{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 54600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004578796509125542,
      "grad_norm": 3.342534303665161,
      "learning_rate": 2.28021978021978e-05,
      "loss": 3.3527626953125,
      "step": 250
    },
    {
      "epoch": 0.009157593018251083,
      "grad_norm": 4.355895042419434,
      "learning_rate": 4.5695970695970695e-05,
      "loss": 1.733473876953125,
      "step": 500
    },
    {
      "epoch": 0.013736389527376625,
      "grad_norm": 1.9130524396896362,
      "learning_rate": 6.85897435897436e-05,
      "loss": 1.234192626953125,
      "step": 750
    },
    {
      "epoch": 0.018315186036502167,
      "grad_norm": 1.457084059715271,
      "learning_rate": 9.148351648351648e-05,
      "loss": 1.120093017578125,
      "step": 1000
    },
    {
      "epoch": 0.022893982545627706,
      "grad_norm": 1.005660891532898,
      "learning_rate": 0.00011437728937728938,
      "loss": 1.04007568359375,
      "step": 1250
    },
    {
      "epoch": 0.02747277905475325,
      "grad_norm": 0.6642019748687744,
      "learning_rate": 0.00013727106227106228,
      "loss": 0.979659912109375,
      "step": 1500
    },
    {
      "epoch": 0.03205157556387879,
      "grad_norm": 0.4342072308063507,
      "learning_rate": 0.00016016483516483518,
      "loss": 0.92401513671875,
      "step": 1750
    },
    {
      "epoch": 0.03663037207300433,
      "grad_norm": 0.30285128951072693,
      "learning_rate": 0.00018305860805860804,
      "loss": 0.8480064086914062,
      "step": 2000
    },
    {
      "epoch": 0.041209168582129876,
      "grad_norm": 0.3807497024536133,
      "learning_rate": 0.00020595238095238094,
      "loss": 0.8091620483398437,
      "step": 2250
    },
    {
      "epoch": 0.04578796509125541,
      "grad_norm": 0.2316020131111145,
      "learning_rate": 0.00022884615384615383,
      "loss": 0.786201171875,
      "step": 2500
    },
    {
      "epoch": 0.050366761600380956,
      "grad_norm": 0.24112890660762787,
      "learning_rate": 0.0002517399267399267,
      "loss": 0.7673829956054687,
      "step": 2750
    },
    {
      "epoch": 0.0549455581095065,
      "grad_norm": 0.209824338555336,
      "learning_rate": 0.00027463369963369965,
      "loss": 0.7533621826171875,
      "step": 3000
    },
    {
      "epoch": 0.059524354618632036,
      "grad_norm": 0.1774982362985611,
      "learning_rate": 0.0002975274725274725,
      "loss": 0.7406448364257813,
      "step": 3250
    },
    {
      "epoch": 0.06410315112775758,
      "grad_norm": 0.18220750987529755,
      "learning_rate": 0.00032042124542124543,
      "loss": 0.7278763427734375,
      "step": 3500
    },
    {
      "epoch": 0.06868194763688312,
      "grad_norm": 0.15290245413780212,
      "learning_rate": 0.0003433150183150183,
      "loss": 0.7186447143554687,
      "step": 3750
    },
    {
      "epoch": 0.07326074414600867,
      "grad_norm": 0.15288487076759338,
      "learning_rate": 0.00036620879120879117,
      "loss": 0.7105338134765625,
      "step": 4000
    },
    {
      "epoch": 0.07783954065513421,
      "grad_norm": 0.1429632157087326,
      "learning_rate": 0.00038910256410256414,
      "loss": 0.702983154296875,
      "step": 4250
    },
    {
      "epoch": 0.08241833716425975,
      "grad_norm": 0.13405482470989227,
      "learning_rate": 0.000411996336996337,
      "loss": 0.6989120483398438,
      "step": 4500
    },
    {
      "epoch": 0.08699713367338528,
      "grad_norm": 0.12790542840957642,
      "learning_rate": 0.00043489010989010993,
      "loss": 0.6919224243164063,
      "step": 4750
    },
    {
      "epoch": 0.09157593018251083,
      "grad_norm": 0.12135355174541473,
      "learning_rate": 0.0004577838827838828,
      "loss": 0.6880528564453126,
      "step": 5000
    },
    {
      "epoch": 0.09615472669163637,
      "grad_norm": 0.11120759695768356,
      "learning_rate": 0.0004806776556776557,
      "loss": 0.6828602294921875,
      "step": 5250
    },
    {
      "epoch": 0.10073352320076191,
      "grad_norm": 0.10983391106128693,
      "learning_rate": 0.0004996031746031746,
      "loss": 0.675973876953125,
      "step": 5500
    },
    {
      "epoch": 0.10531231970988746,
      "grad_norm": 0.13301989436149597,
      "learning_rate": 0.000497059422059422,
      "loss": 0.6739141845703125,
      "step": 5750
    },
    {
      "epoch": 0.109891116219013,
      "grad_norm": 0.0955018475651741,
      "learning_rate": 0.0004945156695156695,
      "loss": 0.667236083984375,
      "step": 6000
    },
    {
      "epoch": 0.11446991272813854,
      "grad_norm": 0.10058317333459854,
      "learning_rate": 0.0004919719169719169,
      "loss": 0.6618697509765625,
      "step": 6250
    },
    {
      "epoch": 0.11904870923726407,
      "grad_norm": 0.0959748700261116,
      "learning_rate": 0.0004894281644281644,
      "loss": 0.6591820068359375,
      "step": 6500
    },
    {
      "epoch": 0.12362750574638962,
      "grad_norm": 0.09256613999605179,
      "learning_rate": 0.0004868844118844119,
      "loss": 0.6521591186523438,
      "step": 6750
    },
    {
      "epoch": 0.12820630225551516,
