{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.19986437774367394,
  "eval_steps": 500,
  "global_step": 1400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014276026981690996,
      "grad_norm": 1.2670224905014038,
      "learning_rate": 0.00016,
      "loss": 2.898906135559082,
      "step": 10
    },
    {
      "epoch": 0.0028552053963381992,
      "grad_norm": 1.2538419961929321,
      "learning_rate": 0.00019992382766008095,
      "loss": 2.378516960144043,
      "step": 20
    },
    {
      "epoch": 0.004282808094507299,
      "grad_norm": 1.409246563911438,
      "learning_rate": 0.0001998286122351821,
      "loss": 2.4753650665283202,
      "step": 30
    },
    {
      "epoch": 0.0057104107926763984,
      "grad_norm": 1.094603180885315,
      "learning_rate": 0.00019973339681028326,
      "loss": 2.2721933364868163,
      "step": 40
    },
    {
      "epoch": 0.007138013490845497,
      "grad_norm": 1.1403776407241821,
      "learning_rate": 0.00019963818138538444,
      "loss": 2.263425827026367,
      "step": 50
    },
    {
      "epoch": 0.008565616189014597,
      "grad_norm": 1.1656428575515747,
      "learning_rate": 0.0001995429659604856,
      "loss": 2.363163185119629,
      "step": 60
    },
    {
      "epoch": 0.009993218887183696,
      "grad_norm": 1.1926625967025757,
      "learning_rate": 0.00019944775053558678,
      "loss": 2.1333871841430665,
      "step": 70
    },
    {
      "epoch": 0.011420821585352797,
      "grad_norm": 0.9967195391654968,
      "learning_rate": 0.00019935253511068794,
      "loss": 2.279196929931641,
      "step": 80
    },
    {
      "epoch": 0.012848424283521896,
      "grad_norm": 1.1345535516738892,
      "learning_rate": 0.00019925731968578912,
      "loss": 2.181261444091797,
      "step": 90
    },
    {
      "epoch": 0.014276026981690995,
      "grad_norm": 1.2285407781600952,
      "learning_rate": 0.00019916210426089027,
      "loss": 2.2282310485839845,
      "step": 100
    },
    {
      "epoch": 0.015703629679860096,
      "grad_norm": 2.191948890686035,
      "learning_rate": 0.00019906688883599146,
      "loss": 2.2829305648803713,
      "step": 110
    },
    {
      "epoch": 0.017131232378029194,
      "grad_norm": 1.1868839263916016,
      "learning_rate": 0.00019897167341109258,
      "loss": 2.1634748458862303,
      "step": 120
    },
    {
      "epoch": 0.018558835076198293,
      "grad_norm": 1.3730543851852417,
      "learning_rate": 0.00019887645798619377,
      "loss": 2.235073471069336,
      "step": 130
    },
    {
      "epoch": 0.019986437774367392,
      "grad_norm": 1.3060146570205688,
      "learning_rate": 0.00019878124256129492,
      "loss": 2.254693031311035,
      "step": 140
    },
    {
      "epoch": 0.021414040472536495,
      "grad_norm": 1.13761305809021,
      "learning_rate": 0.0001986860271363961,
      "loss": 2.255308723449707,
      "step": 150
    },
    {
      "epoch": 0.022841643170705594,
      "grad_norm": 1.2420964241027832,
      "learning_rate": 0.00019859081171149726,
      "loss": 2.199342155456543,
      "step": 160
    },
    {
      "epoch": 0.024269245868874693,
      "grad_norm": 1.2628268003463745,
      "learning_rate": 0.00019849559628659844,
      "loss": 2.2568809509277346,
      "step": 170
    },
    {
      "epoch": 0.02569684856704379,
      "grad_norm": 1.0423402786254883,
      "learning_rate": 0.0001984003808616996,
      "loss": 2.201403045654297,
      "step": 180
    },
    {
      "epoch": 0.02712445126521289,
      "grad_norm": 1.3187193870544434,
      "learning_rate": 0.00019830516543680078,
      "loss": 2.31024055480957,
      "step": 190
    },
    {
      "epoch": 0.02855205396338199,
      "grad_norm": 1.287013292312622,
