{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 200,
  "global_step": 5070,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014795088030773782,
      "grad_norm": 0.08312089741230011,
      "learning_rate": 4.8e-05,
      "loss": 25.3001,
      "step": 25
    },
    {
      "epoch": 0.029590176061547565,
      "grad_norm": 0.16134510934352875,
      "learning_rate": 9.8e-05,
      "loss": 25.2653,
      "step": 50
    },
    {
      "epoch": 0.04438526409232135,
      "grad_norm": 0.20426703989505768,
      "learning_rate": 0.000148,
      "loss": 25.1317,
      "step": 75
    },
    {
      "epoch": 0.05918035212309513,
      "grad_norm": 0.12948599457740784,
      "learning_rate": 0.00019800000000000002,
      "loss": 25.1001,
      "step": 100
    },
    {
      "epoch": 0.07397544015386892,
      "grad_norm": 0.12529096007347107,
      "learning_rate": 0.00019903420523138834,
      "loss": 25.1769,
      "step": 125
    },
    {
      "epoch": 0.0887705281846427,
      "grad_norm": 0.1009916439652443,
      "learning_rate": 0.00019802816901408452,
      "loss": 25.173,
      "step": 150
    },
    {
      "epoch": 0.10356561621541648,
      "grad_norm": 0.11219477653503418,
      "learning_rate": 0.0001970221327967807,
      "loss": 25.0957,
      "step": 175
    },
    {
      "epoch": 0.11836070424619026,
      "grad_norm": 0.08366899192333221,
      "learning_rate": 0.00019601609657947687,
      "loss": 25.069,
      "step": 200
    },
    {
      "epoch": 0.13315579227696406,
      "grad_norm": 0.05875258892774582,
      "learning_rate": 0.00019501006036217304,
      "loss": 25.0362,
      "step": 225
    },
    {
      "epoch": 0.14795088030773784,
      "grad_norm": 0.06766419112682343,
      "learning_rate": 0.00019400402414486922,
      "loss": 25.0112,
      "step": 250
    },
    {
      "epoch": 0.16274596833851163,
      "grad_norm": 0.07124276459217072,
      "learning_rate": 0.0001929979879275654,
      "loss": 25.0194,
      "step": 275
    },
    {
      "epoch": 0.1775410563692854,
      "grad_norm": 0.09075228869915009,
      "learning_rate": 0.0001919919517102616,
      "loss": 25.1531,
      "step": 300
    },
    {
      "epoch": 0.19233614440005917,
      "grad_norm": 0.06596764922142029,
      "learning_rate": 0.00019098591549295774,
      "loss": 25.0991,
      "step": 325
    },
    {
      "epoch": 0.20713123243083295,
      "grad_norm": 0.06218697875738144,
      "learning_rate": 0.00018997987927565392,
      "loss": 25.0787,
      "step": 350
    },
    {
      "epoch": 0.22192632046160674,
      "grad_norm": 0.07952570170164108,
      "learning_rate": 0.00018897384305835012,
      "loss": 25.0317,
      "step": 375
    },
    {
      "epoch": 0.23672140849238052,
      "grad_norm": 0.06121606379747391,
      "learning_rate": 0.0001879678068410463,
      "loss": 25.0975,
      "step": 400
    },
    {
      "epoch": 0.25151649652315433,
      "grad_norm": 0.06957080215215683,
      "learning_rate": 0.00018696177062374247,
      "loss": 25.1054,
      "step": 425
    },
    {
      "epoch": 0.2663115845539281,
      "grad_norm": 0.06280346214771271,
      "learning_rate": 0.00018595573440643862,
      "loss": 25.0019,
      "step": 450
    },
    {
      "epoch": 0.2811066725847019,
      "grad_norm": 0.0642634779214859,
      "learning_rate": 0.00018494969818913482,
      "loss": 25.1581,
      "step": 475
    },
    {
      "epoch": 0.2959017606154757,
      "grad_norm": 0.05680055171251297,
      "learning_rate": 0.000183943661971831,
      "loss": 25.0826,
      "step": 500
    },
    {
      "epoch": 0.31069684864624947,
      "grad_norm": 0.038917265832424164,
      "learning_rate": 0.00018293762575452717,
      "loss": 25.1511,
      "step": 525
    },
    {
      "epoch": 0.32549193667702325,
      "grad_norm": 0.047237247228622437,
      "learning_rate": 0.00018193158953722335,
      "loss": 25.022,
      "step": 550
    },
    {
      "epoch": 0.34028702470779704,
      "grad_norm": 0.04916401579976082,
      "learning_rate": 0.00018092555331991953,
      "loss": 25.0202,
      "step": 575
    },
    {
      "epoch": 0.3550821127385708,
      "grad_norm": 0.06772845983505249,
      "learning_rate": 0.0001799195171026157,
      "loss": 25.0699,
      "step": 600
    },
    {
      "epoch": 0.3698772007693446,
      "grad_norm": 0.048369135707616806,
      "learning_rate": 0.00017891348088531188,
      "loss": 25.0411,
      "step": 625
    },
