{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7012350803225463,
  "eval_steps": 500,
  "global_step": 321000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.1845329605063746e-06,
      "grad_norm": 2.255587100982666,
      "learning_rate": 0.0,
      "loss": 9.08322525024414,
      "step": 1
    },
    {
      "epoch": 0.00021845329605063747,
      "grad_norm": 0.8816911578178406,
      "learning_rate": 0.0001485,
      "loss": 8.32293516216856,
      "step": 100
    },
    {
      "epoch": 0.00043690659210127495,
      "grad_norm": 1.3192135095596313,
      "learning_rate": 0.00029850000000000005,
      "loss": 7.127236938476562,
      "step": 200
    },
    {
      "epoch": 0.0006553598881519125,
      "grad_norm": 0.6860479116439819,
      "learning_rate": 0.0004485,
      "loss": 5.774407958984375,
      "step": 300
    },
    {
      "epoch": 0.0008738131842025499,
      "grad_norm": 0.4212465286254883,
      "learning_rate": 0.0005985000000000001,
      "loss": 6.07599853515625,
      "step": 400
    },
    {
      "epoch": 0.0010922664802531874,
      "grad_norm": 0.42650777101516724,
      "learning_rate": 0.0007485,
      "loss": 5.72325439453125,
      "step": 500
    },
    {
      "epoch": 0.001310719776303825,
      "grad_norm": 0.8157845139503479,
      "learning_rate": 0.0008985,
      "loss": 5.374498901367187,
      "step": 600
    },
    {
      "epoch": 0.0015291730723544623,
      "grad_norm": 0.4278698265552521,
      "learning_rate": 0.0010485,
      "loss": 5.207935791015625,
      "step": 700
    },
    {
      "epoch": 0.0017476263684050998,
      "grad_norm": 0.4734596610069275,
      "learning_rate": 0.0011985000000000001,
      "loss": 5.040882568359375,
      "step": 800
    },
    {
      "epoch": 0.0019660796644557373,
      "grad_norm": 0.9601178169250488,
      "learning_rate": 0.0013485,
      "loss": 4.920305786132812,
      "step": 900
    },
    {
      "epoch": 0.002184532960506375,
      "grad_norm": 0.44838836789131165,
      "learning_rate": 0.0014985,
      "loss": 4.8699337768554685,
      "step": 1000
    },
    {
      "epoch": 0.0024029862565570124,
      "grad_norm": 0.4548332691192627,
      "learning_rate": 0.0016485,
      "loss": 4.7284173583984375,
      "step": 1100
    },
    {
      "epoch": 0.00262143955260765,
      "grad_norm": 0.33958613872528076,
      "learning_rate": 0.0017985000000000002,
      "loss": 4.536319580078125,
      "step": 1200
    },
    {
      "epoch": 0.002839892848658287,
      "grad_norm": 0.36981943249702454,
      "learning_rate": 0.0019485,
      "loss": 4.227422790527344,
      "step": 1300
    },
    {
      "epoch": 0.0030583461447089245,
      "grad_norm": 0.318843811750412,
      "learning_rate": 0.0020985,
      "loss": 4.353344116210938,
      "step": 1400
    },
    {
      "epoch": 0.003276799440759562,
      "grad_norm": 0.2866564989089966,
      "learning_rate": 0.0022485,
      "loss": 4.256644897460937,
      "step": 1500
    },
    {
      "epoch": 0.0034952527368101996,
      "grad_norm": 0.3490343689918518,
      "learning_rate": 0.0023985,
      "loss": 4.181780700683594,
      "step": 1600
    },
    {
      "epoch": 0.003713706032860837,
      "grad_norm": 0.41186341643333435,
      "learning_rate": 0.0025485,
      "loss": 4.137591552734375,
      "step": 1700
    },
    {
      "epoch": 0.003932159328911475,
      "grad_norm": 0.2618832290172577,
      "learning_rate": 0.0026985,
      "loss": 4.110564270019531,
      "step": 1800
    },
    {
      "epoch": 0.004150612624962112,
      "grad_norm": 0.3582988977432251,
      "learning_rate": 0.0028485,
      "loss": 4.033620300292969,
      "step": 1900
    },
    {
      "epoch": 0.00436906592101275,
      "grad_norm": 0.29407480359077454,
      "learning_rate": 0.0029985000000000003,
      "loss": 4.035133056640625,
      "step": 2000
    },
    {
      "epoch": 0.004587519217063387,
      "grad_norm": 0.22795212268829346,
      "learning_rate": 0.003,
      "loss": 3.974623107910156,
      "step": 2100
    },
    {
      "epoch": 0.004805972513114025,
      "grad_norm": 0.20751744508743286,
      "learning_rate": 0.003,
      "loss": 3.9740194702148437,
      "step": 2200
    },
    {
      "epoch": 0.005024425809164662,
      "grad_norm": 0.22139297425746918,
      "learning_rate": 0.003,
      "loss": 3.9664035034179688,
      "step": 2300
    },
    {
      "epoch": 0.0052428791052153,
      "grad_norm": 0.2882986068725586,
      "learning_rate": 0.003,
      "loss": 3.894712219238281,
      "step": 2400
    },
    {
      "epoch": 0.0054613324012659364,
      "grad_norm": 0.24050910770893097,
      "learning_rate": 0.003,
      "loss": 3.86550048828125,
      "step": 2500
    },
    {
      "epoch": 0.005679785697316574,
      "grad_norm": 0.19542890787124634,
      "learning_rate": 0.003,
      "loss": 3.8028628540039064,
      "step": 2600
    },
    {
      "epoch": 0.0058982389933672115,
      "grad_norm": 0.22483991086483002,
      "learning_rate": 0.003,
      "loss": 3.827759094238281,
      "step": 2700
    },
    {
      "epoch": 0.006116692289417849,
      "grad_norm": 0.20627519488334656,
      "learning_rate": 0.003,
      "loss": 3.8404141235351563,
      "step": 2800
    },
    {
      "epoch": 0.0063351455854684866,
      "grad_norm": 0.17682938277721405,
      "learning_rate": 0.003,
      "loss": 3.813418273925781,
      "step": 2900
    },
    {
      "epoch": 0.006553598881519124,
      "grad_norm": 0.2815733253955841,
      "learning_rate": 0.003,
      "loss": 3.7931011962890624,
      "step": 3000
    },
    {
      "epoch": 0.006772052177569762,
      "grad_norm": 0.200336754322052,
      "learning_rate": 0.003,
      "loss": 3.764217529296875,
      "step": 3100
    },
    {
      "epoch": 0.006990505473620399,
      "grad_norm": 0.19158774614334106,
      "learning_rate": 0.003,
      "loss": 3.7359378051757814,
      "step": 3200
    },
    {
      "epoch": 0.007208958769671037,
      "grad_norm": 0.18101529777050018,
      "learning_rate": 0.003,
      "loss": 3.773013000488281,
      "step": 3300
    },
    {
      "epoch": 0.007427412065721674,
      "grad_norm": 0.7771575450897217,
      "learning_rate": 0.003,
      "loss": 3.7371151733398436,
      "step": 3400
    },
    {
      "epoch": 0.007645865361772312,
      "grad_norm": 0.20689968764781952,
      "learning_rate": 0.003,
      "loss": 3.725350646972656,
      "step": 3500
    },
    {
      "epoch": 0.00786431865782295,
      "grad_norm": 0.15840990841388702,
      "learning_rate": 0.003,
      "loss": 3.6854702758789064,
      "step": 3600
    },
    {
      "epoch": 0.008082771953873587,
      "grad_norm": 0.18692198395729065,
      "learning_rate": 0.003,
      "loss": 3.7458792114257813,
      "step": 3700
    },
    {
      "epoch": 0.008301225249924224,
      "grad_norm": 0.15756943821907043,
      "learning_rate": 0.003,
      "loss": 3.7010504150390626,
      "step": 3800
    },
    {
      "epoch": 0.008519678545974862,
      "grad_norm": 0.16101692616939545,
      "learning_rate": 0.003,
      "loss": 3.724727783203125,
      "step": 3900
    },
    {
      "epoch": 0.0087381318420255,
      "grad_norm": 0.17350031435489655,
      "learning_rate": 0.003,
      "loss": 3.6388311767578125,
      "step": 4000
    },
    {
      "epoch": 0.008956585138076137,
      "grad_norm": 0.307090699672699,
      "learning_rate": 0.003,
      "loss": 3.6625192260742185,
      "step": 4100
    },
    {
      "epoch": 0.009175038434126774,
      "grad_norm": 0.17554183304309845,
      "learning_rate": 0.003,
      "loss": 3.6276791381835936,
      "step": 4200
    },
    {
      "epoch": 0.009393491730177412,
      "grad_norm": 0.19869279861450195,
      "learning_rate": 0.003,
      "loss": 3.6753179931640627,
      "step": 4300
    },
    {
      "epoch": 0.00961194502622805,
      "grad_norm": 0.1721080243587494,
      "learning_rate": 0.003,
      "loss": 3.6419528198242186,
      "step": 4400
    },
    {
      "epoch": 0.009830398322278687,
      "grad_norm": 0.16175901889801025,
      "learning_rate": 0.003,
      "loss": 3.6424264526367187,
      "step": 4500
    },
    {
      "epoch": 0.010048851618329325,
      "grad_norm": 0.16099213063716888,
      "learning_rate": 0.003,
      "loss": 3.591856689453125,
      "step": 4600
    },
    {
      "epoch": 0.010267304914379962,
      "grad_norm": 0.16880081593990326,
      "learning_rate": 0.003,
      "loss": 3.6297122192382814,
      "step": 4700
    },
    {
      "epoch": 0.0104857582104306,
      "grad_norm": 0.17125141620635986,
      "learning_rate": 0.003,
      "loss": 3.578116149902344,
      "step": 4800
    },
    {
      "epoch": 0.010704211506481237,
      "grad_norm": 0.24591994285583496,
      "learning_rate": 0.003,
      "loss": 3.5897540283203124,
      "step": 4900
    },
    {
      "epoch": 0.010922664802531873,
      "grad_norm": 0.16242574155330658,
      "learning_rate": 0.003,
      "loss": 3.6433404541015624,
      "step": 5000
    },
    {
      "epoch": 0.01114111809858251,
      "grad_norm": 0.14434590935707092,
      "learning_rate": 0.003,
      "loss": 3.615052490234375,
      "step": 5100
    },
    {
      "epoch": 0.011359571394633148,
      "grad_norm": 0.1432674080133438,
      "learning_rate": 0.003,
      "loss": 3.587109375,
      "step": 5200
    },
    {
      "epoch": 0.011578024690683785,
      "grad_norm": 0.1445230096578598,
      "learning_rate": 0.003,
      "loss": 3.5490536499023437,
      "step": 5300
    },
    {
      "epoch": 0.011796477986734423,
      "grad_norm": 0.13871097564697266,
      "learning_rate": 0.003,
      "loss": 3.5879721069335937,
      "step": 5400
    },
    {
      "epoch": 0.01201493128278506,
      "grad_norm": 0.15358251333236694,
      "learning_rate": 0.003,
      "loss": 3.5590310668945313,
      "step": 5500
    },
    {
      "epoch": 0.012233384578835698,
      "grad_norm": 0.2113238424062729,
      "learning_rate": 0.003,
      "loss": 3.5402783203125,
      "step": 5600
    },
    {
      "epoch": 0.012451837874886336,
      "grad_norm": 0.1575174778699875,
      "learning_rate": 0.003,
      "loss": 3.5282159423828126,
      "step": 5700
    },
    {
      "epoch": 0.012670291170936973,
      "grad_norm": 0.2206973135471344,
      "learning_rate": 0.003,
      "loss": 3.5321197509765625,
      "step": 5800
    },
    {
      "epoch": 0.01288874446698761,
      "grad_norm": 0.1495489776134491,
      "learning_rate": 0.003,
      "loss": 3.5411871337890624,
      "step": 5900
    },
    {
      "epoch": 0.013107197763038248,
      "grad_norm": 0.19098496437072754,
      "learning_rate": 0.003,
      "loss": 3.514726257324219,
      "step": 6000
    },
    {
      "epoch": 0.013325651059088886,
      "grad_norm": 0.2959604263305664,
      "learning_rate": 0.003,
      "loss": 3.53537109375,
      "step": 6100
    },
    {
      "epoch": 0.013544104355139523,
      "grad_norm": 0.15626825392246246,
      "learning_rate": 0.003,
      "loss": 3.5192501831054686,
      "step": 6200
    },
    {
      "epoch": 0.01376255765119016,
      "grad_norm": 0.16896215081214905,
      "learning_rate": 0.003,
      "loss": 3.5495986938476562,
      "step": 6300
    },
    {
      "epoch": 0.013981010947240798,
      "grad_norm": 0.14018405973911285,
      "learning_rate": 0.003,
      "loss": 3.5275753784179686,
      "step": 6400
    },
    {
      "epoch": 0.014199464243291436,
      "grad_norm": 0.15250442922115326,
      "learning_rate": 0.003,
      "loss": 3.5582366943359376,
      "step": 6500
    },
    {
      "epoch": 0.014417917539342073,
      "grad_norm": 0.22132086753845215,
      "learning_rate": 0.003,
      "loss": 3.52295654296875,
      "step": 6600
    },
    {
      "epoch": 0.01463637083539271,
      "grad_norm": 0.1595185250043869,
      "learning_rate": 0.003,
      "loss": 3.5543255615234375,
      "step": 6700
    },
    {
      "epoch": 0.014854824131443348,
      "grad_norm": 0.1608801633119583,
      "learning_rate": 0.003,
      "loss": 3.533863830566406,
      "step": 6800
    },
    {
      "epoch": 0.015073277427493986,
      "grad_norm": 0.15735548734664917,
      "learning_rate": 0.003,
      "loss": 3.5444400024414064,
      "step": 6900
    },
    {
      "epoch": 0.015291730723544623,
      "grad_norm": 0.15741421282291412,
      "learning_rate": 0.003,
      "loss": 3.5775491333007814,
      "step": 7000
    },
    {
      "epoch": 0.015510184019595261,
      "grad_norm": 0.1459587663412094,
      "learning_rate": 0.003,
      "loss": 3.5826260375976564,
      "step": 7100
    },
    {
      "epoch": 0.0157286373156459,
      "grad_norm": 0.17190411686897278,
      "learning_rate": 0.003,
      "loss": 3.5276693725585937,
      "step": 7200
    },
    {
      "epoch": 0.015947090611696534,
      "grad_norm": 0.13370057940483093,
      "learning_rate": 0.003,
      "loss": 3.5145721435546875,
      "step": 7300
    },
    {
      "epoch": 0.016165543907747174,
      "grad_norm": 0.1334085464477539,
      "learning_rate": 0.003,
      "loss": 3.528052978515625,
      "step": 7400
    },
    {
      "epoch": 0.01638399720379781,
      "grad_norm": 0.1612652987241745,
      "learning_rate": 0.003,
      "loss": 3.4622488403320313,
      "step": 7500
    },
    {
      "epoch": 0.01660245049984845,
      "grad_norm": 0.15845361351966858,
      "learning_rate": 0.003,
      "loss": 3.484794921875,
      "step": 7600
    },
    {
      "epoch": 0.016820903795899084,
      "grad_norm": 0.14460201561450958,
      "learning_rate": 0.003,
      "loss": 3.488492126464844,
      "step": 7700
    },
    {
      "epoch": 0.017039357091949724,
      "grad_norm": 0.0004208660975564271,
      "learning_rate": 0.003,
      "loss": 3.0585507202148436,
      "step": 7800
    },
    {
      "epoch": 0.01725781038800036,
      "grad_norm": 0.16746053099632263,
      "learning_rate": 0.003,
      "loss": 3.4115805053710937,
      "step": 7900
    },
    {
      "epoch": 0.017476263684051,
      "grad_norm": 0.12478704750537872,
      "learning_rate": 0.003,
      "loss": 3.5240304565429685,
      "step": 8000
    },
    {
      "epoch": 0.017694716980101634,
      "grad_norm": 0.15716327726840973,
      "learning_rate": 0.003,
      "loss": 3.4820321655273436,
      "step": 8100
    },
    {
      "epoch": 0.017913170276152274,
      "grad_norm": 0.13654641807079315,
      "learning_rate": 0.003,
      "loss": 3.515375061035156,
      "step": 8200
    },
    {
      "epoch": 0.01813162357220291,
      "grad_norm": 0.13003572821617126,
      "learning_rate": 0.003,
      "loss": 3.493472900390625,
      "step": 8300
    },
    {
      "epoch": 0.01835007686825355,
      "grad_norm": 0.14350499212741852,
      "learning_rate": 0.003,
      "loss": 3.4743597412109377,
      "step": 8400
    },
    {
      "epoch": 0.018568530164304185,
      "grad_norm": 0.13438019156455994,
      "learning_rate": 0.003,
      "loss": 3.4803411865234377,
      "step": 8500
    },
    {
      "epoch": 0.018786983460354824,
      "grad_norm": 0.13640356063842773,
      "learning_rate": 0.003,
      "loss": 3.486788635253906,
      "step": 8600
    },
    {
      "epoch": 0.01900543675640546,
      "grad_norm": 0.18971936404705048,
      "learning_rate": 0.003,
      "loss": 3.482457580566406,
      "step": 8700
    },
    {
      "epoch": 0.0192238900524561,
      "grad_norm": 0.1473148614168167,
      "learning_rate": 0.003,
      "loss": 3.456876220703125,
      "step": 8800
    },
    {
      "epoch": 0.019442343348506735,
      "grad_norm": 0.18119043111801147,
      "learning_rate": 0.003,
      "loss": 3.462286376953125,
      "step": 8900
    },
    {
      "epoch": 0.019660796644557374,
      "grad_norm": 0.13301891088485718,
      "learning_rate": 0.003,
      "loss": 3.4378567504882813,
      "step": 9000
    },
    {
      "epoch": 0.01987924994060801,
      "grad_norm": 0.12677288055419922,
      "learning_rate": 0.003,
      "loss": 3.4668447875976565,
      "step": 9100
    },
    {
      "epoch": 0.02009770323665865,
      "grad_norm": 0.1373668909072876,
      "learning_rate": 0.003,
      "loss": 3.443948974609375,
      "step": 9200
    },
    {
      "epoch": 0.020316156532709285,
      "grad_norm": 0.14534036815166473,
      "learning_rate": 0.003,
      "loss": 3.380128173828125,
      "step": 9300
    },
    {
      "epoch": 0.020534609828759924,
      "grad_norm": 0.1568584442138672,
      "learning_rate": 0.003,
      "loss": 3.44497314453125,
      "step": 9400
    },
    {
      "epoch": 0.02075306312481056,
      "grad_norm": 0.1420242041349411,
      "learning_rate": 0.003,
      "loss": 3.4808615112304686,
      "step": 9500
    },
    {
      "epoch": 0.0209715164208612,
      "grad_norm": 0.1322467178106308,
      "learning_rate": 0.003,
      "loss": 3.4551959228515625,
      "step": 9600
    },
    {
      "epoch": 0.021189969716911835,
      "grad_norm": 0.13316933810710907,
      "learning_rate": 0.003,
      "loss": 3.4731900024414064,
      "step": 9700
    },
    {
      "epoch": 0.021408423012962474,
      "grad_norm": 0.15251101553440094,
      "learning_rate": 0.003,
      "loss": 3.4879879760742187,
      "step": 9800
    },
    {
      "epoch": 0.02162687630901311,
      "grad_norm": 0.12604866921901703,
      "learning_rate": 0.003,
      "loss": 3.440266418457031,
      "step": 9900
    },
    {
      "epoch": 0.021845329605063746,
      "grad_norm": 0.17345112562179565,
      "learning_rate": 0.003,
      "loss": 3.406102294921875,
      "step": 10000
    },
    {
      "epoch": 0.022063782901114385,
      "grad_norm": 0.127431258559227,
      "learning_rate": 0.003,
      "loss": 3.4641342163085938,
      "step": 10100
    },
    {
      "epoch": 0.02228223619716502,
      "grad_norm": 0.3970823287963867,
      "learning_rate": 0.003,
      "loss": 3.4580899047851563,
      "step": 10200
    },
    {
      "epoch": 0.02250068949321566,
      "grad_norm": 0.12958978116512299,
      "learning_rate": 0.003,
      "loss": 3.467703857421875,
      "step": 10300
    },
    {
      "epoch": 0.022719142789266296,
      "grad_norm": 0.12477892637252808,
      "learning_rate": 0.003,
      "loss": 3.4370376586914064,
      "step": 10400
    },
    {
      "epoch": 0.022937596085316935,
      "grad_norm": 0.15533806383609772,
      "learning_rate": 0.003,
      "loss": 3.424752502441406,
      "step": 10500
    },
    {
      "epoch": 0.02315604938136757,
      "grad_norm": 0.12429562211036682,
      "learning_rate": 0.003,
      "loss": 3.4563424682617185,
      "step": 10600
    },
    {
      "epoch": 0.02337450267741821,
      "grad_norm": 0.12259926646947861,
      "learning_rate": 0.003,
      "loss": 3.452345886230469,
      "step": 10700
    },
    {
      "epoch": 0.023592955973468846,
      "grad_norm": 0.12801794707775116,
      "learning_rate": 0.003,
      "loss": 3.428161315917969,
      "step": 10800
    },
    {
      "epoch": 0.023811409269519485,
      "grad_norm": 0.12190855294466019,
      "learning_rate": 0.003,
      "loss": 3.4313015747070312,
      "step": 10900
    },
    {
      "epoch": 0.02402986256557012,
      "grad_norm": 0.15164604783058167,
      "learning_rate": 0.003,
      "loss": 3.4190289306640627,
      "step": 11000
    },
    {
      "epoch": 0.02424831586162076,
      "grad_norm": 0.147601917386055,
      "learning_rate": 0.003,
      "loss": 3.426579895019531,
      "step": 11100
    },
    {
      "epoch": 0.024466769157671396,
      "grad_norm": 0.2954082787036896,
      "learning_rate": 0.003,
      "loss": 3.4224453735351563,
      "step": 11200
    },
    {
      "epoch": 0.024685222453722035,
      "grad_norm": 0.12163235992193222,
      "learning_rate": 0.003,
      "loss": 3.4398626708984374,
      "step": 11300
    },
    {
      "epoch": 0.02490367574977267,
      "grad_norm": 0.15871132910251617,
      "learning_rate": 0.003,
      "loss": 3.245552978515625,
      "step": 11400
    },
    {
      "epoch": 0.02512212904582331,
      "grad_norm": 0.12936411798000336,
      "learning_rate": 0.003,
      "loss": 3.463407287597656,
      "step": 11500
    },
    {
      "epoch": 0.025340582341873946,
      "grad_norm": 0.14481250941753387,
      "learning_rate": 0.003,
      "loss": 3.4297866821289062,
      "step": 11600
    },
    {
      "epoch": 0.025559035637924585,
      "grad_norm": 0.1768658310174942,
      "learning_rate": 0.003,
      "loss": 3.4299252319335936,
      "step": 11700
    },
    {
      "epoch": 0.02577748893397522,
      "grad_norm": 0.16980133950710297,
      "learning_rate": 0.003,
      "loss": 3.422637634277344,
      "step": 11800
    },
    {
      "epoch": 0.02599594223002586,
      "grad_norm": 0.14592786133289337,
      "learning_rate": 0.003,
      "loss": 3.4101101684570314,
      "step": 11900
    },
    {
      "epoch": 0.026214395526076496,
      "grad_norm": 0.17400604486465454,
      "learning_rate": 0.003,
      "loss": 3.4130960083007813,
      "step": 12000
    },
    {
      "epoch": 0.026432848822127136,
      "grad_norm": 0.15158580243587494,
      "learning_rate": 0.003,
      "loss": 3.3233709716796875,
      "step": 12100
    },
    {
      "epoch": 0.02665130211817777,
      "grad_norm": 0.1904173642396927,
      "learning_rate": 0.003,
      "loss": 3.369674072265625,
      "step": 12200
    },
    {
      "epoch": 0.02686975541422841,
      "grad_norm": 0.17572258412837982,
      "learning_rate": 0.003,
      "loss": 3.3876129150390626,
      "step": 12300
    },
    {
      "epoch": 0.027088208710279046,
      "grad_norm": 0.17185264825820923,
      "learning_rate": 0.003,
      "loss": 3.4066583251953126,
      "step": 12400
    },
    {
      "epoch": 0.027306662006329686,
      "grad_norm": 0.1479792445898056,
      "learning_rate": 0.003,
      "loss": 3.4205966186523438,
      "step": 12500
    },
    {
      "epoch": 0.02752511530238032,
      "grad_norm": 0.12834446132183075,
      "learning_rate": 0.003,
      "loss": 3.378619384765625,
      "step": 12600
    },
    {
      "epoch": 0.02774356859843096,
      "grad_norm": 0.12408050894737244,
      "learning_rate": 0.003,
      "loss": 3.3828253173828124,
      "step": 12700
    },
    {
      "epoch": 0.027962021894481597,
      "grad_norm": 0.22868679463863373,
      "learning_rate": 0.003,
      "loss": 3.381539306640625,
      "step": 12800
    },
    {
      "epoch": 0.028180475190532236,
      "grad_norm": 0.17433251440525055,
      "learning_rate": 0.003,
      "loss": 3.4322048950195314,
      "step": 12900
    },
    {
      "epoch": 0.02839892848658287,
      "grad_norm": 0.16155290603637695,
      "learning_rate": 0.003,
      "loss": 3.4481887817382812,
      "step": 13000
    },
    {
      "epoch": 0.028617381782633507,
      "grad_norm": 0.15982672572135925,
      "learning_rate": 0.003,
      "loss": 3.4119744873046876,
      "step": 13100
    },
    {
      "epoch": 0.028835835078684147,
      "grad_norm": 0.18386831879615784,
      "learning_rate": 0.003,
      "loss": 3.3510791015625,
      "step": 13200
    },
    {
      "epoch": 0.029054288374734782,
      "grad_norm": 0.17137445509433746,
      "learning_rate": 0.003,
      "loss": 3.393916015625,
      "step": 13300
    },
    {
      "epoch": 0.02927274167078542,
      "grad_norm": 0.13146288692951202,
      "learning_rate": 0.003,
      "loss": 3.3667041015625,
      "step": 13400
    },
    {
      "epoch": 0.029491194966836057,
      "grad_norm": 0.14492550492286682,
      "learning_rate": 0.003,
      "loss": 3.419930114746094,
      "step": 13500
    },
    {
      "epoch": 0.029709648262886697,
      "grad_norm": 0.1275530457496643,
      "learning_rate": 0.003,
      "loss": 3.3596307373046876,
      "step": 13600
    },
    {
      "epoch": 0.029928101558937333,
      "grad_norm": 0.13028651475906372,
      "learning_rate": 0.003,
      "loss": 3.4040185546875,
      "step": 13700
    },
    {
      "epoch": 0.030146554854987972,
      "grad_norm": 0.11924244463443756,
      "learning_rate": 0.003,
      "loss": 3.3670413208007814,
      "step": 13800
    },
    {
      "epoch": 0.030365008151038608,
      "grad_norm": 0.14716394245624542,
      "learning_rate": 0.003,
      "loss": 3.3846261596679685,
      "step": 13900
    },
    {
      "epoch": 0.030583461447089247,
      "grad_norm": 0.13254448771476746,
      "learning_rate": 0.003,
      "loss": 3.364213562011719,
      "step": 14000
    },
    {
      "epoch": 0.030801914743139883,
      "grad_norm": 0.15664011240005493,
      "learning_rate": 0.003,
      "loss": 3.3782522583007815,
      "step": 14100
    },
    {
      "epoch": 0.031020368039190522,
      "grad_norm": 0.15272946655750275,
      "learning_rate": 0.003,
      "loss": 3.3805450439453124,
      "step": 14200
    },
    {
      "epoch": 0.031238821335241158,
      "grad_norm": 0.1525123417377472,
      "learning_rate": 0.003,
      "loss": 3.3752081298828127,
      "step": 14300
    },
    {
      "epoch": 0.0314572746312918,
      "grad_norm": 0.20490288734436035,
      "learning_rate": 0.003,
      "loss": 3.371563720703125,
      "step": 14400
    },
    {
      "epoch": 0.03167572792734243,
      "grad_norm": 0.15253432095050812,
      "learning_rate": 0.003,
      "loss": 3.402916259765625,
      "step": 14500
    },
    {
      "epoch": 0.03189418122339307,
      "grad_norm": 0.13024139404296875,
      "learning_rate": 0.003,
      "loss": 3.4280859375,
      "step": 14600
    },
    {
      "epoch": 0.03211263451944371,
      "grad_norm": 0.1582784652709961,
      "learning_rate": 0.003,
      "loss": 3.3901861572265624,
      "step": 14700
    },
    {
      "epoch": 0.03233108781549435,
      "grad_norm": 0.14428076148033142,
      "learning_rate": 0.003,
      "loss": 3.4218453979492187,
      "step": 14800
    },
    {
      "epoch": 0.03254954111154498,
      "grad_norm": 0.17758288979530334,
      "learning_rate": 0.003,
      "loss": 3.414378662109375,
      "step": 14900
    },
    {
      "epoch": 0.03276799440759562,
      "grad_norm": 0.15624703466892242,
      "learning_rate": 0.003,
      "loss": 3.402666015625,
      "step": 15000
    },
    {
      "epoch": 0.03298644770364626,
      "grad_norm": 0.11428515613079071,
      "learning_rate": 0.003,
      "loss": 3.3660311889648438,
      "step": 15100
    },
    {
      "epoch": 0.0332049009996969,
      "grad_norm": 0.12380622327327728,
      "learning_rate": 0.003,
      "loss": 3.373631591796875,
      "step": 15200
    },
    {
      "epoch": 0.03342335429574753,
      "grad_norm": 0.1253189742565155,
      "learning_rate": 0.003,
      "loss": 3.4366766357421876,
      "step": 15300
    },
    {
      "epoch": 0.03364180759179817,
      "grad_norm": 0.16725805401802063,
      "learning_rate": 0.003,
      "loss": 3.3884176635742187,
      "step": 15400
    },
    {
      "epoch": 0.03386026088784881,
      "grad_norm": 0.11203224956989288,
      "learning_rate": 0.003,
      "loss": 3.38418701171875,
      "step": 15500
    },
    {
      "epoch": 0.03407871418389945,
      "grad_norm": 0.14427132904529572,
      "learning_rate": 0.003,
      "loss": 3.35841552734375,
      "step": 15600
    },
    {
      "epoch": 0.03429716747995008,
      "grad_norm": 0.3464087247848511,
      "learning_rate": 0.003,
      "loss": 3.3959381103515627,
      "step": 15700
    },
    {
      "epoch": 0.03451562077600072,
      "grad_norm": 0.1291625201702118,
      "learning_rate": 0.003,
      "loss": 3.318126220703125,
      "step": 15800
    },
    {
      "epoch": 0.03473407407205136,
      "grad_norm": 0.1512761414051056,
      "learning_rate": 0.003,
      "loss": 3.4096249389648436,
      "step": 15900
    },
    {
      "epoch": 0.034952527368102,
      "grad_norm": 0.13020943105220795,
      "learning_rate": 0.003,
      "loss": 3.394733581542969,
      "step": 16000
    },
    {
      "epoch": 0.03517098066415263,
      "grad_norm": 0.1642727553844452,
      "learning_rate": 0.003,
      "loss": 3.387644958496094,
      "step": 16100
    },
    {
      "epoch": 0.03538943396020327,
      "grad_norm": 0.18252240121364594,
      "learning_rate": 0.003,
      "loss": 3.348713684082031,
      "step": 16200
    },
    {
      "epoch": 0.03560788725625391,
      "grad_norm": 0.12791410088539124,
      "learning_rate": 0.003,
      "loss": 3.3396737670898435,
      "step": 16300
    },
    {
      "epoch": 0.03582634055230455,
      "grad_norm": 0.16357003152370453,
      "learning_rate": 0.003,
      "loss": 3.3477932739257814,
      "step": 16400
    },
    {
      "epoch": 0.03604479384835518,
      "grad_norm": 0.15510688722133636,
      "learning_rate": 0.003,
      "loss": 3.359996337890625,
      "step": 16500
    },
    {
      "epoch": 0.03626324714440582,
      "grad_norm": 0.13001827895641327,
      "learning_rate": 0.003,
      "loss": 3.389567565917969,
      "step": 16600
    },
    {
      "epoch": 0.036481700440456455,
      "grad_norm": 0.1236167848110199,
      "learning_rate": 0.003,
      "loss": 3.3922064208984377,
      "step": 16700
    },
    {
      "epoch": 0.0367001537365071,
      "grad_norm": 0.1220364198088646,
      "learning_rate": 0.003,
      "loss": 3.36064453125,
      "step": 16800
    },
    {
      "epoch": 0.03691860703255773,
      "grad_norm": 0.15455572307109833,
      "learning_rate": 0.003,
      "loss": 3.3853970336914063,
      "step": 16900
    },
    {
      "epoch": 0.03713706032860837,
      "grad_norm": 0.1555703580379486,
      "learning_rate": 0.003,
      "loss": 3.3637930297851564,
      "step": 17000
    },
    {
      "epoch": 0.037355513624659005,
      "grad_norm": 0.12709327042102814,
      "learning_rate": 0.003,
      "loss": 3.3593380737304686,
      "step": 17100
    },
    {
      "epoch": 0.03757396692070965,
      "grad_norm": 0.1316322535276413,
      "learning_rate": 0.003,
      "loss": 3.3686447143554688,
      "step": 17200
    },
    {
      "epoch": 0.037792420216760284,
      "grad_norm": 0.1177879050374031,
      "learning_rate": 0.003,
      "loss": 3.395923767089844,
      "step": 17300
    },
    {
      "epoch": 0.03801087351281092,
      "grad_norm": 0.13159431517124176,
      "learning_rate": 0.003,
      "loss": 3.3620074462890623,
      "step": 17400
    },
    {
      "epoch": 0.038229326808861555,
      "grad_norm": 0.18160413205623627,
      "learning_rate": 0.003,
      "loss": 3.399137268066406,
      "step": 17500
    },
    {
      "epoch": 0.0384477801049122,
      "grad_norm": 0.14702297747135162,
      "learning_rate": 0.003,
      "loss": 3.3676507568359373,
      "step": 17600
    },
    {
      "epoch": 0.038666233400962834,
      "grad_norm": 0.1425740122795105,
      "learning_rate": 0.003,
      "loss": 3.369291076660156,
      "step": 17700
    },
    {
      "epoch": 0.03888468669701347,
      "grad_norm": 0.14931966364383698,
      "learning_rate": 0.003,
      "loss": 3.4102838134765623,
      "step": 17800
    },
    {
      "epoch": 0.039103139993064105,
      "grad_norm": 0.17999820411205292,
      "learning_rate": 0.003,
      "loss": 3.379178466796875,
      "step": 17900
    },
    {
      "epoch": 0.03932159328911475,
      "grad_norm": 0.1291344314813614,
      "learning_rate": 0.003,
      "loss": 3.355089111328125,
      "step": 18000
    },
    {
      "epoch": 0.039540046585165384,
      "grad_norm": 0.1446428745985031,
      "learning_rate": 0.003,
      "loss": 3.3309194946289065,
      "step": 18100
    },
    {
      "epoch": 0.03975849988121602,
      "grad_norm": 0.14135949313640594,
      "learning_rate": 0.003,
      "loss": 3.3592868041992188,
      "step": 18200
    },
    {
      "epoch": 0.039976953177266655,
      "grad_norm": 0.1341768056154251,
      "learning_rate": 0.003,
      "loss": 3.4569125366210938,
      "step": 18300
    },
    {
      "epoch": 0.0401954064733173,
      "grad_norm": 0.17552950978279114,
      "learning_rate": 0.003,
      "loss": 3.3678436279296875,
      "step": 18400
    },
    {
      "epoch": 0.040413859769367934,
      "grad_norm": 0.13788950443267822,
      "learning_rate": 0.003,
      "loss": 3.3702731323242188,
      "step": 18500
    },
    {
      "epoch": 0.04063231306541857,
      "grad_norm": 0.15055698156356812,
      "learning_rate": 0.003,
      "loss": 3.3611465454101563,
      "step": 18600
    },
    {
      "epoch": 0.040850766361469205,
      "grad_norm": 0.14934693276882172,
      "learning_rate": 0.003,
      "loss": 3.3552645874023437,
      "step": 18700
    },
    {
      "epoch": 0.04106921965751985,
      "grad_norm": 0.14292465150356293,
      "learning_rate": 0.003,
      "loss": 3.366205139160156,
      "step": 18800
    },
    {
      "epoch": 0.041287672953570484,
      "grad_norm": 0.18903979659080505,
      "learning_rate": 0.003,
      "loss": 3.371684265136719,
      "step": 18900
    },
    {
      "epoch": 0.04150612624962112,
      "grad_norm": 0.24123075604438782,
      "learning_rate": 0.003,
      "loss": 3.3701324462890625,
      "step": 19000
    },
    {
      "epoch": 0.041724579545671756,
      "grad_norm": 0.07729237526655197,
      "learning_rate": 0.003,
      "loss": 3.298961181640625,
      "step": 19100
    },
    {
      "epoch": 0.0419430328417224,
      "grad_norm": 0.1265183836221695,
      "learning_rate": 0.003,
      "loss": 3.3053384399414063,
      "step": 19200
    },
    {
      "epoch": 0.042161486137773034,
      "grad_norm": 0.1463397592306137,
      "learning_rate": 0.003,
      "loss": 3.268896179199219,
      "step": 19300
    },
    {
      "epoch": 0.04237993943382367,
      "grad_norm": 0.16664332151412964,
      "learning_rate": 0.003,
      "loss": 3.298565673828125,
      "step": 19400
    },
    {
      "epoch": 0.042598392729874306,
      "grad_norm": 0.191655695438385,
      "learning_rate": 0.003,
      "loss": 3.362577209472656,
      "step": 19500
    },
    {
      "epoch": 0.04281684602592495,
      "grad_norm": 0.15652531385421753,
      "learning_rate": 0.003,
      "loss": 3.382750244140625,
      "step": 19600
    },
    {
      "epoch": 0.043035299321975584,
      "grad_norm": 0.1691717952489853,
      "learning_rate": 0.003,
      "loss": 3.38729248046875,
      "step": 19700
    },
    {
      "epoch": 0.04325375261802622,
      "grad_norm": 0.17442384362220764,
      "learning_rate": 0.003,
      "loss": 3.4193304443359374,
      "step": 19800
    },
    {
      "epoch": 0.043472205914076856,
      "grad_norm": 0.1332450658082962,
      "learning_rate": 0.003,
      "loss": 3.392738037109375,
      "step": 19900
    },
    {
      "epoch": 0.04369065921012749,
      "grad_norm": 0.21232371032238007,
      "learning_rate": 0.003,
      "loss": 3.302718200683594,
      "step": 20000
    },
    {
      "epoch": 0.043909112506178134,
      "grad_norm": 0.12638093531131744,
      "learning_rate": 0.003,
      "loss": 3.3222625732421873,
      "step": 20100
    },
    {
      "epoch": 0.04412756580222877,
      "grad_norm": 0.14597079157829285,
      "learning_rate": 0.003,
      "loss": 3.3344183349609375,
      "step": 20200
    },
    {
      "epoch": 0.044346019098279406,
      "grad_norm": 0.18109019100666046,
      "learning_rate": 0.003,
      "loss": 3.355440979003906,
      "step": 20300
    },
    {
      "epoch": 0.04456447239433004,
      "grad_norm": 0.13938353955745697,
      "learning_rate": 0.003,
      "loss": 3.356192321777344,
      "step": 20400
    },
    {
      "epoch": 0.044782925690380684,
      "grad_norm": 0.15982763469219208,
      "learning_rate": 0.003,
      "loss": 3.363128662109375,
      "step": 20500
    },
    {
      "epoch": 0.04500137898643132,
      "grad_norm": 0.13512779772281647,
      "learning_rate": 0.003,
      "loss": 3.352191162109375,
      "step": 20600
    },
    {
      "epoch": 0.045219832282481956,
      "grad_norm": 0.1318831890821457,
      "learning_rate": 0.003,
      "loss": 3.3415237426757813,
      "step": 20700
    },
    {
      "epoch": 0.04543828557853259,
      "grad_norm": 0.1379501074552536,
      "learning_rate": 0.003,
      "loss": 3.31056884765625,
      "step": 20800
    },
    {
      "epoch": 0.045656738874583234,
      "grad_norm": 0.13282452523708344,
      "learning_rate": 0.003,
      "loss": 3.3612637329101562,
      "step": 20900
    },
    {
      "epoch": 0.04587519217063387,
      "grad_norm": 0.16338206827640533,
      "learning_rate": 0.003,
      "loss": 3.3540554809570313,
      "step": 21000
    },
    {
      "epoch": 0.046093645466684506,
      "grad_norm": 0.14283308386802673,
      "learning_rate": 0.003,
      "loss": 2.806424255371094,
      "step": 21100
    },
    {
      "epoch": 0.04631209876273514,
      "grad_norm": 0.1394539177417755,
      "learning_rate": 0.003,
      "loss": 3.337768859863281,
      "step": 21200
    },
    {
      "epoch": 0.046530552058785785,
      "grad_norm": 0.14424312114715576,
      "learning_rate": 0.003,
      "loss": 3.3319973754882812,
      "step": 21300
    },
    {
      "epoch": 0.04674900535483642,
      "grad_norm": 0.13849256932735443,
      "learning_rate": 0.003,
      "loss": 3.357599182128906,
      "step": 21400
    },
    {
      "epoch": 0.046967458650887056,
      "grad_norm": 0.16135214269161224,
      "learning_rate": 0.003,
      "loss": 3.3484396362304687,
      "step": 21500
    },
    {
      "epoch": 0.04718591194693769,