      "learning_rate": 0.00019820995001190194,
      "loss": 2.2775556564331056,
      "step": 200
    },
    {
      "epoch": 0.029979656661551092,
      "grad_norm": 1.445034384727478,
      "learning_rate": 0.00019811473458700312,
      "loss": 2.214271354675293,
      "step": 210
    },
    {
      "epoch": 0.03140725935972019,
      "grad_norm": 1.4336904287338257,
      "learning_rate": 0.00019801951916210427,
      "loss": 2.1211181640625,
      "step": 220
    },
    {
      "epoch": 0.03283486205788929,
      "grad_norm": 1.303303837776184,
      "learning_rate": 0.00019792430373720543,
      "loss": 2.1037008285522463,
      "step": 230
    },
    {
      "epoch": 0.03426246475605839,
      "grad_norm": 1.2367061376571655,
      "learning_rate": 0.0001978290883123066,
      "loss": 2.1291038513183596,
      "step": 240
    },
    {
      "epoch": 0.03569006745422749,
      "grad_norm": 1.314647912979126,
      "learning_rate": 0.00019773387288740777,
      "loss": 2.1351301193237306,
      "step": 250
    },
    {
      "epoch": 0.03711767015239659,
      "grad_norm": 1.3084362745285034,
      "learning_rate": 0.00019763865746250895,
      "loss": 2.0980342864990233,
      "step": 260
    },
    {
      "epoch": 0.038545272850565686,
      "grad_norm": 1.712534785270691,
      "learning_rate": 0.0001975434420376101,
      "loss": 2.25567569732666,
      "step": 270
    },
    {
      "epoch": 0.039972875548734785,
      "grad_norm": 1.5107096433639526,
      "learning_rate": 0.0001974482266127113,
      "loss": 2.198653793334961,
      "step": 280
    },
    {
      "epoch": 0.041400478246903884,
      "grad_norm": 1.1626437902450562,
      "learning_rate": 0.00019735301118781244,
      "loss": 2.136816215515137,
      "step": 290
    },
    {
      "epoch": 0.04282808094507299,
      "grad_norm": 1.551853060722351,
      "learning_rate": 0.00019725779576291362,
      "loss": 2.2106935501098635,
      "step": 300
    },
    {
      "epoch": 0.04425568364324209,
      "grad_norm": 1.5131734609603882,
      "learning_rate": 0.00019716258033801475,
      "loss": 2.0967830657958983,
      "step": 310
    },
    {
      "epoch": 0.04568328634141119,
      "grad_norm": 1.310641884803772,
      "learning_rate": 0.00019706736491311593,
      "loss": 2.2105255126953125,
      "step": 320
    },
    {
      "epoch": 0.047110889039580287,
      "grad_norm": 1.3621881008148193,
      "learning_rate": 0.0001969721494882171,
      "loss": 2.1775463104248045,
      "step": 330
    },
    {
      "epoch": 0.048538491737749385,
      "grad_norm": 1.4618415832519531,
      "learning_rate": 0.00019687693406331827,
      "loss": 2.148931694030762,
      "step": 340
    },
    {
      "epoch": 0.049966094435918484,
      "grad_norm": 1.3173977136611938,
      "learning_rate": 0.00019678171863841943,
      "loss": 2.1974794387817385,
      "step": 350
    },
    {
      "epoch": 0.05139369713408758,
      "grad_norm": 1.1830055713653564,
      "learning_rate": 0.0001966865032135206,
      "loss": 2.1695978164672853,
      "step": 360
    },
    {
      "epoch": 0.05282129983225668,
      "grad_norm": 1.1831724643707275,
      "learning_rate": 0.00019659128778862177,
      "loss": 2.0823343276977537,
      "step": 370
    },
    {
      "epoch": 0.05424890253042578,
      "grad_norm": 1.1693743467330933,
      "learning_rate": 0.00019649607236372295,
      "loss": 2.1867488861083983,
      "step": 380
    },
    {
      "epoch": 0.05567650522859488,
      "grad_norm": 1.25830078125,
      "learning_rate": 0.0001964008569388241,
      "loss": 2.2133615493774412,
      "step": 390
    },
    {
      "epoch": 0.05710410792676398,
      "grad_norm": 1.3678141832351685,
      "learning_rate": 0.00019630564151392529,
      "loss": 2.308313751220703,
