": 0.02203032943298021,
      "learning_rate": 0.0007539966113688812,
      "loss": 1.1167,
      "step": 650
    },
    {
      "epoch": 0.40058099533674796,
      "grad_norm": 0.023078837241982387,
      "learning_rate": 0.0007493832276526181,
      "loss": 1.1344,
      "step": 655
    },
    {
      "epoch": 0.40363886553015826,
      "grad_norm": 0.023966897106968064,
      "learning_rate": 0.0007447414073459017,
      "loss": 1.1227,
      "step": 660
    },
    {
      "epoch": 0.4066967357235685,
      "grad_norm": 0.02168228889218337,
      "learning_rate": 0.000740071679744725,
      "loss": 1.1246,
      "step": 665
    },
    {
      "epoch": 0.4097546059169788,
      "grad_norm": 0.020601206009860356,
      "learning_rate": 0.0007353745773272844,
      "loss": 1.1227,
      "step": 670
    },
    {
      "epoch": 0.4128124761103891,
      "grad_norm": 0.021802890558372243,
      "learning_rate": 0.0007306506356932631,
      "loss": 1.1037,
      "step": 675
    },
    {
      "epoch": 0.4158703463037994,
      "grad_norm": 0.02158104255188381,
      "learning_rate": 0.0007259003935027581,
      "loss": 1.1166,
      "step": 680
    },
    {
      "epoch": 0.4189282164972097,
      "grad_norm": 0.02059398752407913,
      "learning_rate": 0.0007211243924148578,
      "loss": 1.1195,
      "step": 685
    },
    {
      "epoch": 0.42198608669062,
      "grad_norm": 0.022849828674870364,
      "learning_rate": 0.0007163231770258777,
      "loss": 1.1358,
      "step": 690
    },
    {
      "epoch": 0.4250439568840303,
      "grad_norm": 0.022923693857214923,
      "learning_rate": 0.0007114972948072613,
      "loss": 1.1388,
      "step": 695
    },
    {
      "epoch": 0.42810182707744054,
      "grad_norm": 0.02318319704681315,
      "learning_rate": 0.0007066472960431541,
      "loss": 1.1154,
      "step": 700
    },
    {
      "epoch": 0.43115969727085085,
      "grad_norm": 0.02746835308407499,
      "learning_rate": 0.0007017737337676546,
      "loss": 1.1222,
      "step": 705
    },
    {
      "epoch": 0.43421756746426116,
      "grad_norm": 0.02776028621219042,
      "learning_rate": 0.0006968771637017541,
      "loss": 1.1011,
      "step": 710
    },
    {
      "epoch": 0.4372754376576714,
      "grad_norm": 0.024266687223156804,
      "learning_rate": 0.0006919581441899689,
      "loss": 1.1246,
      "step": 715
    },
    {
      "epoch": 0.4403333078510817,
      "grad_norm": 0.02908301149621474,
      "learning_rate": 0.0006870172361366733,
      "loss": 1.1225,
      "step": 720
    },
    {
      "epoch": 0.443391178044492,
      "grad_norm": 0.019862559304176748,
      "learning_rate": 0.0006820550029421413,
      "loss": 1.1367,
      "step": 725
    },
    {
      "epoch": 0.4464490482379023,
      "grad_norm": 0.032405405252682935,
      "learning_rate": 0.000677072010438303,
      "loss": 1.1234,
      "step": 730
    },
    {
      "epoch": 0.4495069184313126,
      "grad_norm": 0.030753416752446607,
      "learning_rate": 0.0006720688268242248,
      "loss": 1.1109,
      "step": 735
    },
    {
      "epoch": 0.4525647886247229,
      "grad_norm": 0.022597155712349652,
      "learning_rate": 0.0006670460226013181,
      "loss": 1.0944,
      "step": 740
    },
    {
      "epoch": 0.4556226588181332,
      "grad_norm": 0.022634198101240257,
      "learning_rate": 0.0006620041705082871,
      "loss": 1.1089,
      "step": 745
    },
    {
      "epoch": 0.45868052901154344,
      "grad_norm": 0.02271478233831073,
      "learning_rate": 0.00065694384545582,
      "loss": 1.1023,
      "step": 750
    },
    {
      "epoch": 0.46173839920495374,
      "grad_norm": 0.027216769976956785,
      "learning_rate": 0.000651865624461034,
      "loss": 1.1058,
      "step": 755
    },
    {
      "epoch": 0.46479626939836405,
      "grad_norm": 0.02071517184981896,
      "learning_rate": 0.0006467700865816791,
      "loss": 1.1083,
      "step": 760
    },
    {
      "epoch": 0.46785413959177435,
      "grad_norm": 0.02555353317127748,
      "learning_rate": 0.0006416578128501092,
      "loss": 1.0981,
      "step": 765
    },
    {
      "epoch": 0.4709120097851846,
      "grad_norm": 0.026631260066706193,
      "learning_rate": 0.0006365293862070285,
      "loss": 1.1091,
      "step": 770
    },
    {
      "epoch": 0.4739698799785949,
      "grad_norm": 0.022198028831592595,
      "learning_rate": 0.0006313853914350207,