    {
      "epoch": 0.38467228880011833,
      "grad_norm": 0.045925214886665344,
      "learning_rate": 0.00017790744466800805,
      "loss": 25.1226,
      "step": 650
    },
    {
      "epoch": 0.3994673768308921,
      "grad_norm": 0.0681011825799942,
      "learning_rate": 0.00017690140845070425,
      "loss": 25.0724,
      "step": 675
    },
    {
      "epoch": 0.4142624648616659,
      "grad_norm": 0.06605461239814758,
      "learning_rate": 0.0001758953722334004,
      "loss": 25.0152,
      "step": 700
    },
    {
      "epoch": 0.4290575528924397,
      "grad_norm": 0.05168164521455765,
      "learning_rate": 0.00017488933601609658,
      "loss": 25.1138,
      "step": 725
    },
    {
      "epoch": 0.44385264092321347,
      "grad_norm": 0.03383536636829376,
      "learning_rate": 0.00017388329979879275,
      "loss": 25.1285,
      "step": 750
    },
    {
      "epoch": 0.45864772895398725,
      "grad_norm": 0.03839387744665146,
      "learning_rate": 0.00017287726358148896,
      "loss": 25.0419,
      "step": 775
    },
    {
      "epoch": 0.47344281698476104,
      "grad_norm": 0.05215064063668251,
      "learning_rate": 0.00017187122736418513,
      "loss": 25.0599,
      "step": 800
    },
    {
      "epoch": 0.4882379050155348,
      "grad_norm": 0.05809099227190018,
      "learning_rate": 0.00017086519114688128,
      "loss": 25.0682,
      "step": 825
    },
    {
      "epoch": 0.5030329930463087,
      "grad_norm": 0.04687444493174553,
      "learning_rate": 0.00016985915492957746,
      "loss": 25.1285,
      "step": 850
    },
    {
      "epoch": 0.5178280810770824,
      "grad_norm": 0.043396566063165665,
      "learning_rate": 0.00016885311871227366,
      "loss": 25.0015,
      "step": 875
    },
    {
      "epoch": 0.5326231691078562,
      "grad_norm": 0.04217955097556114,
      "learning_rate": 0.00016784708249496983,
      "loss": 25.0274,
      "step": 900
    },
    {
      "epoch": 0.54741825713863,
      "grad_norm": 0.04644334316253662,
      "learning_rate": 0.000166841046277666,
      "loss": 25.1121,
      "step": 925
    },
    {
      "epoch": 0.5622133451694038,
      "grad_norm": 0.06119885668158531,
      "learning_rate": 0.00016583501006036218,
      "loss": 25.1759,
      "step": 950
    },
    {
      "epoch": 0.5770084332001776,
      "grad_norm": 0.05505023151636124,
      "learning_rate": 0.00016482897384305836,
      "loss": 25.0348,
      "step": 975
    },
    {
      "epoch": 0.5918035212309514,
      "grad_norm": 0.036642227321863174,
      "learning_rate": 0.00016382293762575454,
      "loss": 25.1238,
      "step": 1000
    },
    {
      "epoch": 0.6065986092617252,
      "grad_norm": 0.020652858540415764,
      "learning_rate": 0.0001628169014084507,
      "loss": 25.042,
      "step": 1025
    },
    {
      "epoch": 0.6213936972924989,
      "grad_norm": 0.03491384536027908,
      "learning_rate": 0.00016181086519114689,
      "loss": 25.03,
      "step": 1050
    },
    {
      "epoch": 0.6361887853232727,
      "grad_norm": 0.04702286049723625,
      "learning_rate": 0.00016080482897384306,
      "loss": 25.055,
      "step": 1075
    },
    {
      "epoch": 0.6509838733540465,
      "grad_norm": 0.04155293107032776,
      "learning_rate": 0.00015979879275653924,
      "loss": 25.0551,
      "step": 1100
    },
    {
      "epoch": 0.6657789613848203,
      "grad_norm": 0.09428809583187103,
      "learning_rate": 0.0001587927565392354,
      "loss": 25.046,
      "step": 1125
    },
    {
      "epoch": 0.6805740494155941,
      "grad_norm": 0.0833851769566536,
      "learning_rate": 0.00015778672032193162,
      "loss": 25.1491,
      "step": 1150
    },
    {
      "epoch": 0.6953691374463679,
      "grad_norm": 0.05562705919146538,
      "learning_rate": 0.0001567806841046278,
      "loss": 25.1716,
      "step": 1175
    },
    {
      "epoch": 0.7101642254771416,
      "grad_norm": 0.03471198305487633,
      "learning_rate": 0.00015577464788732394,
      "loss": 25.0191,
      "step": 1200
    },
    {
      "epoch": 0.7249593135079154,
      "grad_norm": 0.0596119686961174,
      "learning_rate": 0.00015476861167002011,
      "loss": 25.0971,
      "step": 1225
    },
    {
      "epoch": 0.7397544015386892,
      "grad_norm": 0.04158185049891472,
      "learning_rate": 0.00015376257545271632,
      "loss": 25.0796,
      "step": 1250
    },
    {
      "epoch": 0.7545494895694629,
      "grad_norm": 0.04319076985120773,