      "grad_norm": 0.09235742688179016,
      "learning_rate": 0.00048434065934065937,
      "loss": 0.6495025634765625,
      "step": 7000
    },
    {
      "epoch": 0.1327850987646407,
      "grad_norm": 0.09277229756116867,
      "learning_rate": 0.0004817969067969068,
      "loss": 0.6460286865234375,
      "step": 7250
    },
    {
      "epoch": 0.13736389527376625,
      "grad_norm": 0.0949406772851944,
      "learning_rate": 0.00047925315425315426,
      "loss": 0.6419014282226563,
      "step": 7500
    },
    {
      "epoch": 0.1419426917828918,
      "grad_norm": 0.09082936495542526,
      "learning_rate": 0.00047670940170940176,
      "loss": 0.64010888671875,
      "step": 7750
    },
    {
      "epoch": 0.14652148829201733,
      "grad_norm": 0.0872732549905777,
      "learning_rate": 0.0004741656491656492,
      "loss": 0.6353873901367187,
      "step": 8000
    },
    {
      "epoch": 0.15110028480114288,
      "grad_norm": 0.08977802842855453,
      "learning_rate": 0.00047162189662189666,
      "loss": 0.634181640625,
      "step": 8250
    },
    {
      "epoch": 0.15567908131026842,
      "grad_norm": 0.08916153013706207,
      "learning_rate": 0.0004690781440781441,
      "loss": 0.6323787841796875,
      "step": 8500
    },
    {
      "epoch": 0.16025787781939396,
      "grad_norm": 0.08718685060739517,
      "learning_rate": 0.00046653439153439155,
      "loss": 0.6297101440429688,
      "step": 8750
    },
    {
      "epoch": 0.1648366743285195,
      "grad_norm": 0.08362448215484619,
      "learning_rate": 0.000463990638990639,
      "loss": 0.6261585083007812,
      "step": 9000
    },
    {
      "epoch": 0.16941547083764502,
      "grad_norm": 0.08333246409893036,
      "learning_rate": 0.0004614468864468865,
      "loss": 0.625505615234375,
      "step": 9250
    },
    {
      "epoch": 0.17399426734677056,
      "grad_norm": 0.08667623996734619,
      "learning_rate": 0.00045890313390313395,
      "loss": 0.62279931640625,
      "step": 9500
    },
    {
      "epoch": 0.1785730638558961,
      "grad_norm": 0.08940846472978592,
      "learning_rate": 0.0004563593813593814,
      "loss": 0.6183375244140625,
      "step": 9750
    },
    {
      "epoch": 0.18315186036502165,
      "grad_norm": 0.0858025848865509,
      "learning_rate": 0.00045381562881562884,
      "loss": 0.6180489501953125,
      "step": 10000
    },
    {
      "epoch": 0.1877306568741472,
      "grad_norm": 0.08406202495098114,
      "learning_rate": 0.0004512718762718763,
      "loss": 0.6160538940429687,
      "step": 10250
    },
    {
      "epoch": 0.19230945338327274,
      "grad_norm": 0.08236856758594513,
      "learning_rate": 0.00044872812372812374,
      "loss": 0.61333447265625,
      "step": 10500
    },
    {
      "epoch": 0.19688824989239828,
      "grad_norm": 0.07843296974897385,
      "learning_rate": 0.00044618437118437124,
      "loss": 0.6112908935546875,
      "step": 10750
    },
    {
      "epoch": 0.20146704640152382,
      "grad_norm": 0.08862949162721634,
      "learning_rate": 0.0004436406186406187,
      "loss": 0.6111968994140625,
      "step": 11000
    },
    {
      "epoch": 0.20604584291064937,
      "grad_norm": 0.07972651720046997,
      "learning_rate": 0.00044109686609686613,
      "loss": 0.60775244140625,
      "step": 11250
    },
    {
      "epoch": 0.2106246394197749,
      "grad_norm": 0.0773809626698494,
      "learning_rate": 0.0004385531135531136,
      "loss": 0.6076170654296875,
      "step": 11500
    },
    {
      "epoch": 0.21520343592890046,
      "grad_norm": 0.08130772411823273,
      "learning_rate": 0.00043600936100936103,
      "loss": 0.60721044921875,
      "step": 11750
    },
    {
      "epoch": 0.219782232438026,
      "grad_norm": 0.08655981719493866,
      "learning_rate": 0.0004334656084656085,
      "loss": 0.6045301513671875,
      "step": 12000
    },
    {
      "epoch": 0.22436102894715154,
      "grad_norm": 0.07923956960439682,
      "learning_rate": 0.000430921855921856,
      "loss": 0.603427490234375,
      "step": 12250
    },
    {
      "epoch": 0.22893982545627709,
      "grad_norm": 0.07150240242481232,
      "learning_rate": 0.0004283781033781034,
      "loss": 0.6024298095703124,
      "step": 12500
    },
    {
      "epoch": 0.2335186219654026,
      "grad_norm": 0.0733460783958435,
      "learning_rate": 0.00042583435083435087,
      "loss": 0.599318115234375,
      "step": 12750
    },
    {
      "epoch": 0.23809741847452814,
      "grad_norm": 0.08155152201652527,
      "learning_rate": 0.0004232905982905983,
      "loss": 0.600461181640625,
      "step": 13000
    },
    {
      "epoch": 0.2426762149836537,
      "grad_norm": 0.08487660437822342,
      "learning_rate": 0.00042074684574684577,
      "loss": 0.599893310546875,
      "step": 13250
    },
    {
      "epoch": 0.24725501149277923,
      "grad_norm": 0.07263469696044922,
      "learning_rate": 0.0004182030932030932,
      "loss": 0.5981270751953125,
      "step": 13500
    },
    {
      "epoch": 0.2518338080019048,
      "grad_norm": 0.0769294798374176,
      "learning_rate": 0.0004156593406593407,
      "loss": 0.597044921875,
