{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04513469669049836,
  "eval_steps": 500,
  "global_step": 13000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034718997454229514,
      "grad_norm": 0.8856930732727051,
      "learning_rate": 0.00019999994169931,
      "loss": 2.4069,
      "step": 100
    },
    {
      "epoch": 0.0006943799490845903,
      "grad_norm": 0.8890424966812134,
      "learning_rate": 0.0001999997644357777,
      "loss": 2.3882,
      "step": 200
    },
    {
      "epoch": 0.0010415699236268853,
      "grad_norm": 0.8619076013565063,
      "learning_rate": 0.00019999946820366553,
      "loss": 2.4208,
      "step": 300
    },
    {
      "epoch": 0.0013887598981691806,
      "grad_norm": 0.8981874585151672,
      "learning_rate": 0.00019999905300332595,
      "loss": 2.3859,
      "step": 400
    },
    {
      "epoch": 0.0017359498727114757,
      "grad_norm": 1.1088451147079468,
      "learning_rate": 0.0001999985188352529,
      "loss": 2.4031,
      "step": 500
    },
    {
      "epoch": 0.0020831398472537705,
      "grad_norm": 0.8845599889755249,
      "learning_rate": 0.00019999786570008187,
      "loss": 2.3765,
      "step": 600
    },
    {
      "epoch": 0.002430329821796066,
      "grad_norm": 1.1892898082733154,
      "learning_rate": 0.0001999970935985899,
      "loss": 2.4083,
      "step": 700
    },
    {
      "epoch": 0.002777519796338361,
      "grad_norm": 1.2907609939575195,
      "learning_rate": 0.00019999620253169554,
      "loss": 2.4262,
      "step": 800
    },
    {
      "epoch": 0.003124709770880656,
      "grad_norm": 1.511342167854309,
      "learning_rate": 0.00019999519250045886,
      "loss": 2.4077,
      "step": 900
    },
    {
      "epoch": 0.0034718997454229513,
      "grad_norm": 1.2708256244659424,
      "learning_rate": 0.00019999406350608152,
      "loss": 2.4238,
      "step": 1000
    },
    {
      "epoch": 0.003819089719965246,
      "grad_norm": 1.380018949508667,
      "learning_rate": 0.00019999281554990668,
      "loss": 2.4429,
      "step": 1100
    },
    {
      "epoch": 0.004166279694507541,
      "grad_norm": 1.5074928998947144,
      "learning_rate": 0.000199991448633419,
      "loss": 2.4212,
      "step": 1200
    },
    {
      "epoch": 0.004513469669049836,
      "grad_norm": 1.20973801612854,
      "learning_rate": 0.00019998996275824465,
      "loss": 2.4092,
      "step": 1300
    },
    {
      "epoch": 0.004860659643592132,
      "grad_norm": 1.4226404428482056,
      "learning_rate": 0.0001999883579261514,
      "loss": 2.3977,
      "step": 1400
    },
    {
      "epoch": 0.005207849618134427,
      "grad_norm": 1.437606930732727,
      "learning_rate": 0.0001999866341390485,
      "loss": 2.4527,
      "step": 1500
    },
    {
      "epoch": 0.005555039592676722,
      "grad_norm": 1.4428914785385132,
      "learning_rate": 0.00019998479139898668,
      "loss": 2.4495,
      "step": 1600
    },
    {
      "epoch": 0.005902229567219017,
      "grad_norm": 2.573493719100952,
      "learning_rate": 0.00019998282970815832,
      "loss": 2.4216,
      "step": 1700
    },
    {
      "epoch": 0.006249419541761312,
      "grad_norm": 1.491316795349121,
      "learning_rate": 0.00019998074906889715,
      "loss": 2.4209,
      "step": 1800
    },
    {
      "epoch": 0.006596609516303607,
      "grad_norm": 1.9518392086029053,
      "learning_rate": 0.00019997854948367846,
      "loss": 2.4081,
      "step": 1900
    },
    {
      "epoch": 0.006943799490845903,
      "grad_norm": 1.6811418533325195,
      "learning_rate": 0.0001999762309551191,
      "loss": 2.4255,
      "step": 2000
    },
    {
      "epoch": 0.007290989465388197,
      "grad_norm": 1.316292643547058,
      "learning_rate": 0.00019997379348597744,
      "loss": 2.4039,
      "step": 2100
    },
    {