      "grad_norm": 0.12737597525119781,
      "learning_rate": 0.003,
      "loss": 3.32648681640625,
      "step": 21600
    },
    {
      "epoch": 0.047404365242988335,
      "grad_norm": 0.1328800916671753,
      "learning_rate": 0.003,
      "loss": 3.3115444946289063,
      "step": 21700
    },
    {
      "epoch": 0.04762281853903897,
      "grad_norm": 0.13899770379066467,
      "learning_rate": 0.003,
      "loss": 3.315568542480469,
      "step": 21800
    },
    {
      "epoch": 0.047841271835089606,
      "grad_norm": 0.13824427127838135,
      "learning_rate": 0.003,
      "loss": 3.3840231323242187,
      "step": 21900
    },
    {
      "epoch": 0.04805972513114024,
      "grad_norm": 0.13134266436100006,
      "learning_rate": 0.003,
      "loss": 3.332655944824219,
      "step": 22000
    },
    {
      "epoch": 0.048278178427190885,
      "grad_norm": 0.155122771859169,
      "learning_rate": 0.003,
      "loss": 3.3235379028320313,
      "step": 22100
    },
    {
      "epoch": 0.04849663172324152,
      "grad_norm": 0.15229357779026031,
      "learning_rate": 0.003,
      "loss": 3.3199755859375,
      "step": 22200
    },
    {
      "epoch": 0.048715085019292156,
      "grad_norm": 0.12670215964317322,
      "learning_rate": 0.003,
      "loss": 3.316469421386719,
      "step": 22300
    },
    {
      "epoch": 0.04893353831534279,
      "grad_norm": 0.141511932015419,
      "learning_rate": 0.003,
      "loss": 3.3063583374023438,
      "step": 22400
    },
    {
      "epoch": 0.049151991611393435,
      "grad_norm": 0.1661921739578247,
      "learning_rate": 0.003,
      "loss": 3.3516119384765624,
      "step": 22500
    },
    {
      "epoch": 0.04937044490744407,
      "grad_norm": 0.158327117562294,
      "learning_rate": 0.003,
      "loss": 3.31264892578125,
      "step": 22600
    },
    {
      "epoch": 0.049588898203494707,
      "grad_norm": 0.12664683163166046,
      "learning_rate": 0.003,
      "loss": 3.3332479858398436,
      "step": 22700
    },
    {
      "epoch": 0.04980735149954534,
      "grad_norm": 0.16267594695091248,
      "learning_rate": 0.003,
      "loss": 3.3688790893554685,
      "step": 22800
    },
    {
      "epoch": 0.05002580479559598,
      "grad_norm": 0.12839975953102112,
      "learning_rate": 0.003,
      "loss": 3.342285461425781,
      "step": 22900
    },
    {
      "epoch": 0.05024425809164662,
      "grad_norm": 0.12727583944797516,
      "learning_rate": 0.003,
      "loss": 3.3483712768554685,
      "step": 23000
    },
    {
      "epoch": 0.05046271138769726,
      "grad_norm": 0.1626160889863968,
      "learning_rate": 0.003,
      "loss": 3.258794250488281,
      "step": 23100
    },
    {
      "epoch": 0.05068116468374789,
      "grad_norm": 0.1446387618780136,
      "learning_rate": 0.003,
      "loss": 3.360071105957031,
      "step": 23200
    },
    {
      "epoch": 0.05089961797979853,
      "grad_norm": 0.14391113817691803,
      "learning_rate": 0.003,
      "loss": 3.3143096923828126,
      "step": 23300
    },
    {
      "epoch": 0.05111807127584917,
      "grad_norm": 0.1434401422739029,
      "learning_rate": 0.003,
      "loss": 3.325472106933594,
      "step": 23400
    },
    {
      "epoch": 0.05133652457189981,
      "grad_norm": 0.13786746561527252,
      "learning_rate": 0.003,
      "loss": 3.310267333984375,
      "step": 23500
    },
    {
      "epoch": 0.05155497786795044,
      "grad_norm": 0.13826313614845276,
      "learning_rate": 0.003,
      "loss": 3.356964111328125,
      "step": 23600
    },
    {
      "epoch": 0.05177343116400108,
      "grad_norm": 0.12940509617328644,
      "learning_rate": 0.003,
      "loss": 3.3435748291015623,
      "step": 23700
    },
    {
      "epoch": 0.05199188446005172,
      "grad_norm": 0.16012531518936157,
      "learning_rate": 0.003,
      "loss": 3.377527160644531,
      "step": 23800
    },
    {
      "epoch": 0.05221033775610236,
      "grad_norm": 0.15281037986278534,
      "learning_rate": 0.003,
      "loss": 3.3529147338867187,
      "step": 23900
    },
    {
      "epoch": 0.05242879105215299,
      "grad_norm": 0.12364033609628677,
      "learning_rate": 0.003,
      "loss": 3.3162277221679686,
      "step": 24000
    },
    {
      "epoch": 0.05264724434820363,
      "grad_norm": 0.13337066769599915,
      "learning_rate": 0.003,
      "loss": 3.332524719238281,
      "step": 24100
    },
    {
      "epoch": 0.05286569764425427,
      "grad_norm": 0.12411975860595703,
      "learning_rate": 0.003,
      "loss": 3.3512115478515625,
      "step": 24200
    },
    {
      "epoch": 0.05308415094030491,
      "grad_norm": 0.16036230325698853,
      "learning_rate": 0.003,
      "loss": 3.3250997924804686,
      "step": 24300
    },
    {
      "epoch": 0.05330260423635554,
      "grad_norm": 0.22030843794345856,
      "learning_rate": 0.003,
      "loss": 3.304237060546875,
      "step": 24400
    },
    {
      "epoch": 0.05352105753240618,
      "grad_norm": 0.25381991267204285,
      "learning_rate": 0.003,
      "loss": 3.34534423828125,
      "step": 24500
    },
    {
      "epoch": 0.05373951082845682,
      "grad_norm": 0.16389718651771545,
      "learning_rate": 0.003,
      "loss": 3.348591613769531,
      "step": 24600
    },
    {
      "epoch": 0.05395796412450746,
      "grad_norm": 0.14573702216148376,
      "learning_rate": 0.003,
      "loss": 3.3080172729492188,
      "step": 24700
    },
    {
      "epoch": 0.05417641742055809,
      "grad_norm": 0.1497870832681656,
      "learning_rate": 0.003,
      "loss": 3.3553036499023436,
      "step": 24800
    },
    {
      "epoch": 0.05439487071660873,
      "grad_norm": 0.13177230954170227,
      "learning_rate": 0.003,
      "loss": 3.2844012451171873,
      "step": 24900
    },
    {
      "epoch": 0.05461332401265937,
      "grad_norm": 0.15044496953487396,
      "learning_rate": 0.003,
      "loss": 3.3339718627929686,
      "step": 25000
    },
    {
      "epoch": 0.05483177730871001,
      "grad_norm": 0.16820241510868073,
      "learning_rate": 0.003,
      "loss": 3.312646484375,
      "step": 25100
    },
    {
      "epoch": 0.05505023060476064,
      "grad_norm": 0.13994398713111877,
      "learning_rate": 0.003,
      "loss": 3.3246527099609375,
      "step": 25200
    },
    {
      "epoch": 0.05526868390081128,
      "grad_norm": 0.13690656423568726,
      "learning_rate": 0.003,
      "loss": 3.3303009033203126,
      "step": 25300
    },
    {
      "epoch": 0.05548713719686192,
      "grad_norm": 0.1266283243894577,
      "learning_rate": 0.003,
      "loss": 3.3370904541015625,
      "step": 25400
    },
    {
      "epoch": 0.05570559049291256,
      "grad_norm": 0.2835458815097809,
      "learning_rate": 0.003,
      "loss": 3.2755780029296875,
      "step": 25500
    },
    {
      "epoch": 0.05592404378896319,
      "grad_norm": 0.1243748813867569,
      "learning_rate": 0.003,
      "loss": 3.31575927734375,
      "step": 25600
    },
    {
      "epoch": 0.05614249708501383,
      "grad_norm": 0.13248547911643982,
      "learning_rate": 0.003,
      "loss": 3.273077087402344,
      "step": 25700
    },
    {
      "epoch": 0.05636095038106447,
      "grad_norm": 0.1573888212442398,
      "learning_rate": 0.003,
      "loss": 3.329945373535156,
      "step": 25800
    },
    {
      "epoch": 0.05657940367711511,
      "grad_norm": 0.1859431117773056,
      "learning_rate": 0.003,
      "loss": 3.3422332763671876,
      "step": 25900
    },
    {
      "epoch": 0.05679785697316574,
      "grad_norm": 0.14315782487392426,
      "learning_rate": 0.003,
      "loss": 3.321678466796875,
      "step": 26000
    },
    {
      "epoch": 0.05701631026921638,
      "grad_norm": 0.16119340062141418,
      "learning_rate": 0.003,
      "loss": 3.28656982421875,
      "step": 26100
    },
    {
      "epoch": 0.057234763565267015,
      "grad_norm": 0.169467493891716,
      "learning_rate": 0.003,
      "loss": 3.3227874755859377,
      "step": 26200
    },
    {
      "epoch": 0.05745321686131766,
      "grad_norm": 0.13390371203422546,
      "learning_rate": 0.003,
      "loss": 3.3195626831054685,
      "step": 26300
    },
    {
      "epoch": 0.05767167015736829,
      "grad_norm": 0.2256622463464737,
      "learning_rate": 0.003,
      "loss": 3.3732449340820314,
      "step": 26400
    },
    {
      "epoch": 0.05789012345341893,
      "grad_norm": 0.14236938953399658,
      "learning_rate": 0.003,
      "loss": 3.315290832519531,
      "step": 26500
    },
    {
      "epoch": 0.058108576749469565,
      "grad_norm": 0.13468952476978302,
      "learning_rate": 0.003,
      "loss": 3.2961331176757813,
      "step": 26600
    },
    {
      "epoch": 0.05832703004552021,
      "grad_norm": 0.13163988292217255,
      "learning_rate": 0.003,
      "loss": 3.3402911376953126,
      "step": 26700
    },
    {
      "epoch": 0.05854548334157084,
      "grad_norm": 0.16410379111766815,
      "learning_rate": 0.003,
      "loss": 3.3237750244140627,
      "step": 26800
    },
    {
      "epoch": 0.05876393663762148,
      "grad_norm": 0.17589592933654785,
      "learning_rate": 0.003,
      "loss": 3.3025152587890627,
      "step": 26900
    },
    {
      "epoch": 0.058982389933672115,
      "grad_norm": 0.12554213404655457,
      "learning_rate": 0.003,
      "loss": 3.329324035644531,
      "step": 27000
    },
    {
      "epoch": 0.05920084322972276,
      "grad_norm": 0.14356501400470734,
      "learning_rate": 0.003,
      "loss": 3.3095223999023435,
      "step": 27100
    },
    {
      "epoch": 0.059419296525773393,
      "grad_norm": 0.20642130076885223,
      "learning_rate": 0.003,
      "loss": 3.16523681640625,
      "step": 27200
    },
    {
      "epoch": 0.05963774982182403,
      "grad_norm": 0.12734311819076538,
      "learning_rate": 0.003,
      "loss": 3.3130838012695314,
      "step": 27300
    },
    {
      "epoch": 0.059856203117874665,
      "grad_norm": 0.16035129129886627,
      "learning_rate": 0.003,
      "loss": 3.3009878540039064,
      "step": 27400
    },
    {
      "epoch": 0.06007465641392531,
      "grad_norm": 0.1451551616191864,
      "learning_rate": 0.003,
      "loss": 3.3051492309570314,
      "step": 27500
    },
    {
      "epoch": 0.060293109709975944,
      "grad_norm": 0.12821145355701447,
      "learning_rate": 0.003,
      "loss": 3.32,
      "step": 27600
    },
    {
      "epoch": 0.06051156300602658,
      "grad_norm": 0.1578887552022934,
      "learning_rate": 0.003,
      "loss": 3.2693597412109376,
      "step": 27700
    },
    {
      "epoch": 0.060730016302077215,
      "grad_norm": 0.1403341293334961,
      "learning_rate": 0.003,
      "loss": 3.285400085449219,
      "step": 27800
    },
    {
      "epoch": 0.06094846959812786,
      "grad_norm": 0.1922478973865509,
      "learning_rate": 0.003,
      "loss": 3.3167987060546875,
      "step": 27900
    },
    {
      "epoch": 0.061166922894178494,
      "grad_norm": 0.12697449326515198,
      "learning_rate": 0.003,
      "loss": 3.326105651855469,
      "step": 28000
    },
    {
      "epoch": 0.06138537619022913,
      "grad_norm": 0.21215832233428955,
      "learning_rate": 0.003,
      "loss": 3.309931640625,
      "step": 28100
    },
    {
      "epoch": 0.061603829486279765,
      "grad_norm": 0.13175860047340393,
      "learning_rate": 0.003,
      "loss": 3.2714743041992187,
      "step": 28200
    },
    {
      "epoch": 0.06182228278233041,
      "grad_norm": 0.12134334444999695,
      "learning_rate": 0.003,
      "loss": 3.3450942993164063,
      "step": 28300
    },
    {
      "epoch": 0.062040736078381044,
      "grad_norm": 0.16979266703128815,
      "learning_rate": 0.003,
      "loss": 3.277815856933594,
      "step": 28400
    },
    {
      "epoch": 0.06225918937443168,
      "grad_norm": 0.13171924650669098,
      "learning_rate": 0.003,
      "loss": 3.2926800537109373,
      "step": 28500
    },
    {
      "epoch": 0.062477642670482315,
      "grad_norm": 0.13504329323768616,
      "learning_rate": 0.003,
      "loss": 3.304072265625,
      "step": 28600
    },
    {
      "epoch": 0.06269609596653296,
      "grad_norm": 0.1422707885503769,
      "learning_rate": 0.003,
      "loss": 3.2862860107421876,
      "step": 28700
    },
    {
      "epoch": 0.0629145492625836,
      "grad_norm": 0.17020823061466217,
      "learning_rate": 0.003,
      "loss": 3.3183663940429686,
      "step": 28800
    },
    {
      "epoch": 0.06313300255863423,
      "grad_norm": 0.7097678780555725,
      "learning_rate": 0.003,
      "loss": 3.295379333496094,
      "step": 28900
    },
    {
      "epoch": 0.06335145585468487,
      "grad_norm": 0.14952735602855682,
      "learning_rate": 0.003,
      "loss": 3.2717132568359375,
      "step": 29000
    },
    {
      "epoch": 0.0635699091507355,
      "grad_norm": 0.1692362278699875,
      "learning_rate": 0.003,
      "loss": 3.3412515258789064,
      "step": 29100
    },
    {
      "epoch": 0.06378836244678614,
      "grad_norm": 0.15614360570907593,
      "learning_rate": 0.003,
      "loss": 3.3063565063476563,
      "step": 29200
    },
    {
      "epoch": 0.06400681574283679,
      "grad_norm": 0.20806823670864105,
      "learning_rate": 0.003,
      "loss": 3.2843331909179687,
      "step": 29300
    },
    {
      "epoch": 0.06422526903888742,
      "grad_norm": 0.23479899764060974,
      "learning_rate": 0.003,
      "loss": 3.2819674682617186,
      "step": 29400
    },
    {
      "epoch": 0.06444372233493806,
      "grad_norm": 0.15177583694458008,
      "learning_rate": 0.003,
      "loss": 3.3203561401367185,
      "step": 29500
    },
    {
      "epoch": 0.0646621756309887,
      "grad_norm": 0.1472543627023697,
      "learning_rate": 0.003,
      "loss": 3.3170175170898437,
      "step": 29600
    },
    {
      "epoch": 0.06488062892703933,
      "grad_norm": 0.13402847945690155,
      "learning_rate": 0.003,
      "loss": 3.3249472045898436,
      "step": 29700
    },
    {
      "epoch": 0.06509908222308997,
      "grad_norm": 0.1574559062719345,
      "learning_rate": 0.003,
      "loss": 3.3021722412109376,
      "step": 29800
    },
    {
      "epoch": 0.0653175355191406,
      "grad_norm": 0.12917636334896088,
      "learning_rate": 0.003,
      "loss": 3.2708474731445314,
      "step": 29900
    },
    {
      "epoch": 0.06553598881519124,
      "grad_norm": 0.19614313542842865,
      "learning_rate": 0.003,
      "loss": 3.350285949707031,
      "step": 30000
    },
    {
      "epoch": 0.06575444211124187,
      "grad_norm": 0.21345964074134827,
      "learning_rate": 0.003,
      "loss": 3.2905197143554688,
      "step": 30100
    },
    {
      "epoch": 0.06597289540729252,
      "grad_norm": 0.13310234248638153,
      "learning_rate": 0.003,
      "loss": 3.14111572265625,
      "step": 30200
    },
    {
      "epoch": 0.06619134870334316,
      "grad_norm": 0.1672133207321167,
      "learning_rate": 0.003,
      "loss": 3.292821960449219,
      "step": 30300
    },
    {
      "epoch": 0.0664098019993938,
      "grad_norm": 0.15199998021125793,
      "learning_rate": 0.003,
      "loss": 3.281614990234375,
      "step": 30400
    },
    {
      "epoch": 0.06662825529544443,
      "grad_norm": 0.17468766868114471,
      "learning_rate": 0.003,
      "loss": 3.28716552734375,
      "step": 30500
    },
    {
      "epoch": 0.06684670859149507,
      "grad_norm": 0.13380374014377594,
      "learning_rate": 0.003,
      "loss": 3.3208758544921877,
      "step": 30600
    },
    {
      "epoch": 0.0670651618875457,
      "grad_norm": 0.12906578183174133,
      "learning_rate": 0.003,
      "loss": 3.2482403564453124,
      "step": 30700
    },
    {
      "epoch": 0.06728361518359634,
      "grad_norm": 0.16773296892642975,
      "learning_rate": 0.003,
      "loss": 3.2957916259765625,
      "step": 30800
    },
    {
      "epoch": 0.06750206847964697,
      "grad_norm": 0.1382984071969986,
      "learning_rate": 0.003,
      "loss": 3.2812515258789063,
      "step": 30900
    },
    {
      "epoch": 0.06772052177569762,
      "grad_norm": 0.12064798176288605,
      "learning_rate": 0.003,
      "loss": 3.292807312011719,
      "step": 31000
    },
    {
      "epoch": 0.06793897507174826,
      "grad_norm": 0.14423973858356476,
      "learning_rate": 0.003,
      "loss": 3.1367059326171876,
      "step": 31100
    },
    {
      "epoch": 0.0681574283677989,
      "grad_norm": 0.17670339345932007,
      "learning_rate": 0.003,
      "loss": 3.3249557495117186,
      "step": 31200
    },
    {
      "epoch": 0.06837588166384953,
      "grad_norm": 0.13148869574069977,
      "learning_rate": 0.003,
      "loss": 3.323037414550781,
      "step": 31300
    },
    {
      "epoch": 0.06859433495990017,
      "grad_norm": 0.25557222962379456,
      "learning_rate": 0.003,
      "loss": 3.2895745849609375,
      "step": 31400
    },
    {
      "epoch": 0.0688127882559508,
      "grad_norm": 0.1451721489429474,
      "learning_rate": 0.003,
      "loss": 3.30470703125,
      "step": 31500
    },
    {
      "epoch": 0.06903124155200144,
      "grad_norm": 0.14752569794654846,
      "learning_rate": 0.003,
      "loss": 3.2685122680664063,
      "step": 31600
    },
    {
      "epoch": 0.06924969484805207,
      "grad_norm": 0.12468330562114716,
      "learning_rate": 0.003,
      "loss": 3.2936700439453124,
      "step": 31700
    },
    {
      "epoch": 0.06946814814410272,
      "grad_norm": 0.16558866202831268,
      "learning_rate": 0.003,
      "loss": 3.3152020263671873,
      "step": 31800
    },
    {
      "epoch": 0.06968660144015336,
      "grad_norm": 0.1636384129524231,
      "learning_rate": 0.003,
      "loss": 3.311054992675781,
      "step": 31900
    },
    {
      "epoch": 0.069905054736204,
      "grad_norm": 0.13477930426597595,
      "learning_rate": 0.003,
      "loss": 3.2879302978515623,
      "step": 32000
    },
    {
      "epoch": 0.07012350803225463,
      "grad_norm": 0.13240183889865875,
      "learning_rate": 0.003,
      "loss": 3.337416687011719,
      "step": 32100
    },
    {
      "epoch": 0.07034196132830527,
      "grad_norm": 0.1719566434621811,
      "learning_rate": 0.003,
      "loss": 3.2947512817382814,
      "step": 32200
    },
    {
      "epoch": 0.0705604146243559,
      "grad_norm": 0.14052827656269073,
      "learning_rate": 0.003,
      "loss": 3.282734680175781,
      "step": 32300
    },
    {
      "epoch": 0.07077886792040654,
      "grad_norm": 0.13085907697677612,
      "learning_rate": 0.003,
      "loss": 3.297210693359375,
      "step": 32400
    },
    {
      "epoch": 0.07099732121645717,
      "grad_norm": 0.20025353133678436,
      "learning_rate": 0.003,
      "loss": 3.2842779541015625,
      "step": 32500
    },
    {
      "epoch": 0.07121577451250782,
      "grad_norm": 0.1402798742055893,
      "learning_rate": 0.003,
      "loss": 3.298916931152344,
      "step": 32600
    },
    {
      "epoch": 0.07143422780855846,
      "grad_norm": 0.14476116001605988,
      "learning_rate": 0.003,
      "loss": 3.2706668090820314,
      "step": 32700
    },
    {
      "epoch": 0.0716526811046091,
      "grad_norm": 0.13569767773151398,
      "learning_rate": 0.003,
      "loss": 3.2827581787109374,
      "step": 32800
    },
    {
      "epoch": 0.07187113440065973,
      "grad_norm": 0.15818500518798828,
      "learning_rate": 0.003,
      "loss": 3.2876434326171875,
      "step": 32900
    },
    {
      "epoch": 0.07208958769671037,
      "grad_norm": 0.1276344656944275,
      "learning_rate": 0.003,
      "loss": 3.3087249755859376,
      "step": 33000
    },
    {
      "epoch": 0.072308040992761,
      "grad_norm": 0.13138215243816376,
      "learning_rate": 0.003,
      "loss": 3.2812591552734376,
      "step": 33100
    },
    {
      "epoch": 0.07252649428881164,
      "grad_norm": 0.18934592604637146,
      "learning_rate": 0.003,
      "loss": 3.30925537109375,
      "step": 33200
    },
    {
      "epoch": 0.07274494758486227,
      "grad_norm": 0.14984296262264252,
      "learning_rate": 0.003,
      "loss": 3.2924786376953126,
      "step": 33300
    },
    {
      "epoch": 0.07296340088091291,
      "grad_norm": 0.16432835161685944,
      "learning_rate": 0.003,
      "loss": 3.279039306640625,
      "step": 33400
    },
    {
      "epoch": 0.07318185417696356,
      "grad_norm": 0.131127268075943,
      "learning_rate": 0.003,
      "loss": 3.3125900268554687,
      "step": 33500
    },
    {
      "epoch": 0.0734003074730142,
      "grad_norm": 0.15136845409870148,
      "learning_rate": 0.003,
      "loss": 3.3073272705078125,
      "step": 33600
    },
    {
      "epoch": 0.07361876076906483,
      "grad_norm": 0.1228429302573204,
      "learning_rate": 0.003,
      "loss": 3.1849093627929688,
      "step": 33700
    },
    {
      "epoch": 0.07383721406511547,
      "grad_norm": 0.12898238003253937,
      "learning_rate": 0.003,
      "loss": 3.2927169799804688,
      "step": 33800
    },
    {
      "epoch": 0.0740556673611661,
      "grad_norm": 0.3990197777748108,
      "learning_rate": 0.003,
      "loss": 3.3054901123046876,
      "step": 33900
    },
    {
      "epoch": 0.07427412065721674,
      "grad_norm": 0.1889471411705017,
      "learning_rate": 0.003,
      "loss": 3.2711798095703126,
      "step": 34000
    },
    {
      "epoch": 0.07449257395326737,
      "grad_norm": 0.32053592801094055,
      "learning_rate": 0.003,
      "loss": 3.277731628417969,
      "step": 34100
    },
    {
      "epoch": 0.07471102724931801,
      "grad_norm": 0.12476284056901932,
      "learning_rate": 0.003,
      "loss": 3.3241058349609376,
      "step": 34200
    },
    {
      "epoch": 0.07492948054536866,
      "grad_norm": 0.1345445066690445,
      "learning_rate": 0.003,
      "loss": 3.235545349121094,
      "step": 34300
    },
    {
      "epoch": 0.0751479338414193,
      "grad_norm": 0.17160938680171967,
      "learning_rate": 0.003,
      "loss": 3.260941162109375,
      "step": 34400
    },
    {
      "epoch": 0.07536638713746993,
      "grad_norm": 0.15105551481246948,
      "learning_rate": 0.003,
      "loss": 3.2895513916015626,
      "step": 34500
    },
    {
      "epoch": 0.07558484043352057,
      "grad_norm": 0.13841792941093445,
      "learning_rate": 0.003,
      "loss": 3.3118740844726564,
      "step": 34600
    },
    {
      "epoch": 0.0758032937295712,
      "grad_norm": 0.13309921324253082,
      "learning_rate": 0.003,
      "loss": 3.2925543212890624,
      "step": 34700
    },
    {
      "epoch": 0.07602174702562184,
      "grad_norm": 0.13050492107868195,
      "learning_rate": 0.003,
      "loss": 3.2816531372070314,
      "step": 34800
    },
    {
      "epoch": 0.07624020032167247,
      "grad_norm": 0.6023688316345215,
      "learning_rate": 0.003,
      "loss": 3.3055108642578124,
      "step": 34900
    },
    {
      "epoch": 0.07645865361772311,
      "grad_norm": 0.1407451182603836,
      "learning_rate": 0.003,
      "loss": 3.34151611328125,
      "step": 35000
    },
    {
      "epoch": 0.07667710691377376,
      "grad_norm": 0.1305139809846878,
      "learning_rate": 0.003,
      "loss": 3.2856158447265624,
      "step": 35100
    },
    {
      "epoch": 0.0768955602098244,
      "grad_norm": 0.1610284149646759,
      "learning_rate": 0.003,
      "loss": 3.2734844970703123,
      "step": 35200
    },
    {
      "epoch": 0.07711401350587503,
      "grad_norm": 0.13967597484588623,
      "learning_rate": 0.003,
      "loss": 3.256042175292969,
      "step": 35300
    },
    {
      "epoch": 0.07733246680192567,
      "grad_norm": 0.19864661991596222,
      "learning_rate": 0.003,
      "loss": 3.324942321777344,
      "step": 35400
    },
    {
      "epoch": 0.0775509200979763,
      "grad_norm": 0.16039150953292847,
      "learning_rate": 0.003,
      "loss": 3.2831130981445313,
      "step": 35500
    },
    {
      "epoch": 0.07776937339402694,
      "grad_norm": 0.1747000366449356,
      "learning_rate": 0.003,
      "loss": 3.307495422363281,
      "step": 35600
    },
    {
      "epoch": 0.07798782669007757,
      "grad_norm": 0.20273174345493317,
      "learning_rate": 0.003,
      "loss": 3.3177590942382813,
      "step": 35700
    },
    {
      "epoch": 0.07820627998612821,
      "grad_norm": 0.1993030309677124,
      "learning_rate": 0.003,
      "loss": 3.304837341308594,
      "step": 35800
    },
    {
      "epoch": 0.07842473328217886,
      "grad_norm": 0.17900240421295166,
      "learning_rate": 0.003,
      "loss": 3.235675048828125,
      "step": 35900
    },
    {
      "epoch": 0.0786431865782295,
      "grad_norm": 0.14110247790813446,
      "learning_rate": 0.003,
      "loss": 3.19402587890625,
      "step": 36000
    },
    {
      "epoch": 0.07886163987428013,
      "grad_norm": 0.2041473090648651,
      "learning_rate": 0.003,
      "loss": 3.3216961669921874,
      "step": 36100
    },
    {
      "epoch": 0.07908009317033077,
      "grad_norm": 0.19810523092746735,
      "learning_rate": 0.003,
      "loss": 3.2388531494140627,
      "step": 36200
    },
    {
      "epoch": 0.0792985464663814,
      "grad_norm": 0.12772241234779358,
      "learning_rate": 0.003,
      "loss": 3.2910110473632814,
      "step": 36300
    },
    {
      "epoch": 0.07951699976243204,
      "grad_norm": 0.15931345522403717,
      "learning_rate": 0.003,
      "loss": 3.2836883544921873,
      "step": 36400
    },
    {
      "epoch": 0.07973545305848267,
      "grad_norm": 0.13564768433570862,
      "learning_rate": 0.003,
      "loss": 3.3310623168945312,
      "step": 36500
    },
    {
      "epoch": 0.07995390635453331,
      "grad_norm": 0.15236645936965942,
      "learning_rate": 0.003,
      "loss": 3.273614501953125,
      "step": 36600
    },
    {
      "epoch": 0.08017235965058395,
      "grad_norm": 0.14576539397239685,
      "learning_rate": 0.003,
      "loss": 3.3081988525390624,
      "step": 36700
    },
    {
      "epoch": 0.0803908129466346,
      "grad_norm": 0.1572989672422409,
      "learning_rate": 0.003,
      "loss": 3.251156005859375,
      "step": 36800
    },
    {
      "epoch": 0.08060926624268523,
      "grad_norm": 0.15005140006542206,
      "learning_rate": 0.003,
      "loss": 3.2585882568359374,
      "step": 36900
    },
    {
      "epoch": 0.08082771953873587,
      "grad_norm": 0.15507107973098755,
      "learning_rate": 0.003,
      "loss": 3.266631774902344,
      "step": 37000
    },
    {
      "epoch": 0.0810461728347865,
      "grad_norm": 0.17641592025756836,
      "learning_rate": 0.003,
      "loss": 3.239948425292969,
      "step": 37100
    },
    {
      "epoch": 0.08126462613083714,
      "grad_norm": 0.12613926827907562,
      "learning_rate": 0.003,
      "loss": 3.3062588500976564,
      "step": 37200
    },
    {
      "epoch": 0.08148307942688778,
      "grad_norm": 0.2538757920265198,
      "learning_rate": 0.003,
      "loss": 3.278668212890625,
      "step": 37300
    },
    {
      "epoch": 0.08170153272293841,
      "grad_norm": 0.16014288365840912,
      "learning_rate": 0.003,
      "loss": 3.23365966796875,
      "step": 37400
    },
    {
      "epoch": 0.08191998601898905,
      "grad_norm": 0.14398036897182465,
      "learning_rate": 0.003,
      "loss": 3.3074264526367188,
      "step": 37500
    },
    {
      "epoch": 0.0821384393150397,
      "grad_norm": 0.14527015388011932,
      "learning_rate": 0.003,
      "loss": 3.260564270019531,
      "step": 37600
    },
    {
      "epoch": 0.08235689261109033,
      "grad_norm": 0.13640612363815308,
      "learning_rate": 0.003,
      "loss": 3.2675531005859373,
      "step": 37700
    },
    {
      "epoch": 0.08257534590714097,
      "grad_norm": 0.1483987420797348,
      "learning_rate": 0.003,
      "loss": 3.241988525390625,
      "step": 37800
    },
    {
      "epoch": 0.0827937992031916,
      "grad_norm": 0.14941224455833435,
      "learning_rate": 0.003,
      "loss": 3.3164938354492186,
      "step": 37900
    },
    {
      "epoch": 0.08301225249924224,
      "grad_norm": 0.17315177619457245,
      "learning_rate": 0.003,
      "loss": 3.316810302734375,
      "step": 38000
    },
    {
      "epoch": 0.08323070579529288,
      "grad_norm": 0.17823275923728943,
      "learning_rate": 0.003,
      "loss": 3.249942626953125,
      "step": 38100
    },
    {
      "epoch": 0.08344915909134351,
      "grad_norm": 0.20452110469341278,
      "learning_rate": 0.003,
      "loss": 3.2030743408203124,
      "step": 38200
    },
    {
      "epoch": 0.08366761238739415,
      "grad_norm": 0.13244900107383728,
      "learning_rate": 0.003,
      "loss": 3.272771911621094,
      "step": 38300
    },
    {
      "epoch": 0.0838860656834448,
      "grad_norm": 0.14962248504161835,
      "learning_rate": 0.003,
      "loss": 3.3190447998046877,
      "step": 38400
    },
    {
      "epoch": 0.08410451897949543,
      "grad_norm": 0.13936245441436768,
      "learning_rate": 0.003,
      "loss": 3.2822772216796876,
      "step": 38500
    },
    {
      "epoch": 0.08432297227554607,
      "grad_norm": 0.17270345985889435,
      "learning_rate": 0.003,
      "loss": 3.3033078002929686,
      "step": 38600
    },
    {
      "epoch": 0.0845414255715967,
      "grad_norm": 0.17023159563541412,
      "learning_rate": 0.003,
      "loss": 3.2737576293945314,
      "step": 38700
    },
    {
      "epoch": 0.08475987886764734,
      "grad_norm": 0.1845265030860901,
      "learning_rate": 0.003,
      "loss": 3.2791680908203125,
      "step": 38800
    },
    {
      "epoch": 0.08497833216369798,
      "grad_norm": 0.13376891613006592,
      "learning_rate": 0.003,
      "loss": 3.2831585693359373,
      "step": 38900
    },
    {
      "epoch": 0.08519678545974861,
      "grad_norm": 0.1504724621772766,
      "learning_rate": 0.003,
      "loss": 3.3097457885742188,
      "step": 39000
    },
    {
      "epoch": 0.08541523875579925,
      "grad_norm": 0.137648805975914,
      "learning_rate": 0.003,
      "loss": 3.2856106567382812,
      "step": 39100
    },
    {
      "epoch": 0.0856336920518499,
      "grad_norm": 0.1618202179670334,
      "learning_rate": 0.003,
      "loss": 3.267169189453125,
      "step": 39200
    },
    {
      "epoch": 0.08585214534790053,
      "grad_norm": 0.19786691665649414,
      "learning_rate": 0.003,
      "loss": 3.2910052490234376,
      "step": 39300
    },
    {
      "epoch": 0.08607059864395117,
      "grad_norm": 0.15184424817562103,
      "learning_rate": 0.003,
      "loss": 3.317454833984375,
      "step": 39400
    },
    {
      "epoch": 0.0862890519400018,
      "grad_norm": 9.05631160736084,
      "learning_rate": 0.003,
      "loss": 3.2767315673828126,
      "step": 39500
    },
    {
      "epoch": 0.08650750523605244,
      "grad_norm": 0.15465736389160156,
      "learning_rate": 0.003,
      "loss": 2.794194641113281,
      "step": 39600
    },
    {
      "epoch": 0.08672595853210308,
      "grad_norm": 0.16257505118846893,
      "learning_rate": 0.003,
      "loss": 3.2999783325195313,
      "step": 39700
    },
    {
      "epoch": 0.08694441182815371,
      "grad_norm": 0.15374092757701874,
      "learning_rate": 0.003,
      "loss": 3.267034606933594,
      "step": 39800
    },
    {
      "epoch": 0.08716286512420435,
      "grad_norm": 0.18448083102703094,
      "learning_rate": 0.003,
      "loss": 3.2641702270507813,
      "step": 39900
    },
    {
      "epoch": 0.08738131842025498,
      "grad_norm": 0.12463884055614471,
      "learning_rate": 0.003,
      "loss": 3.284293518066406,
      "step": 40000
    },
    {
      "epoch": 0.08759977171630563,
      "grad_norm": 0.2346997857093811,
      "learning_rate": 0.003,
      "loss": 3.3378842163085936,
      "step": 40100
    },
    {
      "epoch": 0.08781822501235627,
      "grad_norm": 0.16173656284809113,
      "learning_rate": 0.003,
      "loss": 3.28466064453125,
      "step": 40200
    },
    {
      "epoch": 0.0880366783084069,
      "grad_norm": 0.15595772862434387,
      "learning_rate": 0.003,
      "loss": 3.260408630371094,
      "step": 40300
    },
    {
      "epoch": 0.08825513160445754,
      "grad_norm": 0.12999649345874786,
      "learning_rate": 0.003,
      "loss": 3.301771545410156,
      "step": 40400
    },
    {
      "epoch": 0.08847358490050818,
      "grad_norm": 0.12810906767845154,
      "learning_rate": 0.003,
      "loss": 3.273116455078125,
      "step": 40500
    },
    {
      "epoch": 0.08869203819655881,
      "grad_norm": 0.18569885194301605,
      "learning_rate": 0.003,
      "loss": 3.2856179809570314,
      "step": 40600
    },
    {
      "epoch": 0.08891049149260945,
      "grad_norm": 0.18256127834320068,
      "learning_rate": 0.003,
      "loss": 3.24281982421875,
      "step": 40700
    },
    {
      "epoch": 0.08912894478866008,
      "grad_norm": 0.1585642695426941,
      "learning_rate": 0.003,
      "loss": 3.2112246704101564,
      "step": 40800
    },
    {
      "epoch": 0.08934739808471073,
      "grad_norm": 0.17732886970043182,
      "learning_rate": 0.003,
      "loss": 3.2847430419921877,
      "step": 40900
    },
    {
      "epoch": 0.08956585138076137,
      "grad_norm": 0.13492503762245178,
      "learning_rate": 0.003,
      "loss": 3.312560729980469,
      "step": 41000
    },
    {
      "epoch": 0.089784304676812,
      "grad_norm": 0.16829057037830353,
      "learning_rate": 0.003,
      "loss": 3.2641729736328124,
      "step": 41100
    },
    {
      "epoch": 0.09000275797286264,
      "grad_norm": 0.18808752298355103,
      "learning_rate": 0.003,
      "loss": 3.2674325561523436,
      "step": 41200
    },
    {
      "epoch": 0.09022121126891328,
      "grad_norm": 0.15025244653224945,
      "learning_rate": 0.003,
      "loss": 3.2771319580078124,
      "step": 41300
    },
    {
      "epoch": 0.09043966456496391,
      "grad_norm": 0.15831509232521057,
      "learning_rate": 0.003,
      "loss": 3.2885198974609375,
      "step": 41400
    },
    {
      "epoch": 0.09065811786101455,
      "grad_norm": 0.1266457885503769,
      "learning_rate": 0.003,
      "loss": 3.268582763671875,
      "step": 41500
    },
    {
      "epoch": 0.09087657115706518,
      "grad_norm": 0.18740995228290558,
      "learning_rate": 0.003,
      "loss": 3.2911370849609374,
      "step": 41600
    },
    {
      "epoch": 0.09109502445311583,
      "grad_norm": 0.1677059382200241,
      "learning_rate": 0.003,
      "loss": 3.32934814453125,
      "step": 41700
    },
    {
      "epoch": 0.09131347774916647,
      "grad_norm": 0.1806642860174179,
      "learning_rate": 0.003,
      "loss": 3.293853759765625,
      "step": 41800
    },
    {
      "epoch": 0.0915319310452171,
      "grad_norm": 0.20180915296077728,
      "learning_rate": 0.003,
      "loss": 3.2697601318359375,
      "step": 41900
    },
    {
      "epoch": 0.09175038434126774,
      "grad_norm": 0.13965576887130737,
      "learning_rate": 0.003,
      "loss": 3.28150146484375,
      "step": 42000
    },
    {
      "epoch": 0.09196883763731838,
      "grad_norm": 0.15903182327747345,
      "learning_rate": 0.003,
      "loss": 3.2683795166015623,
      "step": 42100
    },
    {
      "epoch": 0.09218729093336901,
      "grad_norm": 0.1410466581583023,
      "learning_rate": 0.003,
      "loss": 3.264806823730469,
      "step": 42200
    },
    {
      "epoch": 0.09240574422941965,
      "grad_norm": 0.1510380655527115,
      "learning_rate": 0.003,
      "loss": 3.2732772827148438,
      "step": 42300
    },
    {
      "epoch": 0.09262419752547028,
      "grad_norm": 0.13428038358688354,
      "learning_rate": 0.003,
      "loss": 3.2841482543945313,
      "step": 42400
    },
    {
      "epoch": 0.09284265082152092,
      "grad_norm": 0.17533539235591888,
      "learning_rate": 0.003,
      "loss": 3.2517266845703126,
      "step": 42500
    },
    {
      "epoch": 0.09306110411757157,
      "grad_norm": 0.1411064714193344,
      "learning_rate": 0.003,
      "loss": 3.282726135253906,
      "step": 42600
    },
    {
      "epoch": 0.0932795574136222,
      "grad_norm": 0.19230180978775024,
      "learning_rate": 0.003,
      "loss": 3.2695498657226563,
      "step": 42700
    },
    {
      "epoch": 0.09349801070967284,
      "grad_norm": 0.16757774353027344,
      "learning_rate": 0.003,
      "loss": 3.231575622558594,
      "step": 42800
    },
    {
      "epoch": 0.09371646400572348,
      "grad_norm": 0.17299550771713257,
      "learning_rate": 0.003,
      "loss": 3.28582763671875,
      "step": 42900
    },
    {
      "epoch": 0.09393491730177411,
      "grad_norm": 0.17058102786540985,
      "learning_rate": 0.003,
      "loss": 3.252261047363281,
      "step": 43000
    },
    {
      "epoch": 0.09415337059782475,
      "grad_norm": 0.17918632924556732,
      "learning_rate": 0.003,
      "loss": 3.276212158203125,
      "step": 43100
    },
    {
      "epoch": 0.09437182389387538,
      "grad_norm": 0.16316772997379303,
      "learning_rate": 0.003,
      "loss": 3.2334857177734375,
      "step": 43200
    },
    {
      "epoch": 0.09459027718992602,
      "grad_norm": 0.1895044595003128,
      "learning_rate": 0.003,
      "loss": 3.2556378173828127,
      "step": 43300
    },
    {