      "step": 13750
    },
    {
      "epoch": 0.2564126045110303,
      "grad_norm": 0.0794798731803894,
      "learning_rate": 0.00041311558811558816,
      "loss": 0.5964545288085937,
      "step": 14000
    },
    {
      "epoch": 0.2609914010201559,
      "grad_norm": 0.07667657732963562,
      "learning_rate": 0.0004105718355718356,
      "loss": 0.5919962158203125,
      "step": 14250
    },
    {
      "epoch": 0.2655701975292814,
      "grad_norm": 0.07880273461341858,
      "learning_rate": 0.00040802808302808306,
      "loss": 0.5930234375,
      "step": 14500
    },
    {
      "epoch": 0.2701489940384069,
      "grad_norm": 0.06861519813537598,
      "learning_rate": 0.0004054843304843305,
      "loss": 0.5921943969726563,
      "step": 14750
    },
    {
      "epoch": 0.2747277905475325,
      "grad_norm": 0.0762229785323143,
      "learning_rate": 0.0004029405779405779,
      "loss": 0.5893192749023437,
      "step": 15000
    },
    {
      "epoch": 0.279306587056658,
      "grad_norm": 0.08483275771141052,
      "learning_rate": 0.00040039682539682545,
      "loss": 0.589997314453125,
      "step": 15250
    },
    {
      "epoch": 0.2838853835657836,
      "grad_norm": 0.07121487706899643,
      "learning_rate": 0.0003978530728530729,
      "loss": 0.5913633422851563,
      "step": 15500
    },
    {
      "epoch": 0.2884641800749091,
      "grad_norm": 0.06958875805139542,
      "learning_rate": 0.0003953093203093203,
      "loss": 0.5887347412109375,
      "step": 15750
    },
    {
      "epoch": 0.29304297658403466,
      "grad_norm": 0.08195552974939346,
      "learning_rate": 0.00039276556776556774,
      "loss": 0.5877152099609375,
      "step": 16000
    },
    {
      "epoch": 0.2976217730931602,
      "grad_norm": 0.07579973340034485,
      "learning_rate": 0.0003902218152218152,
      "loss": 0.5861239013671875,
      "step": 16250
    },
    {
      "epoch": 0.30220056960228575,
      "grad_norm": 0.06779183447360992,
      "learning_rate": 0.00038767806267806263,
      "loss": 0.583551025390625,
      "step": 16500
    },
    {
      "epoch": 0.30677936611141127,
      "grad_norm": 0.06482373923063278,
      "learning_rate": 0.00038513431013431014,
      "loss": 0.58420751953125,
      "step": 16750
    },
    {
      "epoch": 0.31135816262053684,
      "grad_norm": 0.07873611152172089,
      "learning_rate": 0.0003825905575905576,
      "loss": 0.5830638427734375,
      "step": 17000
    },
    {
      "epoch": 0.31593695912966235,
      "grad_norm": 0.07843663543462753,
      "learning_rate": 0.00038004680504680503,
      "loss": 0.5826964111328125,
      "step": 17250
    },
    {
      "epoch": 0.3205157556387879,
      "grad_norm": 0.07587391883134842,
      "learning_rate": 0.0003775030525030525,
      "loss": 0.5826300048828125,
      "step": 17500
    },
    {
      "epoch": 0.32509455214791344,
      "grad_norm": 0.0711434856057167,
      "learning_rate": 0.0003749592999592999,
      "loss": 0.58239306640625,
      "step": 17750
    },
    {
      "epoch": 0.329673348657039,
      "grad_norm": 0.07004653662443161,
      "learning_rate": 0.0003724155474155474,
      "loss": 0.5806968994140626,
      "step": 18000
    },
    {
      "epoch": 0.3342521451661645,
      "grad_norm": 0.07417979836463928,
      "learning_rate": 0.0003698717948717949,
      "loss": 0.5811688232421875,
      "step": 18250
    },
    {
      "epoch": 0.33883094167529004,
      "grad_norm": 0.06397568434476852,
      "learning_rate": 0.0003673280423280423,
      "loss": 0.578081787109375,
      "step": 18500
    },
    {
      "epoch": 0.3434097381844156,
      "grad_norm": 0.06324686855077744,
      "learning_rate": 0.00036478428978428977,
      "loss": 0.577623046875,
      "step": 18750
    },
    {
      "epoch": 0.34798853469354113,
      "grad_norm": 0.06681980192661285,
      "learning_rate": 0.0003622405372405372,
      "loss": 0.5780208740234375,
      "step": 19000
    },
    {
      "epoch": 0.3525673312026667,
      "grad_norm": 0.07156607508659363,
      "learning_rate": 0.00035969678469678466,
      "loss": 0.57647021484375,
      "step": 19250
    },
    {
      "epoch": 0.3571461277117922,
      "grad_norm": 0.06628810614347458,
      "learning_rate": 0.00035715303215303216,
      "loss": 0.5765814208984374,
      "step": 19500
    },
    {
      "epoch": 0.3617249242209178,
      "grad_norm": 0.06292615085840225,
      "learning_rate": 0.0003546092796092796,
      "loss": 0.574661865234375,
      "step": 19750
    },
    {
      "epoch": 0.3663037207300433,
      "grad_norm": 0.06046818569302559,
      "learning_rate": 0.00035206552706552706,
      "loss": 0.5743336791992187,
      "step": 20000
    },
    {
      "epoch": 0.3708825172391689,
      "grad_norm": 0.06358954310417175,
      "learning_rate": 0.0003495217745217745,
      "loss": 0.5736307373046875,
      "step": 20250
    },
    {
      "epoch": 0.3754613137482944,
      "grad_norm": 0.06913734972476959,
      "learning_rate": 0.00034697802197802195,
      "loss": 0.5728591918945313,
      "step": 20500
    },
    {
      "epoch": 0.38004011025741996,
      "grad_norm": 0.06982014328241348,