      "epoch": 0.007638179439930492,
      "grad_norm": 1.297400712966919,
      "learning_rate": 0.00019997123707915325,
      "loss": 2.4193,
      "step": 2200
    },
    {
      "epoch": 0.007985369414472789,
      "grad_norm": 1.5318177938461304,
      "learning_rate": 0.00019996856173768785,
      "loss": 2.4258,
      "step": 2300
    },
    {
      "epoch": 0.008332559389015082,
      "grad_norm": 2.240832567214966,
      "learning_rate": 0.00019996576746476413,
      "loss": 2.4457,
      "step": 2400
    },
    {
      "epoch": 0.008679749363557377,
      "grad_norm": 1.50482976436615,
      "learning_rate": 0.00019996285426370636,
      "loss": 2.4521,
      "step": 2500
    },
    {
      "epoch": 0.009026939338099673,
      "grad_norm": 1.1736887693405151,
      "learning_rate": 0.00019995982213798035,
      "loss": 2.4226,
      "step": 2600
    },
    {
      "epoch": 0.009374129312641968,
      "grad_norm": 1.489713430404663,
      "learning_rate": 0.00019995667109119335,
      "loss": 2.4314,
      "step": 2700
    },
    {
      "epoch": 0.009721319287184263,
      "grad_norm": 2.00687313079834,
      "learning_rate": 0.00019995340112709422,
      "loss": 2.4389,
      "step": 2800
    },
    {
      "epoch": 0.010068509261726559,
      "grad_norm": 1.5748944282531738,
      "learning_rate": 0.00019995001224957308,
      "loss": 2.4483,
      "step": 2900
    },
    {
      "epoch": 0.010415699236268854,
      "grad_norm": 1.7045289278030396,
      "learning_rate": 0.00019994650446266175,
      "loss": 2.4407,
      "step": 3000
    },
    {
      "epoch": 0.01076288921081115,
      "grad_norm": 1.3988068103790283,
      "learning_rate": 0.0001999428777705333,
      "loss": 2.462,
      "step": 3100
    },
    {
      "epoch": 0.011110079185353445,
      "grad_norm": 1.3608533143997192,
      "learning_rate": 0.00019993913217750245,
      "loss": 2.4472,
      "step": 3200
    },
    {
      "epoch": 0.011457269159895738,
      "grad_norm": 1.2952604293823242,
      "learning_rate": 0.00019993526768802525,
      "loss": 2.4427,
      "step": 3300
    },
    {
      "epoch": 0.011804459134438033,
      "grad_norm": 2.3562355041503906,
      "learning_rate": 0.0001999312843066992,
      "loss": 2.4659,
      "step": 3400
    },
    {
      "epoch": 0.012151649108980329,
      "grad_norm": 2.296459913253784,
      "learning_rate": 0.00019992718203826337,
      "loss": 2.4795,
      "step": 3500
    },
    {
      "epoch": 0.012498839083522624,
      "grad_norm": 1.3606270551681519,
      "learning_rate": 0.00019992296088759814,
      "loss": 2.463,
      "step": 3600
    },
    {
      "epoch": 0.01284602905806492,
      "grad_norm": 1.6714372634887695,
      "learning_rate": 0.00019991862085972536,
      "loss": 2.43,
      "step": 3700
    },
    {
      "epoch": 0.013193219032607215,
      "grad_norm": 2.1929798126220703,
      "learning_rate": 0.0001999141619598083,
      "loss": 2.4513,
      "step": 3800
    },
    {
      "epoch": 0.01354040900714951,
      "grad_norm": 1.7777063846588135,
      "learning_rate": 0.00019990958419315166,
      "loss": 2.472,
      "step": 3900
    },
    {
      "epoch": 0.013887598981691805,
      "grad_norm": 1.5554057359695435,
      "learning_rate": 0.00019990488756520164,
      "loss": 2.4663,
      "step": 4000
    },
    {
      "epoch": 0.0142347889562341,
      "grad_norm": 1.551933765411377,
      "learning_rate": 0.00019990007208154565,
      "loss": 2.5033,
      "step": 4100
    },
    {
      "epoch": 0.014581978930776394,
      "grad_norm": 1.9665030241012573,
      "learning_rate": 0.00019989513774791267,
      "loss": 2.4518,
      "step": 4200
    },
    {
      "epoch": 0.01492916890531869,
      "grad_norm": 1.5771666765213013,
      "learning_rate": 0.000199890084570173,
      "loss": 2.4703,
      "step": 4300
    },
    {