      "step": 400
    },
    {
      "epoch": 0.05853171062493308,
      "grad_norm": 1.1440492868423462,
      "learning_rate": 0.00019621042608902641,
      "loss": 2.1140726089477537,
      "step": 410
    },
    {
      "epoch": 0.059959313323102184,
      "grad_norm": 1.1869196891784668,
      "learning_rate": 0.0001961152106641276,
      "loss": 2.0346582412719725,
      "step": 420
    },
    {
      "epoch": 0.06138691602127128,
      "grad_norm": 1.4892522096633911,
      "learning_rate": 0.00019601999523922875,
      "loss": 2.2025136947631836,
      "step": 430
    },
    {
      "epoch": 0.06281451871944038,
      "grad_norm": 1.8906227350234985,
      "learning_rate": 0.00019592477981432993,
      "loss": 2.297587776184082,
      "step": 440
    },
    {
      "epoch": 0.06424212141760947,
      "grad_norm": 1.2389851808547974,
      "learning_rate": 0.0001958295643894311,
      "loss": 2.130488395690918,
      "step": 450
    },
    {
      "epoch": 0.06566972411577858,
      "grad_norm": 1.425410509109497,
      "learning_rate": 0.00019573434896453227,
      "loss": 2.144012451171875,
      "step": 460
    },
    {
      "epoch": 0.06709732681394767,
      "grad_norm": 1.3087464570999146,
      "learning_rate": 0.00019563913353963343,
      "loss": 2.2011600494384767,
      "step": 470
    },
    {
      "epoch": 0.06852492951211678,
      "grad_norm": 1.3441588878631592,
      "learning_rate": 0.0001955439181147346,
      "loss": 2.291761016845703,
      "step": 480
    },
    {
      "epoch": 0.06995253221028588,
      "grad_norm": 1.2851412296295166,
      "learning_rate": 0.00019544870268983577,
      "loss": 2.24096622467041,
      "step": 490
    },
    {
      "epoch": 0.07138013490845498,
      "grad_norm": 1.2628257274627686,
      "learning_rate": 0.00019535348726493692,
      "loss": 2.080752944946289,
      "step": 500
    },
    {
      "epoch": 0.07280773760662408,
      "grad_norm": 1.2638740539550781,
      "learning_rate": 0.00019525827184003808,
      "loss": 2.4698177337646485,
      "step": 510
    },
    {
      "epoch": 0.07423534030479317,
      "grad_norm": 1.2560440301895142,
      "learning_rate": 0.00019516305641513926,
      "loss": 2.132457733154297,
      "step": 520
    },
    {
      "epoch": 0.07566294300296228,
      "grad_norm": 1.7629936933517456,
      "learning_rate": 0.0001950678409902404,
      "loss": 2.166901969909668,
      "step": 530
    },
    {
      "epoch": 0.07709054570113137,
      "grad_norm": 1.8175091743469238,
      "learning_rate": 0.0001949726255653416,
      "loss": 2.1663414001464845,
      "step": 540
    },
    {
      "epoch": 0.07851814839930048,
      "grad_norm": 1.1744414567947388,
      "learning_rate": 0.00019487741014044275,
      "loss": 2.388395309448242,
      "step": 550
    },
    {
      "epoch": 0.07994575109746957,
      "grad_norm": 0.9943644404411316,
      "learning_rate": 0.00019478219471554393,
      "loss": 2.1379253387451174,
      "step": 560
    },
    {
      "epoch": 0.08137335379563868,
      "grad_norm": 1.2485833168029785,
      "learning_rate": 0.0001946869792906451,
      "loss": 2.1750890731811525,
      "step": 570
    },
    {
      "epoch": 0.08280095649380777,
      "grad_norm": 1.0852699279785156,
      "learning_rate": 0.00019459176386574627,
      "loss": 2.2631216049194336,
      "step": 580
    },
    {
      "epoch": 0.08422855919197687,
      "grad_norm": 1.5462923049926758,
      "learning_rate": 0.00019449654844084743,
      "loss": 2.2366138458251954,
      "step": 590
    },
    {
      "epoch": 0.08565616189014598,
      "grad_norm": 1.2923717498779297,
      "learning_rate": 0.00019440133301594858,
      "loss": 2.1567543029785154,
      "step": 600
    },
    {