      "learning_rate": 0.0001527565392354125,
      "loss": 25.0667,
      "step": 1275
    },
    {
      "epoch": 0.7693445776002367,
      "grad_norm": 0.03822188079357147,
      "learning_rate": 0.00015175050301810867,
      "loss": 24.9891,
      "step": 1300
    },
    {
      "epoch": 0.7841396656310105,
      "grad_norm": 0.04330127686262131,
      "learning_rate": 0.00015074446680080482,
      "loss": 25.0619,
      "step": 1325
    },
    {
      "epoch": 0.7989347536617842,
      "grad_norm": 0.041904184967279434,
      "learning_rate": 0.00014973843058350102,
      "loss": 25.0861,
      "step": 1350
    },
    {
      "epoch": 0.813729841692558,
      "grad_norm": 0.033138617873191833,
      "learning_rate": 0.0001487323943661972,
      "loss": 25.0589,
      "step": 1375
    },
    {
      "epoch": 0.8285249297233318,
      "grad_norm": 0.041870083659887314,
      "learning_rate": 0.00014772635814889337,
      "loss": 25.0909,
      "step": 1400
    },
    {
      "epoch": 0.8433200177541056,
      "grad_norm": 0.04157957062125206,
      "learning_rate": 0.00014672032193158955,
      "loss": 24.993,
      "step": 1425
    },
    {
      "epoch": 0.8581151057848794,
      "grad_norm": 0.07715047895908356,
      "learning_rate": 0.00014571428571428572,
      "loss": 25.064,
      "step": 1450
    },
    {
      "epoch": 0.8729101938156532,
      "grad_norm": 0.034074705094099045,
      "learning_rate": 0.0001447082494969819,
      "loss": 25.0995,
      "step": 1475
    },
    {
      "epoch": 0.8877052818464269,
      "grad_norm": 0.030254002660512924,
      "learning_rate": 0.00014370221327967807,
      "loss": 25.059,
      "step": 1500
    },
    {
      "epoch": 0.9025003698772007,
      "grad_norm": 0.031632065773010254,
      "learning_rate": 0.00014269617706237425,
      "loss": 25.0555,
      "step": 1525
    },
    {
      "epoch": 0.9172954579079745,
      "grad_norm": 0.041883744299411774,
      "learning_rate": 0.00014169014084507045,
      "loss": 25.077,
      "step": 1550
    },
    {
      "epoch": 0.9320905459387483,
      "grad_norm": 0.03643975779414177,
      "learning_rate": 0.0001406841046277666,
      "loss": 25.0556,
      "step": 1575
    },
    {
      "epoch": 0.9468856339695221,
      "grad_norm": 0.0535462461411953,
      "learning_rate": 0.00013967806841046277,
      "loss": 25.0945,
      "step": 1600
    },
    {
      "epoch": 0.9616807220002959,
      "grad_norm": 0.0349336676299572,
      "learning_rate": 0.00013867203219315898,
      "loss": 25.0823,
      "step": 1625
    },
    {
      "epoch": 0.9764758100310696,
      "grad_norm": 0.041822321712970734,
      "learning_rate": 0.00013766599597585515,
      "loss": 25.0856,
      "step": 1650
    },
    {
      "epoch": 0.9912708980618434,
      "grad_norm": 0.04077128693461418,
      "learning_rate": 0.0001366599597585513,
      "loss": 25.0666,
      "step": 1675
    },
    {
      "epoch": 1.0059180352123096,
      "grad_norm": 0.019722955301404,
      "learning_rate": 0.00013565392354124748,
      "loss": 25.0682,
      "step": 1700
    },
    {
      "epoch": 1.0207131232430833,
      "grad_norm": 0.03321698307991028,
      "learning_rate": 0.00013464788732394368,
      "loss": 25.1371,
      "step": 1725
    },
    {
      "epoch": 1.0355082112738572,
      "grad_norm": 0.041920218616724014,
      "learning_rate": 0.00013364185110663985,
      "loss": 24.9934,
      "step": 1750
    },
    {
      "epoch": 1.0503032993046308,
      "grad_norm": 0.03674553334712982,
      "learning_rate": 0.00013263581488933603,
      "loss": 25.1142,
      "step": 1775
    },
    {
      "epoch": 1.0650983873354047,
      "grad_norm": 0.03412509709596634,
      "learning_rate": 0.00013162977867203218,
      "loss": 25.0697,
      "step": 1800
    },
    {
      "epoch": 1.0798934753661784,
      "grad_norm": 0.039162006229162216,
      "learning_rate": 0.00013062374245472838,
      "loss": 25.0618,
      "step": 1825
    },
    {
      "epoch": 1.0946885633969523,
      "grad_norm": 0.06998290121555328,
      "learning_rate": 0.00012961770623742456,
      "loss": 25.1045,
      "step": 1850
    },
    {
      "epoch": 1.109483651427726,
      "grad_norm": 0.029092537239193916,
      "learning_rate": 0.00012861167002012073,
      "loss": 24.9204,
      "step": 1875
    },
    {
      "epoch": 1.1242787394584999,
      "grad_norm": 0.027615416795015335,
      "learning_rate": 0.0001276056338028169,