      "epoch": 0.09480873048597667,
      "grad_norm": 0.15873974561691284,
      "learning_rate": 0.003,
      "loss": 3.2901712036132813,
      "step": 43400
    },
    {
      "epoch": 0.0950271837820273,
      "grad_norm": 0.17835567891597748,
      "learning_rate": 0.003,
      "loss": 3.264893798828125,
      "step": 43500
    },
    {
      "epoch": 0.09524563707807794,
      "grad_norm": 0.15636888146400452,
      "learning_rate": 0.003,
      "loss": 3.2413174438476564,
      "step": 43600
    },
    {
      "epoch": 0.09546409037412858,
      "grad_norm": 0.14264269173145294,
      "learning_rate": 0.003,
      "loss": 3.268505859375,
      "step": 43700
    },
    {
      "epoch": 0.09568254367017921,
      "grad_norm": 0.15490996837615967,
      "learning_rate": 0.003,
      "loss": 3.235081787109375,
      "step": 43800
    },
    {
      "epoch": 0.09590099696622985,
      "grad_norm": 0.13821007311344147,
      "learning_rate": 0.003,
      "loss": 3.296794128417969,
      "step": 43900
    },
    {
      "epoch": 0.09611945026228048,
      "grad_norm": 0.16242928802967072,
      "learning_rate": 0.003,
      "loss": 3.278422546386719,
      "step": 44000
    },
    {
      "epoch": 0.09633790355833112,
      "grad_norm": 0.15828748047351837,
      "learning_rate": 0.003,
      "loss": 3.225370178222656,
      "step": 44100
    },
    {
      "epoch": 0.09655635685438177,
      "grad_norm": 0.14378058910369873,
      "learning_rate": 0.003,
      "loss": 3.231093444824219,
      "step": 44200
    },
    {
      "epoch": 0.0967748101504324,
      "grad_norm": 0.16862083971500397,
      "learning_rate": 0.003,
      "loss": 3.2397946166992186,
      "step": 44300
    },
    {
      "epoch": 0.09699326344648304,
      "grad_norm": 0.15142101049423218,
      "learning_rate": 0.003,
      "loss": 3.262004699707031,
      "step": 44400
    },
    {
      "epoch": 0.09721171674253368,
      "grad_norm": 0.13464325666427612,
      "learning_rate": 0.003,
      "loss": 3.258009338378906,
      "step": 44500
    },
    {
      "epoch": 0.09743017003858431,
      "grad_norm": 0.17103958129882812,
      "learning_rate": 0.003,
      "loss": 3.2329156494140623,
      "step": 44600
    },
    {
      "epoch": 0.09764862333463495,
      "grad_norm": 0.14914920926094055,
      "learning_rate": 0.003,
      "loss": 3.2394830322265626,
      "step": 44700
    },
    {
      "epoch": 0.09786707663068558,
      "grad_norm": 0.12734802067279816,
      "learning_rate": 0.003,
      "loss": 3.2912030029296875,
      "step": 44800
    },
    {
      "epoch": 0.09808552992673622,
      "grad_norm": 0.17552873492240906,
      "learning_rate": 0.003,
      "loss": 3.2498040771484376,
      "step": 44900
    },
    {
      "epoch": 0.09830398322278687,
      "grad_norm": 0.13984735310077667,
      "learning_rate": 0.003,
      "loss": 3.288653564453125,
      "step": 45000
    },
    {
      "epoch": 0.0985224365188375,
      "grad_norm": 0.19741426408290863,
      "learning_rate": 0.003,
      "loss": 3.252799377441406,
      "step": 45100
    },
    {
      "epoch": 0.09874088981488814,
      "grad_norm": 0.16611187160015106,
      "learning_rate": 0.003,
      "loss": 3.2686611938476564,
      "step": 45200
    },
    {
      "epoch": 0.09895934311093878,
      "grad_norm": 0.170828178524971,
      "learning_rate": 0.003,
      "loss": 3.2928143310546876,
      "step": 45300
    },
    {
      "epoch": 0.09917779640698941,
      "grad_norm": 0.17449995875358582,
      "learning_rate": 0.003,
      "loss": 3.2658261108398436,
      "step": 45400
    },
    {
      "epoch": 0.09939624970304005,
      "grad_norm": 0.19020019471645355,
      "learning_rate": 0.003,
      "loss": 3.285666198730469,
      "step": 45500
    },
    {
      "epoch": 0.09961470299909068,
      "grad_norm": 0.14907898008823395,
      "learning_rate": 0.003,
      "loss": 3.2670388793945313,
      "step": 45600
    },
    {
      "epoch": 0.09983315629514132,
      "grad_norm": 0.13812223076820374,
      "learning_rate": 0.003,
      "loss": 3.287166748046875,
      "step": 45700
    },
    {
      "epoch": 0.10005160959119196,
      "grad_norm": 0.3001323342323303,
      "learning_rate": 0.003,
      "loss": 3.2805682373046876,
      "step": 45800
    },
    {
      "epoch": 0.1002700628872426,
      "grad_norm": 0.1310071498155594,
      "learning_rate": 0.003,
      "loss": 3.266058044433594,
      "step": 45900
    },
    {
      "epoch": 0.10048851618329324,
      "grad_norm": 0.16892723739147186,
      "learning_rate": 0.003,
      "loss": 3.24665283203125,
      "step": 46000
    },
    {
      "epoch": 0.10070696947934388,
      "grad_norm": 0.1784011870622635,
      "learning_rate": 0.003,
      "loss": 3.2515863037109374,
      "step": 46100
    },
    {
      "epoch": 0.10092542277539451,
      "grad_norm": 0.13655558228492737,
      "learning_rate": 0.003,
      "loss": 3.258023986816406,
      "step": 46200
    },
    {
      "epoch": 0.10114387607144515,
      "grad_norm": 0.1459612399339676,
      "learning_rate": 0.003,
      "loss": 3.259796142578125,
      "step": 46300
    },
    {
      "epoch": 0.10136232936749578,
      "grad_norm": 0.13782542943954468,
      "learning_rate": 0.003,
      "loss": 3.270685119628906,
      "step": 46400
    },
    {
      "epoch": 0.10158078266354642,
      "grad_norm": 0.17929984629154205,
      "learning_rate": 0.003,
      "loss": 3.225979919433594,
      "step": 46500
    },
    {
      "epoch": 0.10179923595959706,
      "grad_norm": 0.14070963859558105,
      "learning_rate": 0.003,
      "loss": 3.21829833984375,
      "step": 46600
    },
    {
      "epoch": 0.1020176892556477,
      "grad_norm": 0.13950449228286743,
      "learning_rate": 0.003,
      "loss": 3.2376116943359374,
      "step": 46700
    },
    {
      "epoch": 0.10223614255169834,
      "grad_norm": 0.14981812238693237,
      "learning_rate": 0.003,
      "loss": 3.2612380981445312,
      "step": 46800
    },
    {
      "epoch": 0.10245459584774898,
      "grad_norm": 0.212712824344635,
      "learning_rate": 0.003,
      "loss": 3.221396179199219,
      "step": 46900
    },
    {
      "epoch": 0.10267304914379961,
      "grad_norm": 0.1592969000339508,
      "learning_rate": 0.003,
      "loss": 3.334166259765625,
      "step": 47000
    },
    {
      "epoch": 0.10289150243985025,
      "grad_norm": 0.14095208048820496,
      "learning_rate": 0.003,
      "loss": 3.24810791015625,
      "step": 47100
    },
    {
      "epoch": 0.10310995573590089,
      "grad_norm": 0.36896562576293945,
      "learning_rate": 0.003,
      "loss": 3.1982489013671875,
      "step": 47200
    },
    {
      "epoch": 0.10332840903195152,
      "grad_norm": 0.15950943529605865,
      "learning_rate": 0.003,
      "loss": 3.309072265625,
      "step": 47300
    },
    {
      "epoch": 0.10354686232800216,
      "grad_norm": 0.15521414577960968,
      "learning_rate": 0.003,
      "loss": 3.28739501953125,
      "step": 47400
    },
    {
      "epoch": 0.1037653156240528,
      "grad_norm": 0.16319608688354492,
      "learning_rate": 0.003,
      "loss": 3.276689147949219,
      "step": 47500
    },
    {
      "epoch": 0.10398376892010344,
      "grad_norm": 0.18697327375411987,
      "learning_rate": 0.003,
      "loss": 3.27238037109375,
      "step": 47600
    },
    {
      "epoch": 0.10420222221615408,
      "grad_norm": 0.1398412436246872,
      "learning_rate": 0.003,
      "loss": 3.27921142578125,
      "step": 47700
    },
    {
      "epoch": 0.10442067551220471,
      "grad_norm": 0.14358995854854584,
      "learning_rate": 0.003,
      "loss": 3.2454815673828126,
      "step": 47800
    },
    {
      "epoch": 0.10463912880825535,
      "grad_norm": 0.16363677382469177,
      "learning_rate": 0.003,
      "loss": 3.2582858276367186,
      "step": 47900
    },
    {
      "epoch": 0.10485758210430599,
      "grad_norm": 0.17675544321537018,
      "learning_rate": 0.003,
      "loss": 3.2601687622070314,
      "step": 48000
    },
    {
      "epoch": 0.10507603540035662,
      "grad_norm": 0.18376107513904572,
      "learning_rate": 0.003,
      "loss": 3.235495910644531,
      "step": 48100
    },
    {
      "epoch": 0.10529448869640726,
      "grad_norm": 0.21416816115379333,
      "learning_rate": 0.003,
      "loss": 3.249112243652344,
      "step": 48200
    },
    {
      "epoch": 0.1055129419924579,
      "grad_norm": 0.16644176840782166,
      "learning_rate": 0.003,
      "loss": 3.288675537109375,
      "step": 48300
    },
    {
      "epoch": 0.10573139528850854,
      "grad_norm": 0.18745599687099457,
      "learning_rate": 0.003,
      "loss": 3.2637869262695314,
      "step": 48400
    },
    {
      "epoch": 0.10594984858455918,
      "grad_norm": 0.1422777622938156,
      "learning_rate": 0.003,
      "loss": 3.301553039550781,
      "step": 48500
    },
    {
      "epoch": 0.10616830188060981,
      "grad_norm": 0.18905463814735413,
      "learning_rate": 0.003,
      "loss": 3.28099365234375,
      "step": 48600
    },
    {
      "epoch": 0.10638675517666045,
      "grad_norm": 0.16725865006446838,
      "learning_rate": 0.003,
      "loss": 3.289917297363281,
      "step": 48700
    },
    {
      "epoch": 0.10660520847271109,
      "grad_norm": 0.12857334315776825,
      "learning_rate": 0.003,
      "loss": 3.2987991333007813,
      "step": 48800
    },
    {
      "epoch": 0.10682366176876172,
      "grad_norm": 0.16122519969940186,
      "learning_rate": 0.003,
      "loss": 3.680093078613281,
      "step": 48900
    },
    {
      "epoch": 0.10704211506481236,
      "grad_norm": 0.14388087391853333,
      "learning_rate": 0.003,
      "loss": 3.25523681640625,
      "step": 49000
    },
    {
      "epoch": 0.10726056836086299,
      "grad_norm": 0.16668033599853516,
      "learning_rate": 0.003,
      "loss": 3.2422891235351563,
      "step": 49100
    },
    {
      "epoch": 0.10747902165691364,
      "grad_norm": 0.13040824234485626,
      "learning_rate": 0.003,
      "loss": 3.296384582519531,
      "step": 49200
    },
    {
      "epoch": 0.10769747495296428,
      "grad_norm": 0.13599610328674316,
      "learning_rate": 0.003,
      "loss": 3.2640185546875,
      "step": 49300
    },
    {
      "epoch": 0.10791592824901491,
      "grad_norm": 0.13898426294326782,
      "learning_rate": 0.003,
      "loss": 3.2328057861328126,
      "step": 49400
    },
    {
      "epoch": 0.10813438154506555,
      "grad_norm": 0.14450238645076752,
      "learning_rate": 0.003,
      "loss": 3.2923873901367187,
      "step": 49500
    },
    {
      "epoch": 0.10835283484111619,
      "grad_norm": 0.14214539527893066,
      "learning_rate": 0.003,
      "loss": 3.273054504394531,
      "step": 49600
    },
    {
      "epoch": 0.10857128813716682,
      "grad_norm": 0.15325883030891418,
      "learning_rate": 0.003,
      "loss": 3.2763714599609375,
      "step": 49700
    },
    {
      "epoch": 0.10878974143321746,
      "grad_norm": 0.13748377561569214,
      "learning_rate": 0.003,
      "loss": 3.2571786499023436,
      "step": 49800
    },
    {
      "epoch": 0.10900819472926809,
      "grad_norm": 0.13714741170406342,
      "learning_rate": 0.003,
      "loss": 3.261249694824219,
      "step": 49900
    },
    {
      "epoch": 0.10922664802531874,
      "grad_norm": 0.19914014637470245,
      "learning_rate": 0.003,
      "loss": 3.2609954833984376,
      "step": 50000
    },
    {
      "epoch": 0.10944510132136938,
      "grad_norm": 0.13507208228111267,
      "learning_rate": 0.003,
      "loss": 3.2500015258789063,
      "step": 50100
    },
    {
      "epoch": 0.10966355461742001,
      "grad_norm": 0.15143956243991852,
      "learning_rate": 0.003,
      "loss": 3.23558837890625,
      "step": 50200
    },
    {
      "epoch": 0.10988200791347065,
      "grad_norm": 0.13524244725704193,
      "learning_rate": 0.003,
      "loss": 3.29155029296875,
      "step": 50300
    },
    {
      "epoch": 0.11010046120952129,
      "grad_norm": 0.13512593507766724,
      "learning_rate": 0.003,
      "loss": 3.2667276000976564,
      "step": 50400
    },
    {
      "epoch": 0.11031891450557192,
      "grad_norm": 0.20589660108089447,
      "learning_rate": 0.003,
      "loss": 3.205666198730469,
      "step": 50500
    },
    {
      "epoch": 0.11053736780162256,
      "grad_norm": 0.1325950175523758,
      "learning_rate": 0.003,
      "loss": 3.280411682128906,
      "step": 50600
    },
    {
      "epoch": 0.1107558210976732,
      "grad_norm": 0.20077379047870636,
      "learning_rate": 0.003,
      "loss": 3.2634320068359375,
      "step": 50700
    },
    {
      "epoch": 0.11097427439372384,
      "grad_norm": 0.13376857340335846,
      "learning_rate": 0.003,
      "loss": 3.2247994995117186,
      "step": 50800
    },
    {
      "epoch": 0.11119272768977448,
      "grad_norm": 0.12860968708992004,
      "learning_rate": 0.003,
      "loss": 3.2442669677734375,
      "step": 50900
    },
    {
      "epoch": 0.11141118098582511,
      "grad_norm": 0.20679087936878204,
      "learning_rate": 0.003,
      "loss": 3.266549072265625,
      "step": 51000
    },
    {
      "epoch": 0.11162963428187575,
      "grad_norm": 0.15940430760383606,
      "learning_rate": 0.003,
      "loss": 3.2117828369140624,
      "step": 51100
    },
    {
      "epoch": 0.11184808757792639,
      "grad_norm": 0.4413966238498688,
      "learning_rate": 0.003,
      "loss": 3.2566973876953127,
      "step": 51200
    },
    {
      "epoch": 0.11206654087397702,
      "grad_norm": 0.13706789910793304,
      "learning_rate": 0.003,
      "loss": 3.225574645996094,
      "step": 51300
    },
    {
      "epoch": 0.11228499417002766,
      "grad_norm": 0.16600839793682098,
      "learning_rate": 0.003,
      "loss": 3.226170654296875,
      "step": 51400
    },
    {
      "epoch": 0.1125034474660783,
      "grad_norm": 0.1571975201368332,
      "learning_rate": 0.003,
      "loss": 3.243815612792969,
      "step": 51500
    },
    {
      "epoch": 0.11272190076212894,
      "grad_norm": 0.15486016869544983,
      "learning_rate": 0.003,
      "loss": 3.2734530639648436,
      "step": 51600
    },
    {
      "epoch": 0.11294035405817958,
      "grad_norm": 0.248945951461792,
      "learning_rate": 0.003,
      "loss": 3.2460952758789063,
      "step": 51700
    },
    {
      "epoch": 0.11315880735423021,
      "grad_norm": 0.3302399814128876,
      "learning_rate": 0.003,
      "loss": 3.2613720703125,
      "step": 51800
    },
    {
      "epoch": 0.11337726065028085,
      "grad_norm": 0.13467846810817719,
      "learning_rate": 0.003,
      "loss": 3.2903326416015624,
      "step": 51900
    },
    {
      "epoch": 0.11359571394633149,
      "grad_norm": 0.16056181490421295,
      "learning_rate": 0.003,
      "loss": 3.26580810546875,
      "step": 52000
    },
    {
      "epoch": 0.11381416724238212,
      "grad_norm": 0.246822327375412,
      "learning_rate": 0.003,
      "loss": 3.2113882446289064,
      "step": 52100
    },
    {
      "epoch": 0.11403262053843276,
      "grad_norm": 0.147608682513237,
      "learning_rate": 0.003,
      "loss": 3.24245849609375,
      "step": 52200
    },
    {
      "epoch": 0.1142510738344834,
      "grad_norm": 0.23047684133052826,
      "learning_rate": 0.003,
      "loss": 3.2903311157226565,
      "step": 52300
    },
    {
      "epoch": 0.11446952713053403,
      "grad_norm": 0.2878482937812805,
      "learning_rate": 0.003,
      "loss": 3.236291809082031,
      "step": 52400
    },
    {
      "epoch": 0.11468798042658468,
      "grad_norm": 0.2174333930015564,
      "learning_rate": 0.003,
      "loss": 3.265153503417969,
      "step": 52500
    },
    {
      "epoch": 0.11490643372263531,
      "grad_norm": 0.12833909690380096,
      "learning_rate": 0.003,
      "loss": 3.2255078125,
      "step": 52600
    },
    {
      "epoch": 0.11512488701868595,
      "grad_norm": 0.14357781410217285,
      "learning_rate": 0.003,
      "loss": 3.230517578125,
      "step": 52700
    },
    {
      "epoch": 0.11534334031473659,
      "grad_norm": 0.15023696422576904,
      "learning_rate": 0.003,
      "loss": 3.2729867553710936,
      "step": 52800
    },
    {
      "epoch": 0.11556179361078722,
      "grad_norm": 0.15742431581020355,
      "learning_rate": 0.003,
      "loss": 3.247342224121094,
      "step": 52900
    },
    {
      "epoch": 0.11578024690683786,
      "grad_norm": 0.20336998999118805,
      "learning_rate": 0.003,
      "loss": 3.2814089965820314,
      "step": 53000
    },
    {
      "epoch": 0.1159987002028885,
      "grad_norm": 3.120046377182007,
      "learning_rate": 0.003,
      "loss": 3.1381329345703124,
      "step": 53100
    },
    {
      "epoch": 0.11621715349893913,
      "grad_norm": 0.15897803008556366,
      "learning_rate": 0.003,
      "loss": 3.2455206298828125,
      "step": 53200
    },
    {
      "epoch": 0.11643560679498978,
      "grad_norm": 0.13831640779972076,
      "learning_rate": 0.003,
      "loss": 3.26222900390625,
      "step": 53300
    },
    {
      "epoch": 0.11665406009104042,
      "grad_norm": 0.15329770743846893,
      "learning_rate": 0.003,
      "loss": 3.2434573364257813,
      "step": 53400
    },
    {
      "epoch": 0.11687251338709105,
      "grad_norm": 0.14566101133823395,
      "learning_rate": 0.003,
      "loss": 3.251831359863281,
      "step": 53500
    },
    {
      "epoch": 0.11709096668314169,
      "grad_norm": 0.15514326095581055,
      "learning_rate": 0.003,
      "loss": 3.231817321777344,
      "step": 53600
    },
    {
      "epoch": 0.11730941997919232,
      "grad_norm": 0.17874790728092194,
      "learning_rate": 0.003,
      "loss": 3.2658575439453124,
      "step": 53700
    },
    {
      "epoch": 0.11752787327524296,
      "grad_norm": 0.14967915415763855,
      "learning_rate": 0.003,
      "loss": 3.265608825683594,
      "step": 53800
    },
    {
      "epoch": 0.1177463265712936,
      "grad_norm": 0.17889386415481567,
      "learning_rate": 0.003,
      "loss": 3.2492279052734374,
      "step": 53900
    },
    {
      "epoch": 0.11796477986734423,
      "grad_norm": 0.18566641211509705,
      "learning_rate": 0.003,
      "loss": 3.2798150634765624,
      "step": 54000
    },
    {
      "epoch": 0.11818323316339488,
      "grad_norm": 0.13417650759220123,
      "learning_rate": 0.003,
      "loss": 3.296250915527344,
      "step": 54100
    },
    {
      "epoch": 0.11840168645944552,
      "grad_norm": 0.2071797102689743,
      "learning_rate": 0.003,
      "loss": 3.2186236572265625,
      "step": 54200
    },
    {
      "epoch": 0.11862013975549615,
      "grad_norm": 0.16677580773830414,
      "learning_rate": 0.003,
      "loss": 3.251484680175781,
      "step": 54300
    },
    {
      "epoch": 0.11883859305154679,
      "grad_norm": 0.14466318488121033,
      "learning_rate": 0.003,
      "loss": 3.2654324340820313,
      "step": 54400
    },
    {
      "epoch": 0.11905704634759742,
      "grad_norm": 0.1548251360654831,
      "learning_rate": 0.003,
      "loss": 3.2652987670898437,
      "step": 54500
    },
    {
      "epoch": 0.11927549964364806,
      "grad_norm": 0.15050005912780762,
      "learning_rate": 0.003,
      "loss": 3.251531982421875,
      "step": 54600
    },
    {
      "epoch": 0.1194939529396987,
      "grad_norm": 0.15156231820583344,
      "learning_rate": 0.003,
      "loss": 3.2532913208007814,
      "step": 54700
    },
    {
      "epoch": 0.11971240623574933,
      "grad_norm": 0.12596410512924194,
      "learning_rate": 0.003,
      "loss": 3.250552978515625,
      "step": 54800
    },
    {
      "epoch": 0.11993085953179998,
      "grad_norm": 0.15314988791942596,
      "learning_rate": 0.003,
      "loss": 3.24099609375,
      "step": 54900
    },
    {
      "epoch": 0.12014931282785062,
      "grad_norm": 0.14577282965183258,
      "learning_rate": 0.003,
      "loss": 3.2654632568359374,
      "step": 55000
    },
    {
      "epoch": 0.12036776612390125,
      "grad_norm": 0.1495250016450882,
      "learning_rate": 0.003,
      "loss": 3.22568603515625,
      "step": 55100
    },
    {
      "epoch": 0.12058621941995189,
      "grad_norm": 0.3873007595539093,
      "learning_rate": 0.003,
      "loss": 3.2341241455078125,
      "step": 55200
    },
    {
      "epoch": 0.12080467271600252,
      "grad_norm": 0.18277539312839508,
      "learning_rate": 0.003,
      "loss": 3.24637939453125,
      "step": 55300
    },
    {
      "epoch": 0.12102312601205316,
      "grad_norm": 0.16159602999687195,
      "learning_rate": 0.003,
      "loss": 3.26673828125,
      "step": 55400
    },
    {
      "epoch": 0.1212415793081038,
      "grad_norm": 0.13732564449310303,
      "learning_rate": 0.003,
      "loss": 3.2615036010742187,
      "step": 55500
    },
    {
      "epoch": 0.12146003260415443,
      "grad_norm": 0.16723576188087463,
      "learning_rate": 0.003,
      "loss": 3.2518795776367186,
      "step": 55600
    },
    {
      "epoch": 0.12167848590020507,
      "grad_norm": 0.1542261242866516,
      "learning_rate": 0.003,
      "loss": 3.255987548828125,
      "step": 55700
    },
    {
      "epoch": 0.12189693919625572,
      "grad_norm": 0.6683785319328308,
      "learning_rate": 0.003,
      "loss": 3.085527038574219,
      "step": 55800
    },
    {
      "epoch": 0.12211539249230635,
      "grad_norm": 0.16766637563705444,
      "learning_rate": 0.003,
      "loss": 2.9290505981445314,
      "step": 55900
    },
    {
      "epoch": 0.12233384578835699,
      "grad_norm": 0.15246568620204926,
      "learning_rate": 0.003,
      "loss": 3.2697900390625,
      "step": 56000
    },
    {
      "epoch": 0.12255229908440762,
      "grad_norm": 0.16947342455387115,
      "learning_rate": 0.003,
      "loss": 3.2785888671875,
      "step": 56100
    },
    {
      "epoch": 0.12277075238045826,
      "grad_norm": 0.14360709488391876,
      "learning_rate": 0.003,
      "loss": 3.2266140747070313,
      "step": 56200
    },
    {
      "epoch": 0.1229892056765089,
      "grad_norm": 0.18063582479953766,
      "learning_rate": 0.003,
      "loss": 3.2501126098632813,
      "step": 56300
    },
    {
      "epoch": 0.12320765897255953,
      "grad_norm": 0.20421698689460754,
      "learning_rate": 0.003,
      "loss": 3.2473678588867188,
      "step": 56400
    },
    {
      "epoch": 0.12342611226861017,
      "grad_norm": 0.13375893235206604,
      "learning_rate": 0.003,
      "loss": 3.2326312255859375,
      "step": 56500
    },
    {
      "epoch": 0.12364456556466082,
      "grad_norm": 0.14049290120601654,
      "learning_rate": 0.003,
      "loss": 3.2795941162109377,
      "step": 56600
    },
    {
      "epoch": 0.12386301886071145,
      "grad_norm": 0.1345169097185135,
      "learning_rate": 0.003,
      "loss": 3.2540447998046873,
      "step": 56700
    },
    {
      "epoch": 0.12408147215676209,
      "grad_norm": 0.17882542312145233,
      "learning_rate": 0.003,
      "loss": 3.2614974975585938,
      "step": 56800
    },
    {
      "epoch": 0.12429992545281272,
      "grad_norm": 0.14673982560634613,
      "learning_rate": 0.003,
      "loss": 3.2368304443359377,
      "step": 56900
    },
    {
      "epoch": 0.12451837874886336,
      "grad_norm": 0.15210740268230438,
      "learning_rate": 0.003,
      "loss": 3.2766180419921875,
      "step": 57000
    },
    {
      "epoch": 0.124736832044914,
      "grad_norm": 0.2170865833759308,
      "learning_rate": 0.003,
      "loss": 3.2546124267578125,
      "step": 57100
    },
    {
      "epoch": 0.12495528534096463,
      "grad_norm": 0.16334885358810425,
      "learning_rate": 0.003,
      "loss": 3.27398193359375,
      "step": 57200
    },
    {
      "epoch": 0.12517373863701528,
      "grad_norm": 0.19520652294158936,
      "learning_rate": 0.003,
      "loss": 3.2867977905273436,
      "step": 57300
    },
    {
      "epoch": 0.12539219193306592,
      "grad_norm": 0.1792980581521988,
      "learning_rate": 0.003,
      "loss": 3.25091552734375,
      "step": 57400
    },
    {
      "epoch": 0.12561064522911655,
      "grad_norm": 0.14307785034179688,
      "learning_rate": 0.003,
      "loss": 3.260938720703125,
      "step": 57500
    },
    {
      "epoch": 0.1258290985251672,
      "grad_norm": 0.1585034430027008,
      "learning_rate": 0.003,
      "loss": 3.2435162353515623,
      "step": 57600
    },
    {
      "epoch": 0.12604755182121782,
      "grad_norm": 0.22285203635692596,
      "learning_rate": 0.003,
      "loss": 3.2605624389648438,
      "step": 57700
    },
    {
      "epoch": 0.12626600511726846,
      "grad_norm": 0.16076688468456268,
      "learning_rate": 0.003,
      "loss": 3.247212219238281,
      "step": 57800
    },
    {
      "epoch": 0.1264844584133191,
      "grad_norm": 0.21419702470302582,
      "learning_rate": 0.003,
      "loss": 3.258780212402344,
      "step": 57900
    },
    {
      "epoch": 0.12670291170936973,
      "grad_norm": 0.129261776804924,
      "learning_rate": 0.003,
      "loss": 3.2596731567382813,
      "step": 58000
    },
    {
      "epoch": 0.12692136500542037,
      "grad_norm": 0.13298629224300385,
      "learning_rate": 0.003,
      "loss": 3.2442742919921876,
      "step": 58100
    },
    {
      "epoch": 0.127139818301471,
      "grad_norm": 0.1973569393157959,
      "learning_rate": 0.003,
      "loss": 3.2628631591796875,
      "step": 58200
    },
    {
      "epoch": 0.12735827159752164,
      "grad_norm": 0.14654108881950378,
      "learning_rate": 0.003,
      "loss": 3.2398953247070312,
      "step": 58300
    },
    {
      "epoch": 0.12757672489357227,
      "grad_norm": 0.17198579013347626,
      "learning_rate": 0.003,
      "loss": 3.226218566894531,
      "step": 58400
    },
    {
      "epoch": 0.1277951781896229,
      "grad_norm": 0.13534477353096008,
      "learning_rate": 0.003,
      "loss": 3.2574343872070313,
      "step": 58500
    },
    {
      "epoch": 0.12801363148567357,
      "grad_norm": 0.1584809124469757,
      "learning_rate": 0.003,
      "loss": 3.2984182739257815,
      "step": 58600
    },
    {
      "epoch": 0.1282320847817242,
      "grad_norm": 0.173396497964859,
      "learning_rate": 0.003,
      "loss": 3.260642395019531,
      "step": 58700
    },
    {
      "epoch": 0.12845053807777485,
      "grad_norm": 0.15514875948429108,
      "learning_rate": 0.003,
      "loss": 3.234716796875,
      "step": 58800
    },
    {
      "epoch": 0.12866899137382548,
      "grad_norm": 0.14235849678516388,
      "learning_rate": 0.003,
      "loss": 3.2418527221679687,
      "step": 58900
    },
    {
      "epoch": 0.12888744466987612,
      "grad_norm": 0.16027233004570007,
      "learning_rate": 0.003,
      "loss": 3.2690643310546874,
      "step": 59000
    },
    {
      "epoch": 0.12910589796592675,
      "grad_norm": 0.14568781852722168,
      "learning_rate": 0.003,
      "loss": 3.2454473876953127,
      "step": 59100
    },
    {
      "epoch": 0.1293243512619774,
      "grad_norm": 0.20608089864253998,
      "learning_rate": 0.003,
      "loss": 3.217125244140625,
      "step": 59200
    },
    {
      "epoch": 0.12954280455802802,
      "grad_norm": 0.1591549515724182,
      "learning_rate": 0.003,
      "loss": 3.2709585571289064,
      "step": 59300
    },
    {
      "epoch": 0.12976125785407866,
      "grad_norm": 0.134972482919693,
      "learning_rate": 0.003,
      "loss": 3.28088623046875,
      "step": 59400
    },
    {
      "epoch": 0.1299797111501293,
      "grad_norm": 0.15492945909500122,
      "learning_rate": 0.003,
      "loss": 3.2515249633789063,
      "step": 59500
    },
    {
      "epoch": 0.13019816444617993,
      "grad_norm": 0.1633273810148239,
      "learning_rate": 0.003,
      "loss": 3.2070086669921873,
      "step": 59600
    },
    {
      "epoch": 0.13041661774223057,
      "grad_norm": 0.14716912806034088,
      "learning_rate": 0.003,
      "loss": 3.2317816162109376,
      "step": 59700
    },
    {
      "epoch": 0.1306350710382812,
      "grad_norm": 0.16085785627365112,
      "learning_rate": 0.003,
      "loss": 3.25274658203125,
      "step": 59800
    },
    {
      "epoch": 0.13085352433433184,
      "grad_norm": 0.16605177521705627,
      "learning_rate": 0.003,
      "loss": 3.263970947265625,
      "step": 59900
    },
    {
      "epoch": 0.13107197763038247,
      "grad_norm": 0.16785955429077148,
      "learning_rate": 0.003,
      "loss": 3.22025634765625,
      "step": 60000
    },
    {
      "epoch": 0.1312904309264331,
      "grad_norm": 0.1412438452243805,
      "learning_rate": 0.003,
      "loss": 3.220314636230469,
      "step": 60100
    },
    {
      "epoch": 0.13150888422248375,
      "grad_norm": 0.21565914154052734,
      "learning_rate": 0.003,
      "loss": 3.229644775390625,
      "step": 60200
    },
    {
      "epoch": 0.1317273375185344,
      "grad_norm": 0.19567877054214478,
      "learning_rate": 0.003,
      "loss": 3.249039306640625,
      "step": 60300
    },
    {
      "epoch": 0.13194579081458505,
      "grad_norm": 0.17464599013328552,
      "learning_rate": 0.003,
      "loss": 3.2618002319335937,
      "step": 60400
    },
    {
      "epoch": 0.13216424411063568,
      "grad_norm": 0.1627679020166397,
      "learning_rate": 0.003,
      "loss": 3.180228576660156,
      "step": 60500
    },
    {
      "epoch": 0.13238269740668632,
      "grad_norm": 0.18486280739307404,
      "learning_rate": 0.003,
      "loss": 3.2228204345703126,
      "step": 60600
    },
    {
      "epoch": 0.13260115070273695,
      "grad_norm": 0.22529979050159454,
      "learning_rate": 0.003,
      "loss": 3.2560736083984376,
      "step": 60700
    },
    {
      "epoch": 0.1328196039987876,
      "grad_norm": 0.19143950939178467,
      "learning_rate": 0.003,
      "loss": 3.2156741333007814,
      "step": 60800
    },
    {
      "epoch": 0.13303805729483822,
      "grad_norm": 0.1540822684764862,
      "learning_rate": 0.003,
      "loss": 3.1913638305664063,
      "step": 60900
    },
    {
      "epoch": 0.13325651059088886,
      "grad_norm": 0.13871780037879944,
      "learning_rate": 0.003,
      "loss": 3.2044723510742186,
      "step": 61000
    },
    {
      "epoch": 0.1334749638869395,
      "grad_norm": 0.14368896186351776,
      "learning_rate": 0.003,
      "loss": 3.2619207763671874,
      "step": 61100
    },
    {
      "epoch": 0.13369341718299013,
      "grad_norm": 0.16204333305358887,
      "learning_rate": 0.003,
      "loss": 3.2338299560546875,
      "step": 61200
    },
    {
      "epoch": 0.13391187047904077,
      "grad_norm": 0.13743866980075836,
      "learning_rate": 0.003,
      "loss": 3.2367453002929687,
      "step": 61300
    },
    {
      "epoch": 0.1341303237750914,
      "grad_norm": 0.14885108172893524,
      "learning_rate": 0.003,
      "loss": 3.2349374389648435,
      "step": 61400
    },
    {
      "epoch": 0.13434877707114204,
      "grad_norm": 0.17403972148895264,
      "learning_rate": 0.003,
      "loss": 3.24302734375,
      "step": 61500
    },
    {
      "epoch": 0.13456723036719268,
      "grad_norm": 0.15033158659934998,
      "learning_rate": 0.003,
      "loss": 3.263538818359375,
      "step": 61600
    },
    {
      "epoch": 0.1347856836632433,
      "grad_norm": 0.21722860634326935,
      "learning_rate": 0.003,
      "loss": 3.2349429321289063,
      "step": 61700
    },
    {
      "epoch": 0.13500413695929395,
      "grad_norm": 0.1466379314661026,
      "learning_rate": 0.003,
      "loss": 3.219266052246094,
      "step": 61800
    },
    {
      "epoch": 0.1352225902553446,
      "grad_norm": 0.13940411806106567,
      "learning_rate": 0.003,
      "loss": 3.2392041015625,
      "step": 61900
    },
    {
      "epoch": 0.13544104355139525,
      "grad_norm": 0.13754943013191223,
      "learning_rate": 0.003,
      "loss": 3.252232971191406,
      "step": 62000
    },
    {
      "epoch": 0.13565949684744588,
      "grad_norm": 0.32490044832229614,
      "learning_rate": 0.003,
      "loss": 3.234407653808594,
      "step": 62100
    },
    {
      "epoch": 0.13587795014349652,
      "grad_norm": 0.14267276227474213,
      "learning_rate": 0.003,
      "loss": 3.218851318359375,
      "step": 62200
    },
    {
      "epoch": 0.13609640343954715,
      "grad_norm": 0.21616226434707642,
      "learning_rate": 0.003,
      "loss": 3.2713690185546875,
      "step": 62300
    },
    {
      "epoch": 0.1363148567355978,
      "grad_norm": 0.1464727371931076,
      "learning_rate": 0.003,
      "loss": 3.24201416015625,
      "step": 62400
    },
    {
      "epoch": 0.13653331003164842,
      "grad_norm": 0.5176395177841187,
      "learning_rate": 0.003,
      "loss": 3.2492108154296875,
      "step": 62500
    },
    {
      "epoch": 0.13675176332769906,
      "grad_norm": 0.1350073516368866,
      "learning_rate": 0.003,
      "loss": 3.2798583984375,
      "step": 62600
    },
    {
      "epoch": 0.1369702166237497,
      "grad_norm": 0.18025344610214233,
      "learning_rate": 0.003,
      "loss": 3.2309701538085935,
      "step": 62700
    },
    {
      "epoch": 0.13718866991980033,
      "grad_norm": 0.18821361660957336,
      "learning_rate": 0.003,
      "loss": 3.2689004516601563,
      "step": 62800
    },
    {
      "epoch": 0.13740712321585097,
      "grad_norm": 0.1663011610507965,
      "learning_rate": 0.003,
      "loss": 3.2441537475585935,
      "step": 62900
    },
    {
      "epoch": 0.1376255765119016,
      "grad_norm": 0.15948191285133362,
      "learning_rate": 0.003,
      "loss": 2.7289602661132815,
      "step": 63000
    },
    {
      "epoch": 0.13784402980795224,
      "grad_norm": 0.1529848873615265,
      "learning_rate": 0.003,
      "loss": 3.2516909790039064,
      "step": 63100
    },
    {
      "epoch": 0.13806248310400288,
      "grad_norm": 0.14751732349395752,
      "learning_rate": 0.003,
      "loss": 3.246956481933594,
      "step": 63200
    },
    {
      "epoch": 0.1382809364000535,
      "grad_norm": 0.1541360467672348,
      "learning_rate": 0.003,
      "loss": 3.2233453369140626,
      "step": 63300
    },
    {
      "epoch": 0.13849938969610415,
      "grad_norm": 0.17564933001995087,
      "learning_rate": 0.003,
      "loss": 3.2218228149414063,
      "step": 63400
    },
    {
      "epoch": 0.13871784299215478,
      "grad_norm": 0.14369294047355652,
      "learning_rate": 0.003,
      "loss": 3.3964053344726564,
      "step": 63500
    },
    {
      "epoch": 0.13893629628820545,
      "grad_norm": 0.14323627948760986,
      "learning_rate": 0.003,
      "loss": 3.249570617675781,
      "step": 63600
    },
    {
      "epoch": 0.13915474958425608,
      "grad_norm": 0.1641722321510315,
      "learning_rate": 0.003,
      "loss": 3.1940841674804688,
      "step": 63700
    },
    {
      "epoch": 0.13937320288030672,
      "grad_norm": 0.15655729174613953,
      "learning_rate": 0.003,
      "loss": 3.230262451171875,
      "step": 63800
    },
    {
      "epoch": 0.13959165617635735,
      "grad_norm": 0.23219190537929535,
      "learning_rate": 0.003,
      "loss": 3.260406494140625,
      "step": 63900
    },
    {
      "epoch": 0.139810109472408,
      "grad_norm": 0.15642347931861877,
      "learning_rate": 0.003,
      "loss": 3.266820068359375,
      "step": 64000
    },
    {
      "epoch": 0.14002856276845863,
      "grad_norm": 0.17600469291210175,
      "learning_rate": 0.003,
      "loss": 3.214679870605469,
      "step": 64100
    },
    {
      "epoch": 0.14024701606450926,
      "grad_norm": 0.1333693265914917,
      "learning_rate": 0.003,
      "loss": 3.217235107421875,
      "step": 64200
    },
    {
      "epoch": 0.1404654693605599,
      "grad_norm": 0.17207157611846924,
      "learning_rate": 0.003,
      "loss": 3.2215121459960936,
      "step": 64300
    },
    {
      "epoch": 0.14068392265661053,
      "grad_norm": 0.14259660243988037,
      "learning_rate": 0.003,
      "loss": 3.2310165405273437,
      "step": 64400
    },
    {
      "epoch": 0.14090237595266117,
      "grad_norm": 0.16601745784282684,
      "learning_rate": 0.003,
      "loss": 3.2018670654296875,
      "step": 64500
    },
    {
      "epoch": 0.1411208292487118,
      "grad_norm": 0.14996014535427094,
      "learning_rate": 0.003,
      "loss": 3.21740234375,
      "step": 64600
    },
    {
      "epoch": 0.14133928254476244,
      "grad_norm": 0.16059845685958862,
      "learning_rate": 0.003,
      "loss": 3.204219970703125,
      "step": 64700
    },
    {
      "epoch": 0.14155773584081308,
      "grad_norm": 0.18016761541366577,
      "learning_rate": 0.003,
      "loss": 3.195794982910156,
      "step": 64800
    },
    {
      "epoch": 0.1417761891368637,
      "grad_norm": 0.15482042729854584,
      "learning_rate": 0.003,
      "loss": 3.209017333984375,
      "step": 64900
    },
    {
      "epoch": 0.14199464243291435,
      "grad_norm": 0.19144226610660553,
      "learning_rate": 0.003,
      "loss": 3.210953674316406,
      "step": 65000
    },
    {
      "epoch": 0.14221309572896498,
      "grad_norm": 0.14203697443008423,
      "learning_rate": 0.003,
      "loss": 3.19835205078125,
      "step": 65100
    },
    {
      "epoch": 0.14243154902501565,
