{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9994454567060128,
  "eval_steps": 500,
  "global_step": 1577,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006337637645567614,
      "grad_norm": 1.6142889261245728,
      "learning_rate": 0.0002993658845909955,
      "loss": 2.409,
      "step": 10
    },
    {
      "epoch": 0.012675275291135229,
      "grad_norm": 0.3150716722011566,
      "learning_rate": 0.0002987317691819911,
      "loss": 0.3274,
      "step": 20
    },
    {
      "epoch": 0.019012912936702844,
      "grad_norm": 0.3215585947036743,
      "learning_rate": 0.00029809765377298664,
      "loss": 0.2974,
      "step": 30
    },
    {
      "epoch": 0.025350550582270457,
      "grad_norm": 0.3300665318965912,
      "learning_rate": 0.00029746353836398223,
      "loss": 0.2816,
      "step": 40
    },
    {
      "epoch": 0.031688188227838074,
      "grad_norm": 0.5483732223510742,
      "learning_rate": 0.0002968294229549778,
      "loss": 0.2657,
      "step": 50
    },
    {
      "epoch": 0.03802582587340569,
      "grad_norm": 0.5116819143295288,
      "learning_rate": 0.00029619530754597335,
      "loss": 0.255,
      "step": 60
    },
    {
      "epoch": 0.0443634635189733,
      "grad_norm": 0.36696526408195496,
      "learning_rate": 0.0002955611921369689,
      "loss": 0.2486,
      "step": 70
    },
    {
      "epoch": 0.050701101164540914,
      "grad_norm": 0.6022621393203735,
      "learning_rate": 0.0002949270767279645,
      "loss": 0.2637,
      "step": 80
    },
    {
      "epoch": 0.057038738810108534,
      "grad_norm": 0.542329728603363,
      "learning_rate": 0.00029429296131896,
      "loss": 0.2494,
      "step": 90
    },
    {
      "epoch": 0.06337637645567615,
      "grad_norm": 0.5944090485572815,
      "learning_rate": 0.00029365884590995555,
      "loss": 0.2339,
      "step": 100
    },
    {
      "epoch": 0.06971401410124377,
      "grad_norm": 0.3428844213485718,
      "learning_rate": 0.00029302473050095114,
      "loss": 0.2463,
      "step": 110
    },
    {
      "epoch": 0.07605165174681137,
      "grad_norm": 0.7415475845336914,
      "learning_rate": 0.00029239061509194673,
      "loss": 0.2291,
      "step": 120
    },
    {
      "epoch": 0.082389289392379,
      "grad_norm": 0.7960870862007141,
      "learning_rate": 0.00029175649968294227,
      "loss": 0.2414,
      "step": 130
    },
    {
      "epoch": 0.0887269270379466,
      "grad_norm": 0.36076226830482483,
      "learning_rate": 0.00029112238427393786,
      "loss": 0.2427,
      "step": 140
    },
    {
      "epoch": 0.09506456468351422,
      "grad_norm": 0.9236595034599304,
      "learning_rate": 0.0002904882688649334,
      "loss": 0.2407,
      "step": 150
    },
    {
      "epoch": 0.10140220232908183,
      "grad_norm": 0.5588239431381226,
      "learning_rate": 0.00028985415345592893,
      "loss": 0.2228,
      "step": 160
    },
    {
      "epoch": 0.10773983997464945,
      "grad_norm": 0.2992999255657196,
      "learning_rate": 0.0002892200380469245,
      "loss": 0.2234,
      "step": 170
    },
    {
      "epoch": 0.11407747762021707,
      "grad_norm": 0.4005465805530548,
      "learning_rate": 0.00028858592263792006,
      "loss": 0.2246,
      "step": 180
    },
    {
      "epoch": 0.12041511526578468,
      "grad_norm": 0.9351511001586914,
      "learning_rate": 0.0002879518072289156,
      "loss": 0.2345,
      "step": 190
    },
    {