      "loss": 1.1265,
      "step": 775
    },
    {
      "epoch": 0.4770277501720052,
      "grad_norm": 0.020216593671054946,
      "learning_rate": 0.0006262264150918667,
      "loss": 1.0885,
      "step": 780
    },
    {
      "epoch": 0.48008562036541547,
      "grad_norm": 0.02929161675770138,
      "learning_rate": 0.0006210530454436612,
      "loss": 1.1049,
      "step": 785
    },
    {
      "epoch": 0.48314349055882577,
      "grad_norm": 0.022879526501220927,
      "learning_rate": 0.0006158658723977341,
      "loss": 1.1114,
      "step": 790
    },
    {
      "epoch": 0.4862013607522361,
      "grad_norm": 0.02011420292019708,
      "learning_rate": 0.0006106654874353845,
      "loss": 1.1147,
      "step": 795
    },
    {
      "epoch": 0.4892592309456464,
      "grad_norm": 0.020765554185496773,
      "learning_rate": 0.0006054524835444363,
      "loss": 1.126,
      "step": 800
    },
    {
      "epoch": 0.49231710113905663,
      "grad_norm": 0.021368017020777876,
      "learning_rate": 0.0006002274551516198,
      "loss": 1.1141,
      "step": 805
    },
    {
      "epoch": 0.49537497133246694,
      "grad_norm": 0.023303801824493854,
      "learning_rate": 0.0005949909980547917,
      "loss": 1.1056,
      "step": 810
    },
    {
      "epoch": 0.49843284152587725,
      "grad_norm": 0.020988017572428172,
      "learning_rate": 0.0005897437093549972,
      "loss": 1.1046,
      "step": 815
    },
    {
      "epoch": 0.5014907117192875,
      "grad_norm": 0.0222701220933236,
      "learning_rate": 0.0005844861873883838,
      "loss": 1.0896,
      "step": 820
    },
    {
      "epoch": 0.5045485819126978,
      "grad_norm": 0.02390246675277257,
      "learning_rate": 0.0005792190316579754,
      "loss": 1.1003,
      "step": 825
    },
    {
      "epoch": 0.5076064521061081,
      "grad_norm": 0.024599305753849318,
      "learning_rate": 0.0005739428427653107,
      "loss": 1.1006,
      "step": 830
    },
    {
      "epoch": 0.5106643222995184,
      "grad_norm": 0.021909626214719365,
      "learning_rate": 0.0005686582223419595,
      "loss": 1.0978,
      "step": 835
    },
    {
      "epoch": 0.5137221924929287,
      "grad_norm": 0.020358006124918764,
      "learning_rate": 0.0005633657729809194,
      "loss": 1.0959,
      "step": 840
    },
    {
      "epoch": 0.5167800626863389,
      "grad_norm": 0.0198487307695255,
      "learning_rate": 0.0005580660981679034,
      "loss": 1.1,
      "step": 845
    },
    {
      "epoch": 0.5198379328797492,
      "grad_norm": 0.020615430577747694,
      "learning_rate": 0.0005527598022125259,
      "loss": 1.095,
      "step": 850
    },
    {
      "epoch": 0.5228958030731595,
      "grad_norm": 0.02292927406023271,
      "learning_rate": 0.0005474474901793951,
      "loss": 1.1095,
      "step": 855
    },
    {
      "epoch": 0.5259536732665698,
      "grad_norm": 0.023765712603430467,
      "learning_rate": 0.0005421297678191189,
      "loss": 1.0771,
      "step": 860
    },
    {
      "epoch": 0.5290115434599801,
      "grad_norm": 0.01983795845597764,
      "learning_rate": 0.0005368072414992314,
      "loss": 1.1005,
      "step": 865
    },
    {
      "epoch": 0.5320694136533904,
      "grad_norm": 0.026870791253807334,
      "learning_rate": 0.0005314805181350515,
      "loss": 1.0942,
      "step": 870
    },
    {
      "epoch": 0.5351272838468007,
      "grad_norm": 0.01859295942083269,
      "learning_rate": 0.0005261502051204772,
      "loss": 1.0795,
      "step": 875
    },
    {
      "epoch": 0.538185154040211,
      "grad_norm": 0.024323351242619737,
      "learning_rate": 0.0005208169102587264,
      "loss": 1.0888,
      "step": 880
    },
    {
      "epoch": 0.5412430242336213,
      "grad_norm": 0.02524057653331344,
      "learning_rate": 0.0005154812416930298,
      "loss": 1.0908,
      "step": 885
    },
    {
      "epoch": 0.5443008944270316,
      "grad_norm": 0.018971386204347403,
      "learning_rate": 0.0005101438078372858,
      "loss": 1.0976,
      "step": 890
    },
    {
      "epoch": 0.5473587646204419,
      "grad_norm": 0.019908423848410486,
      "learning_rate": 0.000504805217306685,
      "loss": 1.093,
      "step": 895
    },
    {
      "epoch": 0.5504166348138522,
      "grad_norm": 0.0195002156944646,
      "learning_rate": 0.0004994660788483113,
      "loss": 1.0982,
      "step": 900