      "grad_norm": 0.4821944236755371,
      "learning_rate": 0.003,
      "loss": 3.25100341796875,
      "step": 65200
    },
    {
      "epoch": 0.14265000232106628,
      "grad_norm": 0.15543989837169647,
      "learning_rate": 0.003,
      "loss": 3.20369873046875,
      "step": 65300
    },
    {
      "epoch": 0.14286845561711692,
      "grad_norm": 0.1701357513666153,
      "learning_rate": 0.003,
      "loss": 3.169871520996094,
      "step": 65400
    },
    {
      "epoch": 0.14308690891316755,
      "grad_norm": 0.17308828234672546,
      "learning_rate": 0.003,
      "loss": 3.2284805297851564,
      "step": 65500
    },
    {
      "epoch": 0.1433053622092182,
      "grad_norm": 0.17479535937309265,
      "learning_rate": 0.003,
      "loss": 3.20006103515625,
      "step": 65600
    },
    {
      "epoch": 0.14352381550526883,
      "grad_norm": 0.14500826597213745,
      "learning_rate": 0.003,
      "loss": 3.2878839111328126,
      "step": 65700
    },
    {
      "epoch": 0.14374226880131946,
      "grad_norm": 0.1360345333814621,
      "learning_rate": 0.003,
      "loss": 3.29202880859375,
      "step": 65800
    },
    {
      "epoch": 0.1439607220973701,
      "grad_norm": 0.21259358525276184,
      "learning_rate": 0.003,
      "loss": 3.2273773193359374,
      "step": 65900
    },
    {
      "epoch": 0.14417917539342073,
      "grad_norm": 0.2542419731616974,
      "learning_rate": 0.003,
      "loss": 3.2165481567382814,
      "step": 66000
    },
    {
      "epoch": 0.14439762868947137,
      "grad_norm": 0.24819156527519226,
      "learning_rate": 0.003,
      "loss": 3.243924560546875,
      "step": 66100
    },
    {
      "epoch": 0.144616081985522,
      "grad_norm": 0.13760997354984283,
      "learning_rate": 0.003,
      "loss": 3.2319210815429686,
      "step": 66200
    },
    {
      "epoch": 0.14483453528157264,
      "grad_norm": 0.15245407819747925,
      "learning_rate": 0.003,
      "loss": 3.2334552001953125,
      "step": 66300
    },
    {
      "epoch": 0.14505298857762328,
      "grad_norm": 0.15227407217025757,
      "learning_rate": 0.003,
      "loss": 3.217420959472656,
      "step": 66400
    },
    {
      "epoch": 0.1452714418736739,
      "grad_norm": 0.14392466843128204,
      "learning_rate": 0.003,
      "loss": 3.2076754760742188,
      "step": 66500
    },
    {
      "epoch": 0.14548989516972455,
      "grad_norm": 0.21550512313842773,
      "learning_rate": 0.003,
      "loss": 3.266759338378906,
      "step": 66600
    },
    {
      "epoch": 0.14570834846577518,
      "grad_norm": 0.16961754858493805,
      "learning_rate": 0.003,
      "loss": 3.2540386962890624,
      "step": 66700
    },
    {
      "epoch": 0.14592680176182582,
      "grad_norm": 0.1846882551908493,
      "learning_rate": 0.003,
      "loss": 3.2260113525390626,
      "step": 66800
    },
    {
      "epoch": 0.14614525505787648,
      "grad_norm": 0.17954540252685547,
      "learning_rate": 0.003,
      "loss": 3.2294110107421874,
      "step": 66900
    },
    {
      "epoch": 0.14636370835392712,
      "grad_norm": 0.1706397533416748,
      "learning_rate": 0.003,
      "loss": 3.248121337890625,
      "step": 67000
    },
    {
      "epoch": 0.14658216164997775,
      "grad_norm": 0.17211204767227173,
      "learning_rate": 0.003,
      "loss": 3.2395590209960936,
      "step": 67100
    },
    {
      "epoch": 0.1468006149460284,
      "grad_norm": 0.21838849782943726,
      "learning_rate": 0.003,
      "loss": 3.241527099609375,
      "step": 67200
    },
    {
      "epoch": 0.14701906824207903,
      "grad_norm": 0.19266127049922943,
      "learning_rate": 0.003,
      "loss": 3.2631201171875,
      "step": 67300
    },
    {
      "epoch": 0.14723752153812966,
      "grad_norm": 0.15134894847869873,
      "learning_rate": 0.003,
      "loss": 3.2437713623046873,
      "step": 67400
    },
    {
      "epoch": 0.1474559748341803,
      "grad_norm": 0.34054991602897644,
      "learning_rate": 0.003,
      "loss": 3.2246142578125,
      "step": 67500
    },
    {
      "epoch": 0.14767442813023093,
      "grad_norm": 0.15797755122184753,
      "learning_rate": 0.003,
      "loss": 3.2434561157226565,
      "step": 67600
    },
    {
      "epoch": 0.14789288142628157,
      "grad_norm": 0.1528821587562561,
      "learning_rate": 0.003,
      "loss": 3.2275845336914064,
      "step": 67700
    },
    {
      "epoch": 0.1481113347223322,
      "grad_norm": 0.1330331712961197,
      "learning_rate": 0.003,
      "loss": 3.2324395751953126,
      "step": 67800
    },
    {
      "epoch": 0.14832978801838284,
      "grad_norm": 0.19141782820224762,
      "learning_rate": 0.003,
      "loss": 3.2720477294921877,
      "step": 67900
    },
    {
      "epoch": 0.14854824131443348,
      "grad_norm": 0.13883931934833527,
      "learning_rate": 0.003,
      "loss": 3.272904357910156,
      "step": 68000
    },
    {
      "epoch": 0.1487666946104841,
      "grad_norm": 0.14308680593967438,
      "learning_rate": 0.003,
      "loss": 3.227841491699219,
      "step": 68100
    },
    {
      "epoch": 0.14898514790653475,
      "grad_norm": 0.17235063016414642,
      "learning_rate": 0.003,
      "loss": 3.242052001953125,
      "step": 68200
    },
    {
      "epoch": 0.14920360120258538,
      "grad_norm": 0.17289380729198456,
      "learning_rate": 0.003,
      "loss": 3.2746286010742187,
      "step": 68300
    },
    {
      "epoch": 0.14942205449863602,
      "grad_norm": 0.14802849292755127,
      "learning_rate": 0.003,
      "loss": 3.194547424316406,
      "step": 68400
    },
    {
      "epoch": 0.14964050779468668,
      "grad_norm": 0.19775991141796112,
      "learning_rate": 0.003,
      "loss": 3.181102600097656,
      "step": 68500
    },
    {
      "epoch": 0.14985896109073732,
      "grad_norm": 0.13130341470241547,
      "learning_rate": 0.003,
      "loss": 2.723526611328125,
      "step": 68600
    },
    {
      "epoch": 0.15007741438678796,
      "grad_norm": 0.14095982909202576,
      "learning_rate": 0.003,
      "loss": 3.231905212402344,
      "step": 68700
    },
    {
      "epoch": 0.1502958676828386,
      "grad_norm": 0.14556872844696045,
      "learning_rate": 0.003,
      "loss": 3.2342495727539062,
      "step": 68800
    },
    {
      "epoch": 0.15051432097888923,
      "grad_norm": 0.14050233364105225,
      "learning_rate": 0.003,
      "loss": 3.2132330322265625,
      "step": 68900
    },
    {
      "epoch": 0.15073277427493986,
      "grad_norm": 0.1730201691389084,
      "learning_rate": 0.003,
      "loss": 3.2115792846679687,
      "step": 69000
    },
    {
      "epoch": 0.1509512275709905,
      "grad_norm": 0.20617027580738068,
      "learning_rate": 0.003,
      "loss": 3.2500860595703127,
      "step": 69100
    },
    {
      "epoch": 0.15116968086704113,
      "grad_norm": 0.1822213977575302,
      "learning_rate": 0.003,
      "loss": 3.236435852050781,
      "step": 69200
    },
    {
      "epoch": 0.15138813416309177,
      "grad_norm": 0.17483313381671906,
      "learning_rate": 0.003,
      "loss": 3.253581237792969,
      "step": 69300
    },
    {
      "epoch": 0.1516065874591424,
      "grad_norm": 0.15619760751724243,
      "learning_rate": 0.003,
      "loss": 3.196072692871094,
      "step": 69400
    },
    {
      "epoch": 0.15182504075519304,
      "grad_norm": 0.18323157727718353,
      "learning_rate": 0.003,
      "loss": 3.2476675415039065,
      "step": 69500
    },
    {
      "epoch": 0.15204349405124368,
      "grad_norm": 0.1582677662372589,
      "learning_rate": 0.003,
      "loss": 3.2430215454101563,
      "step": 69600
    },
    {
      "epoch": 0.1522619473472943,
      "grad_norm": 0.15574927628040314,
      "learning_rate": 0.003,
      "loss": 3.219065856933594,
      "step": 69700
    },
    {
      "epoch": 0.15248040064334495,
      "grad_norm": 0.13565471768379211,
      "learning_rate": 0.003,
      "loss": 3.2654583740234373,
      "step": 69800
    },
    {
      "epoch": 0.15269885393939558,
      "grad_norm": 0.1486131101846695,
      "learning_rate": 0.003,
      "loss": 3.2257269287109374,
      "step": 69900
    },
    {
      "epoch": 0.15291730723544622,
      "grad_norm": 0.16414867341518402,
      "learning_rate": 0.003,
      "loss": 3.227646484375,
      "step": 70000
    },
    {
      "epoch": 0.15313576053149686,
      "grad_norm": 0.17787083983421326,
      "learning_rate": 0.003,
      "loss": 3.1835894775390625,
      "step": 70100
    },
    {
      "epoch": 0.15335421382754752,
      "grad_norm": 0.14870117604732513,
      "learning_rate": 0.003,
      "loss": 3.2247634887695313,
      "step": 70200
    },
    {
      "epoch": 0.15357266712359816,
      "grad_norm": 0.14349189400672913,
      "learning_rate": 0.003,
      "loss": 3.171583251953125,
      "step": 70300
    },
    {
      "epoch": 0.1537911204196488,
      "grad_norm": 0.18492130935192108,
      "learning_rate": 0.003,
      "loss": 3.2198065185546874,
      "step": 70400
    },
    {
      "epoch": 0.15400957371569943,
      "grad_norm": 0.18474198877811432,
      "learning_rate": 0.003,
      "loss": 3.2141107177734374,
      "step": 70500
    },
    {
      "epoch": 0.15422802701175006,
      "grad_norm": 0.20480042695999146,
      "learning_rate": 0.003,
      "loss": 3.2477322387695313,
      "step": 70600
    },
    {
      "epoch": 0.1544464803078007,
      "grad_norm": 0.15379810333251953,
      "learning_rate": 0.003,
      "loss": 3.2210733032226564,
      "step": 70700
    },
    {
      "epoch": 0.15466493360385133,
      "grad_norm": 0.1564520001411438,
      "learning_rate": 0.003,
      "loss": 3.2100540161132813,
      "step": 70800
    },
    {
      "epoch": 0.15488338689990197,
      "grad_norm": 0.1851634830236435,
      "learning_rate": 0.003,
      "loss": 3.2196975708007813,
      "step": 70900
    },
    {
      "epoch": 0.1551018401959526,
      "grad_norm": 0.13629335165023804,
      "learning_rate": 0.003,
      "loss": 3.2184857177734374,
      "step": 71000
    },
    {
      "epoch": 0.15532029349200324,
      "grad_norm": 0.13462699949741364,
      "learning_rate": 0.003,
      "loss": 3.2634429931640625,
      "step": 71100
    },
    {
      "epoch": 0.15553874678805388,
      "grad_norm": 0.14812074601650238,
      "learning_rate": 0.003,
      "loss": 3.2562606811523436,
      "step": 71200
    },
    {
      "epoch": 0.1557572000841045,
      "grad_norm": 0.13378751277923584,
      "learning_rate": 0.003,
      "loss": 3.2482659912109373,
      "step": 71300
    },
    {
      "epoch": 0.15597565338015515,
      "grad_norm": 0.16416287422180176,
      "learning_rate": 0.003,
      "loss": 3.1697012329101564,
      "step": 71400
    },
    {
      "epoch": 0.15619410667620579,
      "grad_norm": 0.1352565735578537,
      "learning_rate": 0.003,
      "loss": 3.2339556884765623,
      "step": 71500
    },
    {
      "epoch": 0.15641255997225642,
      "grad_norm": 0.14081928133964539,
      "learning_rate": 0.003,
      "loss": 3.2458950805664064,
      "step": 71600
    },
    {
      "epoch": 0.15663101326830706,
      "grad_norm": 0.1376163810491562,
      "learning_rate": 0.003,
      "loss": 3.21879150390625,
      "step": 71700
    },
    {
      "epoch": 0.15684946656435772,
      "grad_norm": 0.16404809057712555,
      "learning_rate": 0.003,
      "loss": 3.261857604980469,
      "step": 71800
    },
    {
      "epoch": 0.15706791986040836,
      "grad_norm": 0.16098147630691528,
      "learning_rate": 0.003,
      "loss": 3.2662176513671874,
      "step": 71900
    },
    {
      "epoch": 0.157286373156459,
      "grad_norm": 0.19868750870227814,
      "learning_rate": 0.003,
      "loss": 3.25436767578125,
      "step": 72000
    },
    {
      "epoch": 0.15750482645250963,
      "grad_norm": 0.18838000297546387,
      "learning_rate": 0.003,
      "loss": 3.2456134033203123,
      "step": 72100
    },
    {
      "epoch": 0.15772327974856026,
      "grad_norm": 0.18162785470485687,
      "learning_rate": 0.003,
      "loss": 3.2529983520507812,
      "step": 72200
    },
    {
      "epoch": 0.1579417330446109,
      "grad_norm": 0.13635674118995667,
      "learning_rate": 0.003,
      "loss": 3.2445623779296877,
      "step": 72300
    },
    {
      "epoch": 0.15816018634066153,
      "grad_norm": 0.18136821687221527,
      "learning_rate": 0.003,
      "loss": 3.1944915771484377,
      "step": 72400
    },
    {
      "epoch": 0.15837863963671217,
      "grad_norm": 0.16928516328334808,
      "learning_rate": 0.003,
      "loss": 3.2309170532226563,
      "step": 72500
    },
    {
      "epoch": 0.1585970929327628,
      "grad_norm": 0.14556556940078735,
      "learning_rate": 0.003,
      "loss": 3.2353945922851564,
      "step": 72600
    },
    {
      "epoch": 0.15881554622881344,
      "grad_norm": 0.14194248616695404,
      "learning_rate": 0.003,
      "loss": 3.262231750488281,
      "step": 72700
    },
    {
      "epoch": 0.15903399952486408,
      "grad_norm": 0.15043506026268005,
      "learning_rate": 0.003,
      "loss": 3.2179226684570312,
      "step": 72800
    },
    {
      "epoch": 0.15925245282091471,
      "grad_norm": 0.18483737111091614,
      "learning_rate": 0.003,
      "loss": 3.2244232177734373,
      "step": 72900
    },
    {
      "epoch": 0.15947090611696535,
      "grad_norm": 0.17586249113082886,
      "learning_rate": 0.003,
      "loss": 3.1289639282226562,
      "step": 73000
    },
    {
      "epoch": 0.15968935941301599,
      "grad_norm": 0.17315636575222015,
      "learning_rate": 0.003,
      "loss": 3.230426940917969,
      "step": 73100
    },
    {
      "epoch": 0.15990781270906662,
      "grad_norm": 0.14286355674266815,
      "learning_rate": 0.003,
      "loss": 3.2417947387695314,
      "step": 73200
    },
    {
      "epoch": 0.16012626600511726,
      "grad_norm": 0.15196926891803741,
      "learning_rate": 0.003,
      "loss": 3.2354244995117187,
      "step": 73300
    },
    {
      "epoch": 0.1603447193011679,
      "grad_norm": 0.1744149625301361,
      "learning_rate": 0.003,
      "loss": 3.165083923339844,
      "step": 73400
    },
    {
      "epoch": 0.16056317259721856,
      "grad_norm": 0.15688399970531464,
      "learning_rate": 0.003,
      "loss": 3.21979736328125,
      "step": 73500
    },
    {
      "epoch": 0.1607816258932692,
      "grad_norm": 0.1604417860507965,
      "learning_rate": 0.003,
      "loss": 3.223596496582031,
      "step": 73600
    },
    {
      "epoch": 0.16100007918931983,
      "grad_norm": 0.14714471995830536,
      "learning_rate": 0.003,
      "loss": 3.2240216064453127,
      "step": 73700
    },
    {
      "epoch": 0.16121853248537046,
      "grad_norm": 0.18966136872768402,
      "learning_rate": 0.003,
      "loss": 3.197341003417969,
      "step": 73800
    },
    {
      "epoch": 0.1614369857814211,
      "grad_norm": 0.2152947634458542,
      "learning_rate": 0.003,
      "loss": 3.1614569091796874,
      "step": 73900
    },
    {
      "epoch": 0.16165543907747174,
      "grad_norm": 0.14745226502418518,
      "learning_rate": 0.003,
      "loss": 3.2265939331054687,
      "step": 74000
    },
    {
      "epoch": 0.16187389237352237,
      "grad_norm": 0.15095406770706177,
      "learning_rate": 0.003,
      "loss": 3.373876037597656,
      "step": 74100
    },
    {
      "epoch": 0.162092345669573,
      "grad_norm": 0.1664532572031021,
      "learning_rate": 0.003,
      "loss": 3.1829833984375,
      "step": 74200
    },
    {
      "epoch": 0.16231079896562364,
      "grad_norm": 0.14805693924427032,
      "learning_rate": 0.003,
      "loss": 3.207042236328125,
      "step": 74300
    },
    {
      "epoch": 0.16252925226167428,
      "grad_norm": 0.15347807109355927,
      "learning_rate": 0.003,
      "loss": 3.1845889282226563,
      "step": 74400
    },
    {
      "epoch": 0.16274770555772491,
      "grad_norm": 0.20546002686023712,
      "learning_rate": 0.003,
      "loss": 3.1983770751953124,
      "step": 74500
    },
    {
      "epoch": 0.16296615885377555,
      "grad_norm": 0.14666610956192017,
      "learning_rate": 0.003,
      "loss": 3.222270202636719,
      "step": 74600
    },
    {
      "epoch": 0.16318461214982619,
      "grad_norm": 0.15613286197185516,
      "learning_rate": 0.003,
      "loss": 3.2073956298828126,
      "step": 74700
    },
    {
      "epoch": 0.16340306544587682,
      "grad_norm": 0.16200363636016846,
      "learning_rate": 0.003,
      "loss": 3.2018893432617186,
      "step": 74800
    },
    {
      "epoch": 0.16362151874192746,
      "grad_norm": 0.1372697651386261,
      "learning_rate": 0.003,
      "loss": 3.2019302368164064,
      "step": 74900
    },
    {
      "epoch": 0.1638399720379781,
      "grad_norm": 0.1444454938173294,
      "learning_rate": 0.003,
      "loss": 3.189869079589844,
      "step": 75000
    },
    {
      "epoch": 0.16405842533402876,
      "grad_norm": 0.16384346783161163,
      "learning_rate": 0.003,
      "loss": 3.242828674316406,
      "step": 75100
    },
    {
      "epoch": 0.1642768786300794,
      "grad_norm": 0.22108645737171173,
      "learning_rate": 0.003,
      "loss": 3.203451843261719,
      "step": 75200
    },
    {
      "epoch": 0.16449533192613003,
      "grad_norm": 0.155759796500206,
      "learning_rate": 0.003,
      "loss": 3.1484210205078127,
      "step": 75300
    },
    {
      "epoch": 0.16471378522218066,
      "grad_norm": 0.1365097612142563,
      "learning_rate": 0.003,
      "loss": 3.177284851074219,
      "step": 75400
    },
    {
      "epoch": 0.1649322385182313,
      "grad_norm": 0.20308803021907806,
      "learning_rate": 0.003,
      "loss": 3.2935577392578126,
      "step": 75500
    },
    {
      "epoch": 0.16515069181428194,
      "grad_norm": 0.1627846658229828,
      "learning_rate": 0.003,
      "loss": 3.2038775634765626,
      "step": 75600
    },
    {
      "epoch": 0.16536914511033257,
      "grad_norm": 0.15723568201065063,
      "learning_rate": 0.003,
      "loss": 3.18799072265625,
      "step": 75700
    },
    {
      "epoch": 0.1655875984063832,
      "grad_norm": 0.14858828485012054,
      "learning_rate": 0.003,
      "loss": 3.2345623779296875,
      "step": 75800
    },
    {
      "epoch": 0.16580605170243384,
      "grad_norm": 0.16737258434295654,
      "learning_rate": 0.003,
      "loss": 3.1938626098632814,
      "step": 75900
    },
    {
      "epoch": 0.16602450499848448,
      "grad_norm": 0.15170836448669434,
      "learning_rate": 0.003,
      "loss": 3.2006201171875,
      "step": 76000
    },
    {
      "epoch": 0.16624295829453511,
      "grad_norm": 0.1959700584411621,
      "learning_rate": 0.003,
      "loss": 3.254922180175781,
      "step": 76100
    },
    {
      "epoch": 0.16646141159058575,
      "grad_norm": 0.15581128001213074,
      "learning_rate": 0.003,
      "loss": 3.1887762451171877,
      "step": 76200
    },
    {
      "epoch": 0.1666798648866364,
      "grad_norm": 0.14930440485477448,
      "learning_rate": 0.003,
      "loss": 3.2389352416992185,
      "step": 76300
    },
    {
      "epoch": 0.16689831818268702,
      "grad_norm": 0.2020094394683838,
      "learning_rate": 0.003,
      "loss": 3.2333514404296877,
      "step": 76400
    },
    {
      "epoch": 0.16711677147873766,
      "grad_norm": 0.1374303102493286,
      "learning_rate": 0.003,
      "loss": 3.2222906494140626,
      "step": 76500
    },
    {
      "epoch": 0.1673352247747883,
      "grad_norm": 0.15284472703933716,
      "learning_rate": 0.003,
      "loss": 3.2347198486328126,
      "step": 76600
    },
    {
      "epoch": 0.16755367807083893,
      "grad_norm": 0.23065847158432007,
      "learning_rate": 0.003,
      "loss": 3.2416390991210937,
      "step": 76700
    },
    {
      "epoch": 0.1677721313668896,
      "grad_norm": 0.15649299323558807,
      "learning_rate": 0.003,
      "loss": 3.2050161743164063,
      "step": 76800
    },
    {
      "epoch": 0.16799058466294023,
      "grad_norm": 0.14923731982707977,
      "learning_rate": 0.003,
      "loss": 3.2096380615234374,
      "step": 76900
    },
    {
      "epoch": 0.16820903795899086,
      "grad_norm": 0.15309712290763855,
      "learning_rate": 0.003,
      "loss": 3.327672424316406,
      "step": 77000
    },
    {
      "epoch": 0.1684274912550415,
      "grad_norm": 0.1624584048986435,
      "learning_rate": 0.003,
      "loss": 3.0921026611328126,
      "step": 77100
    },
    {
      "epoch": 0.16864594455109214,
      "grad_norm": 0.15112026035785675,
      "learning_rate": 0.003,
      "loss": 3.2112442016601563,
      "step": 77200
    },
    {
      "epoch": 0.16886439784714277,
      "grad_norm": 0.2171279788017273,
      "learning_rate": 0.003,
      "loss": 3.2253741455078124,
      "step": 77300
    },
    {
      "epoch": 0.1690828511431934,
      "grad_norm": 0.14117172360420227,
      "learning_rate": 0.003,
      "loss": 3.26427001953125,
      "step": 77400
    },
    {
      "epoch": 0.16930130443924404,
      "grad_norm": 0.20454275608062744,
      "learning_rate": 0.003,
      "loss": 3.2036868286132814,
      "step": 77500
    },
    {
      "epoch": 0.16951975773529468,
      "grad_norm": 0.15810075402259827,
      "learning_rate": 0.003,
      "loss": 3.2048870849609377,
      "step": 77600
    },
    {
      "epoch": 0.16973821103134532,
      "grad_norm": 0.14809603989124298,
      "learning_rate": 0.003,
      "loss": 3.239774475097656,
      "step": 77700
    },
    {
      "epoch": 0.16995666432739595,
      "grad_norm": 0.13929158449172974,
      "learning_rate": 0.003,
      "loss": 3.182627868652344,
      "step": 77800
    },
    {
      "epoch": 0.1701751176234466,
      "grad_norm": 0.14580564200878143,
      "learning_rate": 0.003,
      "loss": 3.209283752441406,
      "step": 77900
    },
    {
      "epoch": 0.17039357091949722,
      "grad_norm": 0.169144406914711,
      "learning_rate": 0.003,
      "loss": 3.2105447387695314,
      "step": 78000
    },
    {
      "epoch": 0.17061202421554786,
      "grad_norm": 0.18892961740493774,
      "learning_rate": 0.003,
      "loss": 3.179049377441406,
      "step": 78100
    },
    {
      "epoch": 0.1708304775115985,
      "grad_norm": 0.17873692512512207,
      "learning_rate": 0.003,
      "loss": 3.1997015380859377,
      "step": 78200
    },
    {
      "epoch": 0.17104893080764913,
      "grad_norm": 0.16759565472602844,
      "learning_rate": 0.003,
      "loss": 3.2110018920898438,
      "step": 78300
    },
    {
      "epoch": 0.1712673841036998,
      "grad_norm": 0.1694764345884323,
      "learning_rate": 0.003,
      "loss": 3.1810675048828125,
      "step": 78400
    },
    {
      "epoch": 0.17148583739975043,
      "grad_norm": 0.2141251564025879,
      "learning_rate": 0.003,
      "loss": 3.2247308349609374,
      "step": 78500
    },
    {
      "epoch": 0.17170429069580107,
      "grad_norm": 0.1924314647912979,
      "learning_rate": 0.003,
      "loss": 3.246143493652344,
      "step": 78600
    },
    {
      "epoch": 0.1719227439918517,
      "grad_norm": 0.14677858352661133,
      "learning_rate": 0.003,
      "loss": 3.195514831542969,
      "step": 78700
    },
    {
      "epoch": 0.17214119728790234,
      "grad_norm": 0.13610516488552094,
      "learning_rate": 0.003,
      "loss": 3.2029443359375,
      "step": 78800
    },
    {
      "epoch": 0.17235965058395297,
      "grad_norm": 0.1633630096912384,
      "learning_rate": 0.003,
      "loss": 3.1546783447265625,
      "step": 78900
    },
    {
      "epoch": 0.1725781038800036,
      "grad_norm": 0.1665549874305725,
      "learning_rate": 0.003,
      "loss": 3.2146710205078124,
      "step": 79000
    },
    {
      "epoch": 0.17279655717605424,
      "grad_norm": 0.39296653866767883,
      "learning_rate": 0.003,
      "loss": 3.2075177001953126,
      "step": 79100
    },
    {
      "epoch": 0.17301501047210488,
      "grad_norm": 0.28278303146362305,
      "learning_rate": 0.003,
      "loss": 3.201310729980469,
      "step": 79200
    },
    {
      "epoch": 0.17323346376815552,
      "grad_norm": 0.1643471121788025,
      "learning_rate": 0.003,
      "loss": 3.235052490234375,
      "step": 79300
    },
    {
      "epoch": 0.17345191706420615,
      "grad_norm": 0.18586060404777527,
      "learning_rate": 0.003,
      "loss": 3.168081970214844,
      "step": 79400
    },
    {
      "epoch": 0.1736703703602568,
      "grad_norm": 0.19346100091934204,
      "learning_rate": 0.003,
      "loss": 3.218128662109375,
      "step": 79500
    },
    {
      "epoch": 0.17388882365630742,
      "grad_norm": 0.1757037341594696,
      "learning_rate": 0.003,
      "loss": 3.1765069580078125,
      "step": 79600
    },
    {
      "epoch": 0.17410727695235806,
      "grad_norm": 0.15886549651622772,
      "learning_rate": 0.003,
      "loss": 3.2562713623046875,
      "step": 79700
    },
    {
      "epoch": 0.1743257302484087,
      "grad_norm": 0.16389308869838715,
      "learning_rate": 0.003,
      "loss": 3.220198974609375,
      "step": 79800
    },
    {
      "epoch": 0.17454418354445933,
      "grad_norm": 0.30649611353874207,
      "learning_rate": 0.003,
      "loss": 3.2026336669921873,
      "step": 79900
    },
    {
      "epoch": 0.17476263684050997,
      "grad_norm": 0.18294557929039001,
      "learning_rate": 0.003,
      "loss": 3.1905865478515625,
      "step": 80000
    },
    {
      "epoch": 0.17498109013656063,
      "grad_norm": 0.1466442495584488,
      "learning_rate": 0.003,
      "loss": 3.2082867431640625,
      "step": 80100
    },
    {
      "epoch": 0.17519954343261127,
      "grad_norm": 0.15893469750881195,
      "learning_rate": 0.003,
      "loss": 3.0881536865234374,
      "step": 80200
    },
    {
      "epoch": 0.1754179967286619,
      "grad_norm": 0.15483619272708893,
      "learning_rate": 0.003,
      "loss": 3.192733154296875,
      "step": 80300
    },
    {
      "epoch": 0.17563645002471254,
      "grad_norm": 0.19978880882263184,
      "learning_rate": 0.003,
      "loss": 3.2413204956054686,
      "step": 80400
    },
    {
      "epoch": 0.17585490332076317,
      "grad_norm": 0.1491372138261795,
      "learning_rate": 0.003,
      "loss": 3.2084686279296877,
      "step": 80500
    },
    {
      "epoch": 0.1760733566168138,
      "grad_norm": 0.2566303610801697,
      "learning_rate": 0.003,
      "loss": 3.2092715454101564,
      "step": 80600
    },
    {
      "epoch": 0.17629180991286444,
      "grad_norm": 0.2119085043668747,
      "learning_rate": 0.003,
      "loss": 3.222015380859375,
      "step": 80700
    },
    {
      "epoch": 0.17651026320891508,
      "grad_norm": 0.14177367091178894,
      "learning_rate": 0.003,
      "loss": 3.1890496826171875,
      "step": 80800
    },
    {
      "epoch": 0.17672871650496572,
      "grad_norm": 0.1567944884300232,
      "learning_rate": 0.003,
      "loss": 3.248140563964844,
      "step": 80900
    },
    {
      "epoch": 0.17694716980101635,
      "grad_norm": 0.13174422085285187,
      "learning_rate": 0.003,
      "loss": 3.19893798828125,
      "step": 81000
    },
    {
      "epoch": 0.177165623097067,
      "grad_norm": 0.1621484011411667,
      "learning_rate": 0.003,
      "loss": 3.17727783203125,
      "step": 81100
    },
    {
      "epoch": 0.17738407639311762,
      "grad_norm": 0.21841928362846375,
      "learning_rate": 0.003,
      "loss": 3.301322326660156,
      "step": 81200
    },
    {
      "epoch": 0.17760252968916826,
      "grad_norm": 1.0696430206298828,
      "learning_rate": 0.003,
      "loss": 3.2075405883789063,
      "step": 81300
    },
    {
      "epoch": 0.1778209829852189,
      "grad_norm": 0.1451922506093979,
      "learning_rate": 0.003,
      "loss": 3.1747747802734376,
      "step": 81400
    },
    {
      "epoch": 0.17803943628126953,
      "grad_norm": 0.1978912055492401,
      "learning_rate": 0.003,
      "loss": 3.223821716308594,
      "step": 81500
    },
    {
      "epoch": 0.17825788957732017,
      "grad_norm": 0.1773586869239807,
      "learning_rate": 0.003,
      "loss": 3.2137265014648437,
      "step": 81600
    },
    {
      "epoch": 0.17847634287337083,
      "grad_norm": 0.15452352166175842,
      "learning_rate": 0.003,
      "loss": 3.19757568359375,
      "step": 81700
    },
    {
      "epoch": 0.17869479616942147,
      "grad_norm": 0.16110122203826904,
      "learning_rate": 0.003,
      "loss": 3.2170181274414062,
      "step": 81800
    },
    {
      "epoch": 0.1789132494654721,
      "grad_norm": 0.2923918068408966,
      "learning_rate": 0.003,
      "loss": 3.2086199951171874,
      "step": 81900
    },
    {
      "epoch": 0.17913170276152274,
      "grad_norm": 0.13742706179618835,
      "learning_rate": 0.003,
      "loss": 3.203441467285156,
      "step": 82000
    },
    {
      "epoch": 0.17935015605757337,
      "grad_norm": 0.2099335640668869,
      "learning_rate": 0.003,
      "loss": 3.18805908203125,
      "step": 82100
    },
    {
      "epoch": 0.179568609353624,
      "grad_norm": 0.17757396399974823,
      "learning_rate": 0.003,
      "loss": 3.237929382324219,
      "step": 82200
    },
    {
      "epoch": 0.17978706264967464,
      "grad_norm": 0.1552405059337616,
      "learning_rate": 0.003,
      "loss": 3.2098583984375,
      "step": 82300
    },
    {
      "epoch": 0.18000551594572528,
      "grad_norm": 0.18570825457572937,
      "learning_rate": 0.003,
      "loss": 3.218511047363281,
      "step": 82400
    },
    {
      "epoch": 0.18022396924177592,
      "grad_norm": 0.17937444150447845,
      "learning_rate": 0.003,
      "loss": 3.1134356689453124,
      "step": 82500
    },
    {
      "epoch": 0.18044242253782655,
      "grad_norm": 0.2126537710428238,
      "learning_rate": 0.003,
      "loss": 3.181529235839844,
      "step": 82600
    },
    {
      "epoch": 0.1806608758338772,
      "grad_norm": 0.21367910504341125,
      "learning_rate": 0.003,
      "loss": 3.201230773925781,
      "step": 82700
    },
    {
      "epoch": 0.18087932912992782,
      "grad_norm": 0.14153313636779785,
      "learning_rate": 0.003,
      "loss": 3.1745318603515624,
      "step": 82800
    },
    {
      "epoch": 0.18109778242597846,
      "grad_norm": 0.19468209147453308,
      "learning_rate": 0.003,
      "loss": 3.2247454833984377,
      "step": 82900
    },
    {
      "epoch": 0.1813162357220291,
      "grad_norm": 0.15372858941555023,
      "learning_rate": 0.003,
      "loss": 3.1692236328125,
      "step": 83000
    },
    {
      "epoch": 0.18153468901807973,
      "grad_norm": 0.26405900716781616,
      "learning_rate": 0.003,
      "loss": 3.2481961059570312,
      "step": 83100
    },
    {
      "epoch": 0.18175314231413037,
      "grad_norm": 0.13953185081481934,
      "learning_rate": 0.003,
      "loss": 3.185765686035156,
      "step": 83200
    },
    {
      "epoch": 0.181971595610181,
      "grad_norm": 0.17543235421180725,
      "learning_rate": 0.003,
      "loss": 3.2108160400390626,
      "step": 83300
    },
    {
      "epoch": 0.18219004890623167,
      "grad_norm": 0.1657751351594925,
      "learning_rate": 0.003,
      "loss": 3.248452453613281,
      "step": 83400
    },
    {
      "epoch": 0.1824085022022823,
      "grad_norm": 0.169894739985466,
      "learning_rate": 0.003,
      "loss": 3.228109130859375,
      "step": 83500
    },
    {
      "epoch": 0.18262695549833294,
      "grad_norm": 0.3021637499332428,
      "learning_rate": 0.003,
      "loss": 3.2393258666992186,
      "step": 83600
    },
    {
      "epoch": 0.18284540879438357,
      "grad_norm": 0.15600207448005676,
      "learning_rate": 0.003,
      "loss": 3.2102398681640625,
      "step": 83700
    },
    {
      "epoch": 0.1830638620904342,
      "grad_norm": 0.140744149684906,
      "learning_rate": 0.003,
      "loss": 3.1667059326171874,
      "step": 83800
    },
    {
      "epoch": 0.18328231538648485,
      "grad_norm": 0.15589119493961334,
      "learning_rate": 0.003,
      "loss": 3.1936209106445315,
      "step": 83900
    },
    {
      "epoch": 0.18350076868253548,
      "grad_norm": 0.1463201940059662,
      "learning_rate": 0.003,
      "loss": 3.175903015136719,
      "step": 84000
    },
    {
      "epoch": 0.18371922197858612,
      "grad_norm": 0.2008126974105835,
      "learning_rate": 0.003,
      "loss": 3.1910275268554686,
      "step": 84100
    },
    {
      "epoch": 0.18393767527463675,
      "grad_norm": 0.17553767561912537,
      "learning_rate": 0.003,
      "loss": 3.187009582519531,
      "step": 84200
    },
    {
      "epoch": 0.1841561285706874,
      "grad_norm": 0.16969048976898193,
      "learning_rate": 0.003,
      "loss": 3.21021240234375,
      "step": 84300
    },
    {
      "epoch": 0.18437458186673802,
      "grad_norm": 0.5377168655395508,
      "learning_rate": 0.003,
      "loss": 3.1883334350585937,
      "step": 84400
    },
    {
      "epoch": 0.18459303516278866,
      "grad_norm": 0.1619803011417389,
      "learning_rate": 0.003,
      "loss": 3.1760284423828127,
      "step": 84500
    },
    {
      "epoch": 0.1848114884588393,
      "grad_norm": 0.16926124691963196,
      "learning_rate": 0.003,
      "loss": 3.1831094360351564,
      "step": 84600
    },
    {
      "epoch": 0.18502994175488993,
      "grad_norm": 0.16700851917266846,
      "learning_rate": 0.003,
      "loss": 3.1721905517578124,
      "step": 84700
    },
    {
      "epoch": 0.18524839505094057,
      "grad_norm": 0.14603792130947113,
      "learning_rate": 0.003,
      "loss": 3.16665283203125,
      "step": 84800
    },
    {
      "epoch": 0.1854668483469912,
      "grad_norm": 0.24774129688739777,
      "learning_rate": 0.003,
      "loss": 2.9768441772460936,
      "step": 84900
    },
    {
      "epoch": 0.18568530164304184,
      "grad_norm": 0.17643874883651733,
      "learning_rate": 0.003,
      "loss": 2.7105810546875,
      "step": 85000
    },
    {
      "epoch": 0.1859037549390925,
      "grad_norm": 0.16816070675849915,
      "learning_rate": 0.003,
      "loss": 3.1750653076171873,
      "step": 85100
    },
    {
      "epoch": 0.18612220823514314,
      "grad_norm": 0.35066846013069153,
      "learning_rate": 0.003,
      "loss": 3.204986572265625,
      "step": 85200
    },
    {
      "epoch": 0.18634066153119377,
      "grad_norm": 0.17999179661273956,
      "learning_rate": 0.003,
      "loss": 3.170851135253906,
      "step": 85300
    },
    {
      "epoch": 0.1865591148272444,
      "grad_norm": 0.14632770419120789,
      "learning_rate": 0.003,
      "loss": 3.1513735961914064,
      "step": 85400
    },
    {
      "epoch": 0.18677756812329505,
      "grad_norm": 0.14943662285804749,
      "learning_rate": 0.003,
      "loss": 3.226905517578125,
      "step": 85500
    },
    {
      "epoch": 0.18699602141934568,
      "grad_norm": 0.1464826613664627,
      "learning_rate": 0.003,
      "loss": 3.183929138183594,
      "step": 85600
    },
    {
      "epoch": 0.18721447471539632,
      "grad_norm": 0.1445285826921463,
      "learning_rate": 0.003,
      "loss": 3.185249938964844,
      "step": 85700
    },
    {
      "epoch": 0.18743292801144695,
      "grad_norm": 0.15161272883415222,
      "learning_rate": 0.003,
      "loss": 3.1968368530273437,
      "step": 85800
    },
    {
      "epoch": 0.1876513813074976,
      "grad_norm": 0.14321133494377136,
      "learning_rate": 0.003,
      "loss": 3.16796875,
      "step": 85900
    },
    {
      "epoch": 0.18786983460354822,
      "grad_norm": 0.17690575122833252,
      "learning_rate": 0.003,
      "loss": 3.079221496582031,
      "step": 86000
    },
    {
      "epoch": 0.18808828789959886,
      "grad_norm": 0.30789339542388916,
      "learning_rate": 0.003,
      "loss": 3.1597393798828124,
      "step": 86100
    },
    {
      "epoch": 0.1883067411956495,
      "grad_norm": 0.19097469747066498,
      "learning_rate": 0.003,
      "loss": 3.105707092285156,
      "step": 86200
    },
    {
      "epoch": 0.18852519449170013,
      "grad_norm": 0.1602492481470108,
      "learning_rate": 0.003,
      "loss": 3.1880517578125,
      "step": 86300
    },
    {
      "epoch": 0.18874364778775077,
      "grad_norm": 0.1806216835975647,
      "learning_rate": 0.003,
      "loss": 3.1760809326171877,
      "step": 86400
    },
    {
      "epoch": 0.1889621010838014,
      "grad_norm": 0.1637730896472931,
      "learning_rate": 0.003,
      "loss": 3.1409722900390626,
      "step": 86500
    },
    {
      "epoch": 0.18918055437985204,
      "grad_norm": 0.2023204267024994,
      "learning_rate": 0.003,
      "loss": 3.164836120605469,
      "step": 86600
    },
    {
      "epoch": 0.1893990076759027,
      "grad_norm": 0.1658940315246582,
      "learning_rate": 0.003,
      "loss": 3.201011047363281,
      "step": 86700
    },
    {
      "epoch": 0.18961746097195334,
      "grad_norm": 0.1435602456331253,
      "learning_rate": 0.003,
      "loss": 3.1786843872070314,
      "step": 86800
    },
    {
      "epoch": 0.18983591426800397,
      "grad_norm": 0.18763457238674164,
      "learning_rate": 0.003,
      "loss": 3.206578674316406,
      "step": 86900
    },
    {
      "epoch": 0.1900543675640546,
      "grad_norm": 0.25697416067123413,
