{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02333926539662164,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001166963269831082,
      "grad_norm": 0.5096844434738159,
      "learning_rate": 4e-05,
      "loss": 0.5061,
      "step": 1
    },
    {
      "epoch": 0.0002333926539662164,
      "grad_norm": 0.5573846697807312,
      "learning_rate": 8e-05,
      "loss": 0.536,
      "step": 2
    },
    {
      "epoch": 0.0003500889809493246,
      "grad_norm": 0.5168461203575134,
      "learning_rate": 0.00012,
      "loss": 0.5209,
      "step": 3
    },
    {
      "epoch": 0.0004667853079324328,
      "grad_norm": 0.4047943651676178,
      "learning_rate": 0.00016,
      "loss": 0.4604,
      "step": 4
    },
    {
      "epoch": 0.000583481634915541,
      "grad_norm": 0.20825760066509247,
      "learning_rate": 0.0002,
      "loss": 0.3089,
      "step": 5
    },
    {
      "epoch": 0.0007001779618986492,
      "grad_norm": 0.20194634795188904,
      "learning_rate": 0.00019997664642690334,
      "loss": 0.3358,
      "step": 6
    },
    {
      "epoch": 0.0008168742888817575,
      "grad_norm": 0.193731427192688,
      "learning_rate": 0.00019995329285380664,
      "loss": 0.3042,
      "step": 7
    },
    {
      "epoch": 0.0009335706158648656,
      "grad_norm": 0.21419042348861694,
      "learning_rate": 0.00019992993928070996,
      "loss": 0.341,
      "step": 8
    },
    {
      "epoch": 0.001050266942847974,
      "grad_norm": 0.18434806168079376,
      "learning_rate": 0.00019990658570761326,
      "loss": 0.2665,
      "step": 9
    },
    {
      "epoch": 0.001166963269831082,
      "grad_norm": 0.16945861279964447,
      "learning_rate": 0.0001998832321345166,
      "loss": 0.3113,
      "step": 10
    },
    {
      "epoch": 0.0012836595968141902,
      "grad_norm": 0.1379944235086441,
      "learning_rate": 0.0001998598785614199,
      "loss": 0.213,
      "step": 11
    },
    {
      "epoch": 0.0014003559237972985,
      "grad_norm": 0.12341434508562088,
      "learning_rate": 0.00019983652498832322,
      "loss": 0.1954,
      "step": 12
    },
    {
      "epoch": 0.0015170522507804067,
      "grad_norm": 0.12021443247795105,
      "learning_rate": 0.00019981317141522654,
      "loss": 0.2118,
      "step": 13
    },
    {
      "epoch": 0.001633748577763515,
      "grad_norm": 0.16578464210033417,
      "learning_rate": 0.00019978981784212984,
      "loss": 0.2335,
      "step": 14
    },
    {
      "epoch": 0.0017504449047466232,
      "grad_norm": 0.13460949063301086,
      "learning_rate": 0.00019976646426903317,
      "loss": 0.1664,
      "step": 15
    },
    {
      "epoch": 0.0018671412317297312,
      "grad_norm": 0.13434286415576935,
      "learning_rate": 0.0001997431106959365,
      "loss": 0.2334,
      "step": 16
    },
    {
      "epoch": 0.0019838375587128395,
      "grad_norm": 0.15617124736309052,
      "learning_rate": 0.00019971975712283982,
      "loss": 0.267,
      "step": 17
    },
    {
      "epoch": 0.002100533885695948,
      "grad_norm": 0.12410859763622284,
      "learning_rate": 0.00019969640354974312,
      "loss": 0.2141,
      "step": 18
    },
    {
      "epoch": 0.002217230212679056,
      "grad_norm": 0.10960312187671661,
      "learning_rate": 0.00019967304997664645,
      "loss": 0.1625,
      "step": 19
    },
    {
      "epoch": 0.002333926539662164,
      "grad_norm": 0.1421806961297989,
      "learning_rate": 0.00019964969640354975,
      "loss": 0.2529,
      "step": 20
    },
    {
      "epoch": 0.0024506228666452724,
      "grad_norm": 0.1390838772058487,
      "learning_rate": 0.00019962634283045308,
      "loss": 0.1938,
      "step": 21
    },
    {
      "epoch": 0.0025673191936283805,
      "grad_norm": 0.11065292358398438,
      "learning_rate": 0.00019960298925735637,
      "loss": 0.1892,
      "step": 22
    },
    {
      "epoch": 0.002684015520611489,
      "grad_norm": 0.12330306321382523,
      "learning_rate": 0.0001995796356842597,
      "loss": 0.2334,
      "step": 23
    },
    {
      "epoch": 0.002800711847594597,
      "grad_norm": 0.10883963108062744,
      "learning_rate": 0.00019955628211116303,
      "loss": 0.1953,
      "step": 24
    },
    {
      "epoch": 0.002917408174577705,
      "grad_norm": 0.11904892325401306,
      "learning_rate": 0.00019953292853806633,
      "loss": 0.191,
      "step": 25
    },
    {