      "epoch": 0.08708376458831507,
      "grad_norm": 1.3011770248413086,
      "learning_rate": 0.00019430611759104976,
      "loss": 2.1422496795654298,
      "step": 610
    },
    {
      "epoch": 0.08851136728648418,
      "grad_norm": 1.4617754220962524,
      "learning_rate": 0.00019421090216615092,
      "loss": 2.1605356216430662,
      "step": 620
    },
    {
      "epoch": 0.08993896998465327,
      "grad_norm": 1.5295599699020386,
      "learning_rate": 0.0001941156867412521,
      "loss": 2.0025182723999024,
      "step": 630
    },
    {
      "epoch": 0.09136657268282238,
      "grad_norm": 1.3012663125991821,
      "learning_rate": 0.00019402047131635326,
      "loss": 2.1372703552246093,
      "step": 640
    },
    {
      "epoch": 0.09279417538099147,
      "grad_norm": 1.4276515245437622,
      "learning_rate": 0.00019392525589145444,
      "loss": 2.315623474121094,
      "step": 650
    },
    {
      "epoch": 0.09422177807916057,
      "grad_norm": 1.5132569074630737,
      "learning_rate": 0.0001938300404665556,
      "loss": 2.258671760559082,
      "step": 660
    },
    {
      "epoch": 0.09564938077732967,
      "grad_norm": 1.1320735216140747,
      "learning_rate": 0.00019373482504165678,
      "loss": 2.21956844329834,
      "step": 670
    },
    {
      "epoch": 0.09707698347549877,
      "grad_norm": 1.1464308500289917,
      "learning_rate": 0.00019363960961675793,
      "loss": 2.173979949951172,
      "step": 680
    },
    {
      "epoch": 0.09850458617366786,
      "grad_norm": 1.2780959606170654,
      "learning_rate": 0.0001935443941918591,
      "loss": 2.159123992919922,
      "step": 690
    },
    {
      "epoch": 0.09993218887183697,
      "grad_norm": 1.3222688436508179,
      "learning_rate": 0.00019344917876696024,
      "loss": 2.1596654891967773,
      "step": 700
    },
    {
      "epoch": 0.10135979157000606,
      "grad_norm": 1.2251396179199219,
      "learning_rate": 0.00019335396334206143,
      "loss": 2.0882038116455077,
      "step": 710
    },
    {
      "epoch": 0.10278739426817517,
      "grad_norm": 1.2655571699142456,
      "learning_rate": 0.00019325874791716258,
      "loss": 2.1701095581054686,
      "step": 720
    },
    {
      "epoch": 0.10421499696634427,
      "grad_norm": 1.3139557838439941,
      "learning_rate": 0.00019316353249226376,
      "loss": 2.1374244689941406,
      "step": 730
    },
    {
      "epoch": 0.10564259966451336,
      "grad_norm": 0.9476764798164368,
      "learning_rate": 0.00019306831706736492,
      "loss": 2.131810760498047,
      "step": 740
    },
    {
      "epoch": 0.10707020236268247,
      "grad_norm": 1.3916528224945068,
      "learning_rate": 0.0001929731016424661,
      "loss": 2.2276470184326174,
      "step": 750
    },
    {
      "epoch": 0.10849780506085156,
      "grad_norm": 1.2913047075271606,
      "learning_rate": 0.00019287788621756726,
      "loss": 2.0985342025756837,
      "step": 760
    },
    {
      "epoch": 0.10992540775902067,
      "grad_norm": 1.4780009984970093,
      "learning_rate": 0.00019278267079266844,
      "loss": 2.3402137756347656,
      "step": 770
    },
    {
      "epoch": 0.11135301045718976,
      "grad_norm": 1.38652765750885,
      "learning_rate": 0.0001926874553677696,
      "loss": 2.1956760406494142,
      "step": 780
    },
    {
      "epoch": 0.11278061315535887,
      "grad_norm": 1.2437113523483276,
      "learning_rate": 0.00019259223994287075,
      "loss": 2.344030570983887,
      "step": 790
    },
    {
      "epoch": 0.11420821585352796,
      "grad_norm": 1.1223382949829102,
      "learning_rate": 0.0001924970245179719,
      "loss": 2.245418167114258,
      "step": 800
    },
    {
      "epoch": 0.11563581855169706,