      "learning_rate": 0.003,
      "loss": 3.2007901000976564,
      "step": 87000
    },
    {
      "epoch": 0.19027282086010525,
      "grad_norm": 0.20490820705890656,
      "learning_rate": 0.003,
      "loss": 3.161679382324219,
      "step": 87100
    },
    {
      "epoch": 0.19049127415615588,
      "grad_norm": 0.18808764219284058,
      "learning_rate": 0.003,
      "loss": 3.2807861328125,
      "step": 87200
    },
    {
      "epoch": 0.19070972745220652,
      "grad_norm": 0.20605118572711945,
      "learning_rate": 0.003,
      "loss": 3.184476623535156,
      "step": 87300
    },
    {
      "epoch": 0.19092818074825715,
      "grad_norm": 0.15393364429473877,
      "learning_rate": 0.003,
      "loss": 3.179691162109375,
      "step": 87400
    },
    {
      "epoch": 0.1911466340443078,
      "grad_norm": 0.16213102638721466,
      "learning_rate": 0.003,
      "loss": 3.1681033325195314,
      "step": 87500
    },
    {
      "epoch": 0.19136508734035843,
      "grad_norm": 0.1807558238506317,
      "learning_rate": 0.003,
      "loss": 3.190770263671875,
      "step": 87600
    },
    {
      "epoch": 0.19158354063640906,
      "grad_norm": 0.15362854301929474,
      "learning_rate": 0.003,
      "loss": 3.1951593017578124,
      "step": 87700
    },
    {
      "epoch": 0.1918019939324597,
      "grad_norm": 0.3159952163696289,
      "learning_rate": 0.003,
      "loss": 3.156473388671875,
      "step": 87800
    },
    {
      "epoch": 0.19202044722851033,
      "grad_norm": 0.2071072906255722,
      "learning_rate": 0.003,
      "loss": 3.1962716674804685,
      "step": 87900
    },
    {
      "epoch": 0.19223890052456097,
      "grad_norm": 0.21645040810108185,
      "learning_rate": 0.003,
      "loss": 2.6888922119140624,
      "step": 88000
    },
    {
      "epoch": 0.1924573538206116,
      "grad_norm": 0.14421090483665466,
      "learning_rate": 0.003,
      "loss": 2.664625244140625,
      "step": 88100
    },
    {
      "epoch": 0.19267580711666224,
      "grad_norm": 0.14521977305412292,
      "learning_rate": 0.003,
      "loss": 3.1772064208984374,
      "step": 88200
    },
    {
      "epoch": 0.19289426041271288,
      "grad_norm": 0.18281616270542145,
      "learning_rate": 0.003,
      "loss": 3.154764404296875,
      "step": 88300
    },
    {
      "epoch": 0.19311271370876354,
      "grad_norm": 0.16759873926639557,
      "learning_rate": 0.003,
      "loss": 3.2332708740234377,
      "step": 88400
    },
    {
      "epoch": 0.19333116700481418,
      "grad_norm": 0.1650831699371338,
      "learning_rate": 0.003,
      "loss": 3.1961322021484375,
      "step": 88500
    },
    {
      "epoch": 0.1935496203008648,
      "grad_norm": 0.15335407853126526,
      "learning_rate": 0.003,
      "loss": 3.219986572265625,
      "step": 88600
    },
    {
      "epoch": 0.19376807359691545,
      "grad_norm": 0.17449705302715302,
      "learning_rate": 0.003,
      "loss": 3.1900616455078126,
      "step": 88700
    },
    {
      "epoch": 0.19398652689296608,
      "grad_norm": 0.17153072357177734,
      "learning_rate": 0.003,
      "loss": 3.1804873657226564,
      "step": 88800
    },
    {
      "epoch": 0.19420498018901672,
      "grad_norm": 0.2380538284778595,
      "learning_rate": 0.003,
      "loss": 3.2428970336914062,
      "step": 88900
    },
    {
      "epoch": 0.19442343348506735,
      "grad_norm": 0.17524601519107819,
      "learning_rate": 0.003,
      "loss": 3.185479736328125,
      "step": 89000
    },
    {
      "epoch": 0.194641886781118,
      "grad_norm": 0.18849943578243256,
      "learning_rate": 0.003,
      "loss": 3.21683837890625,
      "step": 89100
    },
    {
      "epoch": 0.19486034007716863,
      "grad_norm": 0.22329972684383392,
      "learning_rate": 0.003,
      "loss": 3.213042907714844,
      "step": 89200
    },
    {
      "epoch": 0.19507879337321926,
      "grad_norm": 0.18111512064933777,
      "learning_rate": 0.003,
      "loss": 3.1977069091796877,
      "step": 89300
    },
    {
      "epoch": 0.1952972466692699,
      "grad_norm": 0.16808584332466125,
      "learning_rate": 0.003,
      "loss": 3.2011788940429686,
      "step": 89400
    },
    {
      "epoch": 0.19551569996532053,
      "grad_norm": 0.16412976384162903,
      "learning_rate": 0.003,
      "loss": 3.1853192138671873,
      "step": 89500
    },
    {
      "epoch": 0.19573415326137117,
      "grad_norm": 0.14178995788097382,
      "learning_rate": 0.003,
      "loss": 3.1789019775390623,
      "step": 89600
    },
    {
      "epoch": 0.1959526065574218,
      "grad_norm": 0.16296924650669098,
      "learning_rate": 0.003,
      "loss": 3.190277099609375,
      "step": 89700
    },
    {
      "epoch": 0.19617105985347244,
      "grad_norm": 0.15710635483264923,
      "learning_rate": 0.003,
      "loss": 3.206595764160156,
      "step": 89800
    },
    {
      "epoch": 0.19638951314952308,
      "grad_norm": 0.16058866679668427,
      "learning_rate": 0.003,
      "loss": 3.1978875732421876,
      "step": 89900
    },
    {
      "epoch": 0.19660796644557374,
      "grad_norm": 0.19483326375484467,
      "learning_rate": 0.003,
      "loss": 3.167970886230469,
      "step": 90000
    },
    {
      "epoch": 0.19682641974162438,
      "grad_norm": 0.24953538179397583,
      "learning_rate": 0.003,
      "loss": 3.189050598144531,
      "step": 90100
    },
    {
      "epoch": 0.197044873037675,
      "grad_norm": 0.17547492682933807,
      "learning_rate": 0.003,
      "loss": 3.175340270996094,
      "step": 90200
    },
    {
      "epoch": 0.19726332633372565,
      "grad_norm": 0.1600673347711563,
      "learning_rate": 0.003,
      "loss": 3.142608947753906,
      "step": 90300
    },
    {
      "epoch": 0.19748177962977628,
      "grad_norm": 0.19891978800296783,
      "learning_rate": 0.003,
      "loss": 3.2025765991210937,
      "step": 90400
    },
    {
      "epoch": 0.19770023292582692,
      "grad_norm": 0.21992084383964539,
      "learning_rate": 0.003,
      "loss": 3.1964657592773436,
      "step": 90500
    },
    {
      "epoch": 0.19791868622187755,
      "grad_norm": 0.19522127509117126,
      "learning_rate": 0.003,
      "loss": 3.195756530761719,
      "step": 90600
    },
    {
      "epoch": 0.1981371395179282,
      "grad_norm": 0.18746817111968994,
      "learning_rate": 0.003,
      "loss": 3.184117736816406,
      "step": 90700
    },
    {
      "epoch": 0.19835559281397883,
      "grad_norm": 0.15298475325107574,
      "learning_rate": 0.003,
      "loss": 3.183582458496094,
      "step": 90800
    },
    {
      "epoch": 0.19857404611002946,
      "grad_norm": 0.19623512029647827,
      "learning_rate": 0.003,
      "loss": 3.187120361328125,
      "step": 90900
    },
    {
      "epoch": 0.1987924994060801,
      "grad_norm": 0.17852617800235748,
      "learning_rate": 0.003,
      "loss": 3.1580520629882813,
      "step": 91000
    },
    {
      "epoch": 0.19901095270213073,
      "grad_norm": 0.22779320180416107,
      "learning_rate": 0.003,
      "loss": 3.1618084716796875,
      "step": 91100
    },
    {
      "epoch": 0.19922940599818137,
      "grad_norm": 0.24420838057994843,
      "learning_rate": 0.003,
      "loss": 3.189275817871094,
      "step": 91200
    },
    {
      "epoch": 0.199447859294232,
      "grad_norm": 0.17383147776126862,
      "learning_rate": 0.003,
      "loss": 3.1706887817382814,
      "step": 91300
    },
    {
      "epoch": 0.19966631259028264,
      "grad_norm": 0.21523991227149963,
      "learning_rate": 0.003,
      "loss": 3.20406005859375,
      "step": 91400
    },
    {
      "epoch": 0.19988476588633328,
      "grad_norm": 0.19733121991157532,
      "learning_rate": 0.003,
      "loss": 3.18106689453125,
      "step": 91500
    },
    {
      "epoch": 0.2001032191823839,
      "grad_norm": 0.22286085784435272,
      "learning_rate": 0.003,
      "loss": 3.1443585205078124,
      "step": 91600
    },
    {
      "epoch": 0.20032167247843458,
      "grad_norm": 0.25405412912368774,
      "learning_rate": 0.003,
      "loss": 3.201405029296875,
      "step": 91700
    },
    {
      "epoch": 0.2005401257744852,
      "grad_norm": 0.18054093420505524,
      "learning_rate": 0.003,
      "loss": 3.1207098388671874,
      "step": 91800
    },
    {
      "epoch": 0.20075857907053585,
      "grad_norm": 0.2531103193759918,
      "learning_rate": 0.003,
      "loss": 3.172463073730469,
      "step": 91900
    },
    {
      "epoch": 0.20097703236658648,
      "grad_norm": 0.19328059256076813,
      "learning_rate": 0.003,
      "loss": 3.20841796875,
      "step": 92000
    },
    {
      "epoch": 0.20119548566263712,
      "grad_norm": 0.16797882318496704,
      "learning_rate": 0.003,
      "loss": 3.1828482055664065,
      "step": 92100
    },
    {
      "epoch": 0.20141393895868775,
      "grad_norm": 0.1891237497329712,
      "learning_rate": 0.003,
      "loss": 3.187022399902344,
      "step": 92200
    },
    {
      "epoch": 0.2016323922547384,
      "grad_norm": 0.18582101166248322,
      "learning_rate": 0.003,
      "loss": 3.1867816162109377,
      "step": 92300
    },
    {
      "epoch": 0.20185084555078903,
      "grad_norm": 0.2223065346479416,
      "learning_rate": 0.003,
      "loss": 3.1994952392578124,
      "step": 92400
    },
    {
      "epoch": 0.20206929884683966,
      "grad_norm": 0.13481435179710388,
      "learning_rate": 0.003,
      "loss": 3.17259033203125,
      "step": 92500
    },
    {
      "epoch": 0.2022877521428903,
      "grad_norm": 0.1694314032793045,
      "learning_rate": 0.003,
      "loss": 3.179879455566406,
      "step": 92600
    },
    {
      "epoch": 0.20250620543894093,
      "grad_norm": 0.14082738757133484,
      "learning_rate": 0.003,
      "loss": 3.1622433471679687,
      "step": 92700
    },
    {
      "epoch": 0.20272465873499157,
      "grad_norm": 0.15445734560489655,
      "learning_rate": 0.003,
      "loss": 3.146681213378906,
      "step": 92800
    },
    {
      "epoch": 0.2029431120310422,
      "grad_norm": 0.1701645702123642,
      "learning_rate": 0.003,
      "loss": 3.2219207763671873,
      "step": 92900
    },
    {
      "epoch": 0.20316156532709284,
      "grad_norm": 0.16084595024585724,
      "learning_rate": 0.003,
      "loss": 3.171546630859375,
      "step": 93000
    },
    {
      "epoch": 0.20338001862314348,
      "grad_norm": 0.1549762487411499,
      "learning_rate": 0.003,
      "loss": 3.1478482055664063,
      "step": 93100
    },
    {
      "epoch": 0.2035984719191941,
      "grad_norm": 0.15329527854919434,
      "learning_rate": 0.003,
      "loss": 3.199483642578125,
      "step": 93200
    },
    {
      "epoch": 0.20381692521524478,
      "grad_norm": 0.1530144065618515,
      "learning_rate": 0.003,
      "loss": 3.1848526000976562,
      "step": 93300
    },
    {
      "epoch": 0.2040353785112954,
      "grad_norm": 0.1716870814561844,
      "learning_rate": 0.003,
      "loss": 3.154272155761719,
      "step": 93400
    },
    {
      "epoch": 0.20425383180734605,
      "grad_norm": 0.16520437598228455,
      "learning_rate": 0.003,
      "loss": 3.232624206542969,
      "step": 93500
    },
    {
      "epoch": 0.20447228510339668,
      "grad_norm": 0.22018638253211975,
      "learning_rate": 0.003,
      "loss": 3.177936706542969,
      "step": 93600
    },
    {
      "epoch": 0.20469073839944732,
      "grad_norm": 0.18284861743450165,
      "learning_rate": 0.003,
      "loss": 3.1810137939453127,
      "step": 93700
    },
    {
      "epoch": 0.20490919169549796,
      "grad_norm": 0.22632446885108948,
      "learning_rate": 0.003,
      "loss": 3.1926318359375,
      "step": 93800
    },
    {
      "epoch": 0.2051276449915486,
      "grad_norm": 0.16929064691066742,
      "learning_rate": 0.003,
      "loss": 3.1332843017578127,
      "step": 93900
    },
    {
      "epoch": 0.20534609828759923,
      "grad_norm": 0.15234090387821198,
      "learning_rate": 0.003,
      "loss": 3.1795526123046876,
      "step": 94000
    },
    {
      "epoch": 0.20556455158364986,
      "grad_norm": 1.2888211011886597,
      "learning_rate": 0.003,
      "loss": 3.1836972045898437,
      "step": 94100
    },
    {
      "epoch": 0.2057830048797005,
      "grad_norm": 0.15114560723304749,
      "learning_rate": 0.003,
      "loss": 3.171034240722656,
      "step": 94200
    },
    {
      "epoch": 0.20600145817575113,
      "grad_norm": 0.22760440409183502,
      "learning_rate": 0.003,
      "loss": 3.1925299072265627,
      "step": 94300
    },
    {
      "epoch": 0.20621991147180177,
      "grad_norm": 0.1724519431591034,
      "learning_rate": 0.003,
      "loss": 3.1574478149414062,
      "step": 94400
    },
    {
      "epoch": 0.2064383647678524,
      "grad_norm": 0.14399363100528717,
      "learning_rate": 0.003,
      "loss": 3.160289306640625,
      "step": 94500
    },
    {
      "epoch": 0.20665681806390304,
      "grad_norm": 0.21455234289169312,
      "learning_rate": 0.003,
      "loss": 3.2192218017578127,
      "step": 94600
    },
    {
      "epoch": 0.20687527135995368,
      "grad_norm": 0.143798366189003,
      "learning_rate": 0.003,
      "loss": 3.2235052490234377,
      "step": 94700
    },
    {
      "epoch": 0.2070937246560043,
      "grad_norm": 0.13446617126464844,
      "learning_rate": 0.003,
      "loss": 3.166502685546875,
      "step": 94800
    },
    {
      "epoch": 0.20731217795205495,
      "grad_norm": 0.1853928416967392,
      "learning_rate": 0.003,
      "loss": 3.205904846191406,
      "step": 94900
    },
    {
      "epoch": 0.2075306312481056,
      "grad_norm": 0.1520940512418747,
      "learning_rate": 0.003,
      "loss": 3.2054425048828126,
      "step": 95000
    },
    {
      "epoch": 0.20774908454415625,
      "grad_norm": 0.18492989242076874,
      "learning_rate": 0.003,
      "loss": 3.1887503051757813,
      "step": 95100
    },
    {
      "epoch": 0.20796753784020688,
      "grad_norm": 0.16937538981437683,
      "learning_rate": 0.003,
      "loss": 3.1389309692382814,
      "step": 95200
    },
    {
      "epoch": 0.20818599113625752,
      "grad_norm": 0.1527348905801773,
      "learning_rate": 0.003,
      "loss": 3.2123422241210937,
      "step": 95300
    },
    {
      "epoch": 0.20840444443230816,
      "grad_norm": 0.236098974943161,
      "learning_rate": 0.003,
      "loss": 3.239290466308594,
      "step": 95400
    },
    {
      "epoch": 0.2086228977283588,
      "grad_norm": 0.14385886490345,
      "learning_rate": 0.003,
      "loss": 3.211983947753906,
      "step": 95500
    },
    {
      "epoch": 0.20884135102440943,
      "grad_norm": 0.15831750631332397,
      "learning_rate": 0.003,
      "loss": 3.222947082519531,
      "step": 95600
    },
    {
      "epoch": 0.20905980432046006,
      "grad_norm": 0.1465398520231247,
      "learning_rate": 0.003,
      "loss": 3.2200616455078124,
      "step": 95700
    },
    {
      "epoch": 0.2092782576165107,
      "grad_norm": 0.2297724485397339,
      "learning_rate": 0.003,
      "loss": 3.1978054809570313,
      "step": 95800
    },
    {
      "epoch": 0.20949671091256133,
      "grad_norm": 0.19791044294834137,
      "learning_rate": 0.003,
      "loss": 3.21572021484375,
      "step": 95900
    },
    {
      "epoch": 0.20971516420861197,
      "grad_norm": 0.16529631614685059,
      "learning_rate": 0.003,
      "loss": 3.2116912841796874,
      "step": 96000
    },
    {
      "epoch": 0.2099336175046626,
      "grad_norm": 0.1494702845811844,
      "learning_rate": 0.003,
      "loss": 3.1520919799804688,
      "step": 96100
    },
    {
      "epoch": 0.21015207080071324,
      "grad_norm": 0.18800431489944458,
      "learning_rate": 0.003,
      "loss": 3.1841400146484373,
      "step": 96200
    },
    {
      "epoch": 0.21037052409676388,
      "grad_norm": 0.16817855834960938,
      "learning_rate": 0.003,
      "loss": 3.1894522094726563,
      "step": 96300
    },
    {
      "epoch": 0.2105889773928145,
      "grad_norm": 0.14505019783973694,
      "learning_rate": 0.003,
      "loss": 3.1698458862304686,
      "step": 96400
    },
    {
      "epoch": 0.21080743068886515,
      "grad_norm": 0.3214562237262726,
      "learning_rate": 0.003,
      "loss": 3.2179776000976563,
      "step": 96500
    },
    {
      "epoch": 0.2110258839849158,
      "grad_norm": 0.2016151249408722,
      "learning_rate": 0.003,
      "loss": 3.217587890625,
      "step": 96600
    },
    {
      "epoch": 0.21124433728096645,
      "grad_norm": 0.1868591159582138,
      "learning_rate": 0.003,
      "loss": 3.248324279785156,
      "step": 96700
    },
    {
      "epoch": 0.21146279057701708,
      "grad_norm": 0.14070992171764374,
      "learning_rate": 0.003,
      "loss": 3.188021545410156,
      "step": 96800
    },
    {
      "epoch": 0.21168124387306772,
      "grad_norm": 0.20569053292274475,
      "learning_rate": 0.003,
      "loss": 3.179546203613281,
      "step": 96900
    },
    {
      "epoch": 0.21189969716911836,
      "grad_norm": 0.15633311867713928,
      "learning_rate": 0.003,
      "loss": 2.98917724609375,
      "step": 97000
    },
    {
      "epoch": 0.212118150465169,
      "grad_norm": 0.13893213868141174,
      "learning_rate": 0.003,
      "loss": 3.2265609741210937,
      "step": 97100
    },
    {
      "epoch": 0.21233660376121963,
      "grad_norm": 0.13560397922992706,
      "learning_rate": 0.003,
      "loss": 3.161188049316406,
      "step": 97200
    },
    {
      "epoch": 0.21255505705727026,
      "grad_norm": 0.22136159241199493,
      "learning_rate": 0.003,
      "loss": 3.1796783447265624,
      "step": 97300
    },
    {
      "epoch": 0.2127735103533209,
      "grad_norm": 0.20529834926128387,
      "learning_rate": 0.003,
      "loss": 3.184031677246094,
      "step": 97400
    },
    {
      "epoch": 0.21299196364937154,
      "grad_norm": 0.16357794404029846,
      "learning_rate": 0.003,
      "loss": 3.205530090332031,
      "step": 97500
    },
    {
      "epoch": 0.21321041694542217,
      "grad_norm": 0.1573294699192047,
      "learning_rate": 0.003,
      "loss": 3.1988009643554687,
      "step": 97600
    },
    {
      "epoch": 0.2134288702414728,
      "grad_norm": 0.16560779511928558,
      "learning_rate": 0.003,
      "loss": 3.24091796875,
      "step": 97700
    },
    {
      "epoch": 0.21364732353752344,
      "grad_norm": 0.1558590829372406,
      "learning_rate": 0.003,
      "loss": 3.2470822143554687,
      "step": 97800
    },
    {
      "epoch": 0.21386577683357408,
      "grad_norm": 0.13487383723258972,
      "learning_rate": 0.003,
      "loss": 3.21383544921875,
      "step": 97900
    },
    {
      "epoch": 0.21408423012962471,
      "grad_norm": 0.15421494841575623,
      "learning_rate": 0.003,
      "loss": 3.231658935546875,
      "step": 98000
    },
    {
      "epoch": 0.21430268342567535,
      "grad_norm": 0.17839591205120087,
      "learning_rate": 0.003,
      "loss": 3.2164346313476564,
      "step": 98100
    },
    {
      "epoch": 0.21452113672172599,
      "grad_norm": 0.1539018750190735,
      "learning_rate": 0.003,
      "loss": 3.2122412109375,
      "step": 98200
    },
    {
      "epoch": 0.21473959001777665,
      "grad_norm": 0.16570475697517395,
      "learning_rate": 0.003,
      "loss": 3.2146701049804687,
      "step": 98300
    },
    {
      "epoch": 0.21495804331382729,
      "grad_norm": 0.17220532894134521,
      "learning_rate": 0.003,
      "loss": 3.193248291015625,
      "step": 98400
    },
    {
      "epoch": 0.21517649660987792,
      "grad_norm": 0.1638244241476059,
      "learning_rate": 0.003,
      "loss": 3.2288504028320313,
      "step": 98500
    },
    {
      "epoch": 0.21539494990592856,
      "grad_norm": 0.19310399889945984,
      "learning_rate": 0.003,
      "loss": 3.20605712890625,
      "step": 98600
    },
    {
      "epoch": 0.2156134032019792,
      "grad_norm": 0.16728836297988892,
      "learning_rate": 0.003,
      "loss": 3.182777099609375,
      "step": 98700
    },
    {
      "epoch": 0.21583185649802983,
      "grad_norm": 0.15934403240680695,
      "learning_rate": 0.003,
      "loss": 3.194869079589844,
      "step": 98800
    },
    {
      "epoch": 0.21605030979408046,
      "grad_norm": 0.16646726429462433,
      "learning_rate": 0.003,
      "loss": 3.207718505859375,
      "step": 98900
    },
    {
      "epoch": 0.2162687630901311,
      "grad_norm": 0.2790140211582184,
      "learning_rate": 0.003,
      "loss": 3.1770614624023437,
      "step": 99000
    },
    {
      "epoch": 0.21648721638618174,
      "grad_norm": 0.1910792887210846,
      "learning_rate": 0.003,
      "loss": 3.189217529296875,
      "step": 99100
    },
    {
      "epoch": 0.21670566968223237,
      "grad_norm": 0.19499088823795319,
      "learning_rate": 0.003,
      "loss": 3.2451211547851564,
      "step": 99200
    },
    {
      "epoch": 0.216924122978283,
      "grad_norm": 0.13704334199428558,
      "learning_rate": 0.003,
      "loss": 3.232183532714844,
      "step": 99300
    },
    {
      "epoch": 0.21714257627433364,
      "grad_norm": 0.1589747965335846,
      "learning_rate": 0.003,
      "loss": 3.2211962890625,
      "step": 99400
    },
    {
      "epoch": 0.21736102957038428,
      "grad_norm": 0.1402156502008438,
      "learning_rate": 0.003,
      "loss": 3.2198226928710936,
      "step": 99500
    },
    {
      "epoch": 0.21757948286643491,
      "grad_norm": 0.15935233235359192,
      "learning_rate": 0.003,
      "loss": 3.2299127197265625,
      "step": 99600
    },
    {
      "epoch": 0.21779793616248555,
      "grad_norm": 0.15546433627605438,
      "learning_rate": 0.003,
      "loss": 3.202350769042969,
      "step": 99700
    },
    {
      "epoch": 0.21801638945853619,
      "grad_norm": 0.20298254489898682,
      "learning_rate": 0.003,
      "loss": 3.221640930175781,
      "step": 99800
    },
    {
      "epoch": 0.21823484275458685,
      "grad_norm": 0.18505309522151947,
      "learning_rate": 0.003,
      "loss": 3.217315673828125,
      "step": 99900
    },
    {
      "epoch": 0.21845329605063749,
      "grad_norm": 0.2007245421409607,
      "learning_rate": 0.003,
      "loss": 3.23029052734375,
      "step": 100000
    },
    {
      "epoch": 0.21867174934668812,
      "grad_norm": 0.16363219916820526,
      "learning_rate": 0.003,
      "loss": 3.2147122192382813,
      "step": 100100
    },
    {
      "epoch": 0.21889020264273876,
      "grad_norm": 0.19433718919754028,
      "learning_rate": 0.003,
      "loss": 3.2266812133789062,
      "step": 100200
    },
    {
      "epoch": 0.2191086559387894,
      "grad_norm": 0.14650124311447144,
      "learning_rate": 0.003,
      "loss": 3.198697509765625,
      "step": 100300
    },
    {
      "epoch": 0.21932710923484003,
      "grad_norm": 0.14737825095653534,
      "learning_rate": 0.003,
      "loss": 3.178011779785156,
      "step": 100400
    },
    {
      "epoch": 0.21954556253089066,
      "grad_norm": 0.19723723828792572,
      "learning_rate": 0.003,
      "loss": 3.2108416748046875,
      "step": 100500
    },
    {
      "epoch": 0.2197640158269413,
      "grad_norm": 0.24265453219413757,
      "learning_rate": 0.003,
      "loss": 3.247611389160156,
      "step": 100600
    },
    {
      "epoch": 0.21998246912299194,
      "grad_norm": 0.2030978798866272,
      "learning_rate": 0.003,
      "loss": 2.7322259521484376,
      "step": 100700
    },
    {
      "epoch": 0.22020092241904257,
      "grad_norm": 0.1545838713645935,
      "learning_rate": 0.003,
      "loss": 3.2058575439453123,
      "step": 100800
    },
    {
      "epoch": 0.2204193757150932,
      "grad_norm": 0.15992237627506256,
      "learning_rate": 0.003,
      "loss": 3.2379156494140626,
      "step": 100900
    },
    {
      "epoch": 0.22063782901114384,
      "grad_norm": 0.1919916272163391,
      "learning_rate": 0.003,
      "loss": 3.2084530639648436,
      "step": 101000
    },
    {
      "epoch": 0.22085628230719448,
      "grad_norm": 0.16147805750370026,
      "learning_rate": 0.003,
      "loss": 3.2007907104492186,
      "step": 101100
    },
    {
      "epoch": 0.22107473560324511,
      "grad_norm": 0.16603071987628937,
      "learning_rate": 0.003,
      "loss": 3.176233215332031,
      "step": 101200
    },
    {
      "epoch": 0.22129318889929575,
      "grad_norm": 0.25442710518836975,
      "learning_rate": 0.003,
      "loss": 3.221510009765625,
      "step": 101300
    },
    {
      "epoch": 0.2215116421953464,
      "grad_norm": 0.18280309438705444,
      "learning_rate": 0.003,
      "loss": 3.2156817626953127,
      "step": 101400
    },
    {
      "epoch": 0.22173009549139702,
      "grad_norm": 0.20255111157894135,
      "learning_rate": 0.003,
      "loss": 3.22599609375,
      "step": 101500
    },
    {
      "epoch": 0.22194854878744769,
      "grad_norm": 0.19555102288722992,
      "learning_rate": 0.003,
      "loss": 3.234263610839844,
      "step": 101600
    },
    {
      "epoch": 0.22216700208349832,
      "grad_norm": 0.16481703519821167,
      "learning_rate": 0.003,
      "loss": 3.2006109619140624,
      "step": 101700
    },
    {
      "epoch": 0.22238545537954896,
      "grad_norm": 0.1800691783428192,
      "learning_rate": 0.003,
      "loss": 3.2422198486328124,
      "step": 101800
    },
    {
      "epoch": 0.2226039086755996,
      "grad_norm": 0.19977200031280518,
      "learning_rate": 0.003,
      "loss": 3.214632568359375,
      "step": 101900
    },
    {
      "epoch": 0.22282236197165023,
      "grad_norm": 0.18122437596321106,
      "learning_rate": 0.003,
      "loss": 3.1705487060546873,
      "step": 102000
    },
    {
      "epoch": 0.22304081526770086,
      "grad_norm": 0.17697519063949585,
      "learning_rate": 0.003,
      "loss": 3.2142709350585936,
      "step": 102100
    },
    {
      "epoch": 0.2232592685637515,
      "grad_norm": 0.1942490041255951,
      "learning_rate": 0.003,
      "loss": 3.192371520996094,
      "step": 102200
    },
    {
      "epoch": 0.22347772185980214,
      "grad_norm": 0.14101845026016235,
      "learning_rate": 0.003,
      "loss": 3.1763015747070313,
      "step": 102300
    },
    {
      "epoch": 0.22369617515585277,
      "grad_norm": 0.15464375913143158,
      "learning_rate": 0.003,
      "loss": 3.2267938232421876,
      "step": 102400
    },
    {
      "epoch": 0.2239146284519034,
      "grad_norm": 0.15713827311992645,
      "learning_rate": 0.003,
      "loss": 3.1892242431640625,
      "step": 102500
    },
    {
      "epoch": 0.22413308174795404,
      "grad_norm": 0.19050081074237823,
      "learning_rate": 0.003,
      "loss": 3.203402099609375,
      "step": 102600
    },
    {
      "epoch": 0.22435153504400468,
      "grad_norm": 0.14306189119815826,
      "learning_rate": 0.003,
      "loss": 3.2019168090820314,
      "step": 102700
    },
    {
      "epoch": 0.22456998834005532,
      "grad_norm": 0.17052483558654785,
      "learning_rate": 0.003,
      "loss": 3.191214294433594,
      "step": 102800
    },
    {
      "epoch": 0.22478844163610595,
      "grad_norm": 0.15815363824367523,
      "learning_rate": 0.003,
      "loss": 3.1885943603515625,
      "step": 102900
    },
    {
      "epoch": 0.2250068949321566,
      "grad_norm": 0.19354431331157684,
      "learning_rate": 0.003,
      "loss": 3.1964739990234374,
      "step": 103000
    },
    {
      "epoch": 0.22522534822820722,
      "grad_norm": 0.16281826794147491,
      "learning_rate": 0.003,
      "loss": 3.2205325317382814,
      "step": 103100
    },
    {
      "epoch": 0.2254438015242579,
      "grad_norm": 0.173141747713089,
      "learning_rate": 0.003,
      "loss": 3.1859710693359373,
      "step": 103200
    },
    {
      "epoch": 0.22566225482030852,
      "grad_norm": 0.1682673543691635,
      "learning_rate": 0.003,
      "loss": 3.196368408203125,
      "step": 103300
    },
    {
      "epoch": 0.22588070811635916,
      "grad_norm": 0.20099574327468872,
      "learning_rate": 0.003,
      "loss": 3.1951303100585937,
      "step": 103400
    },
    {
      "epoch": 0.2260991614124098,
      "grad_norm": 0.18030375242233276,
      "learning_rate": 0.003,
      "loss": 3.2207177734375,
      "step": 103500
    },
    {
      "epoch": 0.22631761470846043,
      "grad_norm": 0.21371352672576904,
      "learning_rate": 0.003,
      "loss": 3.184823303222656,
      "step": 103600
    },
    {
      "epoch": 0.22653606800451107,
      "grad_norm": 0.17467491328716278,
      "learning_rate": 0.003,
      "loss": 3.2101016235351563,
      "step": 103700
    },
    {
      "epoch": 0.2267545213005617,
      "grad_norm": 0.18792425096035004,
      "learning_rate": 0.003,
      "loss": 3.1528106689453126,
      "step": 103800
    },
    {
      "epoch": 0.22697297459661234,
      "grad_norm": 0.238530233502388,
      "learning_rate": 0.003,
      "loss": 3.1868878173828126,
      "step": 103900
    },
    {
      "epoch": 0.22719142789266297,
      "grad_norm": 0.155843123793602,
      "learning_rate": 0.003,
      "loss": 3.170243225097656,
      "step": 104000
    },
    {
      "epoch": 0.2274098811887136,
      "grad_norm": 0.18454401195049286,
      "learning_rate": 0.003,
      "loss": 3.1931134033203126,
      "step": 104100
    },
    {
      "epoch": 0.22762833448476424,
      "grad_norm": 0.1799052506685257,
      "learning_rate": 0.003,
      "loss": 3.1812493896484373,
      "step": 104200
    },
    {
      "epoch": 0.22784678778081488,
      "grad_norm": 0.21381621062755585,
      "learning_rate": 0.003,
      "loss": 3.172951965332031,
      "step": 104300
    },
    {
      "epoch": 0.22806524107686552,
      "grad_norm": 0.13922972977161407,
      "learning_rate": 0.003,
      "loss": 3.1882305908203126,
      "step": 104400
    },
    {
      "epoch": 0.22828369437291615,
      "grad_norm": 0.15168224275112152,
      "learning_rate": 0.003,
      "loss": 3.2093801879882813,
      "step": 104500
    },
    {
      "epoch": 0.2285021476689668,
      "grad_norm": 0.23901334404945374,
      "learning_rate": 0.003,
      "loss": 3.165443115234375,
      "step": 104600
    },
    {
      "epoch": 0.22872060096501742,
      "grad_norm": 0.16107922792434692,
      "learning_rate": 0.003,
      "loss": 3.2130291748046873,
      "step": 104700
    },
    {
      "epoch": 0.22893905426106806,
      "grad_norm": 0.8439098596572876,
      "learning_rate": 0.003,
      "loss": 3.19970947265625,
      "step": 104800
    },
    {
      "epoch": 0.22915750755711872,
      "grad_norm": 0.15786705911159515,
      "learning_rate": 0.003,
      "loss": 3.1903897094726563,
      "step": 104900
    },
    {
      "epoch": 0.22937596085316936,
      "grad_norm": 0.15847380459308624,
      "learning_rate": 0.003,
      "loss": 3.189295349121094,
      "step": 105000
    },
    {
      "epoch": 0.22959441414922,
      "grad_norm": 0.32766076922416687,
      "learning_rate": 0.003,
      "loss": 3.1828533935546877,
      "step": 105100
    },
    {
      "epoch": 0.22981286744527063,
      "grad_norm": 0.18468038737773895,
      "learning_rate": 0.003,
      "loss": 3.196568908691406,
      "step": 105200
    },
    {
      "epoch": 0.23003132074132127,
      "grad_norm": 0.1972939521074295,
      "learning_rate": 0.003,
      "loss": 3.159031982421875,
      "step": 105300
    },
    {
      "epoch": 0.2302497740373719,
      "grad_norm": 0.18358947336673737,
      "learning_rate": 0.003,
      "loss": 3.173365478515625,
      "step": 105400
    },
    {
      "epoch": 0.23046822733342254,
      "grad_norm": 0.19217951595783234,
      "learning_rate": 0.003,
      "loss": 3.2317135620117186,
      "step": 105500
    },
    {
      "epoch": 0.23068668062947317,
      "grad_norm": 0.17112338542938232,
      "learning_rate": 0.003,
      "loss": 3.205096435546875,
      "step": 105600
    },
    {
      "epoch": 0.2309051339255238,
      "grad_norm": 0.14539970457553864,
      "learning_rate": 0.003,
      "loss": 3.1683807373046875,
      "step": 105700
    },
    {
      "epoch": 0.23112358722157444,
      "grad_norm": 0.15848980844020844,
      "learning_rate": 0.003,
      "loss": 3.219859313964844,
      "step": 105800
    },
    {
      "epoch": 0.23134204051762508,
      "grad_norm": 0.20147928595542908,
      "learning_rate": 0.003,
      "loss": 3.177248840332031,
      "step": 105900
    },
    {
      "epoch": 0.23156049381367572,
      "grad_norm": 0.1637161672115326,
      "learning_rate": 0.003,
      "loss": 3.2011764526367186,
      "step": 106000
    },
    {
      "epoch": 0.23177894710972635,
      "grad_norm": 0.20364221930503845,
      "learning_rate": 0.003,
      "loss": 3.1972198486328125,
      "step": 106100
    },
    {
      "epoch": 0.231997400405777,
      "grad_norm": 0.15852341055870056,
      "learning_rate": 0.003,
      "loss": 3.1781005859375,
      "step": 106200
    },
    {
      "epoch": 0.23221585370182762,
      "grad_norm": 0.2659218907356262,
      "learning_rate": 0.003,
      "loss": 3.2024310302734373,
      "step": 106300
    },
    {
      "epoch": 0.23243430699787826,
      "grad_norm": 0.15729771554470062,
      "learning_rate": 0.003,
      "loss": 3.1765545654296874,
      "step": 106400
    },
    {
      "epoch": 0.23265276029392892,
      "grad_norm": 0.16436509788036346,
      "learning_rate": 0.003,
      "loss": 3.2103701782226564,
      "step": 106500
    },
    {
      "epoch": 0.23287121358997956,
      "grad_norm": 0.22796779870986938,
      "learning_rate": 0.003,
      "loss": 3.211387939453125,
      "step": 106600
    },
    {
      "epoch": 0.2330896668860302,
      "grad_norm": 0.18208400905132294,
      "learning_rate": 0.003,
      "loss": 3.1726083374023437,
      "step": 106700
    },
    {
      "epoch": 0.23330812018208083,
      "grad_norm": 0.18015295267105103,
      "learning_rate": 0.003,
      "loss": 3.1254708862304685,
      "step": 106800
    },
    {
      "epoch": 0.23352657347813147,
      "grad_norm": 0.1717136651277542,
      "learning_rate": 0.003,
      "loss": 3.19731201171875,
      "step": 106900
    },
    {
      "epoch": 0.2337450267741821,
      "grad_norm": 0.23622432351112366,
      "learning_rate": 0.003,
      "loss": 3.1919650268554687,
      "step": 107000
    },
    {
      "epoch": 0.23396348007023274,
      "grad_norm": 0.148057758808136,
      "learning_rate": 0.003,
      "loss": 3.17125244140625,
      "step": 107100
    },
    {
      "epoch": 0.23418193336628337,
      "grad_norm": 0.14156973361968994,
      "learning_rate": 0.003,
      "loss": 3.201607666015625,
      "step": 107200
    },
    {
      "epoch": 0.234400386662334,
      "grad_norm": 0.3278632164001465,
      "learning_rate": 0.003,
      "loss": 3.1915264892578126,
      "step": 107300
    },
    {
      "epoch": 0.23461883995838465,
      "grad_norm": 0.18710091710090637,
      "learning_rate": 0.003,
      "loss": 3.249506530761719,
      "step": 107400
    },
    {
      "epoch": 0.23483729325443528,
      "grad_norm": 0.1827370971441269,
      "learning_rate": 0.003,
      "loss": 3.201341247558594,
      "step": 107500
    },
    {
      "epoch": 0.23505574655048592,
      "grad_norm": 0.24463097751140594,
      "learning_rate": 0.003,
      "loss": 3.2041506958007813,
      "step": 107600
    },
    {
      "epoch": 0.23527419984653655,
      "grad_norm": 0.1820523589849472,
      "learning_rate": 0.003,
      "loss": 3.2394415283203126,
      "step": 107700
    },
    {
      "epoch": 0.2354926531425872,
      "grad_norm": 0.17374499142169952,
      "learning_rate": 0.003,
      "loss": 3.229110107421875,
      "step": 107800
    },
    {
      "epoch": 0.23571110643863782,
      "grad_norm": 0.1483023315668106,
      "learning_rate": 0.003,
      "loss": 3.18363037109375,
      "step": 107900
    },
    {
      "epoch": 0.23592955973468846,
      "grad_norm": 0.17039185762405396,
      "learning_rate": 0.003,
      "loss": 3.2658441162109373,
      "step": 108000
    },
    {
      "epoch": 0.2361480130307391,
      "grad_norm": 0.1909257471561432,
      "learning_rate": 0.003,
      "loss": 3.2034756469726564,
      "step": 108100
    },
    {
      "epoch": 0.23636646632678976,
      "grad_norm": 0.1725386679172516,
      "learning_rate": 0.003,
      "loss": 3.2072048950195313,
      "step": 108200
    },
    {
      "epoch": 0.2365849196228404,
      "grad_norm": 0.14467132091522217,
      "learning_rate": 0.003,
      "loss": 3.1985675048828126,
      "step": 108300
    },
    {
      "epoch": 0.23680337291889103,
      "grad_norm": 0.1315174400806427,
      "learning_rate": 0.003,
      "loss": 3.2306289672851562,
      "step": 108400
    },
    {
      "epoch": 0.23702182621494167,
      "grad_norm": 0.14547792077064514,
      "learning_rate": 0.003,
      "loss": 3.2040252685546875,
      "step": 108500
    },
    {
      "epoch": 0.2372402795109923,
      "grad_norm": 0.1825241893529892,
      "learning_rate": 0.003,
      "loss": 3.1949697875976564,
      "step": 108600
    },
    {
      "epoch": 0.23745873280704294,
      "grad_norm": 0.1727125644683838,
      "learning_rate": 0.003,
      "loss": 3.2289556884765624,
      "step": 108700
    },
    {