      "learning_rate": 0.0003444342694342694,
      "loss": 0.57314013671875,
      "step": 20750
    },
    {
      "epoch": 0.3846189067665455,
      "grad_norm": 0.06307590007781982,
      "learning_rate": 0.0003418905168905169,
      "loss": 0.5726715087890625,
      "step": 21000
    },
    {
      "epoch": 0.38919770327567105,
      "grad_norm": 0.0676989033818245,
      "learning_rate": 0.00033934676434676435,
      "loss": 0.5700736083984375,
      "step": 21250
    },
    {
      "epoch": 0.39377649978479656,
      "grad_norm": 0.08213786780834198,
      "learning_rate": 0.0003368030118030118,
      "loss": 0.5705738525390625,
      "step": 21500
    },
    {
      "epoch": 0.3983552962939221,
      "grad_norm": 0.06425507366657257,
      "learning_rate": 0.00033425925925925924,
      "loss": 0.56998388671875,
      "step": 21750
    },
    {
      "epoch": 0.40293409280304765,
      "grad_norm": 0.06765250116586685,
      "learning_rate": 0.0003317155067155067,
      "loss": 0.5707243041992187,
      "step": 22000
    },
    {
      "epoch": 0.40751288931217317,
      "grad_norm": 0.07066161930561066,
      "learning_rate": 0.00032917175417175414,
      "loss": 0.5674595947265625,
      "step": 22250
    },
    {
      "epoch": 0.41209168582129874,
      "grad_norm": 0.07193256914615631,
      "learning_rate": 0.00032662800162800164,
      "loss": 0.5684276123046875,
      "step": 22500
    },
    {
      "epoch": 0.41667048233042425,
      "grad_norm": 0.06980223953723907,
      "learning_rate": 0.0003240842490842491,
      "loss": 0.5667611694335938,
      "step": 22750
    },
    {
      "epoch": 0.4212492788395498,
      "grad_norm": 0.06676173955202103,
      "learning_rate": 0.00032154049654049653,
      "loss": 0.5669996337890625,
      "step": 23000
    },
    {
      "epoch": 0.42582807534867534,
      "grad_norm": 0.06899011880159378,
      "learning_rate": 0.000318996743996744,
      "loss": 0.5668095703125,
      "step": 23250
    },
    {
      "epoch": 0.4304068718578009,
      "grad_norm": 0.06902206689119339,
      "learning_rate": 0.00031645299145299143,
      "loss": 0.5664789428710938,
      "step": 23500
    },
    {
      "epoch": 0.4349856683669264,
      "grad_norm": 0.06520352512598038,
      "learning_rate": 0.0003139092389092389,
      "loss": 0.5667901000976563,
      "step": 23750
    },
    {
      "epoch": 0.439564464876052,
      "grad_norm": 0.06156212091445923,
      "learning_rate": 0.0003113654863654864,
      "loss": 0.5641578369140625,
      "step": 24000
    },
    {
      "epoch": 0.4441432613851775,
      "grad_norm": 0.06374220550060272,
      "learning_rate": 0.0003088217338217338,
      "loss": 0.5657506103515625,
      "step": 24250
    },
    {
      "epoch": 0.4487220578943031,
      "grad_norm": 0.06591662019491196,
      "learning_rate": 0.00030627798127798127,
      "loss": 0.56384130859375,
      "step": 24500
    },
    {
      "epoch": 0.4533008544034286,
      "grad_norm": 0.06188199669122696,
      "learning_rate": 0.0003037342287342287,
      "loss": 0.56164990234375,
      "step": 24750
    },
    {
      "epoch": 0.45787965091255417,
      "grad_norm": 0.06126328930258751,
      "learning_rate": 0.00030119047619047616,
      "loss": 0.5632687377929687,
      "step": 25000
    },
    {
      "epoch": 0.4624584474216797,
      "grad_norm": 0.06881853938102722,
      "learning_rate": 0.0002986467236467236,
      "loss": 0.5626099853515625,
      "step": 25250
    },
    {
      "epoch": 0.4670372439308052,
      "grad_norm": 0.06128287687897682,
      "learning_rate": 0.0002961029711029711,
      "loss": 0.5612110595703125,
      "step": 25500
    },
    {
      "epoch": 0.4716160404399308,
      "grad_norm": 0.06223996356129646,
      "learning_rate": 0.00029355921855921856,
      "loss": 0.562291015625,
      "step": 25750
    },
    {
      "epoch": 0.4761948369490563,
      "grad_norm": 0.0587678961455822,
      "learning_rate": 0.000291015466015466,
      "loss": 0.562425048828125,
      "step": 26000
    },
    {
      "epoch": 0.48077363345818186,
      "grad_norm": 0.06476189941167831,
      "learning_rate": 0.00028847171347171346,
      "loss": 0.559524658203125,
      "step": 26250
    },
    {
      "epoch": 0.4853524299673074,
      "grad_norm": 0.05949617549777031,
      "learning_rate": 0.0002859279609279609,
      "loss": 0.5606175537109375,
      "step": 26500
    },
    {
      "epoch": 0.48993122647643295,
      "grad_norm": 0.0664505809545517,
      "learning_rate": 0.00028338420838420835,
      "loss": 0.5592316284179687,
      "step": 26750
    },
    {
      "epoch": 0.49451002298555846,
      "grad_norm": 0.06326252967119217,
      "learning_rate": 0.00028084045584045585,
      "loss": 0.560334716796875,
      "step": 27000
    },
    {
      "epoch": 0.49908881949468403,
      "grad_norm": 0.065422423183918,
      "learning_rate": 0.0002782967032967033,
      "loss": 0.558829833984375,
      "step": 27250
    },
    {
      "epoch": 0.5036676160038096,
      "grad_norm": 0.0695870891213417,
      "learning_rate": 0.00027575295075295075,
      "loss": 0.558175537109375,
      "step": 27500
    },
    {