      "epoch": 0.015276358879860985,
      "grad_norm": 1.750036597251892,
      "learning_rate": 0.0001998849125543384,
      "loss": 2.495,
      "step": 4400
    },
    {
      "epoch": 0.01562354885440328,
      "grad_norm": 1.4305938482284546,
      "learning_rate": 0.00019987962170656188,
      "loss": 2.473,
      "step": 4500
    },
    {
      "epoch": 0.015970738828945577,
      "grad_norm": 1.410703420639038,
      "learning_rate": 0.00019987421203313799,
      "loss": 2.4629,
      "step": 4600
    },
    {
      "epoch": 0.01631792880348787,
      "grad_norm": 1.448388695716858,
      "learning_rate": 0.0001998686835405025,
      "loss": 2.4591,
      "step": 4700
    },
    {
      "epoch": 0.016665118778030164,
      "grad_norm": 1.7654149532318115,
      "learning_rate": 0.00019986303623523258,
      "loss": 2.4754,
      "step": 4800
    },
    {
      "epoch": 0.01701230875257246,
      "grad_norm": 1.8118611574172974,
      "learning_rate": 0.0001998572701240468,
      "loss": 2.4657,
      "step": 4900
    },
    {
      "epoch": 0.017359498727114755,
      "grad_norm": 1.8808069229125977,
      "learning_rate": 0.00019985138521380505,
      "loss": 2.4736,
      "step": 5000
    },
    {
      "epoch": 0.01770668870165705,
      "grad_norm": 1.5441018342971802,
      "learning_rate": 0.00019984538151150846,
      "loss": 2.4785,
      "step": 5100
    },
    {
      "epoch": 0.018053878676199345,
      "grad_norm": 1.6582081317901611,
      "learning_rate": 0.00019983925902429967,
      "loss": 2.4841,
      "step": 5200
    },
    {
      "epoch": 0.01840106865074164,
      "grad_norm": 1.5702968835830688,
      "learning_rate": 0.00019983301775946245,
      "loss": 2.4868,
      "step": 5300
    },
    {
      "epoch": 0.018748258625283936,
      "grad_norm": 2.0732314586639404,
      "learning_rate": 0.00019982665772442205,
      "loss": 2.4601,
      "step": 5400
    },
    {
      "epoch": 0.01909544859982623,
      "grad_norm": 1.4423972368240356,
      "learning_rate": 0.00019982017892674483,
      "loss": 2.4773,
      "step": 5500
    },
    {
      "epoch": 0.019442638574368527,
      "grad_norm": 1.9959121942520142,
      "learning_rate": 0.00019981358137413863,
      "loss": 2.4989,
      "step": 5600
    },
    {
      "epoch": 0.019789828548910822,
      "grad_norm": 1.7514522075653076,
      "learning_rate": 0.0001998068650744524,
      "loss": 2.4689,
      "step": 5700
    },
    {
      "epoch": 0.020137018523453117,
      "grad_norm": 1.6253585815429688,
      "learning_rate": 0.00019980003003567653,
      "loss": 2.4683,
      "step": 5800
    },
    {
      "epoch": 0.020484208497995413,
      "grad_norm": 1.9775470495224,
      "learning_rate": 0.0001997930762659425,
      "loss": 2.4787,
      "step": 5900
    },
    {
      "epoch": 0.020831398472537708,
      "grad_norm": 1.4767321348190308,
      "learning_rate": 0.00019978600377352324,
      "loss": 2.4865,
      "step": 6000
    },
    {
      "epoch": 0.021178588447080003,
      "grad_norm": 2.2066593170166016,
      "learning_rate": 0.00019977881256683273,
      "loss": 2.4826,
      "step": 6100
    },
    {
      "epoch": 0.0215257784216223,
      "grad_norm": 1.9816187620162964,
      "learning_rate": 0.00019977150265442626,
      "loss": 2.486,
      "step": 6200
    },
    {
      "epoch": 0.021872968396164594,
      "grad_norm": 1.573564052581787,
      "learning_rate": 0.0001997640740450004,
      "loss": 2.4893,
      "step": 6300
    },
    {
      "epoch": 0.02222015837070689,
      "grad_norm": 2.1582605838775635,
      "learning_rate": 0.00019975652674739285,
      "loss": 2.4896,
      "step": 6400
    },
    {
      "epoch": 0.02256734834524918,
      "grad_norm": 1.991675615310669,
      "learning_rate": 0.00019974886077058255,
      "loss": 2.5041,
      "step": 6500
    },
    {