      "epoch": 0.23767718610309357,
      "grad_norm": 0.24597737193107605,
      "learning_rate": 0.003,
      "loss": 3.223450012207031,
      "step": 108800
    },
    {
      "epoch": 0.2378956393991442,
      "grad_norm": 0.1414637416601181,
      "learning_rate": 0.003,
      "loss": 3.232257080078125,
      "step": 108900
    },
    {
      "epoch": 0.23811409269519485,
      "grad_norm": 0.15455834567546844,
      "learning_rate": 0.003,
      "loss": 3.2108209228515623,
      "step": 109000
    },
    {
      "epoch": 0.23833254599124548,
      "grad_norm": 0.2669357359409332,
      "learning_rate": 0.003,
      "loss": 3.1880422973632814,
      "step": 109100
    },
    {
      "epoch": 0.23855099928729612,
      "grad_norm": 0.19473835825920105,
      "learning_rate": 0.003,
      "loss": 3.1808990478515624,
      "step": 109200
    },
    {
      "epoch": 0.23876945258334675,
      "grad_norm": 0.17744936048984528,
      "learning_rate": 0.003,
      "loss": 3.1810150146484375,
      "step": 109300
    },
    {
      "epoch": 0.2389879058793974,
      "grad_norm": 0.1516321897506714,
      "learning_rate": 0.003,
      "loss": 3.1612823486328123,
      "step": 109400
    },
    {
      "epoch": 0.23920635917544802,
      "grad_norm": 0.2026938945055008,
      "learning_rate": 0.003,
      "loss": 3.2155911254882814,
      "step": 109500
    },
    {
      "epoch": 0.23942481247149866,
      "grad_norm": 0.21379505097866058,
      "learning_rate": 0.003,
      "loss": 3.2127227783203125,
      "step": 109600
    },
    {
      "epoch": 0.2396432657675493,
      "grad_norm": 0.13985757529735565,
      "learning_rate": 0.003,
      "loss": 3.2153839111328124,
      "step": 109700
    },
    {
      "epoch": 0.23986171906359996,
      "grad_norm": 0.2607848346233368,
      "learning_rate": 0.003,
      "loss": 3.1715011596679688,
      "step": 109800
    },
    {
      "epoch": 0.2400801723596506,
      "grad_norm": 0.2337099313735962,
      "learning_rate": 0.003,
      "loss": 3.1352163696289064,
      "step": 109900
    },
    {
      "epoch": 0.24029862565570123,
      "grad_norm": 0.1557885706424713,
      "learning_rate": 0.003,
      "loss": 3.203826904296875,
      "step": 110000
    },
    {
      "epoch": 0.24051707895175187,
      "grad_norm": 0.15149317681789398,
      "learning_rate": 0.003,
      "loss": 3.1457794189453123,
      "step": 110100
    },
    {
      "epoch": 0.2407355322478025,
      "grad_norm": 0.2450362741947174,
      "learning_rate": 0.003,
      "loss": 3.1606707763671875,
      "step": 110200
    },
    {
      "epoch": 0.24095398554385314,
      "grad_norm": 0.19675183296203613,
      "learning_rate": 0.003,
      "loss": 3.136336669921875,
      "step": 110300
    },
    {
      "epoch": 0.24117243883990377,
      "grad_norm": 0.17948362231254578,
      "learning_rate": 0.003,
      "loss": 3.158858642578125,
      "step": 110400
    },
    {
      "epoch": 0.2413908921359544,
      "grad_norm": 0.16643723845481873,
      "learning_rate": 0.003,
      "loss": 3.157088623046875,
      "step": 110500
    },
    {
      "epoch": 0.24160934543200505,
      "grad_norm": 0.14619401097297668,
      "learning_rate": 0.003,
      "loss": 3.132615051269531,
      "step": 110600
    },
    {
      "epoch": 0.24182779872805568,
      "grad_norm": 0.17994770407676697,
      "learning_rate": 0.003,
      "loss": 3.145055236816406,
      "step": 110700
    },
    {
      "epoch": 0.24204625202410632,
      "grad_norm": 0.19818727672100067,
      "learning_rate": 0.003,
      "loss": 3.173731689453125,
      "step": 110800
    },
    {
      "epoch": 0.24226470532015695,
      "grad_norm": 0.14523686468601227,
      "learning_rate": 0.003,
      "loss": 3.1580401611328126,
      "step": 110900
    },
    {
      "epoch": 0.2424831586162076,
      "grad_norm": 0.16975483298301697,
      "learning_rate": 0.003,
      "loss": 3.1509103393554687,
      "step": 111000
    },
    {
      "epoch": 0.24270161191225822,
      "grad_norm": 0.1531265527009964,
      "learning_rate": 0.003,
      "loss": 3.1599996948242186,
      "step": 111100
    },
    {
      "epoch": 0.24292006520830886,
      "grad_norm": 0.15926402807235718,
      "learning_rate": 0.003,
      "loss": 3.142339172363281,
      "step": 111200
    },
    {
      "epoch": 0.2431385185043595,
      "grad_norm": 0.20109127461910248,
      "learning_rate": 0.003,
      "loss": 3.1263226318359374,
      "step": 111300
    },
    {
      "epoch": 0.24335697180041013,
      "grad_norm": 0.19264379143714905,
      "learning_rate": 0.003,
      "loss": 3.138429870605469,
      "step": 111400
    },
    {
      "epoch": 0.2435754250964608,
      "grad_norm": 0.2017202228307724,
      "learning_rate": 0.003,
      "loss": 3.1567633056640627,
      "step": 111500
    },
    {
      "epoch": 0.24379387839251143,
      "grad_norm": 0.17149969935417175,
      "learning_rate": 0.003,
      "loss": 3.154873046875,
      "step": 111600
    },
    {
      "epoch": 0.24401233168856207,
      "grad_norm": 0.1989082247018814,
      "learning_rate": 0.003,
      "loss": 3.159642333984375,
      "step": 111700
    },
    {
      "epoch": 0.2442307849846127,
      "grad_norm": 0.20310066640377045,
      "learning_rate": 0.003,
      "loss": 3.1391470336914065,
      "step": 111800
    },
    {
      "epoch": 0.24444923828066334,
      "grad_norm": 0.1760169416666031,
      "learning_rate": 0.003,
      "loss": 3.1731060791015624,
      "step": 111900
    },
    {
      "epoch": 0.24466769157671397,
      "grad_norm": 0.16488592326641083,
      "learning_rate": 0.003,
      "loss": 3.17441650390625,
      "step": 112000
    },
    {
      "epoch": 0.2448861448727646,
      "grad_norm": 0.1397256851196289,
      "learning_rate": 0.003,
      "loss": 3.062320556640625,
      "step": 112100
    },
    {
      "epoch": 0.24510459816881525,
      "grad_norm": 0.1884027123451233,
      "learning_rate": 0.003,
      "loss": 3.170846252441406,
      "step": 112200
    },
    {
      "epoch": 0.24532305146486588,
      "grad_norm": 0.19250339269638062,
      "learning_rate": 0.003,
      "loss": 3.136485290527344,
      "step": 112300
    },
    {
      "epoch": 0.24554150476091652,
      "grad_norm": 0.155894473195076,
      "learning_rate": 0.003,
      "loss": 3.153933410644531,
      "step": 112400
    },
    {
      "epoch": 0.24575995805696715,
      "grad_norm": 0.15026205778121948,
      "learning_rate": 0.003,
      "loss": 3.1478778076171876,
      "step": 112500
    },
    {
      "epoch": 0.2459784113530178,
      "grad_norm": 0.1964258998632431,
      "learning_rate": 0.003,
      "loss": 3.173653259277344,
      "step": 112600
    },
    {
      "epoch": 0.24619686464906843,
      "grad_norm": 0.16881966590881348,
      "learning_rate": 0.003,
      "loss": 3.2006106567382813,
      "step": 112700
    },
    {
      "epoch": 0.24641531794511906,
      "grad_norm": 0.189187154173851,
      "learning_rate": 0.003,
      "loss": 3.164288330078125,
      "step": 112800
    },
    {
      "epoch": 0.2466337712411697,
      "grad_norm": 0.16848815977573395,
      "learning_rate": 0.003,
      "loss": 3.1316644287109376,
      "step": 112900
    },
    {
      "epoch": 0.24685222453722033,
      "grad_norm": 0.15248990058898926,
      "learning_rate": 0.003,
      "loss": 3.1296035766601564,
      "step": 113000
    },
    {
      "epoch": 0.247070677833271,
      "grad_norm": 0.21292132139205933,
      "learning_rate": 0.003,
      "loss": 3.1329031372070313,
      "step": 113100
    },
    {
      "epoch": 0.24728913112932163,
      "grad_norm": 0.22059094905853271,
      "learning_rate": 0.003,
      "loss": 3.133268127441406,
      "step": 113200
    },
    {
      "epoch": 0.24750758442537227,
      "grad_norm": 0.16975048184394836,
      "learning_rate": 0.003,
      "loss": 3.1503656005859373,
      "step": 113300
    },
    {
      "epoch": 0.2477260377214229,
      "grad_norm": 0.18195408582687378,
      "learning_rate": 0.003,
      "loss": 3.1662640380859375,
      "step": 113400
    },
    {
      "epoch": 0.24794449101747354,
      "grad_norm": 0.16216278076171875,
      "learning_rate": 0.003,
      "loss": 3.1075955200195313,
      "step": 113500
    },
    {
      "epoch": 0.24816294431352418,
      "grad_norm": 0.2042403370141983,
      "learning_rate": 0.003,
      "loss": 3.1465740966796876,
      "step": 113600
    },
    {
      "epoch": 0.2483813976095748,
      "grad_norm": 0.17982223629951477,
      "learning_rate": 0.003,
      "loss": 2.918134765625,
      "step": 113700
    },
    {
      "epoch": 0.24859985090562545,
      "grad_norm": 0.16524387896060944,
      "learning_rate": 0.003,
      "loss": 3.1114352416992186,
      "step": 113800
    },
    {
      "epoch": 0.24881830420167608,
      "grad_norm": 0.1808774620294571,
      "learning_rate": 0.003,
      "loss": 3.1193252563476563,
      "step": 113900
    },
    {
      "epoch": 0.24903675749772672,
      "grad_norm": 0.18143890798091888,
      "learning_rate": 0.003,
      "loss": 3.146431579589844,
      "step": 114000
    },
    {
      "epoch": 0.24925521079377735,
      "grad_norm": 0.1492440104484558,
      "learning_rate": 0.003,
      "loss": 3.187480773925781,
      "step": 114100
    },
    {
      "epoch": 0.249473664089828,
      "grad_norm": 0.23453925549983978,
      "learning_rate": 0.003,
      "loss": 3.08376220703125,
      "step": 114200
    },
    {
      "epoch": 0.24969211738587863,
      "grad_norm": 0.18290016055107117,
      "learning_rate": 0.003,
      "loss": 3.118404541015625,
      "step": 114300
    },
    {
      "epoch": 0.24991057068192926,
      "grad_norm": 0.16905197501182556,
      "learning_rate": 0.003,
      "loss": 3.1375994873046875,
      "step": 114400
    },
    {
      "epoch": 0.2501290239779799,
      "grad_norm": 0.17251262068748474,
      "learning_rate": 0.003,
      "loss": 3.1640499877929686,
      "step": 114500
    },
    {
      "epoch": 0.25034747727403056,
      "grad_norm": 0.16715526580810547,
      "learning_rate": 0.003,
      "loss": 3.1812918090820315,
      "step": 114600
    },
    {
      "epoch": 0.2505659305700812,
      "grad_norm": 0.18836091458797455,
      "learning_rate": 0.003,
      "loss": 3.099549560546875,
      "step": 114700
    },
    {
      "epoch": 0.25078438386613183,
      "grad_norm": 0.24706906080245972,
      "learning_rate": 0.003,
      "loss": 3.1219192504882813,
      "step": 114800
    },
    {
      "epoch": 0.25100283716218247,
      "grad_norm": 0.16439929604530334,
      "learning_rate": 0.003,
      "loss": 3.087160339355469,
      "step": 114900
    },
    {
      "epoch": 0.2512212904582331,
      "grad_norm": 0.21023960411548615,
      "learning_rate": 0.003,
      "loss": 3.158519287109375,
      "step": 115000
    },
    {
      "epoch": 0.25143974375428374,
      "grad_norm": 0.15426918864250183,
      "learning_rate": 0.003,
      "loss": 3.1479229736328125,
      "step": 115100
    },
    {
      "epoch": 0.2516581970503344,
      "grad_norm": 0.16378799080848694,
      "learning_rate": 0.003,
      "loss": 3.16879638671875,
      "step": 115200
    },
    {
      "epoch": 0.251876650346385,
      "grad_norm": 0.15669791400432587,
      "learning_rate": 0.003,
      "loss": 3.1172305297851564,
      "step": 115300
    },
    {
      "epoch": 0.25209510364243565,
      "grad_norm": 0.24460077285766602,
      "learning_rate": 0.003,
      "loss": 3.130740966796875,
      "step": 115400
    },
    {
      "epoch": 0.2523135569384863,
      "grad_norm": 0.22701039910316467,
      "learning_rate": 0.003,
      "loss": 3.143014221191406,
      "step": 115500
    },
    {
      "epoch": 0.2525320102345369,
      "grad_norm": 0.18664608895778656,
      "learning_rate": 0.003,
      "loss": 3.1169943237304687,
      "step": 115600
    },
    {
      "epoch": 0.25275046353058755,
      "grad_norm": 0.1917290985584259,
      "learning_rate": 0.003,
      "loss": 3.132640075683594,
      "step": 115700
    },
    {
      "epoch": 0.2529689168266382,
      "grad_norm": 0.14543747901916504,
      "learning_rate": 0.003,
      "loss": 3.174365234375,
      "step": 115800
    },
    {
      "epoch": 0.2531873701226888,
      "grad_norm": 0.19407229125499725,
      "learning_rate": 0.003,
      "loss": 3.1486831665039063,
      "step": 115900
    },
    {
      "epoch": 0.25340582341873946,
      "grad_norm": 0.16081637144088745,
      "learning_rate": 0.003,
      "loss": 2.9254141235351563,
      "step": 116000
    },
    {
      "epoch": 0.2536242767147901,
      "grad_norm": 0.20264428853988647,
      "learning_rate": 0.003,
      "loss": 3.1475180053710936,
      "step": 116100
    },
    {
      "epoch": 0.25384273001084073,
      "grad_norm": 0.13481463491916656,
      "learning_rate": 0.003,
      "loss": 3.129048156738281,
      "step": 116200
    },
    {
      "epoch": 0.25406118330689137,
      "grad_norm": 0.16611292958259583,
      "learning_rate": 0.003,
      "loss": 3.1350830078125,
      "step": 116300
    },
    {
      "epoch": 0.254279636602942,
      "grad_norm": 0.18687981367111206,
      "learning_rate": 0.003,
      "loss": 3.135335693359375,
      "step": 116400
    },
    {
      "epoch": 0.25449808989899264,
      "grad_norm": 0.2523234188556671,
      "learning_rate": 0.003,
      "loss": 3.1152474975585935,
      "step": 116500
    },
    {
      "epoch": 0.2547165431950433,
      "grad_norm": 0.18094249069690704,
      "learning_rate": 0.003,
      "loss": 3.1234640502929687,
      "step": 116600
    },
    {
      "epoch": 0.2549349964910939,
      "grad_norm": 0.20491555333137512,
      "learning_rate": 0.003,
      "loss": 3.1479095458984374,
      "step": 116700
    },
    {
      "epoch": 0.25515344978714455,
      "grad_norm": 0.20158524811267853,
      "learning_rate": 0.003,
      "loss": 3.1634478759765625,
      "step": 116800
    },
    {
      "epoch": 0.2553719030831952,
      "grad_norm": 0.20101554691791534,
      "learning_rate": 0.003,
      "loss": 3.1396548461914064,
      "step": 116900
    },
    {
      "epoch": 0.2555903563792458,
      "grad_norm": 0.1438259780406952,
      "learning_rate": 0.003,
      "loss": 3.1369644165039063,
      "step": 117000
    },
    {
      "epoch": 0.25580880967529646,
      "grad_norm": 0.1390850841999054,
      "learning_rate": 0.003,
      "loss": 3.139820251464844,
      "step": 117100
    },
    {
      "epoch": 0.25602726297134715,
      "grad_norm": 0.1506982147693634,
      "learning_rate": 0.003,
      "loss": 3.1354669189453124,
      "step": 117200
    },
    {
      "epoch": 0.2562457162673978,
      "grad_norm": 0.16565769910812378,
      "learning_rate": 0.003,
      "loss": 3.146010437011719,
      "step": 117300
    },
    {
      "epoch": 0.2564641695634484,
      "grad_norm": 0.13977010548114777,
      "learning_rate": 0.003,
      "loss": 3.1299252319335937,
      "step": 117400
    },
    {
      "epoch": 0.25668262285949905,
      "grad_norm": 0.19699348509311676,
      "learning_rate": 0.003,
      "loss": 3.121324462890625,
      "step": 117500
    },
    {
      "epoch": 0.2569010761555497,
      "grad_norm": 0.15574857592582703,
      "learning_rate": 0.003,
      "loss": 3.154246826171875,
      "step": 117600
    },
    {
      "epoch": 0.2571195294516003,
      "grad_norm": 0.16224879026412964,
      "learning_rate": 0.003,
      "loss": 3.1255767822265623,
      "step": 117700
    },
    {
      "epoch": 0.25733798274765096,
      "grad_norm": 0.19783753156661987,
      "learning_rate": 0.003,
      "loss": 3.1510748291015624,
      "step": 117800
    },
    {
      "epoch": 0.2575564360437016,
      "grad_norm": 0.1567201316356659,
      "learning_rate": 0.003,
      "loss": 3.068137512207031,
      "step": 117900
    },
    {
      "epoch": 0.25777488933975223,
      "grad_norm": 0.23760242760181427,
      "learning_rate": 0.003,
      "loss": 3.13155517578125,
      "step": 118000
    },
    {
      "epoch": 0.25799334263580287,
      "grad_norm": 0.19157196581363678,
      "learning_rate": 0.003,
      "loss": 3.1604299926757813,
      "step": 118100
    },
    {
      "epoch": 0.2582117959318535,
      "grad_norm": 0.23139914870262146,
      "learning_rate": 0.003,
      "loss": 3.1489080810546874,
      "step": 118200
    },
    {
      "epoch": 0.25843024922790414,
      "grad_norm": 0.1830720454454422,
      "learning_rate": 0.003,
      "loss": 3.091242370605469,
      "step": 118300
    },
    {
      "epoch": 0.2586487025239548,
      "grad_norm": 0.20480267703533173,
      "learning_rate": 0.003,
      "loss": 3.141184997558594,
      "step": 118400
    },
    {
      "epoch": 0.2588671558200054,
      "grad_norm": 0.16266120970249176,
      "learning_rate": 0.003,
      "loss": 3.160396728515625,
      "step": 118500
    },
    {
      "epoch": 0.25908560911605605,
      "grad_norm": 0.18189287185668945,
      "learning_rate": 0.003,
      "loss": 3.1183380126953124,
      "step": 118600
    },
    {
      "epoch": 0.2593040624121067,
      "grad_norm": 0.18481861054897308,
      "learning_rate": 0.003,
      "loss": 3.142648010253906,
      "step": 118700
    },
    {
      "epoch": 0.2595225157081573,
      "grad_norm": 0.20861801505088806,
      "learning_rate": 0.003,
      "loss": 3.122877197265625,
      "step": 118800
    },
    {
      "epoch": 0.25974096900420796,
      "grad_norm": 0.16465097665786743,
      "learning_rate": 0.003,
      "loss": 3.157867126464844,
      "step": 118900
    },
    {
      "epoch": 0.2599594223002586,
      "grad_norm": 0.1347455084323883,
      "learning_rate": 0.003,
      "loss": 3.126204833984375,
      "step": 119000
    },
    {
      "epoch": 0.2601778755963092,
      "grad_norm": 0.22783678770065308,
      "learning_rate": 0.003,
      "loss": 3.1145480346679686,
      "step": 119100
    },
    {
      "epoch": 0.26039632889235986,
      "grad_norm": 0.18908102810382843,
      "learning_rate": 0.003,
      "loss": 3.1435897827148436,
      "step": 119200
    },
    {
      "epoch": 0.2606147821884105,
      "grad_norm": 0.2350047528743744,
      "learning_rate": 0.003,
      "loss": 3.1211563110351563,
      "step": 119300
    },
    {
      "epoch": 0.26083323548446113,
      "grad_norm": 0.16897456347942352,
      "learning_rate": 0.003,
      "loss": 3.1367947387695314,
      "step": 119400
    },
    {
      "epoch": 0.26105168878051177,
      "grad_norm": 0.16670124232769012,
      "learning_rate": 0.003,
      "loss": 3.121427307128906,
      "step": 119500
    },
    {
      "epoch": 0.2612701420765624,
      "grad_norm": 0.1661265641450882,
      "learning_rate": 0.003,
      "loss": 3.096488037109375,
      "step": 119600
    },
    {
      "epoch": 0.26148859537261304,
      "grad_norm": 0.16746363043785095,
      "learning_rate": 0.003,
      "loss": 3.1369305419921876,
      "step": 119700
    },
    {
      "epoch": 0.2617070486686637,
      "grad_norm": 0.16642019152641296,
      "learning_rate": 0.003,
      "loss": 3.123088073730469,
      "step": 119800
    },
    {
      "epoch": 0.2619255019647143,
      "grad_norm": 0.352807879447937,
      "learning_rate": 0.003,
      "loss": 3.11847900390625,
      "step": 119900
    },
    {
      "epoch": 0.26214395526076495,
      "grad_norm": 0.282635360956192,
      "learning_rate": 0.003,
      "loss": 3.1500448608398437,
      "step": 120000
    },
    {
      "epoch": 0.2623624085568156,
      "grad_norm": 0.17607861757278442,
      "learning_rate": 0.003,
      "loss": 3.1523980712890625,
      "step": 120100
    },
    {
      "epoch": 0.2625808618528662,
      "grad_norm": 0.20902930200099945,
      "learning_rate": 0.003,
      "loss": 3.12585205078125,
      "step": 120200
    },
    {
      "epoch": 0.26279931514891686,
      "grad_norm": 0.16336879134178162,
      "learning_rate": 0.003,
      "loss": 3.1010125732421874,
      "step": 120300
    },
    {
      "epoch": 0.2630177684449675,
      "grad_norm": 0.17145244777202606,
      "learning_rate": 0.003,
      "loss": 3.1193792724609377,
      "step": 120400
    },
    {
      "epoch": 0.2632362217410182,
      "grad_norm": 0.1874585896730423,
      "learning_rate": 0.003,
      "loss": 3.112429504394531,
      "step": 120500
    },
    {
      "epoch": 0.2634546750370688,
      "grad_norm": 0.16599197685718536,
      "learning_rate": 0.003,
      "loss": 3.1309783935546873,
      "step": 120600
    },
    {
      "epoch": 0.26367312833311946,
      "grad_norm": 0.22470302879810333,
      "learning_rate": 0.003,
      "loss": 3.0979190063476563,
      "step": 120700
    },
    {
      "epoch": 0.2638915816291701,
      "grad_norm": 0.25222650170326233,
      "learning_rate": 0.003,
      "loss": 3.1603189086914063,
      "step": 120800
    },
    {
      "epoch": 0.2641100349252207,
      "grad_norm": 0.15623459219932556,
      "learning_rate": 0.003,
      "loss": 3.146209411621094,
      "step": 120900
    },
    {
      "epoch": 0.26432848822127136,
      "grad_norm": 0.19765418767929077,
      "learning_rate": 0.003,
      "loss": 3.118283996582031,
      "step": 121000
    },
    {
      "epoch": 0.264546941517322,
      "grad_norm": 0.27228718996047974,
      "learning_rate": 0.003,
      "loss": 3.12953125,
      "step": 121100
    },
    {
      "epoch": 0.26476539481337263,
      "grad_norm": 0.19979190826416016,
      "learning_rate": 0.003,
      "loss": 3.1466134643554686,
      "step": 121200
    },
    {
      "epoch": 0.26498384810942327,
      "grad_norm": 0.18945246934890747,
      "learning_rate": 0.003,
      "loss": 3.1670947265625,
      "step": 121300
    },
    {
      "epoch": 0.2652023014054739,
      "grad_norm": 0.18201249837875366,
      "learning_rate": 0.003,
      "loss": 3.1588299560546873,
      "step": 121400
    },
    {
      "epoch": 0.26542075470152454,
      "grad_norm": 0.18221046030521393,
      "learning_rate": 0.003,
      "loss": 3.177774658203125,
      "step": 121500
    },
    {
      "epoch": 0.2656392079975752,
      "grad_norm": 0.178348109126091,
      "learning_rate": 0.003,
      "loss": 3.1504315185546874,
      "step": 121600
    },
    {
      "epoch": 0.2658576612936258,
      "grad_norm": 0.17613326013088226,
      "learning_rate": 0.003,
      "loss": 3.1706024169921876,
      "step": 121700
    },
    {
      "epoch": 0.26607611458967645,
      "grad_norm": 0.1819799244403839,
      "learning_rate": 0.003,
      "loss": 3.1582550048828124,
      "step": 121800
    },
    {
      "epoch": 0.2662945678857271,
      "grad_norm": 0.21169109642505646,
      "learning_rate": 0.003,
      "loss": 3.1287002563476562,
      "step": 121900
    },
    {
      "epoch": 0.2665130211817777,
      "grad_norm": 0.17658387124538422,
      "learning_rate": 0.003,
      "loss": 3.1393206787109373,
      "step": 122000
    },
    {
      "epoch": 0.26673147447782836,
      "grad_norm": 0.17100141942501068,
      "learning_rate": 0.003,
      "loss": 3.148631896972656,
      "step": 122100
    },
    {
      "epoch": 0.266949927773879,
      "grad_norm": 0.1690492033958435,
      "learning_rate": 0.003,
      "loss": 3.1369088745117186,
      "step": 122200
    },
    {
      "epoch": 0.26716838106992963,
      "grad_norm": 0.21133515238761902,
      "learning_rate": 0.003,
      "loss": 3.1234674072265625,
      "step": 122300
    },
    {
      "epoch": 0.26738683436598026,
      "grad_norm": 0.1449619084596634,
      "learning_rate": 0.003,
      "loss": 3.2062924194335936,
      "step": 122400
    },
    {
      "epoch": 0.2676052876620309,
      "grad_norm": 0.1649831086397171,
      "learning_rate": 0.003,
      "loss": 3.1165286254882814,
      "step": 122500
    },
    {
      "epoch": 0.26782374095808154,
      "grad_norm": 0.14208738505840302,
      "learning_rate": 0.003,
      "loss": 3.1222979736328127,
      "step": 122600
    },
    {
      "epoch": 0.26804219425413217,
      "grad_norm": 0.2803119421005249,
      "learning_rate": 0.003,
      "loss": 3.1634332275390626,
      "step": 122700
    },
    {
      "epoch": 0.2682606475501828,
      "grad_norm": 0.1829257309436798,
      "learning_rate": 0.003,
      "loss": 3.1225985717773437,
      "step": 122800
    },
    {
      "epoch": 0.26847910084623344,
      "grad_norm": 0.15668363869190216,
      "learning_rate": 0.003,
      "loss": 3.0825006103515626,
      "step": 122900
    },
    {
      "epoch": 0.2686975541422841,
      "grad_norm": 0.18942736089229584,
      "learning_rate": 0.003,
      "loss": 3.1140615844726565,
      "step": 123000
    },
    {
      "epoch": 0.2689160074383347,
      "grad_norm": 0.1751144975423813,
      "learning_rate": 0.003,
      "loss": 3.1174212646484376,
      "step": 123100
    },
    {
      "epoch": 0.26913446073438535,
      "grad_norm": 0.15149031579494476,
      "learning_rate": 0.003,
      "loss": 3.092795715332031,
      "step": 123200
    },
    {
      "epoch": 0.269352914030436,
      "grad_norm": 0.146224707365036,
      "learning_rate": 0.003,
      "loss": 3.1540908813476562,
      "step": 123300
    },
    {
      "epoch": 0.2695713673264866,
      "grad_norm": 0.26576176285743713,
      "learning_rate": 0.003,
      "loss": 3.118391418457031,
      "step": 123400
    },
    {
      "epoch": 0.26978982062253726,
      "grad_norm": 0.17119044065475464,
      "learning_rate": 0.003,
      "loss": 3.145680236816406,
      "step": 123500
    },
    {
      "epoch": 0.2700082739185879,
      "grad_norm": 0.18358702957630157,
      "learning_rate": 0.003,
      "loss": 3.122941589355469,
      "step": 123600
    },
    {
      "epoch": 0.27022672721463853,
      "grad_norm": 0.1615283489227295,
      "learning_rate": 0.003,
      "loss": 3.1004730224609376,
      "step": 123700
    },
    {
      "epoch": 0.2704451805106892,
      "grad_norm": 0.16417482495307922,
      "learning_rate": 0.003,
      "loss": 3.1084674072265623,
      "step": 123800
    },
    {
      "epoch": 0.27066363380673986,
      "grad_norm": 0.15363475680351257,
      "learning_rate": 0.003,
      "loss": 3.1380364990234373,
      "step": 123900
    },
    {
      "epoch": 0.2708820871027905,
      "grad_norm": 0.21433115005493164,
      "learning_rate": 0.003,
      "loss": 3.09521728515625,
      "step": 124000
    },
    {
      "epoch": 0.2711005403988411,
      "grad_norm": 0.16247905790805817,
      "learning_rate": 0.003,
      "loss": 2.980374755859375,
      "step": 124100
    },
    {
      "epoch": 0.27131899369489176,
      "grad_norm": 0.23055775463581085,
      "learning_rate": 0.003,
      "loss": 3.0912255859375,
      "step": 124200
    },
    {
      "epoch": 0.2715374469909424,
      "grad_norm": 0.17991212010383606,
      "learning_rate": 0.003,
      "loss": 3.075794677734375,
      "step": 124300
    },
    {
      "epoch": 0.27175590028699304,
      "grad_norm": 0.15245744585990906,
      "learning_rate": 0.003,
      "loss": 3.1302386474609376,
      "step": 124400
    },
    {
      "epoch": 0.27197435358304367,
      "grad_norm": 0.22990760207176208,
      "learning_rate": 0.003,
      "loss": 3.0966201782226563,
      "step": 124500
    },
    {
      "epoch": 0.2721928068790943,
      "grad_norm": 0.14952386915683746,
      "learning_rate": 0.003,
      "loss": 3.107850341796875,
      "step": 124600
    },
    {
      "epoch": 0.27241126017514494,
      "grad_norm": 0.1720409095287323,
      "learning_rate": 0.003,
      "loss": 3.147486572265625,
      "step": 124700
    },
    {
      "epoch": 0.2726297134711956,
      "grad_norm": 0.16717100143432617,
      "learning_rate": 0.003,
      "loss": 3.1709051513671875,
      "step": 124800
    },
    {
      "epoch": 0.2728481667672462,
      "grad_norm": 0.18736708164215088,
      "learning_rate": 0.003,
      "loss": 3.1149432373046877,
      "step": 124900
    },
    {
      "epoch": 0.27306662006329685,
      "grad_norm": 0.1759713888168335,
      "learning_rate": 0.003,
      "loss": 3.0998104858398436,
      "step": 125000
    },
    {
      "epoch": 0.2732850733593475,
      "grad_norm": 0.2139262855052948,
      "learning_rate": 0.003,
      "loss": 3.0760043334960936,
      "step": 125100
    },
    {
      "epoch": 0.2735035266553981,
      "grad_norm": 0.1517336070537567,
      "learning_rate": 0.003,
      "loss": 3.1243695068359374,
      "step": 125200
    },
    {
      "epoch": 0.27372197995144876,
      "grad_norm": 0.15442916750907898,
      "learning_rate": 0.003,
      "loss": 3.1157635498046874,
      "step": 125300
    },
    {
      "epoch": 0.2739404332474994,
      "grad_norm": 0.1729786992073059,
      "learning_rate": 0.003,
      "loss": 3.130433349609375,
      "step": 125400
    },
    {
      "epoch": 0.27415888654355003,
      "grad_norm": 0.172031968832016,
      "learning_rate": 0.003,
      "loss": 3.114808349609375,
      "step": 125500
    },
    {
      "epoch": 0.27437733983960066,
      "grad_norm": 0.17771190404891968,
      "learning_rate": 0.003,
      "loss": 3.104170837402344,
      "step": 125600
    },
    {
      "epoch": 0.2745957931356513,
      "grad_norm": 0.18168313801288605,
      "learning_rate": 0.003,
      "loss": 3.0751837158203124,
      "step": 125700
    },
    {
      "epoch": 0.27481424643170194,
      "grad_norm": 0.16100353002548218,
      "learning_rate": 0.003,
      "loss": 3.1454086303710938,
      "step": 125800
    },
    {
      "epoch": 0.27503269972775257,
      "grad_norm": 0.2005414068698883,
      "learning_rate": 0.003,
      "loss": 3.121745910644531,
      "step": 125900
    },
    {
      "epoch": 0.2752511530238032,
      "grad_norm": 0.2184487283229828,
      "learning_rate": 0.003,
      "loss": 3.1026446533203127,
      "step": 126000
    },
    {
      "epoch": 0.27546960631985384,
      "grad_norm": 0.17234332859516144,
      "learning_rate": 0.003,
      "loss": 3.1335687255859375,
      "step": 126100
    },
    {
      "epoch": 0.2756880596159045,
      "grad_norm": 0.1576775461435318,
      "learning_rate": 0.003,
      "loss": 3.1129110717773436,
      "step": 126200
    },
    {
      "epoch": 0.2759065129119551,
      "grad_norm": 0.14490582048892975,
      "learning_rate": 0.003,
      "loss": 3.134710693359375,
      "step": 126300
    },
    {
      "epoch": 0.27612496620800575,
      "grad_norm": 0.23765777051448822,
      "learning_rate": 0.003,
      "loss": 3.111960754394531,
      "step": 126400
    },
    {
      "epoch": 0.2763434195040564,
      "grad_norm": 0.19747157394886017,
      "learning_rate": 0.003,
      "loss": 3.0904254150390624,
      "step": 126500
    },
    {
      "epoch": 0.276561872800107,
      "grad_norm": 0.2658751308917999,
      "learning_rate": 0.003,
      "loss": 3.0246206665039064,
      "step": 126600
    },
    {
      "epoch": 0.27678032609615766,
      "grad_norm": 0.1605808287858963,
      "learning_rate": 0.003,
      "loss": 3.0998355102539064,
      "step": 126700
    },
    {
      "epoch": 0.2769987793922083,
      "grad_norm": 0.165673166513443,
      "learning_rate": 0.003,
      "loss": 3.0695989990234374,
      "step": 126800
    },
    {
      "epoch": 0.27721723268825893,
      "grad_norm": 0.18814611434936523,
      "learning_rate": 0.003,
      "loss": 3.0552288818359377,
      "step": 126900
    },
    {
      "epoch": 0.27743568598430957,
      "grad_norm": 0.1825118511915207,
      "learning_rate": 0.003,
      "loss": 3.0807373046875,
      "step": 127000
    },
    {
      "epoch": 0.27765413928036026,
      "grad_norm": 0.17635834217071533,
      "learning_rate": 0.003,
      "loss": 3.0948751831054686,
      "step": 127100
    },
    {
      "epoch": 0.2778725925764109,
      "grad_norm": 0.2630055546760559,
      "learning_rate": 0.003,
      "loss": 3.0975680541992188,
      "step": 127200
    },
    {
      "epoch": 0.27809104587246153,
      "grad_norm": 0.24227474629878998,
      "learning_rate": 0.003,
      "loss": 3.055248107910156,
      "step": 127300
    },
    {
      "epoch": 0.27830949916851216,
      "grad_norm": 0.21120278537273407,
      "learning_rate": 0.003,
      "loss": 3.068297119140625,
      "step": 127400
    },
    {
      "epoch": 0.2785279524645628,
      "grad_norm": 0.3816051483154297,
      "learning_rate": 0.003,
      "loss": 3.0776156616210937,
      "step": 127500
    },
    {
      "epoch": 0.27874640576061344,
      "grad_norm": 0.16917425394058228,
      "learning_rate": 0.003,
      "loss": 3.0876223754882814,
      "step": 127600
    },
    {
      "epoch": 0.27896485905666407,
      "grad_norm": 0.20668604969978333,
      "learning_rate": 0.003,
      "loss": 3.204374084472656,
      "step": 127700
    },
    {
      "epoch": 0.2791833123527147,
      "grad_norm": 0.18532617390155792,
      "learning_rate": 0.003,
      "loss": 3.22772216796875,
      "step": 127800
    },
    {
      "epoch": 0.27940176564876534,
      "grad_norm": 0.1958247721195221,
      "learning_rate": 0.003,
      "loss": 3.193952941894531,
      "step": 127900
    },
    {
      "epoch": 0.279620218944816,
      "grad_norm": 0.22922642529010773,
      "learning_rate": 0.003,
      "loss": 3.187032470703125,
      "step": 128000
    },
    {
      "epoch": 0.2798386722408666,
      "grad_norm": 0.24574919044971466,
      "learning_rate": 0.003,
      "loss": 3.2100088500976565,
      "step": 128100
    },
    {
      "epoch": 0.28005712553691725,
      "grad_norm": 0.1636534333229065,
      "learning_rate": 0.003,
      "loss": 3.194091796875,
      "step": 128200
    },
    {
      "epoch": 0.2802755788329679,
      "grad_norm": 0.23779068887233734,
      "learning_rate": 0.003,
      "loss": 3.189336853027344,
      "step": 128300
    },
    {
      "epoch": 0.2804940321290185,
      "grad_norm": 0.16079804301261902,
      "learning_rate": 0.003,
      "loss": 3.1519854736328123,
      "step": 128400
    },
    {
      "epoch": 0.28071248542506916,
      "grad_norm": 0.1529242843389511,
      "learning_rate": 0.003,
      "loss": 3.179140625,
      "step": 128500
    },
    {
      "epoch": 0.2809309387211198,
      "grad_norm": 0.24319961667060852,
      "learning_rate": 0.003,
      "loss": 3.177486572265625,
      "step": 128600
    },
    {
      "epoch": 0.28114939201717043,
      "grad_norm": 0.18524886667728424,
      "learning_rate": 0.003,
      "loss": 3.190474548339844,
      "step": 128700
    },
    {
      "epoch": 0.28136784531322107,
      "grad_norm": 0.19689129292964935,
      "learning_rate": 0.003,
      "loss": 3.174749450683594,
      "step": 128800
    },
    {
      "epoch": 0.2815862986092717,
      "grad_norm": 0.21814829111099243,
      "learning_rate": 0.003,
      "loss": 3.2250634765625,
      "step": 128900
    },
    {
      "epoch": 0.28180475190532234,
      "grad_norm": 0.27080363035202026,
      "learning_rate": 0.003,
      "loss": 3.1633697509765626,
      "step": 129000
    },
    {
      "epoch": 0.282023205201373,
      "grad_norm": 0.18583400547504425,
      "learning_rate": 0.003,
      "loss": 3.1680859375,
      "step": 129100
    },
    {
      "epoch": 0.2822416584974236,
      "grad_norm": 0.3391522467136383,
      "learning_rate": 0.003,
      "loss": 3.1928253173828125,
      "step": 129200
    },
    {
      "epoch": 0.28246011179347424,
      "grad_norm": 0.23984627425670624,
      "learning_rate": 0.003,
      "loss": 3.1604623413085937,
      "step": 129300
    },
    {
      "epoch": 0.2826785650895249,
      "grad_norm": 0.19537843763828278,
      "learning_rate": 0.003,
      "loss": 3.2140252685546873,
      "step": 129400
    },
    {
      "epoch": 0.2828970183855755,
      "grad_norm": 0.16202545166015625,
      "learning_rate": 0.003,
      "loss": 3.1751544189453127,
      "step": 129500
    },
    {
      "epoch": 0.28311547168162615,
      "grad_norm": 0.15761688351631165,
      "learning_rate": 0.003,
      "loss": 3.1904876708984373,
      "step": 129600
    },
    {
      "epoch": 0.2833339249776768,
      "grad_norm": 0.24658435583114624,
      "learning_rate": 0.003,
      "loss": 3.164392395019531,
      "step": 129700
    },
    {
      "epoch": 0.2835523782737274,
      "grad_norm": 0.18049539625644684,
      "learning_rate": 0.003,
      "loss": 3.2037832641601565,
      "step": 129800
    },
    {
      "epoch": 0.28377083156977806,
      "grad_norm": 0.23034675419330597,
      "learning_rate": 0.003,
      "loss": 3.2158367919921873,
      "step": 129900
    },
    {
      "epoch": 0.2839892848658287,
      "grad_norm": 0.2013300359249115,
      "learning_rate": 0.003,
      "loss": 3.226523132324219,
      "step": 130000
    },
    {
      "epoch": 0.28420773816187933,
      "grad_norm": 0.1996563971042633,
      "learning_rate": 0.003,
      "loss": 3.176661376953125,
      "step": 130100
    },
    {
      "epoch": 0.28442619145792997,
      "grad_norm": 0.23476724326610565,
      "learning_rate": 0.003,
      "loss": 3.1794467163085938,
      "step": 130200
    },
    {
      "epoch": 0.2846446447539806,
      "grad_norm": 0.16203320026397705,
      "learning_rate": 0.003,
      "loss": 3.1501620483398436,
      "step": 130300
    },
    {
      "epoch": 0.2848630980500313,
      "grad_norm": 0.22591614723205566,
      "learning_rate": 0.003,
      "loss": 3.1584625244140625,
      "step": 130400
    },
    {
      "epoch": 0.28508155134608193,