      "epoch": 0.5082464125129351,
      "grad_norm": 0.06475581973791122,
      "learning_rate": 0.0002732091982091982,
      "loss": 0.5586744384765625,
      "step": 27750
    },
    {
      "epoch": 0.5128252090220606,
      "grad_norm": 0.06314811110496521,
      "learning_rate": 0.00027066544566544564,
      "loss": 0.5569791259765625,
      "step": 28000
    },
    {
      "epoch": 0.5174040055311862,
      "grad_norm": 0.06873711943626404,
      "learning_rate": 0.0002681216931216931,
      "loss": 0.5555595092773438,
      "step": 28250
    },
    {
      "epoch": 0.5219828020403118,
      "grad_norm": 0.06372768431901932,
      "learning_rate": 0.0002655779405779406,
      "loss": 0.55628759765625,
      "step": 28500
    },
    {
      "epoch": 0.5265615985494373,
      "grad_norm": 0.06410428136587143,
      "learning_rate": 0.00026303418803418804,
      "loss": 0.5568046875,
      "step": 28750
    },
    {
      "epoch": 0.5311403950585628,
      "grad_norm": 0.0655541867017746,
      "learning_rate": 0.0002604904354904355,
      "loss": 0.555463623046875,
      "step": 29000
    },
    {
      "epoch": 0.5357191915676883,
      "grad_norm": 0.061745524406433105,
      "learning_rate": 0.00025794668294668293,
      "loss": 0.5544102783203125,
      "step": 29250
    },
    {
      "epoch": 0.5402979880768138,
      "grad_norm": 0.06390813738107681,
      "learning_rate": 0.0002554029304029304,
      "loss": 0.5550816650390625,
      "step": 29500
    },
    {
      "epoch": 0.5448767845859395,
      "grad_norm": 0.06350462883710861,
      "learning_rate": 0.0002528591778591779,
      "loss": 0.5545914306640625,
      "step": 29750
    },
    {
      "epoch": 0.549455581095065,
      "grad_norm": 0.07035643607378006,
      "learning_rate": 0.0002503154253154253,
      "loss": 0.5539207763671875,
      "step": 30000
    },
    {
      "epoch": 0.5540343776041905,
      "grad_norm": 0.060600634664297104,
      "learning_rate": 0.0002477716727716728,
      "loss": 0.5543575439453124,
      "step": 30250
    },
    {
      "epoch": 0.558613174113316,
      "grad_norm": 0.07064654678106308,
      "learning_rate": 0.0002452279202279202,
      "loss": 0.5540496826171875,
      "step": 30500
    },
    {
      "epoch": 0.5631919706224416,
      "grad_norm": 0.06378184258937836,
      "learning_rate": 0.00024268416768416767,
      "loss": 0.55242919921875,
      "step": 30750
    },
    {
      "epoch": 0.5677707671315672,
      "grad_norm": 0.062876857817173,
      "learning_rate": 0.00024014041514041514,
      "loss": 0.5535072021484375,
      "step": 31000
    },
    {
      "epoch": 0.5723495636406927,
      "grad_norm": 0.06333809345960617,
      "learning_rate": 0.0002375966625966626,
      "loss": 0.551296142578125,
      "step": 31250
    },
    {
      "epoch": 0.5769283601498182,
      "grad_norm": 0.06588946282863617,
      "learning_rate": 0.00023505291005291004,
      "loss": 0.5515674438476562,
      "step": 31500
    },
    {
      "epoch": 0.5815071566589438,
      "grad_norm": 0.05932895466685295,
      "learning_rate": 0.0002325091575091575,
      "loss": 0.5509488525390625,
      "step": 31750
    },
    {
      "epoch": 0.5860859531680693,
      "grad_norm": 0.06366723030805588,
      "learning_rate": 0.00022996540496540496,
      "loss": 0.549708984375,
      "step": 32000
    },
    {
      "epoch": 0.5906647496771948,
      "grad_norm": 0.06046701595187187,
      "learning_rate": 0.0002274216524216524,
      "loss": 0.548451904296875,
      "step": 32250
    },
    {
      "epoch": 0.5952435461863204,
      "grad_norm": 0.060656215995550156,
      "learning_rate": 0.00022487789987789988,
      "loss": 0.55017724609375,
      "step": 32500
    },
    {
      "epoch": 0.5998223426954459,
      "grad_norm": 0.06226223334670067,
      "learning_rate": 0.00022233414733414733,
      "loss": 0.5499310913085937,
      "step": 32750
    },
    {
      "epoch": 0.6044011392045715,
      "grad_norm": 0.06266618520021439,
      "learning_rate": 0.00021979039479039477,
      "loss": 0.5480341796875,
      "step": 33000
    },
    {
      "epoch": 0.608979935713697,
      "grad_norm": 0.06450474262237549,
      "learning_rate": 0.00021724664224664225,
      "loss": 0.55114453125,
      "step": 33250
    },
    {
      "epoch": 0.6135587322228225,
      "grad_norm": 0.06394919753074646,
      "learning_rate": 0.0002147028897028897,
      "loss": 0.5472305908203124,
      "step": 33500
    },
    {
      "epoch": 0.618137528731948,
      "grad_norm": 0.06171587482094765,
      "learning_rate": 0.00021215913715913714,
      "loss": 0.547580322265625,
      "step": 33750
    },
    {
      "epoch": 0.6227163252410737,
      "grad_norm": 0.058975059539079666,
      "learning_rate": 0.00020961538461538462,
      "loss": 0.5463271484375,
      "step": 34000
    },
    {
      "epoch": 0.6272951217501992,
      "grad_norm": 0.061736807227134705,
      "learning_rate": 0.00020707163207163206,
      "loss": 0.5462554931640625,
      "step": 34250
    },
    {
      "epoch": 0.6318739182593247,
      "grad_norm": 0.06212234124541283,
      "learning_rate": 0.00020452787952787954,