      "loss": 25.066,
      "step": 1900
    },
    {
      "epoch": 1.1390738274892735,
      "grad_norm": 0.029055271297693253,
      "learning_rate": 0.00012659959758551308,
      "loss": 25.0113,
      "step": 1925
    },
    {
      "epoch": 1.1538689155200474,
      "grad_norm": 0.03415543958544731,
      "learning_rate": 0.00012559356136820926,
      "loss": 25.025,
      "step": 1950
    },
    {
      "epoch": 1.1686640035508211,
      "grad_norm": 0.04656201973557472,
      "learning_rate": 0.00012458752515090543,
      "loss": 25.0861,
      "step": 1975
    },
    {
      "epoch": 1.1834590915815948,
      "grad_norm": 0.03144572675228119,
      "learning_rate": 0.0001235814889336016,
      "loss": 25.025,
      "step": 2000
    },
    {
      "epoch": 1.1982541796123687,
      "grad_norm": 0.036187801510095596,
      "learning_rate": 0.0001225754527162978,
      "loss": 25.1279,
      "step": 2025
    },
    {
      "epoch": 1.2130492676431426,
      "grad_norm": 0.031620871275663376,
      "learning_rate": 0.00012156941649899396,
      "loss": 24.9931,
      "step": 2050
    },
    {
      "epoch": 1.2278443556739163,
      "grad_norm": 0.034921254962682724,
      "learning_rate": 0.00012056338028169015,
      "loss": 25.0693,
      "step": 2075
    },
    {
      "epoch": 1.24263944370469,
      "grad_norm": 0.03131638467311859,
      "learning_rate": 0.00011955734406438632,
      "loss": 25.0967,
      "step": 2100
    },
    {
      "epoch": 1.2574345317354638,
      "grad_norm": 0.03819598630070686,
      "learning_rate": 0.0001185513078470825,
      "loss": 25.1187,
      "step": 2125
    },
    {
      "epoch": 1.2722296197662377,
      "grad_norm": 0.02910611405968666,
      "learning_rate": 0.00011754527162977869,
      "loss": 25.1261,
      "step": 2150
    },
    {
      "epoch": 1.2870247077970114,
      "grad_norm": 0.028234301134943962,
      "learning_rate": 0.00011653923541247485,
      "loss": 25.1246,
      "step": 2175
    },
    {
      "epoch": 1.301819795827785,
      "grad_norm": 0.03955462947487831,
      "learning_rate": 0.00011553319919517103,
      "loss": 25.1732,
      "step": 2200
    },
    {
      "epoch": 1.316614883858559,
      "grad_norm": 0.06937497854232788,
      "learning_rate": 0.00011452716297786721,
      "loss": 25.1451,
      "step": 2225
    },
    {
      "epoch": 1.3314099718893329,
      "grad_norm": 0.025304747745394707,
      "learning_rate": 0.00011352112676056339,
      "loss": 25.0555,
      "step": 2250
    },
    {
      "epoch": 1.3462050599201065,
      "grad_norm": 0.03724834695458412,
      "learning_rate": 0.00011251509054325957,
      "loss": 25.0753,
      "step": 2275
    },
    {
      "epoch": 1.3610001479508802,
      "grad_norm": 0.033879607915878296,
      "learning_rate": 0.00011150905432595573,
      "loss": 25.0954,
      "step": 2300
    },
    {
      "epoch": 1.375795235981654,
      "grad_norm": 0.024116437882184982,
      "learning_rate": 0.00011050301810865192,
      "loss": 25.0815,
      "step": 2325
    },
    {
      "epoch": 1.390590324012428,
      "grad_norm": 0.0369427315890789,
      "learning_rate": 0.00010949698189134809,
      "loss": 25.1871,
      "step": 2350
    },
    {
      "epoch": 1.4053854120432017,
      "grad_norm": 0.03194064274430275,
      "learning_rate": 0.00010849094567404428,
      "loss": 25.0658,
      "step": 2375
    },
    {
      "epoch": 1.4201805000739753,
      "grad_norm": 0.028080854564905167,
      "learning_rate": 0.00010748490945674046,
      "loss": 25.072,
      "step": 2400
    },
    {
      "epoch": 1.4349755881047492,
      "grad_norm": 0.028207939118146896,
      "learning_rate": 0.00010647887323943662,
      "loss": 25.0783,
      "step": 2425
    },
    {
      "epoch": 1.4497706761355231,
      "grad_norm": 0.028028592467308044,
      "learning_rate": 0.0001054728370221328,
      "loss": 25.0861,
      "step": 2450
    },
    {
      "epoch": 1.4645657641662968,
      "grad_norm": 0.03247331827878952,
      "learning_rate": 0.00010446680080482898,
      "loss": 25.096,
      "step": 2475
    },
    {
      "epoch": 1.4793608521970705,
      "grad_norm": 0.031846486032009125,
      "learning_rate": 0.00010346076458752516,
      "loss": 25.1463,
      "step": 2500
    },
    {
      "epoch": 1.4941559402278444,
      "grad_norm": 0.02977578528225422,
      "learning_rate": 0.00010245472837022135,
      "loss": 25.0884,
      "step": 2525
    },
    {