      "epoch": 0.1267527529113523,
      "grad_norm": 0.856308102607727,
      "learning_rate": 0.0002873176918199112,
      "loss": 0.2174,
      "step": 200
    },
    {
      "epoch": 0.1330903905569199,
      "grad_norm": 0.6678782105445862,
      "learning_rate": 0.0002866835764109068,
      "loss": 0.2325,
      "step": 210
    },
    {
      "epoch": 0.13942802820248754,
      "grad_norm": 0.43734946846961975,
      "learning_rate": 0.0002860494610019023,
      "loss": 0.2287,
      "step": 220
    },
    {
      "epoch": 0.14576566584805514,
      "grad_norm": 0.3104623854160309,
      "learning_rate": 0.0002854153455928979,
      "loss": 0.2104,
      "step": 230
    },
    {
      "epoch": 0.15210330349362275,
      "grad_norm": 0.2922423183917999,
      "learning_rate": 0.00028478123018389344,
      "loss": 0.2252,
      "step": 240
    },
    {
      "epoch": 0.15844094113919036,
      "grad_norm": 0.6300675272941589,
      "learning_rate": 0.000284147114774889,
      "loss": 0.2139,
      "step": 250
    },
    {
      "epoch": 0.164778578784758,
      "grad_norm": 0.586909830570221,
      "learning_rate": 0.00028351299936588457,
      "loss": 0.2269,
      "step": 260
    },
    {
      "epoch": 0.1711162164303256,
      "grad_norm": 0.9171651601791382,
      "learning_rate": 0.00028287888395688016,
      "loss": 0.2191,
      "step": 270
    },
    {
      "epoch": 0.1774538540758932,
      "grad_norm": 0.6419245004653931,
      "learning_rate": 0.0002822447685478757,
      "loss": 0.2265,
      "step": 280
    },
    {
      "epoch": 0.18379149172146084,
      "grad_norm": 0.3004674017429352,
      "learning_rate": 0.00028161065313887123,
      "loss": 0.2115,
      "step": 290
    },
    {
      "epoch": 0.19012912936702844,
      "grad_norm": 0.5889032483100891,
      "learning_rate": 0.0002809765377298668,
      "loss": 0.2069,
      "step": 300
    },
    {
      "epoch": 0.19646676701259605,
      "grad_norm": 0.7706992626190186,
      "learning_rate": 0.00028034242232086236,
      "loss": 0.2231,
      "step": 310
    },
    {
      "epoch": 0.20280440465816366,
      "grad_norm": 0.45326951146125793,
      "learning_rate": 0.00027970830691185795,
      "loss": 0.224,
      "step": 320
    },
    {
      "epoch": 0.2091420423037313,
      "grad_norm": 0.7560727596282959,
      "learning_rate": 0.0002790741915028535,
      "loss": 0.2133,
      "step": 330
    },
    {
      "epoch": 0.2154796799492989,
      "grad_norm": 0.38263845443725586,
      "learning_rate": 0.000278440076093849,
      "loss": 0.2166,
      "step": 340
    },
    {
      "epoch": 0.2218173175948665,
      "grad_norm": 0.3568837344646454,
      "learning_rate": 0.0002778059606848446,
      "loss": 0.216,
      "step": 350
    },
    {
      "epoch": 0.22815495524043414,
      "grad_norm": 0.7373816967010498,
      "learning_rate": 0.0002771718452758402,
      "loss": 0.2145,
      "step": 360
    },
    {
      "epoch": 0.23449259288600174,
      "grad_norm": 0.6037229299545288,
      "learning_rate": 0.00027653772986683574,
      "loss": 0.2094,
      "step": 370
    },
    {
      "epoch": 0.24083023053156935,
      "grad_norm": 0.4252951741218567,
      "learning_rate": 0.00027590361445783133,
      "loss": 0.212,
      "step": 380
    },
    {
      "epoch": 0.24716786817713698,
      "grad_norm": 0.5818207263946533,
      "learning_rate": 0.00027526949904882686,
      "loss": 0.2159,