      "loss": 0.546873291015625,
      "step": 34500
    },
    {
      "epoch": 0.6364527147684502,
      "grad_norm": 0.06781437247991562,
      "learning_rate": 0.00020198412698412699,
      "loss": 0.5456260986328125,
      "step": 34750
    },
    {
      "epoch": 0.6410315112775758,
      "grad_norm": 0.05848696827888489,
      "learning_rate": 0.00019944037444037443,
      "loss": 0.5449661865234375,
      "step": 35000
    },
    {
      "epoch": 0.6456103077867014,
      "grad_norm": 0.06378760188817978,
      "learning_rate": 0.0001968966218966219,
      "loss": 0.545228515625,
      "step": 35250
    },
    {
      "epoch": 0.6501891042958269,
      "grad_norm": 0.06400810182094574,
      "learning_rate": 0.00019435286935286935,
      "loss": 0.545167724609375,
      "step": 35500
    },
    {
      "epoch": 0.6547679008049524,
      "grad_norm": 0.06151324138045311,
      "learning_rate": 0.0001918091168091168,
      "loss": 0.545171875,
      "step": 35750
    },
    {
      "epoch": 0.659346697314078,
      "grad_norm": 0.06354264169931412,
      "learning_rate": 0.00018926536426536428,
      "loss": 0.545235107421875,
      "step": 36000
    },
    {
      "epoch": 0.6639254938232035,
      "grad_norm": 0.05942839756608009,
      "learning_rate": 0.00018672161172161172,
      "loss": 0.5439722290039063,
      "step": 36250
    },
    {
      "epoch": 0.668504290332329,
      "grad_norm": 0.0653739720582962,
      "learning_rate": 0.00018417785917785917,
      "loss": 0.5418724365234375,
      "step": 36500
    },
    {
      "epoch": 0.6730830868414546,
      "grad_norm": 0.062099047005176544,
      "learning_rate": 0.00018163410663410664,
      "loss": 0.5428839721679688,
      "step": 36750
    },
    {
      "epoch": 0.6776618833505801,
      "grad_norm": 0.06153613328933716,
      "learning_rate": 0.0001790903540903541,
      "loss": 0.5429735717773437,
      "step": 37000
    },
    {
      "epoch": 0.6822406798597057,
      "grad_norm": 0.06720417737960815,
      "learning_rate": 0.00017654660154660154,
      "loss": 0.5424810791015625,
      "step": 37250
    },
    {
      "epoch": 0.6868194763688312,
      "grad_norm": 0.06468328833580017,
      "learning_rate": 0.000174002849002849,
      "loss": 0.5409627685546875,
      "step": 37500
    },
    {
      "epoch": 0.6913982728779567,
      "grad_norm": 0.06758266687393188,
      "learning_rate": 0.00017145909645909646,
      "loss": 0.5416390380859375,
      "step": 37750
    },
    {
      "epoch": 0.6959770693870823,
      "grad_norm": 0.06019122526049614,
      "learning_rate": 0.0001689153439153439,
      "loss": 0.5392860717773438,
      "step": 38000
    },
    {
      "epoch": 0.7005558658962079,
      "grad_norm": 0.06067493185400963,
      "learning_rate": 0.00016637159137159138,
      "loss": 0.540711669921875,
      "step": 38250
    },
    {
      "epoch": 0.7051346624053334,
      "grad_norm": 0.0617203414440155,
      "learning_rate": 0.00016382783882783883,
      "loss": 0.543611572265625,
      "step": 38500
    },
    {
      "epoch": 0.7097134589144589,
      "grad_norm": 0.06383258104324341,
      "learning_rate": 0.00016128408628408628,
      "loss": 0.54111669921875,
      "step": 38750
    },
    {
      "epoch": 0.7142922554235844,
      "grad_norm": 0.06264094263315201,
      "learning_rate": 0.00015874033374033375,
      "loss": 0.5409336547851562,
      "step": 39000
    },
    {
      "epoch": 0.7188710519327101,
      "grad_norm": 0.0582389310002327,
      "learning_rate": 0.0001561965811965812,
      "loss": 0.5385667114257813,
      "step": 39250
    },
    {
      "epoch": 0.7234498484418356,
      "grad_norm": 0.06511319428682327,
      "learning_rate": 0.00015365282865282865,
      "loss": 0.5388533325195313,
      "step": 39500
    },
    {
      "epoch": 0.7280286449509611,
      "grad_norm": 0.06048616021871567,
      "learning_rate": 0.00015110907610907612,
      "loss": 0.539404296875,
      "step": 39750
    },
    {
      "epoch": 0.7326074414600866,
      "grad_norm": 0.06342992931604385,
      "learning_rate": 0.00014856532356532357,
      "loss": 0.5397015380859375,
      "step": 40000
    },
    {
      "epoch": 0.7371862379692121,
      "grad_norm": 0.0633598044514656,
      "learning_rate": 0.00014602157102157101,
      "loss": 0.5383480834960938,
      "step": 40250
    },
    {
      "epoch": 0.7417650344783377,
      "grad_norm": 0.0615195594727993,
      "learning_rate": 0.0001434778184778185,
      "loss": 0.5385945434570313,
      "step": 40500
    },
    {
      "epoch": 0.7463438309874633,
      "grad_norm": 0.05627000704407692,
      "learning_rate": 0.00014093406593406594,
      "loss": 0.53756591796875,
      "step": 40750
    },
    {
      "epoch": 0.7509226274965888,
      "grad_norm": 0.06461521238088608,
      "learning_rate": 0.00013839031339031338,
      "loss": 0.5365997314453125,
      "step": 41000
    },
    {
      "epoch": 0.7555014240057143,
      "grad_norm": 0.06126422807574272,
      "learning_rate": 0.00013584656084656086,
      "loss": 0.5386915893554688,
      "step": 41250
    },
    {
      "epoch": 0.7600802205148399,