      "epoch": 1.5089510282586183,
      "grad_norm": 0.028014151379466057,
      "learning_rate": 0.0001014486921529175,
      "loss": 25.1056,
      "step": 2550
    },
    {
      "epoch": 1.523746116289392,
      "grad_norm": 0.03780132159590721,
      "learning_rate": 0.00010044265593561368,
      "loss": 25.0724,
      "step": 2575
    },
    {
      "epoch": 1.5385412043201656,
      "grad_norm": 0.0535607747733593,
      "learning_rate": 9.943661971830986e-05,
      "loss": 25.078,
      "step": 2600
    },
    {
      "epoch": 1.5533362923509395,
      "grad_norm": 0.03189392760396004,
      "learning_rate": 9.843058350100605e-05,
      "loss": 25.0673,
      "step": 2625
    },
    {
      "epoch": 1.5681313803817134,
      "grad_norm": 0.049738895148038864,
      "learning_rate": 9.742454728370221e-05,
      "loss": 24.9634,
      "step": 2650
    },
    {
      "epoch": 1.582926468412487,
      "grad_norm": 0.02845073491334915,
      "learning_rate": 9.64185110663984e-05,
      "loss": 25.0932,
      "step": 2675
    },
    {
      "epoch": 1.5977215564432607,
      "grad_norm": 0.023111697286367416,
      "learning_rate": 9.541247484909458e-05,
      "loss": 25.0889,
      "step": 2700
    },
    {
      "epoch": 1.6125166444740346,
      "grad_norm": 0.029083825647830963,
      "learning_rate": 9.440643863179075e-05,
      "loss": 25.0686,
      "step": 2725
    },
    {
      "epoch": 1.6273117325048085,
      "grad_norm": 0.02137155272066593,
      "learning_rate": 9.340040241448693e-05,
      "loss": 25.0946,
      "step": 2750
    },
    {
      "epoch": 1.6421068205355822,
      "grad_norm": 0.0255599282681942,
      "learning_rate": 9.23943661971831e-05,
      "loss": 24.9854,
      "step": 2775
    },
    {
      "epoch": 1.6569019085663559,
      "grad_norm": 0.029308602213859558,
      "learning_rate": 9.138832997987928e-05,
      "loss": 25.082,
      "step": 2800
    },
    {
      "epoch": 1.6716969965971298,
      "grad_norm": 0.03403579071164131,
      "learning_rate": 9.038229376257545e-05,
      "loss": 25.0498,
      "step": 2825
    },
    {
      "epoch": 1.6864920846279037,
      "grad_norm": 0.03986509144306183,
      "learning_rate": 8.937625754527164e-05,
      "loss": 25.018,
      "step": 2850
    },
    {
      "epoch": 1.7012871726586773,
      "grad_norm": 0.03191569447517395,
      "learning_rate": 8.83702213279678e-05,
      "loss": 24.9913,
      "step": 2875
    },
    {
      "epoch": 1.716082260689451,
      "grad_norm": 0.04105932265520096,
      "learning_rate": 8.736418511066399e-05,
      "loss": 25.0711,
      "step": 2900
    },
    {
      "epoch": 1.730877348720225,
      "grad_norm": 0.025144483894109726,
      "learning_rate": 8.635814889336017e-05,
      "loss": 25.1367,
      "step": 2925
    },
    {
      "epoch": 1.7456724367509988,
      "grad_norm": 0.043975986540317535,
      "learning_rate": 8.535211267605634e-05,
      "loss": 25.0362,
      "step": 2950
    },
    {
      "epoch": 1.7604675247817725,
      "grad_norm": 0.03802431747317314,
      "learning_rate": 8.434607645875252e-05,
      "loss": 25.0193,
      "step": 2975
    },
    {
      "epoch": 1.7752626128125462,
      "grad_norm": 0.04078783094882965,
      "learning_rate": 8.33400402414487e-05,
      "loss": 25.1258,
      "step": 3000
    },
    {
      "epoch": 1.79005770084332,
      "grad_norm": 0.03382691368460655,
      "learning_rate": 8.233400402414487e-05,
      "loss": 25.1644,
      "step": 3025
    },
    {
      "epoch": 1.804852788874094,
      "grad_norm": 0.038282644003629684,
      "learning_rate": 8.132796780684106e-05,
      "loss": 25.0844,
      "step": 3050
    },
    {
      "epoch": 1.8196478769048676,
      "grad_norm": 0.035348743200302124,
      "learning_rate": 8.032193158953722e-05,
      "loss": 25.0073,
      "step": 3075
    },
    {
      "epoch": 1.8344429649356413,
      "grad_norm": 0.02938913181424141,
      "learning_rate": 7.931589537223341e-05,
      "loss": 25.1201,
      "step": 3100
    },
    {
      "epoch": 1.8492380529664152,
      "grad_norm": 0.07416849583387375,
      "learning_rate": 7.830985915492957e-05,
      "loss": 25.0517,
      "step": 3125
    },
    {
      "epoch": 1.864033140997189,
      "grad_norm": 0.05911872908473015,
      "learning_rate": 7.730382293762576e-05,
      "loss": 25.085,
      "step": 3150
    },
    {
      "epoch": 1.8788282290279628,
      "grad_norm": 0.03909540921449661,