      "grad_norm": 1.5828821659088135,
      "learning_rate": 0.0001924018090930731,
      "loss": 2.2958986282348635,
      "step": 810
    },
    {
      "epoch": 0.11706342124986616,
      "grad_norm": 1.1058349609375,
      "learning_rate": 0.00019230659366817424,
      "loss": 2.0216651916503907,
      "step": 820
    },
    {
      "epoch": 0.11849102394803526,
      "grad_norm": 1.1991469860076904,
      "learning_rate": 0.00019221137824327543,
      "loss": 2.1821861267089844,
      "step": 830
    },
    {
      "epoch": 0.11991862664620437,
      "grad_norm": 1.0211104154586792,
      "learning_rate": 0.00019211616281837658,
      "loss": 2.1515743255615236,
      "step": 840
    },
    {
      "epoch": 0.12134622934437346,
      "grad_norm": 1.163668155670166,
      "learning_rate": 0.00019202094739347776,
      "loss": 2.0592647552490235,
      "step": 850
    },
    {
      "epoch": 0.12277383204254257,
      "grad_norm": 1.0804855823516846,
      "learning_rate": 0.00019192573196857892,
      "loss": 2.0916107177734373,
      "step": 860
    },
    {
      "epoch": 0.12420143474071166,
      "grad_norm": 1.2400697469711304,
      "learning_rate": 0.0001918305165436801,
      "loss": 2.0994134902954102,
      "step": 870
    },
    {
      "epoch": 0.12562903743888076,
      "grad_norm": 1.3643152713775635,
      "learning_rate": 0.00019173530111878123,
      "loss": 2.2519294738769533,
      "step": 880
    },
    {
      "epoch": 0.12705664013704987,
      "grad_norm": 1.3758548498153687,
      "learning_rate": 0.0001916400856938824,
      "loss": 2.22522029876709,
      "step": 890
    },
    {
      "epoch": 0.12848424283521895,
      "grad_norm": 1.1675829887390137,
      "learning_rate": 0.00019154487026898357,
      "loss": 2.1150989532470703,
      "step": 900
    },
    {
      "epoch": 0.12991184553338805,
      "grad_norm": 1.2862130403518677,
      "learning_rate": 0.00019144965484408475,
      "loss": 2.289804458618164,
      "step": 910
    },
    {
      "epoch": 0.13133944823155716,
      "grad_norm": 1.271008849143982,
      "learning_rate": 0.0001913639609616758,
      "loss": 2.1846010208129885,
      "step": 920
    },
    {
      "epoch": 0.13276705092972627,
      "grad_norm": 1.1630209684371948,
      "learning_rate": 0.00019126874553677695,
      "loss": 2.2126953125,
      "step": 930
    },
    {
      "epoch": 0.13419465362789534,
      "grad_norm": 1.1368460655212402,
      "learning_rate": 0.00019117353011187813,
      "loss": 2.178596305847168,
      "step": 940
    },
    {
      "epoch": 0.13562225632606445,
      "grad_norm": 1.0295072793960571,
      "learning_rate": 0.0001910783146869793,
      "loss": 2.2031627655029298,
      "step": 950
    },
    {
      "epoch": 0.13704985902423356,
      "grad_norm": 1.379927396774292,
      "learning_rate": 0.00019098309926208047,
      "loss": 2.120400619506836,
      "step": 960
    },
    {
      "epoch": 0.13847746172240266,
      "grad_norm": 1.1450871229171753,
      "learning_rate": 0.00019088788383718163,
      "loss": 2.151012992858887,
      "step": 970
    },
    {
      "epoch": 0.13990506442057177,
      "grad_norm": 1.0418351888656616,
      "learning_rate": 0.0001907926684122828,
      "loss": 2.1239688873291014,
      "step": 980
    },
    {
      "epoch": 0.14133266711874085,
      "grad_norm": 1.0744861364364624,
      "learning_rate": 0.00019069745298738397,
      "loss": 2.090304374694824,
      "step": 990
    },
    {
      "epoch": 0.14276026981690995,
      "grad_norm": 1.1106981039047241,
      "learning_rate": 0.00019060223756248515,
      "loss": 2.225258636474609,
      "step": 1000
    },
    {
      "epoch": 0.14418787251507906,
      "grad_norm": 1.4493266344070435,