      "step": 390
    },
    {
      "epoch": 0.2535055058227046,
      "grad_norm": 0.7819476127624512,
      "learning_rate": 0.0002746353836398224,
      "loss": 0.2112,
      "step": 400
    },
    {
      "epoch": 0.2598431434682722,
      "grad_norm": 0.6650575399398804,
      "learning_rate": 0.000274001268230818,
      "loss": 0.2081,
      "step": 410
    },
    {
      "epoch": 0.2661807811138398,
      "grad_norm": 0.4109363555908203,
      "learning_rate": 0.0002733671528218136,
      "loss": 0.2029,
      "step": 420
    },
    {
      "epoch": 0.2725184187594074,
      "grad_norm": 0.4742489755153656,
      "learning_rate": 0.0002727330374128091,
      "loss": 0.2229,
      "step": 430
    },
    {
      "epoch": 0.2788560564049751,
      "grad_norm": 0.33365684747695923,
      "learning_rate": 0.00027209892200380465,
      "loss": 0.2053,
      "step": 440
    },
    {
      "epoch": 0.2851936940505427,
      "grad_norm": 0.7879284620285034,
      "learning_rate": 0.00027146480659480024,
      "loss": 0.2081,
      "step": 450
    },
    {
      "epoch": 0.2915313316961103,
      "grad_norm": 17.686824798583984,
      "learning_rate": 0.0002708306911857958,
      "loss": 0.3581,
      "step": 460
    },
    {
      "epoch": 0.2978689693416779,
      "grad_norm": 1.2470951080322266,
      "learning_rate": 0.00027019657577679137,
      "loss": 0.2365,
      "step": 470
    },
    {
      "epoch": 0.3042066069872455,
      "grad_norm": 0.5552864074707031,
      "learning_rate": 0.0002695624603677869,
      "loss": 0.2207,
      "step": 480
    },
    {
      "epoch": 0.3105442446328131,
      "grad_norm": 0.9645744562149048,
      "learning_rate": 0.00026892834495878244,
      "loss": 0.2117,
      "step": 490
    },
    {
      "epoch": 0.3168818822783807,
      "grad_norm": 0.5058091878890991,
      "learning_rate": 0.00026829422954977803,
      "loss": 0.207,
      "step": 500
    },
    {
      "epoch": 0.3232195199239484,
      "grad_norm": 0.537139892578125,
      "learning_rate": 0.0002676601141407736,
      "loss": 0.2079,
      "step": 510
    },
    {
      "epoch": 0.329557157569516,
      "grad_norm": 0.41485828161239624,
      "learning_rate": 0.00026702599873176916,
      "loss": 0.1947,
      "step": 520
    },
    {
      "epoch": 0.3358947952150836,
      "grad_norm": 0.5344266891479492,
      "learning_rate": 0.0002663918833227647,
      "loss": 0.2161,
      "step": 530
    },
    {
      "epoch": 0.3422324328606512,
      "grad_norm": 0.5433288812637329,
      "learning_rate": 0.0002657577679137603,
      "loss": 0.2084,
      "step": 540
    },
    {
      "epoch": 0.3485700705062188,
      "grad_norm": 0.3724132776260376,
      "learning_rate": 0.0002651236525047558,
      "loss": 0.1986,
      "step": 550
    },
    {
      "epoch": 0.3549077081517864,
      "grad_norm": 0.3660731613636017,
      "learning_rate": 0.0002644895370957514,
      "loss": 0.2035,
      "step": 560
    },
    {
      "epoch": 0.361245345797354,
      "grad_norm": 0.5768698453903198,
      "learning_rate": 0.00026385542168674695,
      "loss": 0.2073,
      "step": 570
    },
    {
      "epoch": 0.3675829834429217,
      "grad_norm": 0.305505633354187,
      "learning_rate": 0.00026322130627774254,
      "loss": 0.2027,
      "step": 580
    },
    {
      "epoch": 0.3739206210884893,
      "grad_norm": 0.5128267407417297,
      "learning_rate": 0.0002625871908687381,
      "loss": 0.207,