      "grad_norm": 0.15424208343029022,
      "learning_rate": 0.003,
      "loss": 3.18368896484375,
      "step": 130500
    },
    {
      "epoch": 0.28530000464213257,
      "grad_norm": 0.1743527203798294,
      "learning_rate": 0.003,
      "loss": 3.1977545166015626,
      "step": 130600
    },
    {
      "epoch": 0.2855184579381832,
      "grad_norm": 0.15016095340251923,
      "learning_rate": 0.003,
      "loss": 3.175804443359375,
      "step": 130700
    },
    {
      "epoch": 0.28573691123423384,
      "grad_norm": 0.18600404262542725,
      "learning_rate": 0.003,
      "loss": 3.1796951293945312,
      "step": 130800
    },
    {
      "epoch": 0.2859553645302845,
      "grad_norm": 0.19670964777469635,
      "learning_rate": 0.003,
      "loss": 3.1544488525390624,
      "step": 130900
    },
    {
      "epoch": 0.2861738178263351,
      "grad_norm": 0.1564444750547409,
      "learning_rate": 0.003,
      "loss": 3.13692138671875,
      "step": 131000
    },
    {
      "epoch": 0.28639227112238574,
      "grad_norm": 0.1812867373228073,
      "learning_rate": 0.003,
      "loss": 3.164166259765625,
      "step": 131100
    },
    {
      "epoch": 0.2866107244184364,
      "grad_norm": 0.16804924607276917,
      "learning_rate": 0.003,
      "loss": 3.13121337890625,
      "step": 131200
    },
    {
      "epoch": 0.286829177714487,
      "grad_norm": 0.1703408658504486,
      "learning_rate": 0.003,
      "loss": 3.2148712158203123,
      "step": 131300
    },
    {
      "epoch": 0.28704763101053765,
      "grad_norm": 0.2654840052127838,
      "learning_rate": 0.003,
      "loss": 3.1748138427734376,
      "step": 131400
    },
    {
      "epoch": 0.2872660843065883,
      "grad_norm": 0.14809302985668182,
      "learning_rate": 0.003,
      "loss": 3.2007412719726562,
      "step": 131500
    },
    {
      "epoch": 0.2874845376026389,
      "grad_norm": 0.2317712903022766,
      "learning_rate": 0.003,
      "loss": 3.1763409423828124,
      "step": 131600
    },
    {
      "epoch": 0.28770299089868956,
      "grad_norm": 0.17288662493228912,
      "learning_rate": 0.003,
      "loss": 3.228929443359375,
      "step": 131700
    },
    {
      "epoch": 0.2879214441947402,
      "grad_norm": 0.15619529783725739,
      "learning_rate": 0.003,
      "loss": 3.1699227905273437,
      "step": 131800
    },
    {
      "epoch": 0.28813989749079083,
      "grad_norm": 0.20998290181159973,
      "learning_rate": 0.003,
      "loss": 3.1900537109375,
      "step": 131900
    },
    {
      "epoch": 0.28835835078684147,
      "grad_norm": 0.16902107000350952,
      "learning_rate": 0.003,
      "loss": 3.1908218383789064,
      "step": 132000
    },
    {
      "epoch": 0.2885768040828921,
      "grad_norm": 0.17402586340904236,
      "learning_rate": 0.003,
      "loss": 3.1593307495117187,
      "step": 132100
    },
    {
      "epoch": 0.28879525737894274,
      "grad_norm": 0.2578791081905365,
      "learning_rate": 0.003,
      "loss": 3.1821502685546874,
      "step": 132200
    },
    {
      "epoch": 0.2890137106749934,
      "grad_norm": 0.1539982259273529,
      "learning_rate": 0.003,
      "loss": 3.24119140625,
      "step": 132300
    },
    {
      "epoch": 0.289232163971044,
      "grad_norm": 0.17721042037010193,
      "learning_rate": 0.003,
      "loss": 3.242032470703125,
      "step": 132400
    },
    {
      "epoch": 0.28945061726709465,
      "grad_norm": 0.16132225096225739,
      "learning_rate": 0.003,
      "loss": 3.213353576660156,
      "step": 132500
    },
    {
      "epoch": 0.2896690705631453,
      "grad_norm": 0.16307580471038818,
      "learning_rate": 0.003,
      "loss": 3.2237362670898437,
      "step": 132600
    },
    {
      "epoch": 0.2898875238591959,
      "grad_norm": 0.19305144250392914,
      "learning_rate": 0.003,
      "loss": 3.1388040161132813,
      "step": 132700
    },
    {
      "epoch": 0.29010597715524655,
      "grad_norm": 0.19119708240032196,
      "learning_rate": 0.003,
      "loss": 3.195961608886719,
      "step": 132800
    },
    {
      "epoch": 0.2903244304512972,
      "grad_norm": 0.20485588908195496,
      "learning_rate": 0.003,
      "loss": 3.1509246826171875,
      "step": 132900
    },
    {
      "epoch": 0.2905428837473478,
      "grad_norm": 0.21030651032924652,
      "learning_rate": 0.003,
      "loss": 3.201534423828125,
      "step": 133000
    },
    {
      "epoch": 0.29076133704339846,
      "grad_norm": 0.17510755360126495,
      "learning_rate": 0.003,
      "loss": 3.199417724609375,
      "step": 133100
    },
    {
      "epoch": 0.2909797903394491,
      "grad_norm": 0.32947033643722534,
      "learning_rate": 0.003,
      "loss": 3.2026324462890625,
      "step": 133200
    },
    {
      "epoch": 0.29119824363549973,
      "grad_norm": 0.20043914020061493,
      "learning_rate": 0.003,
      "loss": 3.182317199707031,
      "step": 133300
    },
    {
      "epoch": 0.29141669693155037,
      "grad_norm": 0.19705235958099365,
      "learning_rate": 0.003,
      "loss": 3.2217138671875,
      "step": 133400
    },
    {
      "epoch": 0.291635150227601,
      "grad_norm": 0.16933363676071167,
      "learning_rate": 0.003,
      "loss": 3.2272128295898437,
      "step": 133500
    },
    {
      "epoch": 0.29185360352365164,
      "grad_norm": 0.16237424314022064,
      "learning_rate": 0.003,
      "loss": 3.19873291015625,
      "step": 133600
    },
    {
      "epoch": 0.29207205681970233,
      "grad_norm": 0.1812378317117691,
      "learning_rate": 0.003,
      "loss": 3.180633850097656,
      "step": 133700
    },
    {
      "epoch": 0.29229051011575297,
      "grad_norm": 0.17355945706367493,
      "learning_rate": 0.003,
      "loss": 3.2264837646484374,
      "step": 133800
    },
    {
      "epoch": 0.2925089634118036,
      "grad_norm": 0.17370428144931793,
      "learning_rate": 0.003,
      "loss": 3.176700439453125,
      "step": 133900
    },
    {
      "epoch": 0.29272741670785424,
      "grad_norm": 0.24076209962368011,
      "learning_rate": 0.003,
      "loss": 3.1999746704101564,
      "step": 134000
    },
    {
      "epoch": 0.2929458700039049,
      "grad_norm": 0.1681448370218277,
      "learning_rate": 0.003,
      "loss": 3.1995059204101564,
      "step": 134100
    },
    {
      "epoch": 0.2931643232999555,
      "grad_norm": 0.2963580787181854,
      "learning_rate": 0.003,
      "loss": 3.2250381469726563,
      "step": 134200
    },
    {
      "epoch": 0.29338277659600615,
      "grad_norm": 0.16434602439403534,
      "learning_rate": 0.003,
      "loss": 3.1836260986328124,
      "step": 134300
    },
    {
      "epoch": 0.2936012298920568,
      "grad_norm": 0.19248543679714203,
      "learning_rate": 0.003,
      "loss": 3.2431411743164062,
      "step": 134400
    },
    {
      "epoch": 0.2938196831881074,
      "grad_norm": 0.2197428047657013,
      "learning_rate": 0.003,
      "loss": 3.1926956176757812,
      "step": 134500
    },
    {
      "epoch": 0.29403813648415805,
      "grad_norm": 0.1991998553276062,
      "learning_rate": 0.003,
      "loss": 3.1818472290039064,
      "step": 134600
    },
    {
      "epoch": 0.2942565897802087,
      "grad_norm": 0.18852558732032776,
      "learning_rate": 0.003,
      "loss": 3.1907608032226564,
      "step": 134700
    },
    {
      "epoch": 0.2944750430762593,
      "grad_norm": 0.20869626104831696,
      "learning_rate": 0.003,
      "loss": 3.1867388916015624,
      "step": 134800
    },
    {
      "epoch": 0.29469349637230996,
      "grad_norm": 0.17816461622714996,
      "learning_rate": 0.003,
      "loss": 3.131686096191406,
      "step": 134900
    },
    {
      "epoch": 0.2949119496683606,
      "grad_norm": 0.1907869577407837,
      "learning_rate": 0.003,
      "loss": 3.214499816894531,
      "step": 135000
    },
    {
      "epoch": 0.29513040296441123,
      "grad_norm": 0.15174990892410278,
      "learning_rate": 0.003,
      "loss": 3.210446472167969,
      "step": 135100
    },
    {
      "epoch": 0.29534885626046187,
      "grad_norm": 0.20105698704719543,
      "learning_rate": 0.003,
      "loss": 3.1645794677734376,
      "step": 135200
    },
    {
      "epoch": 0.2955673095565125,
      "grad_norm": 0.19103233516216278,
      "learning_rate": 0.003,
      "loss": 3.164373474121094,
      "step": 135300
    },
    {
      "epoch": 0.29578576285256314,
      "grad_norm": 0.1916809380054474,
      "learning_rate": 0.003,
      "loss": 3.1695938110351562,
      "step": 135400
    },
    {
      "epoch": 0.2960042161486138,
      "grad_norm": 0.1843739002943039,
      "learning_rate": 0.003,
      "loss": 3.1917315673828126,
      "step": 135500
    },
    {
      "epoch": 0.2962226694446644,
      "grad_norm": 0.16667531430721283,
      "learning_rate": 0.003,
      "loss": 3.1886322021484377,
      "step": 135600
    },
    {
      "epoch": 0.29644112274071505,
      "grad_norm": 0.21029360592365265,
      "learning_rate": 0.003,
      "loss": 3.210748596191406,
      "step": 135700
    },
    {
      "epoch": 0.2966595760367657,
      "grad_norm": 0.17889174818992615,
      "learning_rate": 0.003,
      "loss": 3.1713192749023436,
      "step": 135800
    },
    {
      "epoch": 0.2968780293328163,
      "grad_norm": 0.17533376812934875,
      "learning_rate": 0.003,
      "loss": 3.2180303955078124,
      "step": 135900
    },
    {
      "epoch": 0.29709648262886695,
      "grad_norm": 0.1637962907552719,
      "learning_rate": 0.003,
      "loss": 3.2227993774414063,
      "step": 136000
    },
    {
      "epoch": 0.2973149359249176,
      "grad_norm": 0.3537386953830719,
      "learning_rate": 0.003,
      "loss": 3.2023394775390623,
      "step": 136100
    },
    {
      "epoch": 0.2975333892209682,
      "grad_norm": 0.19465351104736328,
      "learning_rate": 0.003,
      "loss": 3.2192376708984374,
      "step": 136200
    },
    {
      "epoch": 0.29775184251701886,
      "grad_norm": 0.2649924159049988,
      "learning_rate": 0.003,
      "loss": 3.177152099609375,
      "step": 136300
    },
    {
      "epoch": 0.2979702958130695,
      "grad_norm": 0.1992715746164322,
      "learning_rate": 0.003,
      "loss": 3.209580078125,
      "step": 136400
    },
    {
      "epoch": 0.29818874910912013,
      "grad_norm": 0.16940732300281525,
      "learning_rate": 0.003,
      "loss": 3.2093356323242186,
      "step": 136500
    },
    {
      "epoch": 0.29840720240517077,
      "grad_norm": 0.16772933304309845,
      "learning_rate": 0.003,
      "loss": 3.221116638183594,
      "step": 136600
    },
    {
      "epoch": 0.2986256557012214,
      "grad_norm": 0.1964656412601471,
      "learning_rate": 0.003,
      "loss": 3.2100775146484377,
      "step": 136700
    },
    {
      "epoch": 0.29884410899727204,
      "grad_norm": 0.2089720517396927,
      "learning_rate": 0.003,
      "loss": 3.203949279785156,
      "step": 136800
    },
    {
      "epoch": 0.2990625622933227,
      "grad_norm": 0.15475992858409882,
      "learning_rate": 0.003,
      "loss": 3.205782470703125,
      "step": 136900
    },
    {
      "epoch": 0.29928101558937337,
      "grad_norm": 0.1778334528207779,
      "learning_rate": 0.003,
      "loss": 3.2443170166015625,
      "step": 137000
    },
    {
      "epoch": 0.299499468885424,
      "grad_norm": 0.1804296225309372,
      "learning_rate": 0.003,
      "loss": 3.21103515625,
      "step": 137100
    },
    {
      "epoch": 0.29971792218147464,
      "grad_norm": 0.20873281359672546,
      "learning_rate": 0.003,
      "loss": 3.2040234375,
      "step": 137200
    },
    {
      "epoch": 0.2999363754775253,
      "grad_norm": 0.24339774250984192,
      "learning_rate": 0.003,
      "loss": 3.1806402587890625,
      "step": 137300
    },
    {
      "epoch": 0.3001548287735759,
      "grad_norm": 0.22704702615737915,
      "learning_rate": 0.003,
      "loss": 3.1972055053710937,
      "step": 137400
    },
    {
      "epoch": 0.30037328206962655,
      "grad_norm": 0.15578119456768036,
      "learning_rate": 0.003,
      "loss": 3.1968524169921877,
      "step": 137500
    },
    {
      "epoch": 0.3005917353656772,
      "grad_norm": 0.2116861343383789,
      "learning_rate": 0.003,
      "loss": 3.20760009765625,
      "step": 137600
    },
    {
      "epoch": 0.3008101886617278,
      "grad_norm": 0.15658578276634216,
      "learning_rate": 0.003,
      "loss": 3.220193176269531,
      "step": 137700
    },
    {
      "epoch": 0.30102864195777845,
      "grad_norm": 0.18922600150108337,
      "learning_rate": 0.003,
      "loss": 3.1731051635742187,
      "step": 137800
    },
    {
      "epoch": 0.3012470952538291,
      "grad_norm": 0.16404539346694946,
      "learning_rate": 0.003,
      "loss": 3.1814349365234373,
      "step": 137900
    },
    {
      "epoch": 0.3014655485498797,
      "grad_norm": 0.20131675899028778,
      "learning_rate": 0.003,
      "loss": 3.1948602294921873,
      "step": 138000
    },
    {
      "epoch": 0.30168400184593036,
      "grad_norm": 0.17711040377616882,
      "learning_rate": 0.003,
      "loss": 3.2230322265625,
      "step": 138100
    },
    {
      "epoch": 0.301902455141981,
      "grad_norm": 0.1827816516160965,
      "learning_rate": 0.003,
      "loss": 3.1611846923828124,
      "step": 138200
    },
    {
      "epoch": 0.30212090843803163,
      "grad_norm": 0.23586484789848328,
      "learning_rate": 0.003,
      "loss": 3.201513671875,
      "step": 138300
    },
    {
      "epoch": 0.30233936173408227,
      "grad_norm": 0.20572659373283386,
      "learning_rate": 0.003,
      "loss": 3.195331726074219,
      "step": 138400
    },
    {
      "epoch": 0.3025578150301329,
      "grad_norm": 0.18462501466274261,
      "learning_rate": 0.003,
      "loss": 3.206833801269531,
      "step": 138500
    },
    {
      "epoch": 0.30277626832618354,
      "grad_norm": 0.17236556112766266,
      "learning_rate": 0.003,
      "loss": 3.178404541015625,
      "step": 138600
    },
    {
      "epoch": 0.3029947216222342,
      "grad_norm": 0.15189675986766815,
      "learning_rate": 0.003,
      "loss": 3.1943118286132814,
      "step": 138700
    },
    {
      "epoch": 0.3032131749182848,
      "grad_norm": 0.1795898973941803,
      "learning_rate": 0.003,
      "loss": 3.2082452392578125,
      "step": 138800
    },
    {
      "epoch": 0.30343162821433545,
      "grad_norm": 0.24792973697185516,
      "learning_rate": 0.003,
      "loss": 3.2121905517578124,
      "step": 138900
    },
    {
      "epoch": 0.3036500815103861,
      "grad_norm": 0.1631484478712082,
      "learning_rate": 0.003,
      "loss": 3.1948968505859376,
      "step": 139000
    },
    {
      "epoch": 0.3038685348064367,
      "grad_norm": 0.17224180698394775,
      "learning_rate": 0.003,
      "loss": 3.2479281616210938,
      "step": 139100
    },
    {
      "epoch": 0.30408698810248735,
      "grad_norm": 0.18179869651794434,
      "learning_rate": 0.003,
      "loss": 3.195875549316406,
      "step": 139200
    },
    {
      "epoch": 0.304305441398538,
      "grad_norm": 0.25769829750061035,
      "learning_rate": 0.003,
      "loss": 3.20810302734375,
      "step": 139300
    },
    {
      "epoch": 0.3045238946945886,
      "grad_norm": 0.19908572733402252,
      "learning_rate": 0.003,
      "loss": 3.1936154174804687,
      "step": 139400
    },
    {
      "epoch": 0.30474234799063926,
      "grad_norm": 0.15726956725120544,
      "learning_rate": 0.003,
      "loss": 3.17328125,
      "step": 139500
    },
    {
      "epoch": 0.3049608012866899,
      "grad_norm": 0.22366781532764435,
      "learning_rate": 0.003,
      "loss": 3.179468078613281,
      "step": 139600
    },
    {
      "epoch": 0.30517925458274053,
      "grad_norm": 0.1611061990261078,
      "learning_rate": 0.003,
      "loss": 3.19077880859375,
      "step": 139700
    },
    {
      "epoch": 0.30539770787879117,
      "grad_norm": 0.17893096804618835,
      "learning_rate": 0.003,
      "loss": 3.221007995605469,
      "step": 139800
    },
    {
      "epoch": 0.3056161611748418,
      "grad_norm": 0.19288408756256104,
      "learning_rate": 0.003,
      "loss": 3.218514709472656,
      "step": 139900
    },
    {
      "epoch": 0.30583461447089244,
      "grad_norm": 0.2554208040237427,
      "learning_rate": 0.003,
      "loss": 2.9139288330078124,
      "step": 140000
    },
    {
      "epoch": 0.3060530677669431,
      "grad_norm": 0.1867968589067459,
      "learning_rate": 0.003,
      "loss": 3.2304754638671875,
      "step": 140100
    },
    {
      "epoch": 0.3062715210629937,
      "grad_norm": 0.19115705788135529,
      "learning_rate": 0.003,
      "loss": 3.1553607177734375,
      "step": 140200
    },
    {
      "epoch": 0.3064899743590444,
      "grad_norm": 0.1747879832983017,
      "learning_rate": 0.003,
      "loss": 3.248841552734375,
      "step": 140300
    },
    {
      "epoch": 0.30670842765509504,
      "grad_norm": 0.21023240685462952,
      "learning_rate": 0.003,
      "loss": 3.2210183715820313,
      "step": 140400
    },
    {
      "epoch": 0.3069268809511457,
      "grad_norm": 0.1795470267534256,
      "learning_rate": 0.003,
      "loss": 3.18628662109375,
      "step": 140500
    },
    {
      "epoch": 0.3071453342471963,
      "grad_norm": 0.17351393401622772,
      "learning_rate": 0.003,
      "loss": 3.19286865234375,
      "step": 140600
    },
    {
      "epoch": 0.30736378754324695,
      "grad_norm": 0.18436656892299652,
      "learning_rate": 0.003,
      "loss": 3.205523681640625,
      "step": 140700
    },
    {
      "epoch": 0.3075822408392976,
      "grad_norm": 0.15725570917129517,
      "learning_rate": 0.003,
      "loss": 3.230887145996094,
      "step": 140800
    },
    {
      "epoch": 0.3078006941353482,
      "grad_norm": 0.21773605048656464,
      "learning_rate": 0.003,
      "loss": 3.228748779296875,
      "step": 140900
    },
    {
      "epoch": 0.30801914743139885,
      "grad_norm": 0.17027831077575684,
      "learning_rate": 0.003,
      "loss": 3.186734313964844,
      "step": 141000
    },
    {
      "epoch": 0.3082376007274495,
      "grad_norm": 0.15384380519390106,
      "learning_rate": 0.003,
      "loss": 3.1859201049804686,
      "step": 141100
    },
    {
      "epoch": 0.3084560540235001,
      "grad_norm": 0.3453856110572815,
      "learning_rate": 0.003,
      "loss": 3.160126037597656,
      "step": 141200
    },
    {
      "epoch": 0.30867450731955076,
      "grad_norm": 0.327231764793396,
      "learning_rate": 0.003,
      "loss": 3.1771490478515627,
      "step": 141300
    },
    {
      "epoch": 0.3088929606156014,
      "grad_norm": 0.28434672951698303,
      "learning_rate": 0.003,
      "loss": 3.1603729248046877,
      "step": 141400
    },
    {
      "epoch": 0.30911141391165203,
      "grad_norm": 0.20859956741333008,
      "learning_rate": 0.003,
      "loss": 3.199524230957031,
      "step": 141500
    },
    {
      "epoch": 0.30932986720770267,
      "grad_norm": 0.16180141270160675,
      "learning_rate": 0.003,
      "loss": 3.217564697265625,
      "step": 141600
    },
    {
      "epoch": 0.3095483205037533,
      "grad_norm": 0.18180030584335327,
      "learning_rate": 0.003,
      "loss": 3.2199407958984376,
      "step": 141700
    },
    {
      "epoch": 0.30976677379980394,
      "grad_norm": 0.16201762855052948,
      "learning_rate": 0.003,
      "loss": 3.174957275390625,
      "step": 141800
    },
    {
      "epoch": 0.3099852270958546,
      "grad_norm": 0.1949051469564438,
      "learning_rate": 0.003,
      "loss": 3.217715148925781,
      "step": 141900
    },
    {
      "epoch": 0.3102036803919052,
      "grad_norm": 0.15087030827999115,
      "learning_rate": 0.003,
      "loss": 3.186820068359375,
      "step": 142000
    },
    {
      "epoch": 0.31042213368795585,
      "grad_norm": 0.168676495552063,
      "learning_rate": 0.003,
      "loss": 3.1756060791015623,
      "step": 142100
    },
    {
      "epoch": 0.3106405869840065,
      "grad_norm": 0.24860401451587677,
      "learning_rate": 0.003,
      "loss": 3.2399252319335936,
      "step": 142200
    },
    {
      "epoch": 0.3108590402800571,
      "grad_norm": 0.15668369829654694,
      "learning_rate": 0.003,
      "loss": 3.199765319824219,
      "step": 142300
    },
    {
      "epoch": 0.31107749357610776,
      "grad_norm": 0.6814060807228088,
      "learning_rate": 0.003,
      "loss": 3.2036663818359377,
      "step": 142400
    },
    {
      "epoch": 0.3112959468721584,
      "grad_norm": 0.1491079330444336,
      "learning_rate": 0.003,
      "loss": 3.225286560058594,
      "step": 142500
    },
    {
      "epoch": 0.311514400168209,
      "grad_norm": 0.15027421712875366,
      "learning_rate": 0.003,
      "loss": 3.2134439086914064,
      "step": 142600
    },
    {
      "epoch": 0.31173285346425966,
      "grad_norm": 0.2214614301919937,
      "learning_rate": 0.003,
      "loss": 3.1999752807617186,
      "step": 142700
    },
    {
      "epoch": 0.3119513067603103,
      "grad_norm": 0.18709635734558105,
      "learning_rate": 0.003,
      "loss": 3.1740081787109373,
      "step": 142800
    },
    {
      "epoch": 0.31216976005636093,
      "grad_norm": 0.24174664914608002,
      "learning_rate": 0.003,
      "loss": 3.2188986206054686,
      "step": 142900
    },
    {
      "epoch": 0.31238821335241157,
      "grad_norm": 0.14840149879455566,
      "learning_rate": 0.003,
      "loss": 3.203288879394531,
      "step": 143000
    },
    {
      "epoch": 0.3126066666484622,
      "grad_norm": 0.3073531687259674,
      "learning_rate": 0.003,
      "loss": 3.257579650878906,
      "step": 143100
    },
    {
      "epoch": 0.31282511994451284,
      "grad_norm": 0.21026237308979034,
      "learning_rate": 0.003,
      "loss": 3.2264254760742186,
      "step": 143200
    },
    {
      "epoch": 0.3130435732405635,
      "grad_norm": 0.16831256449222565,
      "learning_rate": 0.003,
      "loss": 3.1818194580078125,
      "step": 143300
    },
    {
      "epoch": 0.3132620265366141,
      "grad_norm": 0.16093488037586212,
      "learning_rate": 0.003,
      "loss": 3.1373519897460938,
      "step": 143400
    },
    {
      "epoch": 0.31348047983266475,
      "grad_norm": 0.18346524238586426,
      "learning_rate": 0.003,
      "loss": 3.1911004638671874,
      "step": 143500
    },
    {
      "epoch": 0.31369893312871544,
      "grad_norm": 0.18986782431602478,
      "learning_rate": 0.003,
      "loss": 3.177647705078125,
      "step": 143600
    },
    {
      "epoch": 0.3139173864247661,
      "grad_norm": 0.22777634859085083,
      "learning_rate": 0.003,
      "loss": 3.1712738037109376,
      "step": 143700
    },
    {
      "epoch": 0.3141358397208167,
      "grad_norm": 0.14152170717716217,
      "learning_rate": 0.003,
      "loss": 3.2470083618164063,
      "step": 143800
    },
    {
      "epoch": 0.31435429301686735,
      "grad_norm": 0.21601779758930206,
      "learning_rate": 0.003,
      "loss": 3.2211138916015627,
      "step": 143900
    },
    {
      "epoch": 0.314572746312918,
      "grad_norm": 0.16085198521614075,
      "learning_rate": 0.003,
      "loss": 3.1816421508789063,
      "step": 144000
    },
    {
      "epoch": 0.3147911996089686,
      "grad_norm": 0.1805422604084015,
      "learning_rate": 0.003,
      "loss": 3.199898376464844,
      "step": 144100
    },
    {
      "epoch": 0.31500965290501926,
      "grad_norm": 0.2308289259672165,
      "learning_rate": 0.003,
      "loss": 3.208460388183594,
      "step": 144200
    },
    {
      "epoch": 0.3152281062010699,
      "grad_norm": 0.17883312702178955,
      "learning_rate": 0.003,
      "loss": 3.149988098144531,
      "step": 144300
    },
    {
      "epoch": 0.3154465594971205,
      "grad_norm": 0.17172366380691528,
      "learning_rate": 0.003,
      "loss": 3.211492919921875,
      "step": 144400
    },
    {
      "epoch": 0.31566501279317116,
      "grad_norm": 0.3454696536064148,
      "learning_rate": 0.003,
      "loss": 3.1982745361328124,
      "step": 144500
    },
    {
      "epoch": 0.3158834660892218,
      "grad_norm": 0.18591400980949402,
      "learning_rate": 0.003,
      "loss": 3.2074407958984374,
      "step": 144600
    },
    {
      "epoch": 0.31610191938527243,
      "grad_norm": 0.1585206687450409,
      "learning_rate": 0.003,
      "loss": 3.1934228515625,
      "step": 144700
    },
    {
      "epoch": 0.31632037268132307,
      "grad_norm": 0.34315547347068787,
      "learning_rate": 0.003,
      "loss": 3.1926708984375,
      "step": 144800
    },
    {
      "epoch": 0.3165388259773737,
      "grad_norm": 0.17863717675209045,
      "learning_rate": 0.003,
      "loss": 3.1578744506835936,
      "step": 144900
    },
    {
      "epoch": 0.31675727927342434,
      "grad_norm": 0.24649377167224884,
      "learning_rate": 0.003,
      "loss": 3.197144775390625,
      "step": 145000
    },
    {
      "epoch": 0.316975732569475,
      "grad_norm": 0.16562138497829437,
      "learning_rate": 0.003,
      "loss": 3.191086730957031,
      "step": 145100
    },
    {
      "epoch": 0.3171941858655256,
      "grad_norm": 0.17314296960830688,
      "learning_rate": 0.003,
      "loss": 3.2123272705078123,
      "step": 145200
    },
    {
      "epoch": 0.31741263916157625,
      "grad_norm": 0.16946852207183838,
      "learning_rate": 0.003,
      "loss": 3.179129943847656,
      "step": 145300
    },
    {
      "epoch": 0.3176310924576269,
      "grad_norm": 0.17480599880218506,
      "learning_rate": 0.003,
      "loss": 3.2248297119140625,
      "step": 145400
    },
    {
      "epoch": 0.3178495457536775,
      "grad_norm": 0.16407208144664764,
      "learning_rate": 0.003,
      "loss": 3.196800537109375,
      "step": 145500
    },
    {
      "epoch": 0.31806799904972816,
      "grad_norm": 0.20925581455230713,
      "learning_rate": 0.003,
      "loss": 3.18634521484375,
      "step": 145600
    },
    {
      "epoch": 0.3182864523457788,
      "grad_norm": 0.222587451338768,
      "learning_rate": 0.003,
      "loss": 3.2120587158203127,
      "step": 145700
    },
    {
      "epoch": 0.31850490564182943,
      "grad_norm": 0.17559437453746796,
      "learning_rate": 0.003,
      "loss": 3.2094912719726563,
      "step": 145800
    },
    {
      "epoch": 0.31872335893788006,
      "grad_norm": 0.253233939409256,
      "learning_rate": 0.003,
      "loss": 3.1960491943359375,
      "step": 145900
    },
    {
      "epoch": 0.3189418122339307,
      "grad_norm": 0.15889482200145721,
      "learning_rate": 0.003,
      "loss": 3.218516845703125,
      "step": 146000
    },
    {
      "epoch": 0.31916026552998134,
      "grad_norm": 0.23230864107608795,
      "learning_rate": 0.003,
      "loss": 3.1856573486328124,
      "step": 146100
    },
    {
      "epoch": 0.31937871882603197,
      "grad_norm": 0.14948810636997223,
      "learning_rate": 0.003,
      "loss": 3.2190350341796874,
      "step": 146200
    },
    {
      "epoch": 0.3195971721220826,
      "grad_norm": 0.5103902816772461,
      "learning_rate": 0.003,
      "loss": 3.1645404052734376,
      "step": 146300
    },
    {
      "epoch": 0.31981562541813324,
      "grad_norm": 0.1744993031024933,
      "learning_rate": 0.003,
      "loss": 3.2244082641601564,
      "step": 146400
    },
    {
      "epoch": 0.3200340787141839,
      "grad_norm": 0.17527836561203003,
      "learning_rate": 0.003,
      "loss": 3.2356802368164064,
      "step": 146500
    },
    {
      "epoch": 0.3202525320102345,
      "grad_norm": 0.30127814412117004,
      "learning_rate": 0.003,
      "loss": 3.2353482055664062,
      "step": 146600
    },
    {
      "epoch": 0.32047098530628515,
      "grad_norm": 0.1600414365530014,
      "learning_rate": 0.003,
      "loss": 3.21412353515625,
      "step": 146700
    },
    {
      "epoch": 0.3206894386023358,
      "grad_norm": 0.17066684365272522,
      "learning_rate": 0.003,
      "loss": 3.1851055908203123,
      "step": 146800
    },
    {
      "epoch": 0.3209078918983865,
      "grad_norm": 0.17907121777534485,
      "learning_rate": 0.003,
      "loss": 3.18966552734375,
      "step": 146900
    },
    {
      "epoch": 0.3211263451944371,
      "grad_norm": 0.16637155413627625,
      "learning_rate": 0.003,
      "loss": 3.190469055175781,
      "step": 147000
    },
    {
      "epoch": 0.32134479849048775,
      "grad_norm": 0.19598500430583954,
      "learning_rate": 0.003,
      "loss": 3.1495361328125,
      "step": 147100
    },
    {
      "epoch": 0.3215632517865384,
      "grad_norm": 0.17670966684818268,
      "learning_rate": 0.003,
      "loss": 3.193385009765625,
      "step": 147200
    },
    {
      "epoch": 0.321781705082589,
      "grad_norm": 0.15445983409881592,
      "learning_rate": 0.003,
      "loss": 3.1991397094726564,
      "step": 147300
    },
    {
      "epoch": 0.32200015837863966,
      "grad_norm": 0.18516457080841064,
      "learning_rate": 0.003,
      "loss": 3.094637145996094,
      "step": 147400
    },
    {
      "epoch": 0.3222186116746903,
      "grad_norm": 0.19677746295928955,
      "learning_rate": 0.003,
      "loss": 3.196466979980469,
      "step": 147500
    },
    {
      "epoch": 0.3224370649707409,
      "grad_norm": 0.1936854124069214,
      "learning_rate": 0.003,
      "loss": 3.1779425048828127,
      "step": 147600
    },
    {
      "epoch": 0.32265551826679156,
      "grad_norm": 0.19209504127502441,
      "learning_rate": 0.003,
      "loss": 3.1815972900390626,
      "step": 147700
    },
    {
      "epoch": 0.3228739715628422,
      "grad_norm": 0.1692599505186081,
      "learning_rate": 0.003,
      "loss": 3.185713195800781,
      "step": 147800
    },
    {
      "epoch": 0.32309242485889283,
      "grad_norm": 0.19620276987552643,
      "learning_rate": 0.003,
      "loss": 3.1745257568359375,
      "step": 147900
    },
    {
      "epoch": 0.32331087815494347,
      "grad_norm": 0.23885881900787354,
      "learning_rate": 0.003,
      "loss": 3.13314697265625,
      "step": 148000
    },
    {
      "epoch": 0.3235293314509941,
      "grad_norm": 0.15670974552631378,
      "learning_rate": 0.003,
      "loss": 3.141082763671875,
      "step": 148100
    },
    {
      "epoch": 0.32374778474704474,
      "grad_norm": 0.17646116018295288,
      "learning_rate": 0.003,
      "loss": 3.17531982421875,
      "step": 148200
    },
    {
      "epoch": 0.3239662380430954,
      "grad_norm": 0.23557858169078827,
      "learning_rate": 0.003,
      "loss": 3.19098388671875,
      "step": 148300
    },
    {
      "epoch": 0.324184691339146,
      "grad_norm": 0.14398302137851715,
      "learning_rate": 0.003,
      "loss": 3.1819873046875,
      "step": 148400
    },
    {
      "epoch": 0.32440314463519665,
      "grad_norm": 0.18726244568824768,
      "learning_rate": 0.003,
      "loss": 3.1925845336914063,
      "step": 148500
    },
    {
      "epoch": 0.3246215979312473,
      "grad_norm": 0.2285359650850296,
      "learning_rate": 0.003,
      "loss": 3.20674072265625,
      "step": 148600
    },
    {
      "epoch": 0.3248400512272979,
      "grad_norm": 0.17976802587509155,
      "learning_rate": 0.003,
      "loss": 3.173955993652344,
      "step": 148700
    },
    {
      "epoch": 0.32505850452334856,
      "grad_norm": 0.1975952386856079,
      "learning_rate": 0.003,
      "loss": 2.6845458984375,
      "step": 148800
    },
    {
      "epoch": 0.3252769578193992,
      "grad_norm": 0.15447331964969635,
      "learning_rate": 0.003,
      "loss": 3.1710690307617186,
      "step": 148900
    },
    {
      "epoch": 0.32549541111544983,
      "grad_norm": 0.18206952512264252,
      "learning_rate": 0.003,
      "loss": 3.158231506347656,
      "step": 149000
    },
    {
      "epoch": 0.32571386441150046,
      "grad_norm": 0.17522966861724854,
      "learning_rate": 0.003,
      "loss": 3.1928945922851564,
      "step": 149100
    },
    {
      "epoch": 0.3259323177075511,
      "grad_norm": 0.16397172212600708,
      "learning_rate": 0.003,
      "loss": 3.2015060424804687,
      "step": 149200
    },
    {
      "epoch": 0.32615077100360174,
      "grad_norm": 0.21215063333511353,
      "learning_rate": 0.003,
      "loss": 3.1936944580078124,
      "step": 149300
    },
    {
      "epoch": 0.32636922429965237,
      "grad_norm": 0.2076343297958374,
      "learning_rate": 0.003,
      "loss": 2.6863333129882814,
      "step": 149400
    },
    {
      "epoch": 0.326587677595703,
      "grad_norm": 0.2564661502838135,
      "learning_rate": 0.003,
      "loss": 3.208557434082031,
      "step": 149500
    },
    {
      "epoch": 0.32680613089175364,
      "grad_norm": 0.18941468000411987,
      "learning_rate": 0.003,
      "loss": 3.137552490234375,
      "step": 149600
    },
    {
      "epoch": 0.3270245841878043,
      "grad_norm": 0.1444561928510666,
      "learning_rate": 0.003,
      "loss": 3.248238830566406,
      "step": 149700
    },
    {
      "epoch": 0.3272430374838549,
      "grad_norm": 0.26616400480270386,
      "learning_rate": 0.003,
      "loss": 3.21462890625,
      "step": 149800
    },
    {
      "epoch": 0.32746149077990555,
      "grad_norm": 0.20099005103111267,
      "learning_rate": 0.003,
      "loss": 3.169850158691406,
      "step": 149900
    },
    {
      "epoch": 0.3276799440759562,
      "grad_norm": 0.16536197066307068,
      "learning_rate": 0.003,
      "loss": 3.1830929565429686,
      "step": 150000
    },
    {
      "epoch": 0.3278983973720068,
      "grad_norm": 0.18397554755210876,
      "learning_rate": 0.003,
      "loss": 3.2401638793945313,
      "step": 150100
    },
    {
      "epoch": 0.3281168506680575,
      "grad_norm": 0.16635970771312714,
      "learning_rate": 0.003,
      "loss": 3.1912631225585937,
      "step": 150200
    },
    {
      "epoch": 0.32833530396410815,
      "grad_norm": 0.1743297576904297,
      "learning_rate": 0.003,
      "loss": 3.2167935180664062,
      "step": 150300
    },
    {
      "epoch": 0.3285537572601588,
      "grad_norm": 0.2537592947483063,
      "learning_rate": 0.003,
      "loss": 3.2288177490234373,
      "step": 150400
    },
    {
      "epoch": 0.3287722105562094,
      "grad_norm": 0.1927787810564041,
      "learning_rate": 0.003,
      "loss": 3.170396423339844,
      "step": 150500
    },
    {
      "epoch": 0.32899066385226006,
      "grad_norm": 0.23473043739795685,
      "learning_rate": 0.003,
      "loss": 3.1796908569335938,
      "step": 150600
    },
    {
      "epoch": 0.3292091171483107,
      "grad_norm": 0.2488144338130951,
      "learning_rate": 0.003,
      "loss": 3.16794189453125,
      "step": 150700
    },
    {
      "epoch": 0.32942757044436133,
      "grad_norm": 0.21751940250396729,
      "learning_rate": 0.003,
      "loss": 3.185949401855469,
      "step": 150800
    },
    {
      "epoch": 0.32964602374041196,
      "grad_norm": 0.22387519478797913,
      "learning_rate": 0.003,
      "loss": 3.202431945800781,
      "step": 150900
    },
    {
      "epoch": 0.3298644770364626,
      "grad_norm": 0.1522534191608429,
      "learning_rate": 0.003,
      "loss": 3.211038818359375,
      "step": 151000
    },
    {
      "epoch": 0.33008293033251324,
      "grad_norm": 0.17218022048473358,
      "learning_rate": 0.003,
      "loss": 3.1591448974609375,
      "step": 151100
    },
    {
      "epoch": 0.33030138362856387,
      "grad_norm": 0.17332923412322998,
      "learning_rate": 0.003,
      "loss": 3.147066955566406,
      "step": 151200
    },
    {
      "epoch": 0.3305198369246145,
      "grad_norm": 0.16366907954216003,
      "learning_rate": 0.003,
      "loss": 3.228832092285156,
      "step": 151300
    },
    {
      "epoch": 0.33073829022066514,
      "grad_norm": 0.18040701746940613,
      "learning_rate": 0.003,
      "loss": 3.154132080078125,
      "step": 151400
    },
    {
      "epoch": 0.3309567435167158,
      "grad_norm": 0.17774927616119385,
      "learning_rate": 0.003,
      "loss": 3.192138671875,
      "step": 151500
    },
    {
      "epoch": 0.3311751968127664,
      "grad_norm": 0.20536623895168304,
      "learning_rate": 0.003,
      "loss": 3.18081787109375,
      "step": 151600
    },
    {
      "epoch": 0.33139365010881705,
      "grad_norm": 0.20949424803256989,
      "learning_rate": 0.003,
      "loss": 3.1637872314453124,
      "step": 151700
    },
    {
      "epoch": 0.3316121034048677,
      "grad_norm": 0.2223246991634369,
      "learning_rate": 0.003,
      "loss": 3.1776608276367186,
      "step": 151800
    },
    {
      "epoch": 0.3318305567009183,
      "grad_norm": 0.17206287384033203,
      "learning_rate": 0.003,
      "loss": 3.15651123046875,
      "step": 151900
    },
    {
      "epoch": 0.33204900999696896,
      "grad_norm": 0.21758702397346497,
      "learning_rate": 0.003,
      "loss": 3.1671078491210936,
      "step": 152000
    },
    {
      "epoch": 0.3322674632930196,
      "grad_norm": 0.18254788219928741,
      "learning_rate": 0.003,
      "loss": 3.1718585205078127,
      "step": 152100
    },
    {
      "epoch": 0.33248591658907023,
      "grad_norm": 0.18393871188163757,
      "learning_rate": 0.003,
      "loss": 3.1879238891601562,