      "epoch": 0.0030341045015608134,
      "grad_norm": 0.09328188002109528,
      "learning_rate": 0.00019950957496496965,
      "loss": 0.1517,
      "step": 26
    },
    {
      "epoch": 0.0031508008285439214,
      "grad_norm": 0.10651596635580063,
      "learning_rate": 0.00019948622139187295,
      "loss": 0.1778,
      "step": 27
    },
    {
      "epoch": 0.00326749715552703,
      "grad_norm": 0.09824363142251968,
      "learning_rate": 0.00019946286781877628,
      "loss": 0.1412,
      "step": 28
    },
    {
      "epoch": 0.003384193482510138,
      "grad_norm": 0.0911468043923378,
      "learning_rate": 0.00019943951424567958,
      "loss": 0.1413,
      "step": 29
    },
    {
      "epoch": 0.0035008898094932464,
      "grad_norm": 0.10707972198724747,
      "learning_rate": 0.0001994161606725829,
      "loss": 0.166,
      "step": 30
    },
    {
      "epoch": 0.0036175861364763544,
      "grad_norm": 0.1010749414563179,
      "learning_rate": 0.00019939280709948623,
      "loss": 0.1762,
      "step": 31
    },
    {
      "epoch": 0.0037342824634594624,
      "grad_norm": 0.11201727390289307,
      "learning_rate": 0.00019936945352638953,
      "loss": 0.1691,
      "step": 32
    },
    {
      "epoch": 0.003850978790442571,
      "grad_norm": 0.10435190051794052,
      "learning_rate": 0.00019934609995329286,
      "loss": 0.1615,
      "step": 33
    },
    {
      "epoch": 0.003967675117425679,
      "grad_norm": 0.10385840386152267,
      "learning_rate": 0.0001993227463801962,
      "loss": 0.1395,
      "step": 34
    },
    {
      "epoch": 0.004084371444408787,
      "grad_norm": 0.10580045729875565,
      "learning_rate": 0.00019929939280709951,
      "loss": 0.188,
      "step": 35
    },
    {
      "epoch": 0.004201067771391896,
      "grad_norm": 0.10571294277906418,
      "learning_rate": 0.00019927603923400281,
      "loss": 0.1778,
      "step": 36
    },
    {
      "epoch": 0.004317764098375003,
      "grad_norm": 0.11938229203224182,
      "learning_rate": 0.00019925268566090614,
      "loss": 0.2181,
      "step": 37
    },
    {
      "epoch": 0.004434460425358112,
      "grad_norm": 0.09765143692493439,
      "learning_rate": 0.00019922933208780944,
      "loss": 0.13,
      "step": 38
    },
    {
      "epoch": 0.00455115675234122,
      "grad_norm": 0.11270410567522049,
      "learning_rate": 0.00019920597851471277,
      "loss": 0.1988,
      "step": 39
    },
    {
      "epoch": 0.004667853079324328,
      "grad_norm": 0.09199155867099762,
      "learning_rate": 0.0001991826249416161,
      "loss": 0.1616,
      "step": 40
    },
    {
      "epoch": 0.004784549406307436,
      "grad_norm": 0.10620560497045517,
      "learning_rate": 0.0001991592713685194,
      "loss": 0.1728,
      "step": 41
    },
    {
      "epoch": 0.004901245733290545,
      "grad_norm": 0.09054724127054214,
      "learning_rate": 0.00019913591779542272,
      "loss": 0.1369,
      "step": 42
    },
    {
      "epoch": 0.005017942060273653,
      "grad_norm": 0.10327401012182236,
      "learning_rate": 0.00019911256422232602,
      "loss": 0.1708,
      "step": 43
    },
    {
      "epoch": 0.005134638387256761,
      "grad_norm": 0.09473054111003876,
      "learning_rate": 0.00019908921064922935,
      "loss": 0.1589,
      "step": 44
    },
    {
      "epoch": 0.005251334714239869,
      "grad_norm": 0.10536584258079529,
      "learning_rate": 0.00019906585707613265,
      "loss": 0.1962,
      "step": 45
    },
    {
      "epoch": 0.005368031041222978,
      "grad_norm": 0.10594025254249573,
      "learning_rate": 0.00019904250350303597,
      "loss": 0.1893,
      "step": 46
    },
    {
      "epoch": 0.005484727368206085,
      "grad_norm": 0.09798738360404968,
      "learning_rate": 0.00019901914992993927,
      "loss": 0.1759,
      "step": 47
    },
    {
      "epoch": 0.005601423695189194,
      "grad_norm": 0.08874180912971497,
      "learning_rate": 0.0001989957963568426,
      "loss": 0.1558,
      "step": 48
    },
    {
      "epoch": 0.005718120022172302,
      "grad_norm": 0.11178728193044662,
      "learning_rate": 0.00019897244278374593,
      "loss": 0.1745,
      "step": 49
    },
    {
      "epoch": 0.00583481634915541,
      "grad_norm": 0.0964571163058281,
      "learning_rate": 0.00019894908921064923,
      "loss": 0.1751,
      "step": 50
    },
    {
      "epoch": 0.005951512676138518,