      "step": 590
    },
    {
      "epoch": 0.3802582587340569,
      "grad_norm": 0.4295850694179535,
      "learning_rate": 0.00026195307545973367,
      "loss": 0.2154,
      "step": 600
    },
    {
      "epoch": 0.3865958963796245,
      "grad_norm": 0.5752875208854675,
      "learning_rate": 0.0002613189600507292,
      "loss": 0.2044,
      "step": 610
    },
    {
      "epoch": 0.3929335340251921,
      "grad_norm": 0.32594314217567444,
      "learning_rate": 0.00026068484464172474,
      "loss": 0.1926,
      "step": 620
    },
    {
      "epoch": 0.3992711716707597,
      "grad_norm": 0.34995755553245544,
      "learning_rate": 0.00026005072923272033,
      "loss": 0.2024,
      "step": 630
    },
    {
      "epoch": 0.4056088093163273,
      "grad_norm": 0.30470767617225647,
      "learning_rate": 0.00025941661382371587,
      "loss": 0.204,
      "step": 640
    },
    {
      "epoch": 0.411946446961895,
      "grad_norm": 0.9187641739845276,
      "learning_rate": 0.00025878249841471146,
      "loss": 0.211,
      "step": 650
    },
    {
      "epoch": 0.4182840846074626,
      "grad_norm": 0.8582721948623657,
      "learning_rate": 0.00025814838300570705,
      "loss": 0.1983,
      "step": 660
    },
    {
      "epoch": 0.4246217222530302,
      "grad_norm": 0.6197007894515991,
      "learning_rate": 0.0002575142675967026,
      "loss": 0.1975,
      "step": 670
    },
    {
      "epoch": 0.4309593598985978,
      "grad_norm": 0.4113485515117645,
      "learning_rate": 0.0002568801521876981,
      "loss": 0.1993,
      "step": 680
    },
    {
      "epoch": 0.4372969975441654,
      "grad_norm": 0.3764086663722992,
      "learning_rate": 0.0002562460367786937,
      "loss": 0.1884,
      "step": 690
    },
    {
      "epoch": 0.443634635189733,
      "grad_norm": 0.6583007574081421,
      "learning_rate": 0.00025561192136968925,
      "loss": 0.2092,
      "step": 700
    },
    {
      "epoch": 0.44997227283530067,
      "grad_norm": 0.6544474959373474,
      "learning_rate": 0.00025497780596068484,
      "loss": 0.1997,
      "step": 710
    },
    {
      "epoch": 0.4563099104808683,
      "grad_norm": 0.3778369128704071,
      "learning_rate": 0.0002543436905516804,
      "loss": 0.2019,
      "step": 720
    },
    {
      "epoch": 0.4626475481264359,
      "grad_norm": 0.3147338032722473,
      "learning_rate": 0.00025370957514267596,
      "loss": 0.1899,
      "step": 730
    },
    {
      "epoch": 0.4689851857720035,
      "grad_norm": 0.4564040005207062,
      "learning_rate": 0.0002530754597336715,
      "loss": 0.2029,
      "step": 740
    },
    {
      "epoch": 0.4753228234175711,
      "grad_norm": 0.5435693860054016,
      "learning_rate": 0.0002524413443246671,
      "loss": 0.2057,
      "step": 750
    },
    {
      "epoch": 0.4816604610631387,
      "grad_norm": 0.34006282687187195,
      "learning_rate": 0.0002518072289156626,
      "loss": 0.1909,
      "step": 760
    },
    {
      "epoch": 0.4879980987087063,
      "grad_norm": 0.46839743852615356,
      "learning_rate": 0.00025117311350665816,
      "loss": 0.1996,
      "step": 770
    },
    {
      "epoch": 0.49433573635427397,
      "grad_norm": 0.3562382459640503,
      "learning_rate": 0.00025053899809765375,
      "loss": 0.1937,
      "step": 780
    },
    {
      "epoch": 0.5006733739998416,
      "grad_norm": 0.35229429602622986,
      "learning_rate": 0.0002499048826886493,