      "learning_rate": 7.629778672032194e-05,
      "loss": 25.0817,
      "step": 3175
    },
    {
      "epoch": 1.8936233170587364,
      "grad_norm": 0.03437948599457741,
      "learning_rate": 7.529175050301811e-05,
      "loss": 25.0958,
      "step": 3200
    },
    {
      "epoch": 1.9084184050895103,
      "grad_norm": 0.03295779228210449,
      "learning_rate": 7.428571428571429e-05,
      "loss": 25.075,
      "step": 3225
    },
    {
      "epoch": 1.9232134931202842,
      "grad_norm": 0.028107503429055214,
      "learning_rate": 7.327967806841046e-05,
      "loss": 25.0909,
      "step": 3250
    },
    {
      "epoch": 1.938008581151058,
      "grad_norm": 0.03533456474542618,
      "learning_rate": 7.227364185110664e-05,
      "loss": 25.0143,
      "step": 3275
    },
    {
      "epoch": 1.9528036691818316,
      "grad_norm": 0.030729498714208603,
      "learning_rate": 7.126760563380283e-05,
      "loss": 25.0024,
      "step": 3300
    },
    {
      "epoch": 1.9675987572126055,
      "grad_norm": 0.02123214863240719,
      "learning_rate": 7.0261569416499e-05,
      "loss": 25.1211,
      "step": 3325
    },
    {
      "epoch": 1.9823938452433794,
      "grad_norm": 0.03742063418030739,
      "learning_rate": 6.925553319919518e-05,
      "loss": 25.1436,
      "step": 3350
    },
    {
      "epoch": 1.997188933274153,
      "grad_norm": 0.03187941387295723,
      "learning_rate": 6.824949698189135e-05,
      "loss": 24.9736,
      "step": 3375
    },
    {
      "epoch": 2.011836070424619,
      "grad_norm": 0.032343629747629166,
      "learning_rate": 6.724346076458753e-05,
      "loss": 25.0978,
      "step": 3400
    },
    {
      "epoch": 2.026631158455393,
      "grad_norm": 0.032404378056526184,
      "learning_rate": 6.62374245472837e-05,
      "loss": 25.0795,
      "step": 3425
    },
    {
      "epoch": 2.0414262464861666,
      "grad_norm": 0.025061512365937233,
      "learning_rate": 6.523138832997988e-05,
      "loss": 25.0731,
      "step": 3450
    },
    {
      "epoch": 2.0562213345169402,
      "grad_norm": 0.03708725795149803,
      "learning_rate": 6.422535211267607e-05,
      "loss": 25.1702,
      "step": 3475
    },
    {
      "epoch": 2.0710164225477143,
      "grad_norm": 0.030988432466983795,
      "learning_rate": 6.321931589537223e-05,
      "loss": 25.0596,
      "step": 3500
    },
    {
      "epoch": 2.085811510578488,
      "grad_norm": 0.02645169198513031,
      "learning_rate": 6.221327967806842e-05,
      "loss": 25.078,
      "step": 3525
    },
    {
      "epoch": 2.1006065986092617,
      "grad_norm": 0.032431282103061676,
      "learning_rate": 6.120724346076458e-05,
      "loss": 25.0198,
      "step": 3550
    },
    {
      "epoch": 2.1154016866400354,
      "grad_norm": 0.02121451124548912,
      "learning_rate": 6.0201207243460764e-05,
      "loss": 25.103,
      "step": 3575
    },
    {
      "epoch": 2.1301967746708095,
      "grad_norm": 0.02786272205412388,
      "learning_rate": 5.9195171026156946e-05,
      "loss": 25.1066,
      "step": 3600
    },
    {
      "epoch": 2.144991862701583,
      "grad_norm": 0.031123634427785873,
      "learning_rate": 5.818913480885312e-05,
      "loss": 25.0548,
      "step": 3625
    },
    {
      "epoch": 2.159786950732357,
      "grad_norm": 0.02966328151524067,
      "learning_rate": 5.71830985915493e-05,
      "loss": 25.072,
      "step": 3650
    },
    {
      "epoch": 2.1745820387631305,
      "grad_norm": 0.03140266612172127,
      "learning_rate": 5.617706237424547e-05,
      "loss": 25.0909,
      "step": 3675
    },
    {
      "epoch": 2.1893771267939046,
      "grad_norm": 0.02315523661673069,
      "learning_rate": 5.5171026156941655e-05,
      "loss": 25.0799,
      "step": 3700
    },
    {
      "epoch": 2.2041722148246783,
      "grad_norm": 0.030268024653196335,
      "learning_rate": 5.416498993963784e-05,
      "loss": 25.031,
      "step": 3725
    },
    {
      "epoch": 2.218967302855452,
      "grad_norm": 0.028935110196471214,
      "learning_rate": 5.3158953722334005e-05,
      "loss": 25.0775,
      "step": 3750
    },
    {
      "epoch": 2.2337623908862256,
      "grad_norm": 0.025782838463783264,
      "learning_rate": 5.215291750503019e-05,
      "loss": 25.0107,
      "step": 3775
    },
    {
      "epoch": 2.2485574789169998,
      "grad_norm": 0.032656069844961166,
      "learning_rate": 5.1146881287726356e-05,
      "loss": 25.0786,
      "step": 3800
    },
    {