      "epoch": 0.022914538319791476,
      "grad_norm": 1.781675934791565,
      "learning_rate": 0.00019974107612368962,
      "loss": 2.475,
      "step": 6600
    },
    {
      "epoch": 0.02326172829433377,
      "grad_norm": 1.6764287948608398,
      "learning_rate": 0.00019973317281597538,
      "loss": 2.5048,
      "step": 6700
    },
    {
      "epoch": 0.023608918268876067,
      "grad_norm": 2.408081531524658,
      "learning_rate": 0.00019972515085684233,
      "loss": 2.49,
      "step": 6800
    },
    {
      "epoch": 0.023956108243418362,
      "grad_norm": 2.09415864944458,
      "learning_rate": 0.00019971701025583402,
      "loss": 2.5058,
      "step": 6900
    },
    {
      "epoch": 0.024303298217960657,
      "grad_norm": 1.9584619998931885,
      "learning_rate": 0.00019970875102263532,
      "loss": 2.4775,
      "step": 7000
    },
    {
      "epoch": 0.024650488192502953,
      "grad_norm": 1.894208550453186,
      "learning_rate": 0.00019970037316707212,
      "loss": 2.4997,
      "step": 7100
    },
    {
      "epoch": 0.024997678167045248,
      "grad_norm": 1.6168571710586548,
      "learning_rate": 0.00019969187669911142,
      "loss": 2.4641,
      "step": 7200
    },
    {
      "epoch": 0.025344868141587543,
      "grad_norm": 2.0909547805786133,
      "learning_rate": 0.0001996832616288614,
      "loss": 2.48,
      "step": 7300
    },
    {
      "epoch": 0.02569205811612984,
      "grad_norm": 2.2160308361053467,
      "learning_rate": 0.0001996745279665713,
      "loss": 2.512,
      "step": 7400
    },
    {
      "epoch": 0.026039248090672134,
      "grad_norm": 1.6042606830596924,
      "learning_rate": 0.0001996656757226315,
      "loss": 2.4831,
      "step": 7500
    },
    {
      "epoch": 0.02638643806521443,
      "grad_norm": 2.216085910797119,
      "learning_rate": 0.00019965670490757335,
      "loss": 2.4778,
      "step": 7600
    },
    {
      "epoch": 0.026733628039756725,
      "grad_norm": 1.5685747861862183,
      "learning_rate": 0.00019964761553206936,
      "loss": 2.4861,
      "step": 7700
    },
    {
      "epoch": 0.02708081801429902,
      "grad_norm": 1.4898216724395752,
      "learning_rate": 0.00019963840760693307,
      "loss": 2.5092,
      "step": 7800
    },
    {
      "epoch": 0.027428007988841315,
      "grad_norm": 1.7341415882110596,
      "learning_rate": 0.00019962908114311902,
      "loss": 2.5128,
      "step": 7900
    },
    {
      "epoch": 0.02777519796338361,
      "grad_norm": 1.6686646938323975,
      "learning_rate": 0.0001996196361517228,
      "loss": 2.4971,
      "step": 8000
    },
    {
      "epoch": 0.028122387937925906,
      "grad_norm": 2.1513888835906982,
      "learning_rate": 0.00019961007264398105,
      "loss": 2.4927,
      "step": 8100
    },
    {
      "epoch": 0.0284695779124682,
      "grad_norm": 1.3236947059631348,
      "learning_rate": 0.0001996003906312713,
      "loss": 2.4967,
      "step": 8200
    },
    {
      "epoch": 0.028816767887010496,
      "grad_norm": 1.6354811191558838,
      "learning_rate": 0.00019959059012511214,
      "loss": 2.4954,
      "step": 8300
    },
    {
      "epoch": 0.029163957861552788,
      "grad_norm": 1.8133015632629395,
      "learning_rate": 0.00019958067113716316,
      "loss": 2.4878,
      "step": 8400
    },
    {
      "epoch": 0.029511147836095084,
      "grad_norm": 2.2775697708129883,
      "learning_rate": 0.00019957063367922486,
      "loss": 2.4828,
      "step": 8500
    },
    {
      "epoch": 0.02985833781063738,
      "grad_norm": 2.0718913078308105,
      "learning_rate": 0.0001995604777632387,
      "loss": 2.5039,
      "step": 8600
    },
    {
      "epoch": 0.030205527785179674,
      "grad_norm": 1.5673631429672241,
      "learning_rate": 0.00019955020340128697,
      "loss": 2.509,
      "step": 8700
    },
    {