      "learning_rate": 0.00019050702213758628,
      "loss": 2.0656681060791016,
      "step": 1010
    },
    {
      "epoch": 0.14561547521324816,
      "grad_norm": 1.1414896249771118,
      "learning_rate": 0.00019041180671268746,
      "loss": 2.103784942626953,
      "step": 1020
    },
    {
      "epoch": 0.14704307791141724,
      "grad_norm": 1.3252989053726196,
      "learning_rate": 0.00019031659128778861,
      "loss": 2.2042461395263673,
      "step": 1030
    },
    {
      "epoch": 0.14847068060958635,
      "grad_norm": 1.265684962272644,
      "learning_rate": 0.0001902213758628898,
      "loss": 1.9412918090820312,
      "step": 1040
    },
    {
      "epoch": 0.14989828330775545,
      "grad_norm": 1.3606458902359009,
      "learning_rate": 0.00019012616043799095,
      "loss": 2.187259292602539,
      "step": 1050
    },
    {
      "epoch": 0.15132588600592456,
      "grad_norm": 1.0192638635635376,
      "learning_rate": 0.00019003094501309213,
      "loss": 2.182966423034668,
      "step": 1060
    },
    {
      "epoch": 0.15275348870409364,
      "grad_norm": 1.5140159130096436,
      "learning_rate": 0.0001899357295881933,
      "loss": 2.3263607025146484,
      "step": 1070
    },
    {
      "epoch": 0.15418109140226274,
      "grad_norm": 1.1377187967300415,
      "learning_rate": 0.00018984051416329447,
      "loss": 2.159488868713379,
      "step": 1080
    },
    {
      "epoch": 0.15560869410043185,
      "grad_norm": 1.1288865804672241,
      "learning_rate": 0.00018974529873839563,
      "loss": 2.306215286254883,
      "step": 1090
    },
    {
      "epoch": 0.15703629679860096,
      "grad_norm": 1.280045747756958,
      "learning_rate": 0.00018965008331349678,
      "loss": 2.225907897949219,
      "step": 1100
    },
    {
      "epoch": 0.15846389949677006,
      "grad_norm": 1.145614743232727,
      "learning_rate": 0.00018955486788859797,
      "loss": 2.1122207641601562,
      "step": 1110
    },
    {
      "epoch": 0.15989150219493914,
      "grad_norm": 1.1612759828567505,
      "learning_rate": 0.00018945965246369912,
      "loss": 2.2271358489990236,
      "step": 1120
    },
    {
      "epoch": 0.16131910489310824,
      "grad_norm": 1.0958333015441895,
      "learning_rate": 0.0001893644370388003,
      "loss": 2.088473320007324,
      "step": 1130
    },
    {
      "epoch": 0.16274670759127735,
      "grad_norm": 1.1749203205108643,
      "learning_rate": 0.00018926922161390146,
      "loss": 2.091511917114258,
      "step": 1140
    },
    {
      "epoch": 0.16417431028944646,
      "grad_norm": 1.1318912506103516,
      "learning_rate": 0.00018917400618900264,
      "loss": 2.2805349349975588,
      "step": 1150
    },
    {
      "epoch": 0.16560191298761553,
      "grad_norm": 1.220713496208191,
      "learning_rate": 0.0001890787907641038,
      "loss": 2.129801940917969,
      "step": 1160
    },
    {
      "epoch": 0.16702951568578464,
      "grad_norm": 1.0876924991607666,
      "learning_rate": 0.00018898357533920498,
      "loss": 2.0997352600097656,
      "step": 1170
    },
    {
      "epoch": 0.16845711838395375,
      "grad_norm": 1.175884485244751,
      "learning_rate": 0.00018888835991430613,
      "loss": 2.0686941146850586,
      "step": 1180
    },
    {
      "epoch": 0.16988472108212285,
      "grad_norm": 1.3588541746139526,
      "learning_rate": 0.00018879314448940732,
      "loss": 2.2050849914550783,
      "step": 1190
    },
    {
      "epoch": 0.17131232378029196,
      "grad_norm": 1.26045560836792,
      "learning_rate": 0.00018869792906450844,
      "loss": 2.1561567306518556,
      "step": 1200
    },
    {
      "epoch": 0.17273992647846104,
      "grad_norm": 1.0756542682647705,
      "learning_rate": 0.00018860271363960963,