      "loss": 0.198,
      "step": 790
    },
    {
      "epoch": 0.5070110116454092,
      "grad_norm": 0.539817750453949,
      "learning_rate": 0.0002492707672796449,
      "loss": 0.1942,
      "step": 800
    },
    {
      "epoch": 0.5133486492909768,
      "grad_norm": 0.3757067322731018,
      "learning_rate": 0.00024863665187064047,
      "loss": 0.1966,
      "step": 810
    },
    {
      "epoch": 0.5196862869365444,
      "grad_norm": 0.5510461926460266,
      "learning_rate": 0.000248002536461636,
      "loss": 0.2021,
      "step": 820
    },
    {
      "epoch": 0.526023924582112,
      "grad_norm": 0.515483558177948,
      "learning_rate": 0.00024736842105263154,
      "loss": 0.2015,
      "step": 830
    },
    {
      "epoch": 0.5323615622276796,
      "grad_norm": 0.4190600514411926,
      "learning_rate": 0.00024673430564362713,
      "loss": 0.1822,
      "step": 840
    },
    {
      "epoch": 0.5386991998732472,
      "grad_norm": 0.7067417502403259,
      "learning_rate": 0.00024610019023462267,
      "loss": 0.201,
      "step": 850
    },
    {
      "epoch": 0.5450368375188148,
      "grad_norm": 0.4557970464229584,
      "learning_rate": 0.0002454660748256182,
      "loss": 0.1944,
      "step": 860
    },
    {
      "epoch": 0.5513744751643824,
      "grad_norm": 0.2890704274177551,
      "learning_rate": 0.0002448319594166138,
      "loss": 0.188,
      "step": 870
    },
    {
      "epoch": 0.5577121128099501,
      "grad_norm": 0.7139009237289429,
      "learning_rate": 0.0002441978440076094,
      "loss": 0.1894,
      "step": 880
    },
    {
      "epoch": 0.5640497504555178,
      "grad_norm": 0.46737805008888245,
      "learning_rate": 0.00024356372859860492,
      "loss": 0.1858,
      "step": 890
    },
    {
      "epoch": 0.5703873881010854,
      "grad_norm": 0.5491992235183716,
      "learning_rate": 0.0002429296131896005,
      "loss": 0.2049,
      "step": 900
    },
    {
      "epoch": 0.576725025746653,
      "grad_norm": 0.4642735719680786,
      "learning_rate": 0.00024229549778059605,
      "loss": 0.1963,
      "step": 910
    },
    {
      "epoch": 0.5830626633922206,
      "grad_norm": 0.3879190981388092,
      "learning_rate": 0.0002416613823715916,
      "loss": 0.1952,
      "step": 920
    },
    {
      "epoch": 0.5894003010377882,
      "grad_norm": 0.3346266746520996,
      "learning_rate": 0.00024102726696258715,
      "loss": 0.1921,
      "step": 930
    },
    {
      "epoch": 0.5957379386833558,
      "grad_norm": 0.49900051951408386,
      "learning_rate": 0.0002403931515535827,
      "loss": 0.1809,
      "step": 940
    },
    {
      "epoch": 0.6020755763289234,
      "grad_norm": 0.4249061644077301,
      "learning_rate": 0.00023975903614457828,
      "loss": 0.1865,
      "step": 950
    },
    {
      "epoch": 0.608413213974491,
      "grad_norm": 0.39760246872901917,
      "learning_rate": 0.00023912492073557387,
      "loss": 0.1914,
      "step": 960
    },
    {
      "epoch": 0.6147508516200586,
      "grad_norm": 0.4665059745311737,
      "learning_rate": 0.00023849080532656943,
      "loss": 0.1857,
      "step": 970
    },
    {
      "epoch": 0.6210884892656262,
      "grad_norm": 0.4482426047325134,
      "learning_rate": 0.00023785668991756497,
      "loss": 0.1904,
      "step": 980
    },
    {
      "epoch": 0.6274261269111938,
      "grad_norm": 0.5875295996665955,
      "learning_rate": 0.00023722257450856053,