      "epoch": 0.03055271775972197,
      "grad_norm": 2.0072789192199707,
      "learning_rate": 0.00019953981060559305,
      "loss": 2.491,
      "step": 8800
    },
    {
      "epoch": 0.030899907734264265,
      "grad_norm": 2.3539609909057617,
      "learning_rate": 0.00019952929938852113,
      "loss": 2.4983,
      "step": 8900
    },
    {
      "epoch": 0.03124709770880656,
      "grad_norm": 1.8251752853393555,
      "learning_rate": 0.00019951866976257622,
      "loss": 2.5033,
      "step": 9000
    },
    {
      "epoch": 0.031594287683348855,
      "grad_norm": 1.6241949796676636,
      "learning_rate": 0.00019950792174040433,
      "loss": 2.5094,
      "step": 9100
    },
    {
      "epoch": 0.031941477657891154,
      "grad_norm": 1.5035438537597656,
      "learning_rate": 0.00019949705533479225,
      "loss": 2.4837,
      "step": 9200
    },
    {
      "epoch": 0.032288667632433446,
      "grad_norm": 1.893409252166748,
      "learning_rate": 0.0001994860705586676,
      "loss": 2.5021,
      "step": 9300
    },
    {
      "epoch": 0.03263585760697574,
      "grad_norm": 1.8297152519226074,
      "learning_rate": 0.00019947496742509885,
      "loss": 2.5236,
      "step": 9400
    },
    {
      "epoch": 0.03298304758151804,
      "grad_norm": 2.074918508529663,
      "learning_rate": 0.00019946374594729524,
      "loss": 2.482,
      "step": 9500
    },
    {
      "epoch": 0.03333023755606033,
      "grad_norm": 1.6647151708602905,
      "learning_rate": 0.0001994524061386069,
      "loss": 2.5089,
      "step": 9600
    },
    {
      "epoch": 0.03367742753060263,
      "grad_norm": 1.5688285827636719,
      "learning_rate": 0.0001994409480125246,
      "loss": 2.5003,
      "step": 9700
    },
    {
      "epoch": 0.03402461750514492,
      "grad_norm": 1.8745393753051758,
      "learning_rate": 0.00019942937158268,
      "loss": 2.4874,
      "step": 9800
    },
    {
      "epoch": 0.03437180747968722,
      "grad_norm": 1.7022066116333008,
      "learning_rate": 0.0001994176768628454,
      "loss": 2.5015,
      "step": 9900
    },
    {
      "epoch": 0.03471899745422951,
      "grad_norm": 1.9979243278503418,
      "learning_rate": 0.00019940586386693393,
      "loss": 2.5114,
      "step": 10000
    },
    {
      "epoch": 0.03506618742877181,
      "grad_norm": 1.6992466449737549,
      "learning_rate": 0.00019939393260899932,
      "loss": 2.4883,
      "step": 10100
    },
    {
      "epoch": 0.0354133774033141,
      "grad_norm": 2.0469751358032227,
      "learning_rate": 0.0001993818831032361,
      "loss": 2.5112,
      "step": 10200
    },
    {
      "epoch": 0.0357605673778564,
      "grad_norm": 1.9578917026519775,
      "learning_rate": 0.0001993697153639794,
      "loss": 2.4968,
      "step": 10300
    },
    {
      "epoch": 0.03610775735239869,
      "grad_norm": 2.140726089477539,
      "learning_rate": 0.000199357429405705,
      "loss": 2.5204,
      "step": 10400
    },
    {
      "epoch": 0.03645494732694099,
      "grad_norm": 1.6723066568374634,
      "learning_rate": 0.00019934502524302948,
      "loss": 2.5112,
      "step": 10500
    },
    {
      "epoch": 0.03680213730148328,
      "grad_norm": 1.6627919673919678,
      "learning_rate": 0.00019933250289070982,
      "loss": 2.5194,
      "step": 10600
    },
    {
      "epoch": 0.03714932727602558,
      "grad_norm": 1.9078980684280396,
      "learning_rate": 0.00019931986236364379,
      "loss": 2.519,
      "step": 10700
    },
    {
      "epoch": 0.03749651725056787,
      "grad_norm": 1.7164194583892822,
      "learning_rate": 0.00019930710367686963,
      "loss": 2.5215,
      "step": 10800
    },
    {
      "epoch": 0.03784370722511017,
      "grad_norm": 3.068312883377075,
      "learning_rate": 0.0001992942268455662,
      "loss": 2.4945,
      "step": 10900
    },
    {