      "grad_norm": 0.10600943863391876,
      "learning_rate": 0.00019892573563755255,
      "loss": 0.1656,
      "step": 51
    },
    {
      "epoch": 0.006068209003121627,
      "grad_norm": 0.10203580558300018,
      "learning_rate": 0.00019890238206445585,
      "loss": 0.1621,
      "step": 52
    },
    {
      "epoch": 0.006184905330104735,
      "grad_norm": 0.11010047048330307,
      "learning_rate": 0.0001988790284913592,
      "loss": 0.1789,
      "step": 53
    },
    {
      "epoch": 0.006301601657087843,
      "grad_norm": 0.11551900953054428,
      "learning_rate": 0.0001988556749182625,
      "loss": 0.1794,
      "step": 54
    },
    {
      "epoch": 0.006418297984070951,
      "grad_norm": 0.11391794681549072,
      "learning_rate": 0.00019883232134516583,
      "loss": 0.1765,
      "step": 55
    },
    {
      "epoch": 0.00653499431105406,
      "grad_norm": 0.11572562158107758,
      "learning_rate": 0.00019880896777206913,
      "loss": 0.2161,
      "step": 56
    },
    {
      "epoch": 0.006651690638037167,
      "grad_norm": 0.09810175001621246,
      "learning_rate": 0.00019878561419897246,
      "loss": 0.1534,
      "step": 57
    },
    {
      "epoch": 0.006768386965020276,
      "grad_norm": 0.10156040638685226,
      "learning_rate": 0.00019876226062587579,
      "loss": 0.1514,
      "step": 58
    },
    {
      "epoch": 0.006885083292003384,
      "grad_norm": 0.09523003548383713,
      "learning_rate": 0.00019873890705277909,
      "loss": 0.1345,
      "step": 59
    },
    {
      "epoch": 0.007001779618986493,
      "grad_norm": 0.11223362386226654,
      "learning_rate": 0.0001987155534796824,
      "loss": 0.1995,
      "step": 60
    },
    {
      "epoch": 0.0071184759459696,
      "grad_norm": 0.09502169489860535,
      "learning_rate": 0.0001986921999065857,
      "loss": 0.1428,
      "step": 61
    },
    {
      "epoch": 0.007235172272952709,
      "grad_norm": 0.11790277063846588,
      "learning_rate": 0.00019866884633348904,
      "loss": 0.1592,
      "step": 62
    },
    {
      "epoch": 0.007351868599935817,
      "grad_norm": 0.0922728031873703,
      "learning_rate": 0.00019864549276039234,
      "loss": 0.1264,
      "step": 63
    },
    {
      "epoch": 0.007468564926918925,
      "grad_norm": 0.09835848957300186,
      "learning_rate": 0.00019862213918729566,
      "loss": 0.131,
      "step": 64
    },
    {
      "epoch": 0.007585261253902033,
      "grad_norm": 0.1120564341545105,
      "learning_rate": 0.000198598785614199,
      "loss": 0.1605,
      "step": 65
    },
    {
      "epoch": 0.007701957580885142,
      "grad_norm": 0.10365966707468033,
      "learning_rate": 0.0001985754320411023,
      "loss": 0.1458,
      "step": 66
    },
    {
      "epoch": 0.00781865390786825,
      "grad_norm": 0.12009326368570328,
      "learning_rate": 0.00019855207846800562,
      "loss": 0.1818,
      "step": 67
    },
    {
      "epoch": 0.007935350234851358,
      "grad_norm": 0.10382229834794998,
      "learning_rate": 0.00019852872489490892,
      "loss": 0.1695,
      "step": 68
    },
    {
      "epoch": 0.008052046561834466,
      "grad_norm": 0.12162943184375763,
      "learning_rate": 0.00019850537132181224,
      "loss": 0.1916,
      "step": 69
    },
    {
      "epoch": 0.008168742888817575,
      "grad_norm": 0.1090371385216713,
      "learning_rate": 0.00019848201774871554,
      "loss": 0.1733,
      "step": 70
    },
    {
      "epoch": 0.008285439215800683,
      "grad_norm": 0.1108129546046257,
      "learning_rate": 0.00019845866417561887,
      "loss": 0.1533,
      "step": 71
    },
    {
      "epoch": 0.008402135542783792,
      "grad_norm": 0.10778584331274033,
      "learning_rate": 0.0001984353106025222,
      "loss": 0.1729,
      "step": 72
    },
    {
      "epoch": 0.008518831869766898,
      "grad_norm": 0.14670732617378235,
      "learning_rate": 0.00019841195702942552,
      "loss": 0.1499,
      "step": 73
    },
    {
      "epoch": 0.008635528196750007,
      "grad_norm": 0.10100234299898148,
      "learning_rate": 0.00019838860345632882,
      "loss": 0.1556,
      "step": 74
    },
    {
      "epoch": 0.008752224523733115,
      "grad_norm": 0.11347773671150208,
      "learning_rate": 0.00019836524988323215,
      "loss": 0.1783,
      "step": 75
    },
    {
      "epoch": 0.008868920850716224,
      "grad_norm": 0.09582630544900894,