      "loss": 0.1961,
      "step": 990
    },
    {
      "epoch": 0.6337637645567614,
      "grad_norm": 0.3540550768375397,
      "learning_rate": 0.0002365884590995561,
      "loss": 0.1894,
      "step": 1000
    },
    {
      "epoch": 0.640101402202329,
      "grad_norm": 0.39407670497894287,
      "learning_rate": 0.00023595434369055166,
      "loss": 0.1868,
      "step": 1010
    },
    {
      "epoch": 0.6464390398478967,
      "grad_norm": 0.3376408517360687,
      "learning_rate": 0.00023532022828154722,
      "loss": 0.1892,
      "step": 1020
    },
    {
      "epoch": 0.6527766774934644,
      "grad_norm": 0.347345769405365,
      "learning_rate": 0.0002346861128725428,
      "loss": 0.1873,
      "step": 1030
    },
    {
      "epoch": 0.659114315139032,
      "grad_norm": 0.3818947374820709,
      "learning_rate": 0.00023405199746353835,
      "loss": 0.1836,
      "step": 1040
    },
    {
      "epoch": 0.6654519527845996,
      "grad_norm": 0.36459505558013916,
      "learning_rate": 0.0002334178820545339,
      "loss": 0.1976,
      "step": 1050
    },
    {
      "epoch": 0.6717895904301672,
      "grad_norm": 0.4520089030265808,
      "learning_rate": 0.00023278376664552947,
      "loss": 0.1964,
      "step": 1060
    },
    {
      "epoch": 0.6781272280757348,
      "grad_norm": 0.5031911134719849,
      "learning_rate": 0.00023214965123652504,
      "loss": 0.1892,
      "step": 1070
    },
    {
      "epoch": 0.6844648657213024,
      "grad_norm": 0.7651061415672302,
      "learning_rate": 0.00023151553582752057,
      "loss": 0.186,
      "step": 1080
    },
    {
      "epoch": 0.69080250336687,
      "grad_norm": 0.49742498993873596,
      "learning_rate": 0.00023088142041851614,
      "loss": 0.1812,
      "step": 1090
    },
    {
      "epoch": 0.6971401410124376,
      "grad_norm": 0.4136335551738739,
      "learning_rate": 0.0002302473050095117,
      "loss": 0.1944,
      "step": 1100
    },
    {
      "epoch": 0.7034777786580052,
      "grad_norm": 0.32826468348503113,
      "learning_rate": 0.0002296131896005073,
      "loss": 0.1959,
      "step": 1110
    },
    {
      "epoch": 0.7098154163035728,
      "grad_norm": 0.4136222004890442,
      "learning_rate": 0.00022897907419150285,
      "loss": 0.1817,
      "step": 1120
    },
    {
      "epoch": 0.7161530539491404,
      "grad_norm": 0.3633563816547394,
      "learning_rate": 0.0002283449587824984,
      "loss": 0.1899,
      "step": 1130
    },
    {
      "epoch": 0.722490691594708,
      "grad_norm": 0.4116598963737488,
      "learning_rate": 0.00022771084337349395,
      "loss": 0.1883,
      "step": 1140
    },
    {
      "epoch": 0.7288283292402757,
      "grad_norm": 0.43437546491622925,
      "learning_rate": 0.00022707672796448952,
      "loss": 0.1891,
      "step": 1150
    },
    {
      "epoch": 0.7351659668858433,
      "grad_norm": 0.7089232206344604,
      "learning_rate": 0.00022644261255548508,
      "loss": 0.1774,
      "step": 1160
    },
    {
      "epoch": 0.741503604531411,
      "grad_norm": 0.30157792568206787,
      "learning_rate": 0.00022580849714648062,
      "loss": 0.1912,
      "step": 1170
    },
    {
      "epoch": 0.7478412421769786,
      "grad_norm": 0.4012957215309143,
      "learning_rate": 0.0002251743817374762,
      "loss": 0.1821,
      "step": 1180
    },
    {
      "epoch": 0.7541788798225462,
      "grad_norm": 0.5319772958755493,