      "epoch": 0.03819089719965246,
      "grad_norm": 2.505039691925049,
      "learning_rate": 0.00019928123188505298,
      "loss": 2.5483,
      "step": 11000
    },
    {
      "epoch": 0.038538087174194754,
      "grad_norm": 2.145158529281616,
      "learning_rate": 0.0001992681188107899,
      "loss": 2.5419,
      "step": 11100
    },
    {
      "epoch": 0.03888527714873705,
      "grad_norm": 1.8821165561676025,
      "learning_rate": 0.00019925488763837743,
      "loss": 2.5087,
      "step": 11200
    },
    {
      "epoch": 0.039232467123279345,
      "grad_norm": 2.026528835296631,
      "learning_rate": 0.00019924153838355653,
      "loss": 2.5185,
      "step": 11300
    },
    {
      "epoch": 0.039579657097821644,
      "grad_norm": 1.9918049573898315,
      "learning_rate": 0.00019922807106220866,
      "loss": 2.5275,
      "step": 11400
    },
    {
      "epoch": 0.039926847072363936,
      "grad_norm": 2.444620132446289,
      "learning_rate": 0.00019921448569035577,
      "loss": 2.526,
      "step": 11500
    },
    {
      "epoch": 0.040274037046906234,
      "grad_norm": 1.7009233236312866,
      "learning_rate": 0.00019920078228416018,
      "loss": 2.5264,
      "step": 11600
    },
    {
      "epoch": 0.040621227021448526,
      "grad_norm": 1.8496342897415161,
      "learning_rate": 0.0001991869608599247,
      "loss": 2.535,
      "step": 11700
    },
    {
      "epoch": 0.040968416995990825,
      "grad_norm": 2.300175905227661,
      "learning_rate": 0.0001991730214340925,
      "loss": 2.5206,
      "step": 11800
    },
    {
      "epoch": 0.04131560697053312,
      "grad_norm": 1.6839985847473145,
      "learning_rate": 0.00019915896402324722,
      "loss": 2.4998,
      "step": 11900
    },
    {
      "epoch": 0.041662796945075416,
      "grad_norm": 2.480787754058838,
      "learning_rate": 0.00019914478864411272,
      "loss": 2.535,
      "step": 12000
    },
    {
      "epoch": 0.04200998691961771,
      "grad_norm": 2.3724234104156494,
      "learning_rate": 0.00019913049531355333,
      "loss": 2.5177,
      "step": 12100
    },
    {
      "epoch": 0.042357176894160006,
      "grad_norm": 1.5725799798965454,
      "learning_rate": 0.00019911608404857365,
      "loss": 2.5088,
      "step": 12200
    },
    {
      "epoch": 0.0427043668687023,
      "grad_norm": 2.066396951675415,
      "learning_rate": 0.0001991015548663186,
      "loss": 2.508,
      "step": 12300
    },
    {
      "epoch": 0.0430515568432446,
      "grad_norm": 1.7157249450683594,
      "learning_rate": 0.0001990869077840734,
      "loss": 2.4944,
      "step": 12400
    },
    {
      "epoch": 0.04339874681778689,
      "grad_norm": 1.8114676475524902,
      "learning_rate": 0.00019907214281926348,
      "loss": 2.5094,
      "step": 12500
    },
    {
      "epoch": 0.04374593679232919,
      "grad_norm": 2.00364351272583,
      "learning_rate": 0.00019905725998945457,
      "loss": 2.4996,
      "step": 12600
    },
    {
      "epoch": 0.04409312676687148,
      "grad_norm": 1.508483648300171,
      "learning_rate": 0.00019904225931235262,
      "loss": 2.5075,
      "step": 12700
    },
    {
      "epoch": 0.04444031674141378,
      "grad_norm": 1.5554753541946411,
      "learning_rate": 0.00019902714080580373,
      "loss": 2.5246,
      "step": 12800
    },
    {
      "epoch": 0.04478750671595607,
      "grad_norm": 2.1974375247955322,
      "learning_rate": 0.00019901190448779423,
      "loss": 2.5293,
      "step": 12900
    },
    {
      "epoch": 0.04513469669049836,
      "grad_norm": 2.0555918216705322,
      "learning_rate": 0.00019899655037645064,
      "loss": 2.5065,
      "step": 13000
    }
  ],
  "logging_steps": 100,
  "max_steps": 288027,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.5663994175872614e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}