      "learning_rate": 0.00019834189631013548,
      "loss": 0.1516,
      "step": 76
    },
    {
      "epoch": 0.008985617177699332,
      "grad_norm": 0.09301317483186722,
      "learning_rate": 0.00019831854273703878,
      "loss": 0.1491,
      "step": 77
    },
    {
      "epoch": 0.00910231350468244,
      "grad_norm": 0.12455611675977707,
      "learning_rate": 0.0001982951891639421,
      "loss": 0.1654,
      "step": 78
    },
    {
      "epoch": 0.00921900983166555,
      "grad_norm": 0.11573786288499832,
      "learning_rate": 0.0001982718355908454,
      "loss": 0.2097,
      "step": 79
    },
    {
      "epoch": 0.009335706158648656,
      "grad_norm": 0.09937581419944763,
      "learning_rate": 0.00019824848201774873,
      "loss": 0.1563,
      "step": 80
    },
    {
      "epoch": 0.009452402485631764,
      "grad_norm": 0.11743341386318207,
      "learning_rate": 0.00019822512844465203,
      "loss": 0.1656,
      "step": 81
    },
    {
      "epoch": 0.009569098812614873,
      "grad_norm": 0.10934270918369293,
      "learning_rate": 0.00019820177487155536,
      "loss": 0.1468,
      "step": 82
    },
    {
      "epoch": 0.009685795139597981,
      "grad_norm": 0.11555736511945724,
      "learning_rate": 0.00019817842129845868,
      "loss": 0.1815,
      "step": 83
    },
    {
      "epoch": 0.00980249146658109,
      "grad_norm": 0.11791291832923889,
      "learning_rate": 0.00019815506772536198,
      "loss": 0.1807,
      "step": 84
    },
    {
      "epoch": 0.009919187793564198,
      "grad_norm": 0.1130499318242073,
      "learning_rate": 0.0001981317141522653,
      "loss": 0.1698,
      "step": 85
    },
    {
      "epoch": 0.010035884120547307,
      "grad_norm": 0.10540090501308441,
      "learning_rate": 0.0001981083605791686,
      "loss": 0.1582,
      "step": 86
    },
    {
      "epoch": 0.010152580447530413,
      "grad_norm": 0.09527558833360672,
      "learning_rate": 0.00019808500700607194,
      "loss": 0.1387,
      "step": 87
    },
    {
      "epoch": 0.010269276774513522,
      "grad_norm": 0.11643368750810623,
      "learning_rate": 0.00019806165343297524,
      "loss": 0.1842,
      "step": 88
    },
    {
      "epoch": 0.01038597310149663,
      "grad_norm": 0.11340148001909256,
      "learning_rate": 0.00019803829985987856,
      "loss": 0.1616,
      "step": 89
    },
    {
      "epoch": 0.010502669428479739,
      "grad_norm": 0.12303619831800461,
      "learning_rate": 0.0001980149462867819,
      "loss": 0.1872,
      "step": 90
    },
    {
      "epoch": 0.010619365755462847,
      "grad_norm": 0.09786645323038101,
      "learning_rate": 0.0001979915927136852,
      "loss": 0.1567,
      "step": 91
    },
    {
      "epoch": 0.010736062082445956,
      "grad_norm": 0.10433386266231537,
      "learning_rate": 0.00019796823914058854,
      "loss": 0.1783,
      "step": 92
    },
    {
      "epoch": 0.010852758409429062,
      "grad_norm": 0.31017664074897766,
      "learning_rate": 0.00019794488556749184,
      "loss": 0.1546,
      "step": 93
    },
    {
      "epoch": 0.01096945473641217,
      "grad_norm": 0.10538630187511444,
      "learning_rate": 0.00019792153199439517,
      "loss": 0.1562,
      "step": 94
    },
    {
      "epoch": 0.01108615106339528,
      "grad_norm": 0.10152962803840637,
      "learning_rate": 0.00019789817842129847,
      "loss": 0.1573,
      "step": 95
    },
    {
      "epoch": 0.011202847390378388,
      "grad_norm": 0.1028379276394844,
      "learning_rate": 0.0001978748248482018,
      "loss": 0.151,
      "step": 96
    },
    {
      "epoch": 0.011319543717361496,
      "grad_norm": 0.10292468219995499,
      "learning_rate": 0.0001978514712751051,
      "loss": 0.1642,
      "step": 97
    },
    {
      "epoch": 0.011436240044344605,
      "grad_norm": 0.10416844487190247,
      "learning_rate": 0.00019782811770200842,
      "loss": 0.1701,
      "step": 98
    },
    {
      "epoch": 0.011552936371327713,
      "grad_norm": 0.10852757841348648,
      "learning_rate": 0.00019780476412891172,
      "loss": 0.1474,
      "step": 99
    },
    {
      "epoch": 0.01166963269831082,
      "grad_norm": 0.10577951371669769,
      "learning_rate": 0.00019778141055581505,
      "loss": 0.18,
      "step": 100
    },
    {
      "epoch": 0.011786329025293928,
      "grad_norm": 0.08033058792352676,