      "learning_rate": 0.00022454026632847177,
      "loss": 0.1748,
      "step": 1190
    },
    {
      "epoch": 0.7605165174681138,
      "grad_norm": 0.34556815028190613,
      "learning_rate": 0.00022390615091946733,
      "loss": 0.1946,
      "step": 1200
    },
    {
      "epoch": 0.7668541551136814,
      "grad_norm": 0.43295615911483765,
      "learning_rate": 0.0002232720355104629,
      "loss": 0.1799,
      "step": 1210
    },
    {
      "epoch": 0.773191792759249,
      "grad_norm": 0.3238721787929535,
      "learning_rate": 0.00022263792010145843,
      "loss": 0.1912,
      "step": 1220
    },
    {
      "epoch": 0.7795294304048166,
      "grad_norm": 0.39405253529548645,
      "learning_rate": 0.000222003804692454,
      "loss": 0.1902,
      "step": 1230
    },
    {
      "epoch": 0.7858670680503842,
      "grad_norm": 0.35559186339378357,
      "learning_rate": 0.00022136968928344956,
      "loss": 0.1756,
      "step": 1240
    },
    {
      "epoch": 0.7922047056959518,
      "grad_norm": 0.31320518255233765,
      "learning_rate": 0.00022073557387444512,
      "loss": 0.1948,
      "step": 1250
    },
    {
      "epoch": 0.7985423433415194,
      "grad_norm": 0.3586606979370117,
      "learning_rate": 0.0002201014584654407,
      "loss": 0.1768,
      "step": 1260
    },
    {
      "epoch": 0.804879980987087,
      "grad_norm": 0.37648022174835205,
      "learning_rate": 0.00021946734305643625,
      "loss": 0.1763,
      "step": 1270
    },
    {
      "epoch": 0.8112176186326546,
      "grad_norm": 0.4442378282546997,
      "learning_rate": 0.0002188332276474318,
      "loss": 0.1694,
      "step": 1280
    },
    {
      "epoch": 0.8175552562782223,
      "grad_norm": 0.5687398314476013,
      "learning_rate": 0.00021819911223842738,
      "loss": 0.1856,
      "step": 1290
    },
    {
      "epoch": 0.82389289392379,
      "grad_norm": 0.3056432008743286,
      "learning_rate": 0.00021756499682942294,
      "loss": 0.1847,
      "step": 1300
    },
    {
      "epoch": 0.8302305315693576,
      "grad_norm": 0.42267075181007385,
      "learning_rate": 0.0002169308814204185,
      "loss": 0.1889,
      "step": 1310
    },
    {
      "epoch": 0.8365681692149252,
      "grad_norm": 0.320975661277771,
      "learning_rate": 0.00021629676601141404,
      "loss": 0.187,
      "step": 1320
    },
    {
      "epoch": 0.8429058068604928,
      "grad_norm": 0.6148353815078735,
      "learning_rate": 0.0002156626506024096,
      "loss": 0.1748,
      "step": 1330
    },
    {
      "epoch": 0.8492434445060604,
      "grad_norm": 0.6128231883049011,
      "learning_rate": 0.0002150285351934052,
      "loss": 0.1797,
      "step": 1340
    },
    {
      "epoch": 0.855581082151628,
      "grad_norm": 0.32467806339263916,
      "learning_rate": 0.00021439441978440076,
      "loss": 0.1713,
      "step": 1350
    },
    {
      "epoch": 0.8619187197971956,
      "grad_norm": 0.34791630506515503,
      "learning_rate": 0.00021376030437539632,
      "loss": 0.1716,
      "step": 1360
    },
    {
      "epoch": 0.8682563574427632,
      "grad_norm": 0.36184781789779663,
      "learning_rate": 0.00021312618896639186,
      "loss": 0.1817,
      "step": 1370
    },
    {
      "epoch": 0.8745939950883308,
      "grad_norm": 0.2984809875488281,
      "learning_rate": 0.00021249207355738742,
      "loss": 0.1925,
      "step": 1380
    },
    {
      "epoch": 0.8809316327338984,