      "grad_norm": 0.05774404853582382,
      "learning_rate": 0.0001333028083028083,
      "loss": 0.5380045776367187,
      "step": 41500
    },
    {
      "epoch": 0.7646590170239654,
      "grad_norm": 0.06210438162088394,
      "learning_rate": 0.00013075905575905575,
      "loss": 0.5373387451171875,
      "step": 41750
    },
    {
      "epoch": 0.769237813533091,
      "grad_norm": 0.06252729892730713,
      "learning_rate": 0.00012821530321530323,
      "loss": 0.5376387939453126,
      "step": 42000
    },
    {
      "epoch": 0.7738166100422165,
      "grad_norm": 0.06452998518943787,
      "learning_rate": 0.00012567155067155067,
      "loss": 0.5358265380859375,
      "step": 42250
    },
    {
      "epoch": 0.7783954065513421,
      "grad_norm": 0.0634666383266449,
      "learning_rate": 0.00012312779812779812,
      "loss": 0.5373413696289062,
      "step": 42500
    },
    {
      "epoch": 0.7829742030604676,
      "grad_norm": 0.06478540599346161,
      "learning_rate": 0.0001205840455840456,
      "loss": 0.53590234375,
      "step": 42750
    },
    {
      "epoch": 0.7875529995695931,
      "grad_norm": 0.06542439013719559,
      "learning_rate": 0.00011804029304029304,
      "loss": 0.5361544189453125,
      "step": 43000
    },
    {
      "epoch": 0.7921317960787186,
      "grad_norm": 0.061942797154188156,
      "learning_rate": 0.0001154965404965405,
      "loss": 0.5337443237304688,
      "step": 43250
    },
    {
      "epoch": 0.7967105925878442,
      "grad_norm": 0.05985584482550621,
      "learning_rate": 0.00011295278795278796,
      "loss": 0.5335606689453125,
      "step": 43500
    },
    {
      "epoch": 0.8012893890969698,
      "grad_norm": 0.05933161452412605,
      "learning_rate": 0.00011040903540903541,
      "loss": 0.5334180908203126,
      "step": 43750
    },
    {
      "epoch": 0.8058681856060953,
      "grad_norm": 0.06226200982928276,
      "learning_rate": 0.00010786528286528287,
      "loss": 0.5355284423828125,
      "step": 44000
    },
    {
      "epoch": 0.8104469821152208,
      "grad_norm": 0.06400461494922638,
      "learning_rate": 0.00010532153032153033,
      "loss": 0.534538818359375,
      "step": 44250
    },
    {
      "epoch": 0.8150257786243463,
      "grad_norm": 0.05959906429052353,
      "learning_rate": 0.00010277777777777778,
      "loss": 0.533162109375,
      "step": 44500
    },
    {
      "epoch": 0.819604575133472,
      "grad_norm": 0.06476127356290817,
      "learning_rate": 0.00010023402523402524,
      "loss": 0.5328413696289063,
      "step": 44750
    },
    {
      "epoch": 0.8241833716425975,
      "grad_norm": 0.06384240090847015,
      "learning_rate": 9.76902726902727e-05,
      "loss": 0.5334242553710937,
      "step": 45000
    },
    {
      "epoch": 0.828762168151723,
      "grad_norm": 0.06064584106206894,
      "learning_rate": 9.514652014652015e-05,
      "loss": 0.5317213745117187,
      "step": 45250
    },
    {
      "epoch": 0.8333409646608485,
      "grad_norm": 0.06094207242131233,
      "learning_rate": 9.260276760276761e-05,
      "loss": 0.5321604614257812,
      "step": 45500
    },
    {
      "epoch": 0.8379197611699741,
      "grad_norm": 0.06116236746311188,
      "learning_rate": 9.005901505901507e-05,
      "loss": 0.5310498657226562,
      "step": 45750
    },
    {
      "epoch": 0.8424985576790996,
      "grad_norm": 0.06410134583711624,
      "learning_rate": 8.751526251526252e-05,
      "loss": 0.5318917846679687,
      "step": 46000
    },
    {
      "epoch": 0.8470773541882252,
      "grad_norm": 0.059746153652668,
      "learning_rate": 8.497150997150998e-05,
      "loss": 0.5324998168945313,
      "step": 46250
    },
    {
      "epoch": 0.8516561506973507,
      "grad_norm": 0.06164969503879547,
      "learning_rate": 8.242775742775744e-05,
      "loss": 0.5311779174804687,
      "step": 46500
    },
    {
      "epoch": 0.8562349472064763,
      "grad_norm": 0.06264585256576538,
      "learning_rate": 7.988400488400489e-05,
      "loss": 0.5288109741210938,
      "step": 46750
    },
    {
      "epoch": 0.8608137437156018,
      "grad_norm": 0.06309522688388824,
      "learning_rate": 7.734025234025235e-05,
      "loss": 0.5295328369140625,
      "step": 47000
    },
    {
      "epoch": 0.8653925402247273,
      "grad_norm": 0.06573944538831711,
      "learning_rate": 7.479649979649981e-05,
      "loss": 0.5310571899414063,
      "step": 47250
    },
    {
      "epoch": 0.8699713367338529,
      "grad_norm": 0.06289469450712204,
      "learning_rate": 7.225274725274724e-05,
      "loss": 0.5286151733398438,
      "step": 47500
    },
    {
      "epoch": 0.8745501332429784,
      "grad_norm": 0.0591423362493515,
      "learning_rate": 6.97089947089947e-05,
      "loss": 0.5285560913085937,
      "step": 47750
    },
    {
      "epoch": 0.879128929752104,
      "grad_norm": 0.06373240053653717,
      "learning_rate": 6.716524216524216e-05,
      "loss": 0.52852880859375,
      "step": 48000
    },
    {
      "epoch": 0.8837077262612295,
      "grad_norm": 0.06770361214876175,
      "learning_rate": 6.462148962148962e-05,
      "loss": 0.5289181518554688,
      "step": 48250