    },
    {
      "epoch": 0.5534745050072625,
      "grad_norm": 0.019088935901819853,
      "learning_rate": 0.0004941270012717269,
      "loss": 1.0946,
      "step": 905
    },
    {
      "epoch": 0.5565323752006728,
      "grad_norm": 0.020956181295062905,
      "learning_rate": 0.000488788593379552,
      "loss": 1.0927,
      "step": 910
    },
    {
      "epoch": 0.559590245394083,
      "grad_norm": 0.02058468157622052,
      "learning_rate": 0.00048345146389804425,
      "loss": 1.0778,
      "step": 915
    },
    {
      "epoch": 0.5626481155874933,
      "grad_norm": 0.023584369471082292,
      "learning_rate": 0.00047811622140768727,
      "loss": 1.0821,
      "step": 920
    },
    {
      "epoch": 0.5657059857809036,
      "grad_norm": 0.019349421074761057,
      "learning_rate": 0.0004727834742737955,
      "loss": 1.107,
      "step": 925
    },
    {
      "epoch": 0.5687638559743139,
      "grad_norm": 0.020725187288479826,
      "learning_rate": 0.0004674538305771433,
      "loss": 1.1124,
      "step": 930
    },
    {
      "epoch": 0.5718217261677242,
      "grad_norm": 0.02330784277601695,
      "learning_rate": 0.00046212789804462765,
      "loss": 1.0776,
      "step": 935
    },
    {
      "epoch": 0.5748795963611345,
      "grad_norm": 0.020779970593931846,
      "learning_rate": 0.0004568062839799696,
      "loss": 1.0936,
      "step": 940
    },
    {
      "epoch": 0.5779374665545448,
      "grad_norm": 0.02310004433856537,
      "learning_rate": 0.000451489595194466,
      "loss": 1.0816,
      "step": 945
    },
    {
      "epoch": 0.580995336747955,
      "grad_norm": 0.020049876509611084,
      "learning_rate": 0.00044617843793779517,
      "loss": 1.0776,
      "step": 950
    },
    {
      "epoch": 0.5840532069413653,
      "grad_norm": 0.019669039054560983,
      "learning_rate": 0.00044087341782888823,
      "loss": 1.0813,
      "step": 955
    },
    {
      "epoch": 0.5871110771347756,
      "grad_norm": 0.019875654721293167,
      "learning_rate": 0.0004355751397868713,
      "loss": 1.0899,
      "step": 960
    },
    {
      "epoch": 0.5901689473281859,
      "grad_norm": 0.020596024583719397,
      "learning_rate": 0.0004302842079620885,
      "loss": 1.0753,
      "step": 965
    },
    {
      "epoch": 0.5932268175215962,
      "grad_norm": 0.020513561070135005,
      "learning_rate": 0.0004250012256672117,
      "loss": 1.0659,
      "step": 970
    },
    {
      "epoch": 0.5962846877150065,
      "grad_norm": 0.021144651470144736,
      "learning_rate": 0.00041972679530844647,
      "loss": 1.0839,
      "step": 975
    },
    {
      "epoch": 0.5993425579084168,
      "grad_norm": 0.021711998053494025,
      "learning_rate": 0.0004144615183168409,
      "loss": 1.0849,
      "step": 980
    },
    {
      "epoch": 0.602400428101827,
      "grad_norm": 0.022407376804965174,
      "learning_rate": 0.0004092059950797062,
      "loss": 1.0609,
      "step": 985
    },
    {
      "epoch": 0.6054582982952373,
      "grad_norm": 0.02333806103193432,
      "learning_rate": 0.0004039608248721548,
      "loss": 1.0886,
      "step": 990
    },
    {
      "epoch": 0.6085161684886476,
      "grad_norm": 0.024102796234038874,
      "learning_rate": 0.00039872660578876785,
      "loss": 1.0737,
      "step": 995
    },
    {
      "epoch": 0.611574038682058,
      "grad_norm": 0.019357290501165046,
      "learning_rate": 0.00039350393467539515,
      "loss": 1.08,
      "step": 1000
    },
    {
      "epoch": 0.6146319088754683,
      "grad_norm": 0.020142530815836432,
      "learning_rate": 0.0003882934070610981,
      "loss": 1.0656,
      "step": 1005
    },
    {
      "epoch": 0.6176897790688786,
      "grad_norm": 0.018608575204815583,
      "learning_rate": 0.00038309561709024356,
      "loss": 1.0637,
      "step": 1010
    },
    {
      "epoch": 0.6207476492622889,
      "grad_norm": 0.021214222795490626,
      "learning_rate": 0.0003779111574547537,
      "loss": 1.08,
      "step": 1015
    },
    {
      "epoch": 0.6238055194556991,
      "grad_norm": 0.022933622407233706,
      "learning_rate": 0.00037274061932652413,
      "loss": 1.0664,
      "step": 1020
    },
    {
      "epoch": 0.6268633896491094,
      "grad_norm": 0.019706448651309442,
      "learning_rate": 0.000367584592290013,
      "loss": 1.0806,
      "step": 1025
    },
    {