      "learning_rate": 0.00019775805698271838,
      "loss": 0.1211,
      "step": 101
    },
    {
      "epoch": 0.011903025352277037,
      "grad_norm": 0.1296456754207611,
      "learning_rate": 0.00019773470340962167,
      "loss": 0.1822,
      "step": 102
    },
    {
      "epoch": 0.012019721679260145,
      "grad_norm": 0.114451102912426,
      "learning_rate": 0.000197711349836525,
      "loss": 0.1756,
      "step": 103
    },
    {
      "epoch": 0.012136418006243254,
      "grad_norm": 0.10711831599473953,
      "learning_rate": 0.0001976879962634283,
      "loss": 0.1622,
      "step": 104
    },
    {
      "epoch": 0.012253114333226362,
      "grad_norm": 0.11008073389530182,
      "learning_rate": 0.00019766464269033163,
      "loss": 0.1554,
      "step": 105
    },
    {
      "epoch": 0.01236981066020947,
      "grad_norm": 0.1160978451371193,
      "learning_rate": 0.00019764128911723493,
      "loss": 0.1667,
      "step": 106
    },
    {
      "epoch": 0.012486506987192577,
      "grad_norm": 0.1413351148366928,
      "learning_rate": 0.00019761793554413825,
      "loss": 0.191,
      "step": 107
    },
    {
      "epoch": 0.012603203314175686,
      "grad_norm": 0.08713728189468384,
      "learning_rate": 0.00019759458197104158,
      "loss": 0.1353,
      "step": 108
    },
    {
      "epoch": 0.012719899641158794,
      "grad_norm": 0.09029239416122437,
      "learning_rate": 0.00019757122839794488,
      "loss": 0.1078,
      "step": 109
    },
    {
      "epoch": 0.012836595968141903,
      "grad_norm": 0.09928172081708908,
      "learning_rate": 0.0001975478748248482,
      "loss": 0.136,
      "step": 110
    },
    {
      "epoch": 0.012953292295125011,
      "grad_norm": 0.11607584357261658,
      "learning_rate": 0.00019752452125175153,
      "loss": 0.1861,
      "step": 111
    },
    {
      "epoch": 0.01306998862210812,
      "grad_norm": 0.12424415349960327,
      "learning_rate": 0.00019750116767865486,
      "loss": 0.1987,
      "step": 112
    },
    {
      "epoch": 0.013186684949091228,
      "grad_norm": 0.12206408381462097,
      "learning_rate": 0.00019747781410555816,
      "loss": 0.2091,
      "step": 113
    },
    {
      "epoch": 0.013303381276074335,
      "grad_norm": 0.09520223736763,
      "learning_rate": 0.0001974544605324615,
      "loss": 0.1318,
      "step": 114
    },
    {
      "epoch": 0.013420077603057443,
      "grad_norm": 0.10052375495433807,
      "learning_rate": 0.0001974311069593648,
      "loss": 0.1675,
      "step": 115
    },
    {
      "epoch": 0.013536773930040552,
      "grad_norm": 0.09986284375190735,
      "learning_rate": 0.00019740775338626811,
      "loss": 0.1496,
      "step": 116
    },
    {
      "epoch": 0.01365347025702366,
      "grad_norm": 0.09899864345788956,
      "learning_rate": 0.00019738439981317144,
      "loss": 0.1427,
      "step": 117
    },
    {
      "epoch": 0.013770166584006769,
      "grad_norm": 0.09922472387552261,
      "learning_rate": 0.00019736104624007474,
      "loss": 0.1412,
      "step": 118
    },
    {
      "epoch": 0.013886862910989877,
      "grad_norm": 0.08671886473894119,
      "learning_rate": 0.00019733769266697807,
      "loss": 0.1305,
      "step": 119
    },
    {
      "epoch": 0.014003559237972986,
      "grad_norm": 0.10284463316202164,
      "learning_rate": 0.00019731433909388137,
      "loss": 0.1455,
      "step": 120
    },
    {
      "epoch": 0.014120255564956092,
      "grad_norm": 0.12423279136419296,
      "learning_rate": 0.0001972909855207847,
      "loss": 0.1984,
      "step": 121
    },
    {
      "epoch": 0.0142369518919392,
      "grad_norm": 0.12210292369127274,
      "learning_rate": 0.000197267631947688,
      "loss": 0.1854,
      "step": 122
    },
    {
      "epoch": 0.01435364821892231,
      "grad_norm": 0.10566538572311401,
      "learning_rate": 0.00019724427837459132,
      "loss": 0.1347,
      "step": 123
    },
    {
      "epoch": 0.014470344545905418,
      "grad_norm": 0.09597185254096985,
      "learning_rate": 0.00019722092480149465,
      "loss": 0.133,
      "step": 124
    },
    {
      "epoch": 0.014587040872888526,
      "grad_norm": 0.11847853660583496,
      "learning_rate": 0.00019719757122839795,
      "loss": 0.1788,
      "step": 125
    },
    {
      "epoch": 0.014703737199871635,
      "grad_norm": 0.10845934599637985,
      "learning_rate": 0.00019717421765530127,