    },
    {
      "epoch": 0.888286522770355,
      "grad_norm": 0.06282202154397964,
      "learning_rate": 6.207773707773707e-05,
      "loss": 0.5284034423828124,
      "step": 48500
    },
    {
      "epoch": 0.8928653192794805,
      "grad_norm": 0.06374731659889221,
      "learning_rate": 5.953398453398454e-05,
      "loss": 0.5279761962890624,
      "step": 48750
    },
    {
      "epoch": 0.8974441157886062,
      "grad_norm": 0.060556381940841675,
      "learning_rate": 5.699023199023199e-05,
      "loss": 0.5265902709960938,
      "step": 49000
    },
    {
      "epoch": 0.9020229122977317,
      "grad_norm": 0.06243932247161865,
      "learning_rate": 5.444647944647945e-05,
      "loss": 0.5270482149991123,
      "step": 49250
    },
    {
      "epoch": 0.9066017088068572,
      "grad_norm": 0.05966382101178169,
      "learning_rate": 5.1902726902726907e-05,
      "loss": 0.5288416748046875,
      "step": 49500
    },
    {
      "epoch": 0.9111805053159827,
      "grad_norm": 0.06264135241508484,
      "learning_rate": 4.935897435897436e-05,
      "loss": 0.5250919189453125,
      "step": 49750
    },
    {
      "epoch": 0.9157593018251083,
      "grad_norm": 0.060594044625759125,
      "learning_rate": 4.681522181522182e-05,
      "loss": 0.527917724609375,
      "step": 50000
    },
    {
      "epoch": 0.9203380983342339,
      "grad_norm": 0.06120523810386658,
      "learning_rate": 4.4271469271469275e-05,
      "loss": 0.5259210205078125,
      "step": 50250
    },
    {
      "epoch": 0.9249168948433594,
      "grad_norm": 0.0615825429558754,
      "learning_rate": 4.172771672771673e-05,
      "loss": 0.5261221923828125,
      "step": 50500
    },
    {
      "epoch": 0.9294956913524849,
      "grad_norm": 0.06489884108304977,
      "learning_rate": 3.918396418396418e-05,
      "loss": 0.52599853515625,
      "step": 50750
    },
    {
      "epoch": 0.9340744878616104,
      "grad_norm": 0.06422311812639236,
      "learning_rate": 3.664021164021164e-05,
      "loss": 0.5265205078125,
      "step": 51000
    },
    {
      "epoch": 0.938653284370736,
      "grad_norm": 0.06154436618089676,
      "learning_rate": 3.409645909645909e-05,
      "loss": 0.52559375,
      "step": 51250
    },
    {
      "epoch": 0.9432320808798615,
      "grad_norm": 0.06325343251228333,
      "learning_rate": 3.155270655270655e-05,
      "loss": 0.526312255859375,
      "step": 51500
    },
    {
      "epoch": 0.9478108773889871,
      "grad_norm": 0.060577958822250366,
      "learning_rate": 2.900895400895401e-05,
      "loss": 0.5263541259765625,
      "step": 51750
    },
    {
      "epoch": 0.9523896738981126,
      "grad_norm": 0.0622745044529438,
      "learning_rate": 2.6465201465201467e-05,
      "loss": 0.5247227783203126,
      "step": 52000
    },
    {
      "epoch": 0.9569684704072382,
      "grad_norm": 0.061482541263103485,
      "learning_rate": 2.3921448921448924e-05,
      "loss": 0.522807861328125,
      "step": 52250
    },
    {
      "epoch": 0.9615472669163637,
      "grad_norm": 0.0617360919713974,
      "learning_rate": 2.1377696377696378e-05,
      "loss": 0.524948486328125,
      "step": 52500
    },
    {
      "epoch": 0.9661260634254892,
      "grad_norm": 0.06259670853614807,
      "learning_rate": 1.8833943833943832e-05,
      "loss": 0.52488330078125,
      "step": 52750
    },
    {
      "epoch": 0.9707048599346147,
      "grad_norm": 0.0630236268043518,
      "learning_rate": 1.629019129019129e-05,
      "loss": 0.5252532958984375,
      "step": 53000
    },
    {
      "epoch": 0.9752836564437404,
      "grad_norm": 0.0633007138967514,
      "learning_rate": 1.3746438746438745e-05,
      "loss": 0.5238004150390625,
      "step": 53250
    },
    {
      "epoch": 0.9798624529528659,
      "grad_norm": 0.05867809057235718,
      "learning_rate": 1.1202686202686203e-05,
      "loss": 0.5233538818359375,
      "step": 53500
    },
    {
      "epoch": 0.9844412494619914,
      "grad_norm": 0.06631673127412796,
      "learning_rate": 8.658933658933658e-06,
      "loss": 0.5244312744140625,
      "step": 53750
    },
    {
      "epoch": 0.9890200459711169,
      "grad_norm": 0.06228270381689072,
      "learning_rate": 6.115181115181116e-06,
      "loss": 0.523883056640625,
      "step": 54000
    },
    {
      "epoch": 0.9935988424802424,
      "grad_norm": 0.06517703086137772,
      "learning_rate": 3.5714285714285714e-06,
      "loss": 0.52413623046875,
      "step": 54250
    },
    {
      "epoch": 0.9981776389893681,
      "grad_norm": 0.06215018779039383,
      "learning_rate": 1.0276760276760277e-06,
      "loss": 0.5219486694335937,
      "step": 54500
    },
    {
      "epoch": 1.0,
      "step": 54600,
      "total_flos": 9.745954960876503e+18,
      "train_loss": 0.052523610041691704,
      "train_runtime": 7246.7996,
      "train_samples_per_second": 482.193,
      "train_steps_per_second": 7.534
    }
  ],
  "logging_steps": 250,
  "max_steps": 54600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5460,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.745954960876503e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}