      "epoch": 0.6299212598425197,
      "grad_norm": 0.02379452277464871,
      "learning_rate": 0.00036244366427501265,
      "loss": 1.0664,
      "step": 1030
    },
    {
      "epoch": 0.63297913003593,
      "grad_norm": 0.022836969922118866,
      "learning_rate": 0.0003573184214896087,
      "loss": 1.0702,
      "step": 1035
    },
    {
      "epoch": 0.6360370002293403,
      "grad_norm": 0.0220847265087786,
      "learning_rate": 0.0003522094483533369,
      "loss": 1.0777,
      "step": 1040
    },
    {
      "epoch": 0.6390948704227506,
      "grad_norm": 0.021238471439531986,
      "learning_rate": 0.000347117327430542,
      "loss": 1.0827,
      "step": 1045
    },
    {
      "epoch": 0.6421527406161608,
      "grad_norm": 0.01967371179793323,
      "learning_rate": 0.0003420426393639508,
      "loss": 1.0638,
      "step": 1050
    },
    {
      "epoch": 0.6452106108095711,
      "grad_norm": 0.022296186314483487,
      "learning_rate": 0.00033698596280846125,
      "loss": 1.0639,
      "step": 1055
    },
    {
      "epoch": 0.6482684810029814,
      "grad_norm": 0.02241422770345421,
      "learning_rate": 0.0003319478743651609,
      "loss": 1.0851,
      "step": 1060
    },
    {
      "epoch": 0.6513263511963917,
      "grad_norm": 0.02523497459965589,
      "learning_rate": 0.0003269289485155783,
      "loss": 1.0847,
      "step": 1065
    },
    {
      "epoch": 0.654384221389802,
      "grad_norm": 0.025512702330510183,
      "learning_rate": 0.00032192975755617506,
      "loss": 1.0662,
      "step": 1070
    },
    {
      "epoch": 0.6574420915832123,
      "grad_norm": 0.019599747988122102,
      "learning_rate": 0.00031695087153308976,
      "loss": 1.0766,
      "step": 1075
    },
    {
      "epoch": 0.6604999617766226,
      "grad_norm": 0.01962272505893558,
      "learning_rate": 0.0003119928581771362,
      "loss": 1.0625,
      "step": 1080
    },
    {
      "epoch": 0.6635578319700328,
      "grad_norm": 0.019771169590040102,
      "learning_rate": 0.0003070562828390662,
      "loss": 1.0689,
      "step": 1085
    },
    {
      "epoch": 0.6666157021634431,
      "grad_norm": 0.02030493911602512,
      "learning_rate": 0.00030214170842510435,
      "loss": 1.0769,
      "step": 1090
    },
    {
      "epoch": 0.6696735723568534,
      "grad_norm": 0.024601514965605153,
      "learning_rate": 0.0002972496953327607,
      "loss": 1.062,
      "step": 1095
    },
    {
      "epoch": 0.6727314425502637,
      "grad_norm": 0.01994828738024262,
      "learning_rate": 0.00029238080138693025,
      "loss": 1.0775,
      "step": 1100
    },
    {
      "epoch": 0.675789312743674,
      "grad_norm": 0.028014612142516805,
      "learning_rate": 0.0002875355817762856,
      "loss": 1.0567,
      "step": 1105
    },
    {
      "epoch": 0.6788471829370843,
      "grad_norm": 0.02154035563943042,
      "learning_rate": 0.0002827145889899698,
      "loss": 1.0451,
      "step": 1110
    },
    {
      "epoch": 0.6819050531304947,
      "grad_norm": 0.019908200712777067,
      "learning_rate": 0.0002779183727545973,
      "loss": 1.0715,
      "step": 1115
    },
    {
      "epoch": 0.6849629233239048,
      "grad_norm": 0.019831506624958018,
      "learning_rate": 0.0002731474799715701,
      "loss": 1.0794,
      "step": 1120
    },
    {
      "epoch": 0.6880207935173152,
      "grad_norm": 0.020609762986790316,
      "learning_rate": 0.00026840245465471535,
      "loss": 1.0648,
      "step": 1125
    },
    {
      "epoch": 0.6910786637107255,
      "grad_norm": 0.018373460203891627,
      "learning_rate": 0.0002636838378682534,
      "loss": 1.0642,
      "step": 1130
    },
    {
      "epoch": 0.6941365339041358,
      "grad_norm": 0.021227917010586402,
      "learning_rate": 0.00025899216766510114,
      "loss": 1.0574,
      "step": 1135
    },
    {
      "epoch": 0.6971944040975461,
      "grad_norm": 0.021984002313747204,
      "learning_rate": 0.0002543279790255192,
      "loss": 1.0603,
      "step": 1140
    },
    {
      "epoch": 0.7002522742909564,
      "grad_norm": 0.02355426186863231,
      "learning_rate": 0.00024969180379610934,
      "loss": 1.0586,
      "step": 1145
    },
    {
      "epoch": 0.7033101444843667,
      "grad_norm": 0.024678418156208182,
      "learning_rate": 0.00024508417062916885,
      "loss": 1.0661,
      "step": 1150
    },
    {
      "epoch": 0.7063680146777769,