      "epoch": 2.2633525669477734,
      "grad_norm": 0.02676152065396309,
      "learning_rate": 5.014084507042254e-05,
      "loss": 25.1132,
      "step": 3825
    },
    {
      "epoch": 2.278147654978547,
      "grad_norm": 0.05472303926944733,
      "learning_rate": 4.9134808853118714e-05,
      "loss": 25.0132,
      "step": 3850
    },
    {
      "epoch": 2.2929427430093208,
      "grad_norm": 0.028085239231586456,
      "learning_rate": 4.812877263581489e-05,
      "loss": 25.0521,
      "step": 3875
    },
    {
      "epoch": 2.307737831040095,
      "grad_norm": 0.030685044825077057,
      "learning_rate": 4.712273641851107e-05,
      "loss": 25.1104,
      "step": 3900
    },
    {
      "epoch": 2.3225329190708686,
      "grad_norm": 0.03963826224207878,
      "learning_rate": 4.611670020120725e-05,
      "loss": 25.0079,
      "step": 3925
    },
    {
      "epoch": 2.3373280071016422,
      "grad_norm": 0.025965016335248947,
      "learning_rate": 4.511066398390342e-05,
      "loss": 25.0729,
      "step": 3950
    },
    {
      "epoch": 2.352123095132416,
      "grad_norm": 0.0241608377546072,
      "learning_rate": 4.41046277665996e-05,
      "loss": 25.0157,
      "step": 3975
    },
    {
      "epoch": 2.3669181831631896,
      "grad_norm": 0.028290821239352226,
      "learning_rate": 4.3098591549295774e-05,
      "loss": 25.102,
      "step": 4000
    },
    {
      "epoch": 2.3817132711939637,
      "grad_norm": 0.0340087004005909,
      "learning_rate": 4.2092555331991956e-05,
      "loss": 25.028,
      "step": 4025
    },
    {
      "epoch": 2.3965083592247374,
      "grad_norm": 0.04680619016289711,
      "learning_rate": 4.108651911468813e-05,
      "loss": 25.1001,
      "step": 4050
    },
    {
      "epoch": 2.411303447255511,
      "grad_norm": 0.0324757918715477,
      "learning_rate": 4.008048289738431e-05,
      "loss": 25.0479,
      "step": 4075
    },
    {
      "epoch": 2.426098535286285,
      "grad_norm": 0.0365682914853096,
      "learning_rate": 3.907444668008048e-05,
      "loss": 25.0715,
      "step": 4100
    },
    {
      "epoch": 2.440893623317059,
      "grad_norm": 0.030593266710639,
      "learning_rate": 3.806841046277666e-05,
      "loss": 25.11,
      "step": 4125
    },
    {
      "epoch": 2.4556887113478325,
      "grad_norm": 0.031157072633504868,
      "learning_rate": 3.706237424547283e-05,
      "loss": 25.0853,
      "step": 4150
    },
    {
      "epoch": 2.470483799378606,
      "grad_norm": 0.03608427569270134,
      "learning_rate": 3.6056338028169015e-05,
      "loss": 24.9746,
      "step": 4175
    },
    {
      "epoch": 2.48527888740938,
      "grad_norm": 0.025035865604877472,
      "learning_rate": 3.505030181086519e-05,
      "loss": 25.0303,
      "step": 4200
    },
    {
      "epoch": 2.500073975440154,
      "grad_norm": 0.031874652951955795,
      "learning_rate": 3.4044265593561366e-05,
      "loss": 25.1169,
      "step": 4225
    },
    {
      "epoch": 2.5148690634709276,
      "grad_norm": 0.02959771454334259,
      "learning_rate": 3.303822937625755e-05,
      "loss": 25.0229,
      "step": 4250
    },
    {
      "epoch": 2.5296641515017013,
      "grad_norm": 0.029369182884693146,
      "learning_rate": 3.2032193158953724e-05,
      "loss": 25.1294,
      "step": 4275
    },
    {
      "epoch": 2.5444592395324754,
      "grad_norm": 0.03211820125579834,
      "learning_rate": 3.1026156941649906e-05,
      "loss": 25.0991,
      "step": 4300
    },
    {
      "epoch": 2.559254327563249,
      "grad_norm": 0.0338427871465683,
      "learning_rate": 3.002012072434608e-05,
      "loss": 25.0448,
      "step": 4325
    },
    {
      "epoch": 2.574049415594023,
      "grad_norm": 0.03451085835695267,
      "learning_rate": 2.9014084507042254e-05,
      "loss": 25.0453,
      "step": 4350
    },
    {
      "epoch": 2.5888445036247965,
      "grad_norm": 0.02821294404566288,
      "learning_rate": 2.8008048289738433e-05,
      "loss": 25.0382,
      "step": 4375
    },
    {
      "epoch": 2.60363959165557,
      "grad_norm": 0.032822128385305405,
      "learning_rate": 2.7002012072434608e-05,
      "loss": 25.0809,
      "step": 4400
    },
    {
      "epoch": 2.6184346796863442,
      "grad_norm": 0.03818770870566368,
      "learning_rate": 2.5995975855130787e-05,
      "loss": 25.067,
      "step": 4425
    },
    {
      "epoch": 2.633229767717118,
      "grad_norm": 0.03749888017773628,