      "grad_norm": 0.3217010498046875,
      "learning_rate": 0.00021185795814838298,
      "loss": 0.1884,
      "step": 1390
    },
    {
      "epoch": 0.887269270379466,
      "grad_norm": 0.32817527651786804,
      "learning_rate": 0.00021122384273937855,
      "loss": 0.1797,
      "step": 1400
    },
    {
      "epoch": 0.8936069080250336,
      "grad_norm": 0.3350455164909363,
      "learning_rate": 0.00021058972733037414,
      "loss": 0.1746,
      "step": 1410
    },
    {
      "epoch": 0.8999445456706013,
      "grad_norm": 0.3384022116661072,
      "learning_rate": 0.00020995561192136967,
      "loss": 0.1796,
      "step": 1420
    },
    {
      "epoch": 0.9062821833161689,
      "grad_norm": 0.37266311049461365,
      "learning_rate": 0.00020932149651236524,
      "loss": 0.1798,
      "step": 1430
    },
    {
      "epoch": 0.9126198209617365,
      "grad_norm": 0.3353017270565033,
      "learning_rate": 0.0002086873811033608,
      "loss": 0.1824,
      "step": 1440
    },
    {
      "epoch": 0.9189574586073042,
      "grad_norm": 0.4691619277000427,
      "learning_rate": 0.00020805326569435636,
      "loss": 0.1722,
      "step": 1450
    },
    {
      "epoch": 0.9252950962528718,
      "grad_norm": 0.5046979784965515,
      "learning_rate": 0.0002074191502853519,
      "loss": 0.182,
      "step": 1460
    },
    {
      "epoch": 0.9316327338984394,
      "grad_norm": 0.43848350644111633,
      "learning_rate": 0.00020678503487634746,
      "loss": 0.1795,
      "step": 1470
    },
    {
      "epoch": 0.937970371544007,
      "grad_norm": 0.36225542426109314,
      "learning_rate": 0.00020615091946734303,
      "loss": 0.1834,
      "step": 1480
    },
    {
      "epoch": 0.9443080091895746,
      "grad_norm": 0.34802907705307007,
      "learning_rate": 0.00020551680405833862,
      "loss": 0.1809,
      "step": 1490
    },
    {
      "epoch": 0.9506456468351422,
      "grad_norm": 0.6984723806381226,
      "learning_rate": 0.00020488268864933418,
      "loss": 0.1767,
      "step": 1500
    },
    {
      "epoch": 0.9569832844807098,
      "grad_norm": 0.32185426354408264,
      "learning_rate": 0.00020424857324032972,
      "loss": 0.1801,
      "step": 1510
    },
    {
      "epoch": 0.9633209221262774,
      "grad_norm": 0.3562312424182892,
      "learning_rate": 0.00020361445783132528,
      "loss": 0.1962,
      "step": 1520
    },
    {
      "epoch": 0.969658559771845,
      "grad_norm": 0.4363330006599426,
      "learning_rate": 0.00020298034242232084,
      "loss": 0.1785,
      "step": 1530
    },
    {
      "epoch": 0.9759961974174126,
      "grad_norm": 0.3066689670085907,
      "learning_rate": 0.0002023462270133164,
      "loss": 0.1762,
      "step": 1540
    },
    {
      "epoch": 0.9823338350629802,
      "grad_norm": 0.3895578980445862,
      "learning_rate": 0.00020171211160431194,
      "loss": 0.1701,
      "step": 1550
    },
    {
      "epoch": 0.9886714727085479,
      "grad_norm": 0.3306889832019806,
      "learning_rate": 0.00020107799619530753,
      "loss": 0.1781,
      "step": 1560
    },
    {
      "epoch": 0.9950091103541155,
      "grad_norm": 0.40368223190307617,
      "learning_rate": 0.0002004438807863031,
      "loss": 0.1815,
      "step": 1570
    }
  ],
  "logging_steps": 10,
  "max_steps": 4731,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8508092447949062e+19,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}