      "grad_norm": 0.02082314009145273,
      "learning_rate": 0.0002405056049224103,
      "loss": 1.0651,
      "step": 1155
    },
    {
      "epoch": 0.7094258848711872,
      "grad_norm": 0.02162054379835859,
      "learning_rate": 0.0002359566287590511,
      "loss": 1.0715,
      "step": 1160
    },
    {
      "epoch": 0.7124837550645975,
      "grad_norm": 0.021178840967147644,
      "learning_rate": 0.00023143776084828178,
      "loss": 1.045,
      "step": 1165
    },
    {
      "epoch": 0.7155416252580078,
      "grad_norm": 0.023789035651104056,
      "learning_rate": 0.00022694951646611884,
      "loss": 1.0618,
      "step": 1170
    },
    {
      "epoch": 0.7185994954514181,
      "grad_norm": 0.019246434577242334,
      "learning_rate": 0.0002224924073966484,
      "loss": 1.0638,
      "step": 1175
    },
    {
      "epoch": 0.7216573656448284,
      "grad_norm": 0.018166777369856113,
      "learning_rate": 0.00021806694187366976,
      "loss": 1.0551,
      "step": 1180
    },
    {
      "epoch": 0.7247152358382387,
      "grad_norm": 0.01932908428350948,
      "learning_rate": 0.00021367362452274198,
      "loss": 1.0559,
      "step": 1185
    },
    {
      "epoch": 0.7277731060316489,
      "grad_norm": 0.019018633917993133,
      "learning_rate": 0.00020931295630364222,
      "loss": 1.0542,
      "step": 1190
    },
    {
      "epoch": 0.7308309762250592,
      "grad_norm": 0.019157449963553598,
      "learning_rate": 0.00020498543445324346,
      "loss": 1.0572,
      "step": 1195
    },
    {
      "epoch": 0.7338888464184695,
      "grad_norm": 0.018701309680460174,
      "learning_rate": 0.00020069155242881525,
      "loss": 1.064,
      "step": 1200
    },
    {
      "epoch": 0.7369467166118798,
      "grad_norm": 0.020107359392638562,
      "learning_rate": 0.00019643179985175525,
      "loss": 1.0427,
      "step": 1205
    },
    {
      "epoch": 0.7400045868052901,
      "grad_norm": 0.018162781703447546,
      "learning_rate": 0.00019220666245176016,
      "loss": 1.0486,
      "step": 1210
    },
    {
      "epoch": 0.7430624569987004,
      "grad_norm": 0.019847164271580075,
      "learning_rate": 0.00018801662201143815,
      "loss": 1.0353,
      "step": 1215
    },
    {
      "epoch": 0.7461203271921107,
      "grad_norm": 0.020732633406869302,
      "learning_rate": 0.00018386215631137248,
      "loss": 1.064,
      "step": 1220
    },
    {
      "epoch": 0.7491781973855209,
      "grad_norm": 0.020348214250739332,
      "learning_rate": 0.00017974373907564167,
      "loss": 1.052,
      "step": 1225
    },
    {
      "epoch": 0.7522360675789312,
      "grad_norm": 0.019382936149259185,
      "learning_rate": 0.000175661839917801,
      "loss": 1.0632,
      "step": 1230
    },
    {
      "epoch": 0.7552939377723416,
      "grad_norm": 0.020617077209785874,
      "learning_rate": 0.0001716169242873346,
      "loss": 1.0603,
      "step": 1235
    },
    {
      "epoch": 0.7583518079657519,
      "grad_norm": 0.018721534354599865,
      "learning_rate": 0.0001676094534165807,
      "loss": 1.0504,
      "step": 1240
    },
    {
      "epoch": 0.7614096781591622,
      "grad_norm": 0.019523624424920942,
      "learning_rate": 0.00016363988426813865,
      "loss": 1.0605,
      "step": 1245
    },
    {
      "epoch": 0.7644675483525725,
      "grad_norm": 0.021325379023544762,
      "learning_rate": 0.00015970866948276208,
      "loss": 1.0502,
      "step": 1250
    },
    {
      "epoch": 0.7675254185459828,
      "grad_norm": 0.018381651158354734,
      "learning_rate": 0.00015581625732774562,
      "loss": 1.0695,
      "step": 1255
    },
    {
      "epoch": 0.770583288739393,
      "grad_norm": 0.017773314789403843,
      "learning_rate": 0.00015196309164581046,
      "loss": 1.0564,
      "step": 1260
    },
    {
      "epoch": 0.7736411589328033,
      "grad_norm": 0.018755748204595284,
      "learning_rate": 0.00014814961180449339,
      "loss": 1.0372,
      "step": 1265
    },
    {
      "epoch": 0.7766990291262136,
      "grad_norm": 0.025065839963610673,
      "learning_rate": 0.0001443762526460468,
      "loss": 1.058,
      "step": 1270
    },
    {
      "epoch": 0.7797568993196239,
      "grad_norm": 0.022671037009366964,
      "learning_rate": 0.00014064344443785504,
      "loss": 1.0486,
      "step": 1275
    },
    {
      "epoch": 0.7828147695130342,