      "learning_rate": 2.4989939637826962e-05,
      "loss": 25.091,
      "step": 4450
    },
    {
      "epoch": 2.6480248557478916,
      "grad_norm": 0.027703339233994484,
      "learning_rate": 2.398390342052314e-05,
      "loss": 25.1411,
      "step": 4475
    },
    {
      "epoch": 2.6628199437786657,
      "grad_norm": 0.03599558025598526,
      "learning_rate": 2.2977867203219317e-05,
      "loss": 25.0994,
      "step": 4500
    },
    {
      "epoch": 2.6776150318094394,
      "grad_norm": 0.030554693192243576,
      "learning_rate": 2.1971830985915496e-05,
      "loss": 25.0371,
      "step": 4525
    },
    {
      "epoch": 2.692410119840213,
      "grad_norm": 0.02407955750823021,
      "learning_rate": 2.096579476861167e-05,
      "loss": 25.0952,
      "step": 4550
    },
    {
      "epoch": 2.7072052078709867,
      "grad_norm": 0.03127657622098923,
      "learning_rate": 1.9959758551307846e-05,
      "loss": 25.1274,
      "step": 4575
    },
    {
      "epoch": 2.7220002959017604,
      "grad_norm": 0.03968256711959839,
      "learning_rate": 1.8953722334004025e-05,
      "loss": 24.9342,
      "step": 4600
    },
    {
      "epoch": 2.7367953839325345,
      "grad_norm": 0.034262653440237045,
      "learning_rate": 1.79476861167002e-05,
      "loss": 25.1047,
      "step": 4625
    },
    {
      "epoch": 2.751590471963308,
      "grad_norm": 0.022854868322610855,
      "learning_rate": 1.6941649899396376e-05,
      "loss": 25.1082,
      "step": 4650
    },
    {
      "epoch": 2.766385559994082,
      "grad_norm": 0.03031456097960472,
      "learning_rate": 1.5935613682092555e-05,
      "loss": 25.0574,
      "step": 4675
    },
    {
      "epoch": 2.781180648024856,
      "grad_norm": 0.033804699778556824,
      "learning_rate": 1.4929577464788732e-05,
      "loss": 25.0682,
      "step": 4700
    },
    {
      "epoch": 2.7959757360556297,
      "grad_norm": 0.03536156564950943,
      "learning_rate": 1.3923541247484911e-05,
      "loss": 25.0752,
      "step": 4725
    },
    {
      "epoch": 2.8107708240864033,
      "grad_norm": 0.02477777935564518,
      "learning_rate": 1.2917505030181087e-05,
      "loss": 25.0747,
      "step": 4750
    },
    {
      "epoch": 2.825565912117177,
      "grad_norm": 0.03472886234521866,
      "learning_rate": 1.1911468812877265e-05,
      "loss": 25.058,
      "step": 4775
    },
    {
      "epoch": 2.8403610001479507,
      "grad_norm": 0.03604018688201904,
      "learning_rate": 1.0905432595573441e-05,
      "loss": 25.1504,
      "step": 4800
    },
    {
      "epoch": 2.855156088178725,
      "grad_norm": 0.03106354922056198,
      "learning_rate": 9.899396378269618e-06,
      "loss": 25.1244,
      "step": 4825
    },
    {
      "epoch": 2.8699511762094985,
      "grad_norm": 0.033049870282411575,
      "learning_rate": 8.893360160965795e-06,
      "loss": 25.1288,
      "step": 4850
    },
    {
      "epoch": 2.884746264240272,
      "grad_norm": 0.03024250827729702,
      "learning_rate": 7.887323943661972e-06,
      "loss": 25.0513,
      "step": 4875
    },
    {
      "epoch": 2.8995413522710463,
      "grad_norm": 0.032848477363586426,
      "learning_rate": 6.881287726358149e-06,
      "loss": 25.0365,
      "step": 4900
    },
    {
      "epoch": 2.91433644030182,
      "grad_norm": 0.03320826590061188,
      "learning_rate": 5.875251509054326e-06,
      "loss": 25.1055,
      "step": 4925
    },
    {
      "epoch": 2.9291315283325936,
      "grad_norm": 0.033013731241226196,
      "learning_rate": 4.869215291750504e-06,
      "loss": 25.1015,
      "step": 4950
    },
    {
      "epoch": 2.9439266163633673,
      "grad_norm": 0.026161963120102882,
      "learning_rate": 3.86317907444668e-06,
      "loss": 25.0681,
      "step": 4975
    },
    {
      "epoch": 2.958721704394141,
      "grad_norm": 0.031280238181352615,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 25.0965,
      "step": 5000
    },
    {
      "epoch": 2.973516792424915,
      "grad_norm": 0.02889222465455532,
      "learning_rate": 1.8511066398390342e-06,
      "loss": 25.0899,
      "step": 5025
    },
    {
      "epoch": 2.9883118804556887,
      "grad_norm": 0.04580514132976532,
      "learning_rate": 8.450704225352112e-07,
      "loss": 25.1615,
      "step": 5050
    }
  ],
  "logging_steps": 25,
  "max_steps": 5070,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.599080012584059e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}