      "loss": 0.1509,
      "step": 126
    },
    {
      "epoch": 0.014820433526854743,
      "grad_norm": 0.09963663667440414,
      "learning_rate": 0.00019715086408220457,
      "loss": 0.1677,
      "step": 127
    },
    {
      "epoch": 0.01493712985383785,
      "grad_norm": 0.09440722316503525,
      "learning_rate": 0.0001971275105091079,
      "loss": 0.1396,
      "step": 128
    },
    {
      "epoch": 0.015053826180820958,
      "grad_norm": 0.11402937024831772,
      "learning_rate": 0.0001971041569360112,
      "loss": 0.18,
      "step": 129
    },
    {
      "epoch": 0.015170522507804067,
      "grad_norm": 0.1282823383808136,
      "learning_rate": 0.00019708080336291455,
      "loss": 0.1817,
      "step": 130
    },
    {
      "epoch": 0.015287218834787175,
      "grad_norm": 0.09704853594303131,
      "learning_rate": 0.00019705744978981785,
      "loss": 0.1502,
      "step": 131
    },
    {
      "epoch": 0.015403915161770284,
      "grad_norm": 0.09895353019237518,
      "learning_rate": 0.00019703409621672118,
      "loss": 0.1477,
      "step": 132
    },
    {
      "epoch": 0.015520611488753392,
      "grad_norm": 0.10989242792129517,
      "learning_rate": 0.00019701074264362448,
      "loss": 0.1483,
      "step": 133
    },
    {
      "epoch": 0.0156373078157365,
      "grad_norm": 0.11348774284124374,
      "learning_rate": 0.0001969873890705278,
      "loss": 0.1787,
      "step": 134
    },
    {
      "epoch": 0.01575400414271961,
      "grad_norm": 0.10849590599536896,
      "learning_rate": 0.00019696403549743113,
      "loss": 0.1564,
      "step": 135
    },
    {
      "epoch": 0.015870700469702716,
      "grad_norm": 0.10929839313030243,
      "learning_rate": 0.00019694068192433443,
      "loss": 0.1481,
      "step": 136
    },
    {
      "epoch": 0.015987396796685826,
      "grad_norm": 0.09660619497299194,
      "learning_rate": 0.00019691732835123776,
      "loss": 0.1433,
      "step": 137
    },
    {
      "epoch": 0.016104093123668933,
      "grad_norm": 0.11423259973526001,
      "learning_rate": 0.00019689397477814106,
      "loss": 0.1342,
      "step": 138
    },
    {
      "epoch": 0.01622078945065204,
      "grad_norm": 0.10947205871343613,
      "learning_rate": 0.00019687062120504439,
      "loss": 0.1825,
      "step": 139
    },
    {
      "epoch": 0.01633748577763515,
      "grad_norm": 0.11746672540903091,
      "learning_rate": 0.00019684726763194768,
      "loss": 0.1766,
      "step": 140
    },
    {
      "epoch": 0.016454182104618256,
      "grad_norm": 0.1152237206697464,
      "learning_rate": 0.000196823914058851,
      "loss": 0.161,
      "step": 141
    },
    {
      "epoch": 0.016570878431601366,
      "grad_norm": 0.10848015546798706,
      "learning_rate": 0.00019680056048575434,
      "loss": 0.1541,
      "step": 142
    },
    {
      "epoch": 0.016687574758584473,
      "grad_norm": 0.12663570046424866,
      "learning_rate": 0.00019677720691265764,
      "loss": 0.1891,
      "step": 143
    },
    {
      "epoch": 0.016804271085567583,
      "grad_norm": 0.1088947057723999,
      "learning_rate": 0.00019675385333956096,
      "loss": 0.1505,
      "step": 144
    },
    {
      "epoch": 0.01692096741255069,
      "grad_norm": 0.10418037325143814,
      "learning_rate": 0.00019673049976646426,
      "loss": 0.151,
      "step": 145
    },
    {
      "epoch": 0.017037663739533797,
      "grad_norm": 0.08672403544187546,
      "learning_rate": 0.0001967071461933676,
      "loss": 0.1213,
      "step": 146
    },
    {
      "epoch": 0.017154360066516907,
      "grad_norm": 0.10863472521305084,
      "learning_rate": 0.0001966837926202709,
      "loss": 0.1552,
      "step": 147
    },
    {
      "epoch": 0.017271056393500014,
      "grad_norm": 0.10580800473690033,
      "learning_rate": 0.00019666043904717422,
      "loss": 0.1589,
      "step": 148
    },
    {
      "epoch": 0.017387752720483124,
      "grad_norm": 0.09545203298330307,
      "learning_rate": 0.00019663708547407754,
      "loss": 0.139,
      "step": 149
    },
    {
      "epoch": 0.01750444904746623,
      "grad_norm": 0.14016349613666534,
      "learning_rate": 0.00019661373190098087,
      "loss": 0.2126,
      "step": 150
    },
    {
      "epoch": 0.01762114537444934,
      "grad_norm": 0.11033914983272552,
      "learning_rate": 0.00019659037832788417,