      "grad_norm": 0.021001365810248977,
      "learning_rate": 0.0001369516128233716,
      "loss": 1.0684,
      "step": 1280
    },
    {
      "epoch": 0.7858726397064445,
      "grad_norm": 0.02187887791955955,
      "learning_rate": 0.00013330117877358383,
      "loss": 1.0488,
      "step": 1285
    },
    {
      "epoch": 0.7889305098998548,
      "grad_norm": 0.017361526578702963,
      "learning_rate": 0.00012969255853901142,
      "loss": 1.0378,
      "step": 1290
    },
    {
      "epoch": 0.791988380093265,
      "grad_norm": 0.01766771162161045,
      "learning_rate": 0.00012612616360224138,
      "loss": 1.0369,
      "step": 1295
    },
    {
      "epoch": 0.7950462502866753,
      "grad_norm": 0.021322450785295783,
      "learning_rate": 0.00012260240063100846,
      "loss": 1.0639,
      "step": 1300
    },
    {
      "epoch": 0.7981041204800856,
      "grad_norm": 0.020380850502793722,
      "learning_rate": 0.00011912167143182279,
      "loss": 1.0493,
      "step": 1305
    },
    {
      "epoch": 0.8011619906734959,
      "grad_norm": 0.018397926034012132,
      "learning_rate": 0.00011568437290415395,
      "loss": 1.0541,
      "step": 1310
    },
    {
      "epoch": 0.8042198608669062,
      "grad_norm": 0.017133257784555725,
      "learning_rate": 0.00011229089699517242,
      "loss": 1.0523,
      "step": 1315
    },
    {
      "epoch": 0.8072777310603165,
      "grad_norm": 0.01819525737040671,
      "learning_rate": 0.00010894163065505753,
      "loss": 1.0468,
      "step": 1320
    },
    {
      "epoch": 0.8103356012537268,
      "grad_norm": 0.02028545883645919,
      "learning_rate": 0.00010563695579287402,
      "loss": 1.0629,
      "step": 1325
    },
    {
      "epoch": 0.813393471447137,
      "grad_norm": 0.01787173264557234,
      "learning_rate": 0.00010237724923302406,
      "loss": 1.0351,
      "step": 1330
    },
    {
      "epoch": 0.8164513416405473,
      "grad_norm": 0.018194742191756992,
      "learning_rate": 9.916288267227824e-05,
      "loss": 1.0598,
      "step": 1335
    },
    {
      "epoch": 0.8195092118339576,
      "grad_norm": 0.019378519353161313,
      "learning_rate": 9.599422263739289e-05,
      "loss": 1.0608,
      "step": 1340
    },
    {
      "epoch": 0.822567082027368,
      "grad_norm": 0.01902789612845712,
      "learning_rate": 9.287163044331498e-05,
      "loss": 1.0501,
      "step": 1345
    },
    {
      "epoch": 0.8256249522207783,
      "grad_norm": 0.018581047910824787,
      "learning_rate": 8.979546215198265e-05,
      "loss": 1.0458,
      "step": 1350
    },
    {
      "epoch": 0.8286828224141886,
      "grad_norm": 0.01799606775719105,
      "learning_rate": 8.676606853172426e-05,
      "loss": 1.0403,
      "step": 1355
    },
    {
      "epoch": 0.8317406926075988,
      "grad_norm": 0.01874997273444636,
      "learning_rate": 8.378379501726096e-05,
      "loss": 1.0672,
      "step": 1360
    },
    {
      "epoch": 0.8347985628010091,
      "grad_norm": 0.01729209570770116,
      "learning_rate": 8.084898167031746e-05,
      "loss": 1.0519,
      "step": 1365
    },
    {
      "epoch": 0.8378564329944194,
      "grad_norm": 0.020489335055326883,
      "learning_rate": 7.796196314084614e-05,
      "loss": 1.0332,
      "step": 1370
    },
    {
      "epoch": 0.8409143031878297,
      "grad_norm": 0.018824889864362003,
      "learning_rate": 7.512306862886681e-05,
      "loss": 1.0349,
      "step": 1375
    },
    {
      "epoch": 0.84397217338124,
      "grad_norm": 0.018493904385427234,
      "learning_rate": 7.233262184692974e-05,
      "loss": 1.0458,
      "step": 1380
    },
    {
      "epoch": 0.8470300435746503,
      "grad_norm": 0.021431180850593753,
      "learning_rate": 6.959094098320295e-05,
      "loss": 1.042,
      "step": 1385
    },
    {
      "epoch": 0.8500879137680606,
      "grad_norm": 0.01774287881523113,
      "learning_rate": 6.68983386651898e-05,
      "loss": 1.0463,
      "step": 1390
    },
    {
      "epoch": 0.8531457839614708,
      "grad_norm": 0.019191338242596227,
      "learning_rate": 6.425512192408112e-05,
      "loss": 1.0428,
      "step": 1395
    },
    {
      "epoch": 0.8562036541548811,
      "grad_norm": 0.01894785926804795,
      "learning_rate": 6.166159215974521e-05,
      "loss": 1.0435,
      "step": 1400
    },
    {
      "epoch": 0.8592615243482914,
      "grad_norm": 0.016825213446883102,