      "loss": 2.163359832763672,
      "step": 1210
    },
    {
      "epoch": 0.17416752917663014,
      "grad_norm": 1.308608055114746,
      "learning_rate": 0.00018850749821471078,
      "loss": 2.209610366821289,
      "step": 1220
    },
    {
      "epoch": 0.17559513187479925,
      "grad_norm": 1.369969129562378,
      "learning_rate": 0.00018841228278981196,
      "loss": 2.3173370361328125,
      "step": 1230
    },
    {
      "epoch": 0.17702273457296835,
      "grad_norm": 1.2242190837860107,
      "learning_rate": 0.00018831706736491312,
      "loss": 2.149942398071289,
      "step": 1240
    },
    {
      "epoch": 0.17845033727113743,
      "grad_norm": 1.226375937461853,
      "learning_rate": 0.0001882218519400143,
      "loss": 2.152383232116699,
      "step": 1250
    },
    {
      "epoch": 0.17987793996930654,
      "grad_norm": 2.0897111892700195,
      "learning_rate": 0.00018812663651511546,
      "loss": 2.070216751098633,
      "step": 1260
    },
    {
      "epoch": 0.18130554266747564,
      "grad_norm": 1.239769697189331,
      "learning_rate": 0.00018803142109021664,
      "loss": 2.1863370895385743,
      "step": 1270
    },
    {
      "epoch": 0.18273314536564475,
      "grad_norm": 1.2516264915466309,
      "learning_rate": 0.0001879362056653178,
      "loss": 2.154579734802246,
      "step": 1280
    },
    {
      "epoch": 0.18416074806381383,
      "grad_norm": 1.300251841545105,
      "learning_rate": 0.00018784099024041895,
      "loss": 2.084653854370117,
      "step": 1290
    },
    {
      "epoch": 0.18558835076198293,
      "grad_norm": 1.5401705503463745,
      "learning_rate": 0.0001877457748155201,
      "loss": 2.1652135848999023,
      "step": 1300
    },
    {
      "epoch": 0.18701595346015204,
      "grad_norm": 1.388256549835205,
      "learning_rate": 0.0001876505593906213,
      "loss": 2.215251350402832,
      "step": 1310
    },
    {
      "epoch": 0.18844355615832115,
      "grad_norm": 1.0548882484436035,
      "learning_rate": 0.00018755534396572244,
      "loss": 2.057052230834961,
      "step": 1320
    },
    {
      "epoch": 0.18987115885649025,
      "grad_norm": 1.318389654159546,
      "learning_rate": 0.00018746012854082363,
      "loss": 2.1746826171875,
      "step": 1330
    },
    {
      "epoch": 0.19129876155465933,
      "grad_norm": 1.1861886978149414,
      "learning_rate": 0.00018736491311592478,
      "loss": 2.107588005065918,
      "step": 1340
    },
    {
      "epoch": 0.19272636425282844,
      "grad_norm": 1.0857220888137817,
      "learning_rate": 0.00018726969769102596,
      "loss": 2.1044857025146486,
      "step": 1350
    },
    {
      "epoch": 0.19415396695099754,
      "grad_norm": 1.144823670387268,
      "learning_rate": 0.00018717448226612712,
      "loss": 2.132158660888672,
      "step": 1360
    },
    {
      "epoch": 0.19558156964916665,
      "grad_norm": 1.1121206283569336,
      "learning_rate": 0.0001870792668412283,
      "loss": 2.1906471252441406,
      "step": 1370
    },
    {
      "epoch": 0.19700917234733573,
      "grad_norm": 1.2356815338134766,
      "learning_rate": 0.00018698405141632946,
      "loss": 2.2056690216064454,
      "step": 1380
    },
    {
      "epoch": 0.19843677504550483,
      "grad_norm": 1.3212710618972778,
      "learning_rate": 0.0001868888359914306,
      "loss": 2.168708610534668,
      "step": 1390
    },
    {
      "epoch": 0.19986437774367394,
      "grad_norm": 1.1257580518722534,
      "learning_rate": 0.00018679362056653177,
      "loss": 2.18591423034668,
      "step": 1400
    }
  ],
  "logging_steps": 10,
  "max_steps": 21015,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.868324052310016e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}