      "loss": 0.1644,
      "step": 151
    },
    {
      "epoch": 0.017737841701432448,
      "grad_norm": 0.10455331206321716,
      "learning_rate": 0.0001965670247547875,
      "loss": 0.1499,
      "step": 152
    },
    {
      "epoch": 0.017854538028415554,
      "grad_norm": 0.11884409189224243,
      "learning_rate": 0.00019654367118169082,
      "loss": 0.1731,
      "step": 153
    },
    {
      "epoch": 0.017971234355398664,
      "grad_norm": 0.11076351255178452,
      "learning_rate": 0.00019652031760859412,
      "loss": 0.1782,
      "step": 154
    },
    {
      "epoch": 0.01808793068238177,
      "grad_norm": 0.11540203541517258,
      "learning_rate": 0.00019649696403549745,
      "loss": 0.1731,
      "step": 155
    },
    {
      "epoch": 0.01820462700936488,
      "grad_norm": 0.09334211051464081,
      "learning_rate": 0.00019647361046240075,
      "loss": 0.1576,
      "step": 156
    },
    {
      "epoch": 0.018321323336347988,
      "grad_norm": 0.11943213641643524,
      "learning_rate": 0.00019645025688930408,
      "loss": 0.1715,
      "step": 157
    },
    {
      "epoch": 0.0184380196633311,
      "grad_norm": 0.08858149498701096,
      "learning_rate": 0.00019642690331620738,
      "loss": 0.1282,
      "step": 158
    },
    {
      "epoch": 0.018554715990314205,
      "grad_norm": 0.10284683853387833,
      "learning_rate": 0.0001964035497431107,
      "loss": 0.1727,
      "step": 159
    },
    {
      "epoch": 0.018671412317297312,
      "grad_norm": 0.10812927782535553,
      "learning_rate": 0.00019638019617001403,
      "loss": 0.1741,
      "step": 160
    },
    {
      "epoch": 0.018788108644280422,
      "grad_norm": 0.08129740506410599,
      "learning_rate": 0.00019635684259691733,
      "loss": 0.107,
      "step": 161
    },
    {
      "epoch": 0.01890480497126353,
      "grad_norm": 0.11642193049192429,
      "learning_rate": 0.00019633348902382066,
      "loss": 0.1768,
      "step": 162
    },
    {
      "epoch": 0.01902150129824664,
      "grad_norm": 0.10036379098892212,
      "learning_rate": 0.00019631013545072396,
      "loss": 0.1458,
      "step": 163
    },
    {
      "epoch": 0.019138197625229746,
      "grad_norm": 0.0957493856549263,
      "learning_rate": 0.00019628678187762728,
      "loss": 0.143,
      "step": 164
    },
    {
      "epoch": 0.019254893952212856,
      "grad_norm": 0.12155473232269287,
      "learning_rate": 0.00019626342830453058,
      "loss": 0.1807,
      "step": 165
    },
    {
      "epoch": 0.019371590279195963,
      "grad_norm": 0.11061038821935654,
      "learning_rate": 0.0001962400747314339,
      "loss": 0.1699,
      "step": 166
    },
    {
      "epoch": 0.01948828660617907,
      "grad_norm": 0.10963009297847748,
      "learning_rate": 0.00019621672115833724,
      "loss": 0.1638,
      "step": 167
    },
    {
      "epoch": 0.01960498293316218,
      "grad_norm": 0.11229882389307022,
      "learning_rate": 0.00019619336758524056,
      "loss": 0.1788,
      "step": 168
    },
    {
      "epoch": 0.019721679260145286,
      "grad_norm": 0.10003431886434555,
      "learning_rate": 0.0001961700140121439,
      "loss": 0.1547,
      "step": 169
    },
    {
      "epoch": 0.019838375587128396,
      "grad_norm": 0.09698428958654404,
      "learning_rate": 0.0001961466604390472,
      "loss": 0.1193,
      "step": 170
    },
    {
      "epoch": 0.019955071914111503,
      "grad_norm": 0.10166200250387192,
      "learning_rate": 0.00019612330686595052,
      "loss": 0.1511,
      "step": 171
    },
    {
      "epoch": 0.020071768241094613,
      "grad_norm": 0.10210378468036652,
      "learning_rate": 0.00019609995329285382,
      "loss": 0.1563,
      "step": 172
    },
    {
      "epoch": 0.02018846456807772,
      "grad_norm": 0.09979470074176788,
      "learning_rate": 0.00019607659971975714,
      "loss": 0.1317,
      "step": 173
    },
    {
      "epoch": 0.020305160895060827,
      "grad_norm": 0.12395334988832474,
      "learning_rate": 0.00019605324614666044,
      "loss": 0.1791,
      "step": 174
    },
    {
      "epoch": 0.020421857222043937,
      "grad_norm": 0.11577446013689041,
      "learning_rate": 0.00019602989257356377,
      "loss": 0.1681,
      "step": 175
    },
    {
      "epoch": 0.020538553549027044,
      "grad_norm": 0.10168549418449402,
      "learning_rate": 0.00019600653900046707,