      "learning_rate": 5.911804510635965e-05,
      "loss": 1.0447,
      "step": 1405
    },
    {
      "epoch": 0.8623193945417017,
      "grad_norm": 0.016963551769271477,
      "learning_rate": 5.6624770798689665e-05,
      "loss": 1.0412,
      "step": 1410
    },
    {
      "epoch": 0.865377264735112,
      "grad_norm": 0.016723668733144115,
      "learning_rate": 5.418205353901562e-05,
      "loss": 1.0684,
      "step": 1415
    },
    {
      "epoch": 0.8684351349285223,
      "grad_norm": 0.019698338107007437,
      "learning_rate": 5.179017186471557e-05,
      "loss": 1.0379,
      "step": 1420
    },
    {
      "epoch": 0.8714930051219326,
      "grad_norm": 0.017265614379559306,
      "learning_rate": 4.94493985165036e-05,
      "loss": 1.0454,
      "step": 1425
    },
    {
      "epoch": 0.8745508753153428,
      "grad_norm": 0.01778176463464062,
      "learning_rate": 4.7160000407329765e-05,
      "loss": 1.0431,
      "step": 1430
    },
    {
      "epoch": 0.8776087455087531,
      "grad_norm": 0.019057294957546256,
      "learning_rate": 4.492223859194533e-05,
      "loss": 1.0442,
      "step": 1435
    },
    {
      "epoch": 0.8806666157021634,
      "grad_norm": 0.018453421610507247,
      "learning_rate": 4.273636823713467e-05,
      "loss": 1.0437,
      "step": 1440
    },
    {
      "epoch": 0.8837244858955737,
      "grad_norm": 0.01765155626929793,
      "learning_rate": 4.0602638592619257e-05,
      "loss": 1.0415,
      "step": 1445
    },
    {
      "epoch": 0.886782356088984,
      "grad_norm": 0.017862026611963264,
      "learning_rate": 3.8521292962636625e-05,
      "loss": 1.0436,
      "step": 1450
    },
    {
      "epoch": 0.8898402262823943,
      "grad_norm": 0.017606797127937533,
      "learning_rate": 3.649256867819667e-05,
      "loss": 1.04,
      "step": 1455
    },
    {
      "epoch": 0.8928980964758046,
      "grad_norm": 0.017151387009890048,
      "learning_rate": 3.451669707001942e-05,
      "loss": 1.0578,
      "step": 1460
    },
    {
      "epoch": 0.8959559666692148,
      "grad_norm": 0.017195927947563305,
      "learning_rate": 3.259390344215707e-05,
      "loss": 1.0462,
      "step": 1465
    },
    {
      "epoch": 0.8990138368626251,
      "grad_norm": 0.01845679676674692,
      "learning_rate": 3.072440704630258e-05,
      "loss": 1.0555,
      "step": 1470
    },
    {
      "epoch": 0.9020717070560355,
      "grad_norm": 0.016944392213100467,
      "learning_rate": 2.8908421056789703e-05,
      "loss": 1.033,
      "step": 1475
    },
    {
      "epoch": 0.9051295772494458,
      "grad_norm": 0.018432906406152354,
      "learning_rate": 2.7146152546284663e-05,
      "loss": 1.0508,
      "step": 1480
    },
    {
      "epoch": 0.9081874474428561,
      "grad_norm": 0.017706430050248204,
      "learning_rate": 2.5437802462174144e-05,
      "loss": 1.0407,
      "step": 1485
    },
    {
      "epoch": 0.9112453176362664,
      "grad_norm": 0.01825937227605355,
      "learning_rate": 2.3783565603652024e-05,
      "loss": 1.0191,
      "step": 1490
    },
    {
      "epoch": 0.9143031878296767,
      "grad_norm": 0.017170141434300536,
      "learning_rate": 2.218363059950651e-05,
      "loss": 1.0381,
      "step": 1495
    },
    {
      "epoch": 0.9173610580230869,
      "grad_norm": 0.021018198836607237,
      "learning_rate": 2.0638179886611542e-05,
      "loss": 1.0342,
      "step": 1500
    },
    {
      "epoch": 0.9204189282164972,
      "grad_norm": 0.018670756565939955,
      "learning_rate": 1.9147389689123884e-05,
      "loss": 1.038,
      "step": 1505
    },
    {
      "epoch": 0.9234767984099075,
      "grad_norm": 0.01840746015098489,
      "learning_rate": 1.771142999838854e-05,
      "loss": 1.0576,
      "step": 1510
    },
    {
      "epoch": 0.9265346686033178,
      "grad_norm": 0.01791437481490544,
      "learning_rate": 1.633046455355519e-05,
      "loss": 1.0547,
      "step": 1515
    },
    {
      "epoch": 0.9295925387967281,
      "grad_norm": 0.016561566008186503,
      "learning_rate": 1.5004650822907306e-05,
      "loss": 1.0429,
      "step": 1520
    },
    {
      "epoch": 0.9326504089901384,
      "grad_norm": 0.017211669368685612,
      "learning_rate": 1.373413998590639e-05,
      "loss": 1.0412,
      "step": 1525
    },
    {
      "epoch": 0.9357082791835487,
      "grad_norm": 0.01917485719407648,
      "learning_rate": 1.2519076915953443e-05,
      "loss": 1.0329,
      "step": 1530
    },
    {
      "epoch": 0.9387661493769589,
      "grad_norm": 0.019235379531641828,
      "learning_rate": 1.1359600163869276e-05,
      "loss": 1.0509,
      "step": 1535
    },
    {
      "epoch": 0.9418240195703692,
      "grad_norm": 0.017132686744869362,
      "learning_rate": 1.0255841942096056e-05,
      "loss": 1.0402,
      "step": 1540
    },
    {
      "epoch": 0.9448818897637795,
      "grad_norm": 0.018593609192373937,
      "learning_rate": 9.207928109621122e-06,
      "loss": 1.0409,
      "step": 1545
    },
    {
      "epoch": 0.9479397599571898,
      "grad_norm": 0.01776794448761931,
      "learning_rate": 8.21597815762587e-06,
      "loss": 1.0242,
      "step": 1550
    },
    {
      "epoch": 0.9509976301506001,
      "grad_norm": 0.019644926869063512,
      "learning_rate": 7.280105195860254e-06,
      "loss": 1.0306,
      "step": 1555
    },
    {
      "epoch": 0.9540555003440104,
      "grad_norm": 0.016710041757227387,
      "learning_rate": 6.400415939745275e-06,
      "loss": 1.0281,
      "step": 1560
    },
    {
      "epoch": 0.9571133705374207,
      "grad_norm": 0.018527383142328113,
      "learning_rate": 5.577010698204488e-06,
      "loss": 1.0493,
      "step": 1565
    },
    {
      "epoch": 0.9601712407308309,
      "grad_norm": 0.01587941593451175,
      "learning_rate": 4.809983362225878e-06,
      "loss": 1.0287,
      "step": 1570
    },
    {
      "epoch": 0.9632291109242412,
      "grad_norm": 0.01784011524370286,
      "learning_rate": 4.0994213941557e-06,
      "loss": 1.0494,
      "step": 1575
    },
    {
      "epoch": 0.9662869811176515,
      "grad_norm": 0.022229608533606754,
      "learning_rate": 3.4454058177253998e-06,
      "loss": 1.0245,
      "step": 1580
    },
    {
      "epoch": 0.9693448513110619,
      "grad_norm": 0.01771675468251995,
      "learning_rate": 2.8480112088128396e-06,
      "loss": 1.0539,
      "step": 1585
    },
    {
      "epoch": 0.9724027215044722,
      "grad_norm": 0.019318982313098143,
      "learning_rate": 2.307305686938266e-06,
      "loss": 1.0364,
      "step": 1590
    },
    {
      "epoch": 0.9754605916978825,
      "grad_norm": 0.01763551427180363,
      "learning_rate": 1.8233509074969124e-06,
      "loss": 1.0387,
      "step": 1595
    },
    {
      "epoch": 0.9785184618912928,
      "grad_norm": 0.020265580264344555,
      "learning_rate": 1.3962020547287345e-06,
      "loss": 1.0375,
      "step": 1600
    },
    {
      "epoch": 0.981576332084703,
      "grad_norm": 0.017705249951308937,
      "learning_rate": 1.0259078354257212e-06,
      "loss": 1.0463,
      "step": 1605
    },
    {
      "epoch": 0.9846342022781133,
      "grad_norm": 0.01899318507681047,
      "learning_rate": 7.12510473377892e-07,
      "loss": 1.0499,
      "step": 1610
    },
    {
      "epoch": 0.9876920724715236,
      "grad_norm": 0.20527421150604633,
      "learning_rate": 4.5604570455887175e-07,
      "loss": 1.0321,
      "step": 1615
    },
    {
      "epoch": 0.9907499426649339,
      "grad_norm": 0.01969626150373465,
      "learning_rate": 2.565427730508163e-07,
      "loss": 1.0622,
      "step": 1620
    },
    {
      "epoch": 0.9938078128583442,
      "grad_norm": 0.01846687245559012,
      "learning_rate": 1.1402442770985788e-07,
      "loss": 1.0443,
      "step": 1625
    },
    {
      "epoch": 0.9968656830517545,
      "grad_norm": 0.01754718213075641,
      "learning_rate": 2.8506919571902325e-08,
      "loss": 1.0413,
      "step": 1630
    },
    {
      "epoch": 0.9999235532451648,
      "grad_norm": 0.01654015476154834,
      "learning_rate": 0.0,
      "loss": 1.031,
      "step": 1635
    },
    {
      "epoch": 0.9999235532451648,
      "eval_loss": 1.415837049484253,
      "eval_runtime": 621.6735,
      "eval_samples_per_second": 33.703,
      "eval_steps_per_second": 8.426,
      "step": 1635
    },
    {
      "epoch": 0.9999235532451648,
      "step": 1635,
      "total_flos": 1.1949402256048128e+17,
      "train_loss": 1.1248935338554031,
      "train_runtime": 10312.3192,
      "train_samples_per_second": 10.148,
      "train_steps_per_second": 0.159
    }
  ],
  "logging_steps": 5,
  "max_steps": 1635,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1949402256048128e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}