      "loss": 0.1404,
      "step": 176
    },
    {
      "epoch": 0.020655249876010154,
      "grad_norm": 0.1242406889796257,
      "learning_rate": 0.0001959831854273704,
      "loss": 0.1673,
      "step": 177
    },
    {
      "epoch": 0.02077194620299326,
      "grad_norm": 0.09891916811466217,
      "learning_rate": 0.00019595983185427372,
      "loss": 0.1298,
      "step": 178
    },
    {
      "epoch": 0.020888642529976367,
      "grad_norm": 0.15590757131576538,
      "learning_rate": 0.00019593647828117702,
      "loss": 0.1705,
      "step": 179
    },
    {
      "epoch": 0.021005338856959477,
      "grad_norm": 0.08277418464422226,
      "learning_rate": 0.00019591312470808035,
      "loss": 0.1104,
      "step": 180
    },
    {
      "epoch": 0.021122035183942584,
      "grad_norm": 0.10521771758794785,
      "learning_rate": 0.00019588977113498365,
      "loss": 0.1442,
      "step": 181
    },
    {
      "epoch": 0.021238731510925694,
      "grad_norm": 0.10389945656061172,
      "learning_rate": 0.00019586641756188698,
      "loss": 0.1448,
      "step": 182
    },
    {
      "epoch": 0.0213554278379088,
      "grad_norm": 0.11086277663707733,
      "learning_rate": 0.00019584306398879027,
      "loss": 0.1555,
      "step": 183
    },
    {
      "epoch": 0.02147212416489191,
      "grad_norm": 0.1056290939450264,
      "learning_rate": 0.0001958197104156936,
      "loss": 0.161,
      "step": 184
    },
    {
      "epoch": 0.021588820491875018,
      "grad_norm": 0.11331475526094437,
      "learning_rate": 0.00019579635684259693,
      "loss": 0.1236,
      "step": 185
    },
    {
      "epoch": 0.021705516818858125,
      "grad_norm": 0.09584867209196091,
      "learning_rate": 0.00019577300326950023,
      "loss": 0.1282,
      "step": 186
    },
    {
      "epoch": 0.021822213145841235,
      "grad_norm": 0.11787907034158707,
      "learning_rate": 0.00019574964969640358,
      "loss": 0.1843,
      "step": 187
    },
    {
      "epoch": 0.02193890947282434,
      "grad_norm": 0.10822898149490356,
      "learning_rate": 0.00019572629612330688,
      "loss": 0.1638,
      "step": 188
    },
    {
      "epoch": 0.022055605799807452,
      "grad_norm": 0.25267189741134644,
      "learning_rate": 0.0001957029425502102,
      "loss": 0.1718,
      "step": 189
    },
    {
      "epoch": 0.02217230212679056,
      "grad_norm": 0.1412399560213089,
      "learning_rate": 0.0001956795889771135,
      "loss": 0.1803,
      "step": 190
    },
    {
      "epoch": 0.02228899845377367,
      "grad_norm": 0.11052538454532623,
      "learning_rate": 0.00019565623540401683,
      "loss": 0.1638,
      "step": 191
    },
    {
      "epoch": 0.022405694780756776,
      "grad_norm": 0.11876215785741806,
      "learning_rate": 0.00019563288183092013,
      "loss": 0.2179,
      "step": 192
    },
    {
      "epoch": 0.022522391107739882,
      "grad_norm": 0.10292577743530273,
      "learning_rate": 0.00019560952825782346,
      "loss": 0.1568,
      "step": 193
    },
    {
      "epoch": 0.022639087434722992,
      "grad_norm": 0.10467737168073654,
      "learning_rate": 0.0001955861746847268,
      "loss": 0.156,
      "step": 194
    },
    {
      "epoch": 0.0227557837617061,
      "grad_norm": 0.116755910217762,
      "learning_rate": 0.0001955628211116301,
      "loss": 0.1665,
      "step": 195
    },
    {
      "epoch": 0.02287248008868921,
      "grad_norm": 0.09144476056098938,
      "learning_rate": 0.00019553946753853341,
      "loss": 0.1356,
      "step": 196
    },
    {
      "epoch": 0.022989176415672316,
      "grad_norm": 0.09073708951473236,
      "learning_rate": 0.00019551611396543671,
      "loss": 0.14,
      "step": 197
    },
    {
      "epoch": 0.023105872742655426,
      "grad_norm": 0.10096915066242218,
      "learning_rate": 0.00019549276039234004,
      "loss": 0.1595,
      "step": 198
    },
    {
      "epoch": 0.023222569069638533,
      "grad_norm": 0.10241077095270157,
      "learning_rate": 0.00019546940681924334,
      "loss": 0.1479,
      "step": 199
    },
    {
      "epoch": 0.02333926539662164,
      "grad_norm": 0.10773292183876038,
      "learning_rate": 0.00019544605324614667,
      "loss": 0.1548,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 8569,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4879936776325523e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}