      "step": 152200
    },
    {
      "epoch": 0.33270436988512087,
      "grad_norm": 0.23279863595962524,
      "learning_rate": 0.003,
      "loss": 3.192552185058594,
      "step": 152300
    },
    {
      "epoch": 0.3329228231811715,
      "grad_norm": 0.18877536058425903,
      "learning_rate": 0.003,
      "loss": 3.177838134765625,
      "step": 152400
    },
    {
      "epoch": 0.33314127647722214,
      "grad_norm": 0.1876782476902008,
      "learning_rate": 0.003,
      "loss": 3.132906494140625,
      "step": 152500
    },
    {
      "epoch": 0.3333597297732728,
      "grad_norm": 0.16887180507183075,
      "learning_rate": 0.003,
      "loss": 3.2051397705078126,
      "step": 152600
    },
    {
      "epoch": 0.3335781830693234,
      "grad_norm": 0.1972004771232605,
      "learning_rate": 0.003,
      "loss": 3.1865728759765624,
      "step": 152700
    },
    {
      "epoch": 0.33379663636537404,
      "grad_norm": 0.2580986022949219,
      "learning_rate": 0.003,
      "loss": 3.2121429443359375,
      "step": 152800
    },
    {
      "epoch": 0.3340150896614247,
      "grad_norm": 0.1952686458826065,
      "learning_rate": 0.003,
      "loss": 3.1715158081054686,
      "step": 152900
    },
    {
      "epoch": 0.3342335429574753,
      "grad_norm": 0.22782842814922333,
      "learning_rate": 0.003,
      "loss": 3.1909320068359377,
      "step": 153000
    },
    {
      "epoch": 0.33445199625352595,
      "grad_norm": 0.2532144784927368,
      "learning_rate": 0.003,
      "loss": 3.2305587768554687,
      "step": 153100
    },
    {
      "epoch": 0.3346704495495766,
      "grad_norm": 0.22145599126815796,
      "learning_rate": 0.003,
      "loss": 3.2270474243164062,
      "step": 153200
    },
    {
      "epoch": 0.3348889028456272,
      "grad_norm": 0.21716009080410004,
      "learning_rate": 0.003,
      "loss": 3.1774713134765626,
      "step": 153300
    },
    {
      "epoch": 0.33510735614167786,
      "grad_norm": 0.31625574827194214,
      "learning_rate": 0.003,
      "loss": 2.6925650024414063,
      "step": 153400
    },
    {
      "epoch": 0.33532580943772855,
      "grad_norm": 0.18389812111854553,
      "learning_rate": 0.003,
      "loss": 3.2025628662109376,
      "step": 153500
    },
    {
      "epoch": 0.3355442627337792,
      "grad_norm": 0.18168075382709503,
      "learning_rate": 0.003,
      "loss": 3.1919210815429686,
      "step": 153600
    },
    {
      "epoch": 0.3357627160298298,
      "grad_norm": 0.19095513224601746,
      "learning_rate": 0.003,
      "loss": 3.170085754394531,
      "step": 153700
    },
    {
      "epoch": 0.33598116932588046,
      "grad_norm": 0.24979139864444733,
      "learning_rate": 0.003,
      "loss": 3.196229248046875,
      "step": 153800
    },
    {
      "epoch": 0.3361996226219311,
      "grad_norm": 0.24247103929519653,
      "learning_rate": 0.003,
      "loss": 3.155550231933594,
      "step": 153900
    },
    {
      "epoch": 0.33641807591798173,
      "grad_norm": 0.2211730033159256,
      "learning_rate": 0.003,
      "loss": 3.2138156127929687,
      "step": 154000
    },
    {
      "epoch": 0.33663652921403237,
      "grad_norm": 0.1641773283481598,
      "learning_rate": 0.003,
      "loss": 3.1940878295898436,
      "step": 154100
    },
    {
      "epoch": 0.336854982510083,
      "grad_norm": 0.1894778609275818,
      "learning_rate": 0.003,
      "loss": 3.2004910278320313,
      "step": 154200
    },
    {
      "epoch": 0.33707343580613364,
      "grad_norm": 0.1566590666770935,
      "learning_rate": 0.003,
      "loss": 3.1311114501953123,
      "step": 154300
    },
    {
      "epoch": 0.3372918891021843,
      "grad_norm": 0.19558022916316986,
      "learning_rate": 0.003,
      "loss": 3.164029235839844,
      "step": 154400
    },
    {
      "epoch": 0.3375103423982349,
      "grad_norm": 0.21856990456581116,
      "learning_rate": 0.003,
      "loss": 3.1604824829101563,
      "step": 154500
    },
    {
      "epoch": 0.33772879569428554,
      "grad_norm": 0.19755780696868896,
      "learning_rate": 0.003,
      "loss": 3.158997802734375,
      "step": 154600
    },
    {
      "epoch": 0.3379472489903362,
      "grad_norm": 0.15918242931365967,
      "learning_rate": 0.003,
      "loss": 3.230296325683594,
      "step": 154700
    },
    {
      "epoch": 0.3381657022863868,
      "grad_norm": 0.24871376156806946,
      "learning_rate": 0.003,
      "loss": 2.9430838012695313,
      "step": 154800
    },
    {
      "epoch": 0.33838415558243745,
      "grad_norm": 0.24803753197193146,
      "learning_rate": 0.003,
      "loss": 3.2192874145507813,
      "step": 154900
    },
    {
      "epoch": 0.3386026088784881,
      "grad_norm": 0.17800495028495789,
      "learning_rate": 0.003,
      "loss": 3.204012756347656,
      "step": 155000
    },
    {
      "epoch": 0.3388210621745387,
      "grad_norm": 0.25822532176971436,
      "learning_rate": 0.003,
      "loss": 3.18099365234375,
      "step": 155100
    },
    {
      "epoch": 0.33903951547058936,
      "grad_norm": 0.16437004506587982,
      "learning_rate": 0.003,
      "loss": 3.183768310546875,
      "step": 155200
    },
    {
      "epoch": 0.33925796876664,
      "grad_norm": 0.1815718412399292,
      "learning_rate": 0.003,
      "loss": 3.076330261230469,
      "step": 155300
    },
    {
      "epoch": 0.33947642206269063,
      "grad_norm": 0.1795693188905716,
      "learning_rate": 0.003,
      "loss": 3.1956195068359374,
      "step": 155400
    },
    {
      "epoch": 0.33969487535874127,
      "grad_norm": 0.9455909729003906,
      "learning_rate": 0.003,
      "loss": 3.154691467285156,
      "step": 155500
    },
    {
      "epoch": 0.3399133286547919,
      "grad_norm": 0.188655823469162,
      "learning_rate": 0.003,
      "loss": 3.1824188232421875,
      "step": 155600
    },
    {
      "epoch": 0.34013178195084254,
      "grad_norm": 0.19210544228553772,
      "learning_rate": 0.003,
      "loss": 3.18107177734375,
      "step": 155700
    },
    {
      "epoch": 0.3403502352468932,
      "grad_norm": 0.16656406223773956,
      "learning_rate": 0.003,
      "loss": 3.1568673706054686,
      "step": 155800
    },
    {
      "epoch": 0.3405686885429438,
      "grad_norm": 0.22872625291347504,
      "learning_rate": 0.003,
      "loss": 3.171075744628906,
      "step": 155900
    },
    {
      "epoch": 0.34078714183899445,
      "grad_norm": 0.16131971776485443,
      "learning_rate": 0.003,
      "loss": 3.167562255859375,
      "step": 156000
    },
    {
      "epoch": 0.3410055951350451,
      "grad_norm": 0.15685568749904633,
      "learning_rate": 0.003,
      "loss": 3.1865103149414065,
      "step": 156100
    },
    {
      "epoch": 0.3412240484310957,
      "grad_norm": 0.22560730576515198,
      "learning_rate": 0.003,
      "loss": 3.208013916015625,
      "step": 156200
    },
    {
      "epoch": 0.34144250172714635,
      "grad_norm": 0.1931314617395401,
      "learning_rate": 0.003,
      "loss": 3.1950698852539063,
      "step": 156300
    },
    {
      "epoch": 0.341660955023197,
      "grad_norm": 0.1877717822790146,
      "learning_rate": 0.003,
      "loss": 3.1804913330078124,
      "step": 156400
    },
    {
      "epoch": 0.3418794083192476,
      "grad_norm": 0.2338135540485382,
      "learning_rate": 0.003,
      "loss": 3.1736178588867188,
      "step": 156500
    },
    {
      "epoch": 0.34209786161529826,
      "grad_norm": 0.2008652240037918,
      "learning_rate": 0.003,
      "loss": 3.1773001098632814,
      "step": 156600
    },
    {
      "epoch": 0.3423163149113489,
      "grad_norm": 0.17682594060897827,
      "learning_rate": 0.003,
      "loss": 3.19855712890625,
      "step": 156700
    },
    {
      "epoch": 0.3425347682073996,
      "grad_norm": 0.1595831662416458,
      "learning_rate": 0.003,
      "loss": 3.1685079956054687,
      "step": 156800
    },
    {
      "epoch": 0.3427532215034502,
      "grad_norm": 0.14333690702915192,
      "learning_rate": 0.003,
      "loss": 3.187269592285156,
      "step": 156900
    },
    {
      "epoch": 0.34297167479950086,
      "grad_norm": 0.2140931487083435,
      "learning_rate": 0.003,
      "loss": 3.1413455200195313,
      "step": 157000
    },
    {
      "epoch": 0.3431901280955515,
      "grad_norm": 0.22988301515579224,
      "learning_rate": 0.003,
      "loss": 3.222878723144531,
      "step": 157100
    },
    {
      "epoch": 0.34340858139160213,
      "grad_norm": 0.1641242504119873,
      "learning_rate": 0.003,
      "loss": 3.16712890625,
      "step": 157200
    },
    {
      "epoch": 0.34362703468765277,
      "grad_norm": 0.1825564205646515,
      "learning_rate": 0.003,
      "loss": 3.16823486328125,
      "step": 157300
    },
    {
      "epoch": 0.3438454879837034,
      "grad_norm": 0.18540945649147034,
      "learning_rate": 0.003,
      "loss": 3.1882949829101563,
      "step": 157400
    },
    {
      "epoch": 0.34406394127975404,
      "grad_norm": 0.2009730190038681,
      "learning_rate": 0.003,
      "loss": 3.2248907470703125,
      "step": 157500
    },
    {
      "epoch": 0.3442823945758047,
      "grad_norm": 0.17075271904468536,
      "learning_rate": 0.003,
      "loss": 3.0380267333984374,
      "step": 157600
    },
    {
      "epoch": 0.3445008478718553,
      "grad_norm": 0.1846093088388443,
      "learning_rate": 0.003,
      "loss": 3.610770263671875,
      "step": 157700
    },
    {
      "epoch": 0.34471930116790594,
      "grad_norm": 0.16304230690002441,
      "learning_rate": 0.003,
      "loss": 3.1604934692382813,
      "step": 157800
    },
    {
      "epoch": 0.3449377544639566,
      "grad_norm": 0.19401445984840393,
      "learning_rate": 0.003,
      "loss": 3.1814840698242186,
      "step": 157900
    },
    {
      "epoch": 0.3451562077600072,
      "grad_norm": 0.15682169795036316,
      "learning_rate": 0.003,
      "loss": 3.1792025756835938,
      "step": 158000
    },
    {
      "epoch": 0.34537466105605785,
      "grad_norm": 0.21715964376926422,
      "learning_rate": 0.003,
      "loss": 3.2103289794921874,
      "step": 158100
    },
    {
      "epoch": 0.3455931143521085,
      "grad_norm": 0.167643204331398,
      "learning_rate": 0.003,
      "loss": 3.1870416259765624,
      "step": 158200
    },
    {
      "epoch": 0.3458115676481591,
      "grad_norm": 0.21195171773433685,
      "learning_rate": 0.003,
      "loss": 3.2112298583984376,
      "step": 158300
    },
    {
      "epoch": 0.34603002094420976,
      "grad_norm": 0.20956410467624664,
      "learning_rate": 0.003,
      "loss": 3.1495452880859376,
      "step": 158400
    },
    {
      "epoch": 0.3462484742402604,
      "grad_norm": 0.17523027956485748,
      "learning_rate": 0.003,
      "loss": 3.1977639770507813,
      "step": 158500
    },
    {
      "epoch": 0.34646692753631103,
      "grad_norm": 0.1980908364057541,
      "learning_rate": 0.003,
      "loss": 3.1888766479492188,
      "step": 158600
    },
    {
      "epoch": 0.34668538083236167,
      "grad_norm": 0.14576759934425354,
      "learning_rate": 0.003,
      "loss": 3.16719482421875,
      "step": 158700
    },
    {
      "epoch": 0.3469038341284123,
      "grad_norm": 0.16576829552650452,
      "learning_rate": 0.003,
      "loss": 3.214666442871094,
      "step": 158800
    },
    {
      "epoch": 0.34712228742446294,
      "grad_norm": 0.16519513726234436,
      "learning_rate": 0.003,
      "loss": 3.1716073608398436,
      "step": 158900
    },
    {
      "epoch": 0.3473407407205136,
      "grad_norm": 0.24041765928268433,
      "learning_rate": 0.003,
      "loss": 3.1977297973632814,
      "step": 159000
    },
    {
      "epoch": 0.3475591940165642,
      "grad_norm": 0.20679371058940887,
      "learning_rate": 0.003,
      "loss": 3.1427734375,
      "step": 159100
    },
    {
      "epoch": 0.34777764731261485,
      "grad_norm": 0.13883677124977112,
      "learning_rate": 0.003,
      "loss": 3.21267333984375,
      "step": 159200
    },
    {
      "epoch": 0.3479961006086655,
      "grad_norm": 0.26354363560676575,
      "learning_rate": 0.003,
      "loss": 3.2137460327148437,
      "step": 159300
    },
    {
      "epoch": 0.3482145539047161,
      "grad_norm": 0.20705294609069824,
      "learning_rate": 0.003,
      "loss": 3.1597760009765623,
      "step": 159400
    },
    {
      "epoch": 0.34843300720076675,
      "grad_norm": 0.22643183171749115,
      "learning_rate": 0.003,
      "loss": 3.167184143066406,
      "step": 159500
    },
    {
      "epoch": 0.3486514604968174,
      "grad_norm": 0.18660259246826172,
      "learning_rate": 0.003,
      "loss": 2.986766052246094,
      "step": 159600
    },
    {
      "epoch": 0.348869913792868,
      "grad_norm": 0.15333609282970428,
      "learning_rate": 0.003,
      "loss": 3.2087274169921876,
      "step": 159700
    },
    {
      "epoch": 0.34908836708891866,
      "grad_norm": 0.22221969068050385,
      "learning_rate": 0.003,
      "loss": 3.1692669677734373,
      "step": 159800
    },
    {
      "epoch": 0.3493068203849693,
      "grad_norm": 0.22474493086338043,
      "learning_rate": 0.003,
      "loss": 3.1715362548828123,
      "step": 159900
    },
    {
      "epoch": 0.34952527368101993,
      "grad_norm": 0.198649063706398,
      "learning_rate": 0.003,
      "loss": 3.157160339355469,
      "step": 160000
    },
    {
      "epoch": 0.3497437269770706,
      "grad_norm": 0.15874658524990082,
      "learning_rate": 0.003,
      "loss": 3.153104553222656,
      "step": 160100
    },
    {
      "epoch": 0.34996218027312126,
      "grad_norm": 0.16205880045890808,
      "learning_rate": 0.003,
      "loss": 3.1441021728515626,
      "step": 160200
    },
    {
      "epoch": 0.3501806335691719,
      "grad_norm": 0.15748894214630127,
      "learning_rate": 0.003,
      "loss": 3.1915768432617186,
      "step": 160300
    },
    {
      "epoch": 0.35039908686522253,
      "grad_norm": 0.16804157197475433,
      "learning_rate": 0.003,
      "loss": 2.852764892578125,
      "step": 160400
    },
    {
      "epoch": 0.35061754016127317,
      "grad_norm": 0.1834060698747635,
      "learning_rate": 0.003,
      "loss": 3.20140380859375,
      "step": 160500
    },
    {
      "epoch": 0.3508359934573238,
      "grad_norm": 0.17118389904499054,
      "learning_rate": 0.003,
      "loss": 3.1939096069335937,
      "step": 160600
    },
    {
      "epoch": 0.35105444675337444,
      "grad_norm": 0.1672763228416443,
      "learning_rate": 0.003,
      "loss": 3.1681689453125,
      "step": 160700
    },
    {
      "epoch": 0.3512729000494251,
      "grad_norm": 0.19242221117019653,
      "learning_rate": 0.003,
      "loss": 3.1664584350585936,
      "step": 160800
    },
    {
      "epoch": 0.3514913533454757,
      "grad_norm": 0.15714991092681885,
      "learning_rate": 0.003,
      "loss": 3.109347229003906,
      "step": 160900
    },
    {
      "epoch": 0.35170980664152635,
      "grad_norm": 0.15889999270439148,
      "learning_rate": 0.003,
      "loss": 3.2017071533203123,
      "step": 161000
    },
    {
      "epoch": 0.351928259937577,
      "grad_norm": 0.1645916849374771,
      "learning_rate": 0.003,
      "loss": 3.167985534667969,
      "step": 161100
    },
    {
      "epoch": 0.3521467132336276,
      "grad_norm": 0.23582269251346588,
      "learning_rate": 0.003,
      "loss": 3.177903137207031,
      "step": 161200
    },
    {
      "epoch": 0.35236516652967825,
      "grad_norm": 0.19157132506370544,
      "learning_rate": 0.003,
      "loss": 3.191995849609375,
      "step": 161300
    },
    {
      "epoch": 0.3525836198257289,
      "grad_norm": 0.20941288769245148,
      "learning_rate": 0.003,
      "loss": 3.153175964355469,
      "step": 161400
    },
    {
      "epoch": 0.3528020731217795,
      "grad_norm": 0.1850237399339676,
      "learning_rate": 0.003,
      "loss": 3.170132751464844,
      "step": 161500
    },
    {
      "epoch": 0.35302052641783016,
      "grad_norm": 0.16023872792720795,
      "learning_rate": 0.003,
      "loss": 3.1849407958984375,
      "step": 161600
    },
    {
      "epoch": 0.3532389797138808,
      "grad_norm": 0.16243669390678406,
      "learning_rate": 0.003,
      "loss": 3.1426345825195314,
      "step": 161700
    },
    {
      "epoch": 0.35345743300993143,
      "grad_norm": 0.18923358619213104,
      "learning_rate": 0.003,
      "loss": 3.1663934326171876,
      "step": 161800
    },
    {
      "epoch": 0.35367588630598207,
      "grad_norm": 0.1994985044002533,
      "learning_rate": 0.003,
      "loss": 3.2043157958984376,
      "step": 161900
    },
    {
      "epoch": 0.3538943396020327,
      "grad_norm": 0.19438615441322327,
      "learning_rate": 0.003,
      "loss": 3.2031292724609375,
      "step": 162000
    },
    {
      "epoch": 0.35411279289808334,
      "grad_norm": 0.1888693869113922,
      "learning_rate": 0.003,
      "loss": 3.174179992675781,
      "step": 162100
    },
    {
      "epoch": 0.354331246194134,
      "grad_norm": 0.20153461396694183,
      "learning_rate": 0.003,
      "loss": 3.2011062622070314,
      "step": 162200
    },
    {
      "epoch": 0.3545496994901846,
      "grad_norm": 0.25670602917671204,
      "learning_rate": 0.003,
      "loss": 3.2489642333984374,
      "step": 162300
    },
    {
      "epoch": 0.35476815278623525,
      "grad_norm": 0.3643508851528168,
      "learning_rate": 0.003,
      "loss": 3.1777423095703123,
      "step": 162400
    },
    {
      "epoch": 0.3549866060822859,
      "grad_norm": 0.14907072484493256,
      "learning_rate": 0.003,
      "loss": 3.182525634765625,
      "step": 162500
    },
    {
      "epoch": 0.3552050593783365,
      "grad_norm": 0.18209069967269897,
      "learning_rate": 0.003,
      "loss": 3.164674072265625,
      "step": 162600
    },
    {
      "epoch": 0.35542351267438715,
      "grad_norm": 0.2017740160226822,
      "learning_rate": 0.003,
      "loss": 3.194468688964844,
      "step": 162700
    },
    {
      "epoch": 0.3556419659704378,
      "grad_norm": 0.17735159397125244,
      "learning_rate": 0.003,
      "loss": 3.179418029785156,
      "step": 162800
    },
    {
      "epoch": 0.3558604192664884,
      "grad_norm": 0.25465652346611023,
      "learning_rate": 0.003,
      "loss": 3.181459655761719,
      "step": 162900
    },
    {
      "epoch": 0.35607887256253906,
      "grad_norm": 0.15170180797576904,
      "learning_rate": 0.003,
      "loss": 3.1619601440429688,
      "step": 163000
    },
    {
      "epoch": 0.3562973258585897,
      "grad_norm": 0.18672648072242737,
      "learning_rate": 0.003,
      "loss": 3.165998840332031,
      "step": 163100
    },
    {
      "epoch": 0.35651577915464033,
      "grad_norm": 0.21018573641777039,
      "learning_rate": 0.003,
      "loss": 3.1902142333984376,
      "step": 163200
    },
    {
      "epoch": 0.35673423245069097,
      "grad_norm": 0.5577970743179321,
      "learning_rate": 0.003,
      "loss": 3.1940487670898436,
      "step": 163300
    },
    {
      "epoch": 0.35695268574674166,
      "grad_norm": 0.22371803224086761,
      "learning_rate": 0.003,
      "loss": 3.1257666015625,
      "step": 163400
    },
    {
      "epoch": 0.3571711390427923,
      "grad_norm": 0.17022310197353363,
      "learning_rate": 0.003,
      "loss": 3.1521151733398436,
      "step": 163500
    },
    {
      "epoch": 0.35738959233884293,
      "grad_norm": 0.16075775027275085,
      "learning_rate": 0.003,
      "loss": 3.1516033935546877,
      "step": 163600
    },
    {
      "epoch": 0.35760804563489357,
      "grad_norm": 0.16093774139881134,
      "learning_rate": 0.003,
      "loss": 3.1644271850585937,
      "step": 163700
    },
    {
      "epoch": 0.3578264989309442,
      "grad_norm": 0.20827049016952515,
      "learning_rate": 0.003,
      "loss": 3.182415771484375,
      "step": 163800
    },
    {
      "epoch": 0.35804495222699484,
      "grad_norm": 0.17943401634693146,
      "learning_rate": 0.003,
      "loss": 3.1575823974609376,
      "step": 163900
    },
    {
      "epoch": 0.3582634055230455,
      "grad_norm": 0.19859860837459564,
      "learning_rate": 0.003,
      "loss": 3.145097351074219,
      "step": 164000
    },
    {
      "epoch": 0.3584818588190961,
      "grad_norm": 0.20336900651454926,
      "learning_rate": 0.003,
      "loss": 3.185714111328125,
      "step": 164100
    },
    {
      "epoch": 0.35870031211514675,
      "grad_norm": 0.18309247493743896,
      "learning_rate": 0.003,
      "loss": 3.1826467895507813,
      "step": 164200
    },
    {
      "epoch": 0.3589187654111974,
      "grad_norm": 0.17939050495624542,
      "learning_rate": 0.003,
      "loss": 3.1910614013671874,
      "step": 164300
    },
    {
      "epoch": 0.359137218707248,
      "grad_norm": 0.20175869762897491,
      "learning_rate": 0.003,
      "loss": 3.1837725830078125,
      "step": 164400
    },
    {
      "epoch": 0.35935567200329865,
      "grad_norm": 0.21120579540729523,
      "learning_rate": 0.003,
      "loss": 3.1697833251953127,
      "step": 164500
    },
    {
      "epoch": 0.3595741252993493,
      "grad_norm": 0.1523100584745407,
      "learning_rate": 0.003,
      "loss": 3.161806945800781,
      "step": 164600
    },
    {
      "epoch": 0.3597925785953999,
      "grad_norm": 0.18864744901657104,
      "learning_rate": 0.003,
      "loss": 3.1357794189453125,
      "step": 164700
    },
    {
      "epoch": 0.36001103189145056,
      "grad_norm": 0.1667052060365677,
      "learning_rate": 0.003,
      "loss": 3.1624359130859374,
      "step": 164800
    },
    {
      "epoch": 0.3602294851875012,
      "grad_norm": 0.5051073431968689,
      "learning_rate": 0.003,
      "loss": 3.1776788330078123,
      "step": 164900
    },
    {
      "epoch": 0.36044793848355183,
      "grad_norm": 0.1835436075925827,
      "learning_rate": 0.003,
      "loss": 3.2048748779296874,
      "step": 165000
    },
    {
      "epoch": 0.36066639177960247,
      "grad_norm": 0.2018285095691681,
      "learning_rate": 0.003,
      "loss": 3.1898895263671876,
      "step": 165100
    },
    {
      "epoch": 0.3608848450756531,
      "grad_norm": 0.2360716611146927,
      "learning_rate": 0.003,
      "loss": 3.1715792846679687,
      "step": 165200
    },
    {
      "epoch": 0.36110329837170374,
      "grad_norm": 0.19357648491859436,
      "learning_rate": 0.003,
      "loss": 3.1751763916015623,
      "step": 165300
    },
    {
      "epoch": 0.3613217516677544,
      "grad_norm": 0.22794722020626068,
      "learning_rate": 0.003,
      "loss": 3.1800875854492188,
      "step": 165400
    },
    {
      "epoch": 0.361540204963805,
      "grad_norm": 0.18184566497802734,
      "learning_rate": 0.003,
      "loss": 3.2099285888671876,
      "step": 165500
    },
    {
      "epoch": 0.36175865825985565,
      "grad_norm": 0.1959710717201233,
      "learning_rate": 0.003,
      "loss": 3.0024569702148436,
      "step": 165600
    },
    {
      "epoch": 0.3619771115559063,
      "grad_norm": 0.2441798746585846,
      "learning_rate": 0.003,
      "loss": 3.160757751464844,
      "step": 165700
    },
    {
      "epoch": 0.3621955648519569,
      "grad_norm": 0.2302255481481552,
      "learning_rate": 0.003,
      "loss": 3.1961187744140624,
      "step": 165800
    },
    {
      "epoch": 0.36241401814800756,
      "grad_norm": 0.22491635382175446,
      "learning_rate": 0.003,
      "loss": 3.1815185546875,
      "step": 165900
    },
    {
      "epoch": 0.3626324714440582,
      "grad_norm": 0.19608400762081146,
      "learning_rate": 0.003,
      "loss": 3.2075823974609374,
      "step": 166000
    },
    {
      "epoch": 0.3628509247401088,
      "grad_norm": 0.18288902938365936,
      "learning_rate": 0.003,
      "loss": 3.1492605590820313,
      "step": 166100
    },
    {
      "epoch": 0.36306937803615946,
      "grad_norm": 0.20123060047626495,
      "learning_rate": 0.003,
      "loss": 3.1266104125976564,
      "step": 166200
    },
    {
      "epoch": 0.3632878313322101,
      "grad_norm": 0.16410323977470398,
      "learning_rate": 0.003,
      "loss": 3.211439208984375,
      "step": 166300
    },
    {
      "epoch": 0.36350628462826073,
      "grad_norm": 0.27165287733078003,
      "learning_rate": 0.003,
      "loss": 3.137961730957031,
      "step": 166400
    },
    {
      "epoch": 0.36372473792431137,
      "grad_norm": 0.17709319293498993,
      "learning_rate": 0.003,
      "loss": 3.179796142578125,
      "step": 166500
    },
    {
      "epoch": 0.363943191220362,
      "grad_norm": 0.1782919019460678,
      "learning_rate": 0.003,
      "loss": 3.16959716796875,
      "step": 166600
    },
    {
      "epoch": 0.3641616445164127,
      "grad_norm": 0.35208815336227417,
      "learning_rate": 0.003,
      "loss": 3.157923583984375,
      "step": 166700
    },
    {
      "epoch": 0.36438009781246333,
      "grad_norm": 0.2911792993545532,
      "learning_rate": 0.003,
      "loss": 3.1828079223632812,
      "step": 166800
    },
    {
      "epoch": 0.36459855110851397,
      "grad_norm": 0.1510099470615387,
      "learning_rate": 0.003,
      "loss": 3.1355581665039063,
      "step": 166900
    },
    {
      "epoch": 0.3648170044045646,
      "grad_norm": 0.15822523832321167,
      "learning_rate": 0.003,
      "loss": 3.156095275878906,
      "step": 167000
    },
    {
      "epoch": 0.36503545770061524,
      "grad_norm": 0.21178464591503143,
      "learning_rate": 0.003,
      "loss": 3.1742117309570315,
      "step": 167100
    },
    {
      "epoch": 0.3652539109966659,
      "grad_norm": 0.1757752001285553,
      "learning_rate": 0.003,
      "loss": 3.174485778808594,
      "step": 167200
    },
    {
      "epoch": 0.3654723642927165,
      "grad_norm": 0.18174314498901367,
      "learning_rate": 0.003,
      "loss": 3.14523193359375,
      "step": 167300
    },
    {
      "epoch": 0.36569081758876715,
      "grad_norm": 0.518521249294281,
      "learning_rate": 0.003,
      "loss": 3.1884396362304686,
      "step": 167400
    },
    {
      "epoch": 0.3659092708848178,
      "grad_norm": 0.16352346539497375,
      "learning_rate": 0.003,
      "loss": 3.2025137329101563,
      "step": 167500
    },
    {
      "epoch": 0.3661277241808684,
      "grad_norm": 0.18585847318172455,
      "learning_rate": 0.003,
      "loss": 3.1688381958007814,
      "step": 167600
    },
    {
      "epoch": 0.36634617747691905,
      "grad_norm": 0.1814800202846527,
      "learning_rate": 0.003,
      "loss": 3.1297698974609376,
      "step": 167700
    },
    {
      "epoch": 0.3665646307729697,
      "grad_norm": 0.21663619577884674,
      "learning_rate": 0.003,
      "loss": 3.1845257568359373,
      "step": 167800
    },
    {
      "epoch": 0.3667830840690203,
      "grad_norm": 0.19967739284038544,
      "learning_rate": 0.003,
      "loss": 3.168363037109375,
      "step": 167900
    },
    {
      "epoch": 0.36700153736507096,
      "grad_norm": 0.21710465848445892,
      "learning_rate": 0.003,
      "loss": 3.141382141113281,
      "step": 168000
    },
    {
      "epoch": 0.3672199906611216,
      "grad_norm": 0.1510242074728012,
      "learning_rate": 0.003,
      "loss": 3.1255453491210936,
      "step": 168100
    },
    {
      "epoch": 0.36743844395717223,
      "grad_norm": 0.17854678630828857,
      "learning_rate": 0.003,
      "loss": 3.161729431152344,
      "step": 168200
    },
    {
      "epoch": 0.36765689725322287,
      "grad_norm": 0.17349831759929657,
      "learning_rate": 0.003,
      "loss": 3.1506829833984376,
      "step": 168300
    },
    {
      "epoch": 0.3678753505492735,
      "grad_norm": 0.20964941382408142,
      "learning_rate": 0.003,
      "loss": 3.1614804077148437,
      "step": 168400
    },
    {
      "epoch": 0.36809380384532414,
      "grad_norm": 0.18232828378677368,
      "learning_rate": 0.003,
      "loss": 3.1394619750976562,
      "step": 168500
    },
    {
      "epoch": 0.3683122571413748,
      "grad_norm": 0.18587465584278107,
      "learning_rate": 0.003,
      "loss": 3.138177490234375,
      "step": 168600
    },
    {
      "epoch": 0.3685307104374254,
      "grad_norm": 0.16894890367984772,
      "learning_rate": 0.003,
      "loss": 3.140600280761719,
      "step": 168700
    },
    {
      "epoch": 0.36874916373347605,
      "grad_norm": 0.1663913130760193,
      "learning_rate": 0.003,
      "loss": 3.1340020751953124,
      "step": 168800
    },
    {
      "epoch": 0.3689676170295267,
      "grad_norm": 0.18308806419372559,
      "learning_rate": 0.003,
      "loss": 3.1322091674804686,
      "step": 168900
    },
    {
      "epoch": 0.3691860703255773,
      "grad_norm": 0.17913620173931122,
      "learning_rate": 0.003,
      "loss": 3.1869467163085936,
      "step": 169000
    },
    {
      "epoch": 0.36940452362162796,
      "grad_norm": 0.17994114756584167,
      "learning_rate": 0.003,
      "loss": 3.161597900390625,
      "step": 169100
    },
    {
      "epoch": 0.3696229769176786,
      "grad_norm": 0.24657736718654633,
      "learning_rate": 0.003,
      "loss": 3.18466796875,
      "step": 169200
    },
    {
      "epoch": 0.3698414302137292,
      "grad_norm": 0.2047869861125946,
      "learning_rate": 0.003,
      "loss": 3.159703369140625,
      "step": 169300
    },
    {
      "epoch": 0.37005988350977986,
      "grad_norm": 0.19242806732654572,
      "learning_rate": 0.003,
      "loss": 3.1549224853515625,
      "step": 169400
    },
    {
      "epoch": 0.3702783368058305,
      "grad_norm": 0.16597582399845123,
      "learning_rate": 0.003,
      "loss": 2.662752685546875,
      "step": 169500
    },
    {
      "epoch": 0.37049679010188113,
      "grad_norm": 0.16965866088867188,
      "learning_rate": 0.003,
      "loss": 3.1691912841796874,
      "step": 169600
    },
    {
      "epoch": 0.37071524339793177,
      "grad_norm": 0.20084130764007568,
      "learning_rate": 0.003,
      "loss": 3.1637203979492186,
      "step": 169700
    },
    {
      "epoch": 0.3709336966939824,
      "grad_norm": 0.2667574882507324,
      "learning_rate": 0.003,
      "loss": 3.2269778442382813,
      "step": 169800
    },
    {
      "epoch": 0.37115214999003304,
      "grad_norm": 0.15130512416362762,
      "learning_rate": 0.003,
      "loss": 3.1921926879882814,
      "step": 169900
    },
    {
      "epoch": 0.3713706032860837,
      "grad_norm": 0.174052894115448,
      "learning_rate": 0.003,
      "loss": 3.1462887573242186,
      "step": 170000
    },
    {
      "epoch": 0.37158905658213437,
      "grad_norm": 0.2540212869644165,
      "learning_rate": 0.003,
      "loss": 3.191412048339844,
      "step": 170100
    },
    {
      "epoch": 0.371807509878185,
      "grad_norm": 0.1751745641231537,
      "learning_rate": 0.003,
      "loss": 3.163149719238281,
      "step": 170200
    },
    {
      "epoch": 0.37202596317423564,
      "grad_norm": 0.00035413738805800676,
      "learning_rate": 0.003,
      "loss": 2.687419738769531,
      "step": 170300
    },
    {
      "epoch": 0.3722444164702863,
      "grad_norm": 0.2043706476688385,
      "learning_rate": 0.003,
      "loss": 3.1186868286132814,
      "step": 170400
    },
    {
      "epoch": 0.3724628697663369,
      "grad_norm": 0.1679484248161316,
      "learning_rate": 0.003,
      "loss": 3.1967398071289064,
      "step": 170500
    },
    {
      "epoch": 0.37268132306238755,
      "grad_norm": 0.2904697358608246,
      "learning_rate": 0.003,
      "loss": 3.1709967041015625,
      "step": 170600
    },
    {
      "epoch": 0.3728997763584382,
      "grad_norm": 0.21322306990623474,
      "learning_rate": 0.003,
      "loss": 3.141817321777344,
      "step": 170700
    },
    {
      "epoch": 0.3731182296544888,
      "grad_norm": 0.14787624776363373,
      "learning_rate": 0.003,
      "loss": 3.2048321533203126,
      "step": 170800
    },
    {
      "epoch": 0.37333668295053946,
      "grad_norm": 0.17608416080474854,
      "learning_rate": 0.003,
      "loss": 3.1848239135742187,
      "step": 170900
    },
    {
      "epoch": 0.3735551362465901,
      "grad_norm": 0.1883745938539505,
      "learning_rate": 0.003,
      "loss": 3.1780520629882814,
      "step": 171000
    },
    {
      "epoch": 0.3737735895426407,
      "grad_norm": 0.20483990013599396,
      "learning_rate": 0.003,
      "loss": 3.147355041503906,
      "step": 171100
    },
    {
      "epoch": 0.37399204283869136,
      "grad_norm": 0.17721770703792572,
      "learning_rate": 0.003,
      "loss": 3.1759442138671874,
      "step": 171200
    },
    {
      "epoch": 0.374210496134742,
      "grad_norm": 0.20947828888893127,
      "learning_rate": 0.003,
      "loss": 3.153690185546875,
      "step": 171300
    },
    {
      "epoch": 0.37442894943079263,
      "grad_norm": 0.18290311098098755,
      "learning_rate": 0.003,
      "loss": 3.1686737060546877,
      "step": 171400
    },
    {
      "epoch": 0.37464740272684327,
      "grad_norm": 0.1574389636516571,
      "learning_rate": 0.003,
      "loss": 3.1793585205078125,
      "step": 171500
    },
    {
      "epoch": 0.3748658560228939,
      "grad_norm": 0.15030884742736816,
      "learning_rate": 0.003,
      "loss": 3.1732888793945313,
      "step": 171600
    },
    {
      "epoch": 0.37508430931894454,
      "grad_norm": 0.16997474431991577,
      "learning_rate": 0.003,
      "loss": 3.188775634765625,
      "step": 171700
    },
    {
      "epoch": 0.3753027626149952,
      "grad_norm": 0.22101706266403198,
      "learning_rate": 0.003,
      "loss": 3.197449035644531,
      "step": 171800
    },
    {
      "epoch": 0.3755212159110458,
      "grad_norm": 0.17496024072170258,
      "learning_rate": 0.003,
      "loss": 3.203875732421875,
      "step": 171900
    },
    {
      "epoch": 0.37573966920709645,
      "grad_norm": 0.17610163986682892,
      "learning_rate": 0.003,
      "loss": 3.1838259887695313,
      "step": 172000
    },
    {
      "epoch": 0.3759581225031471,
      "grad_norm": 0.23574644327163696,
      "learning_rate": 0.003,
      "loss": 3.2316879272460937,
      "step": 172100
    },
    {
      "epoch": 0.3761765757991977,
      "grad_norm": 0.1853731870651245,
      "learning_rate": 0.003,
      "loss": 3.16897216796875,
      "step": 172200
    },
    {
      "epoch": 0.37639502909524836,
      "grad_norm": 0.20266756415367126,
      "learning_rate": 0.003,
      "loss": 3.190309753417969,
      "step": 172300
    },
    {
      "epoch": 0.376613482391299,
      "grad_norm": 0.20375439524650574,
      "learning_rate": 0.003,
      "loss": 3.1641986083984377,
      "step": 172400
    },
    {
      "epoch": 0.37683193568734963,
      "grad_norm": 0.20845149457454681,
      "learning_rate": 0.003,
      "loss": 3.210990295410156,
      "step": 172500
    },
    {
      "epoch": 0.37705038898340026,
      "grad_norm": 0.19991101324558258,
      "learning_rate": 0.003,
      "loss": 3.2443212890625,
      "step": 172600
    },
    {
      "epoch": 0.3772688422794509,
      "grad_norm": 0.154100701212883,
      "learning_rate": 0.003,
      "loss": 3.2246954345703127,
      "step": 172700
    },
    {
      "epoch": 0.37748729557550154,
      "grad_norm": 0.1711597740650177,
      "learning_rate": 0.003,
      "loss": 3.2270681762695315,
      "step": 172800
    },
    {
      "epoch": 0.37770574887155217,
      "grad_norm": 0.247129425406456,
      "learning_rate": 0.003,
      "loss": 3.20664306640625,
      "step": 172900
    },
    {
      "epoch": 0.3779242021676028,
      "grad_norm": 0.24660581350326538,
      "learning_rate": 0.003,
      "loss": 3.2140847778320314,
      "step": 173000
    },
    {
      "epoch": 0.37814265546365344,
      "grad_norm": 0.18991594016551971,
      "learning_rate": 0.003,
      "loss": 3.2020697021484374,
      "step": 173100
    },
    {
      "epoch": 0.3783611087597041,
      "grad_norm": 0.26336154341697693,
      "learning_rate": 0.003,
      "loss": 3.2781741333007814,
      "step": 173200
    },
    {
      "epoch": 0.3785795620557547,
      "grad_norm": 0.22249069809913635,
      "learning_rate": 0.003,
      "loss": 3.2405606079101563,
      "step": 173300
    },
    {
      "epoch": 0.3787980153518054,
      "grad_norm": 0.16853059828281403,
      "learning_rate": 0.003,
      "loss": 3.2344839477539065,
      "step": 173400
    },
    {
      "epoch": 0.37901646864785604,
      "grad_norm": 0.20300891995429993,
      "learning_rate": 0.003,
      "loss": 3.2035012817382813,
      "step": 173500
    },
    {
      "epoch": 0.3792349219439067,
      "grad_norm": 0.18374000489711761,
      "learning_rate": 0.003,
      "loss": 3.185467529296875,
      "step": 173600
    },
    {
      "epoch": 0.3794533752399573,
      "grad_norm": 0.1773572713136673,
      "learning_rate": 0.003,
      "loss": 3.164620361328125,
      "step": 173700
    },
    {
      "epoch": 0.37967182853600795,
      "grad_norm": 0.1525661200284958,
      "learning_rate": 0.003,
      "loss": 3.199691162109375,
      "step": 173800
    },
    {
      "epoch": 0.3798902818320586,
      "grad_norm": 0.17256557941436768,
      "learning_rate": 0.003,
      "loss": 3.224908447265625,
      "step": 173900
    },
    {
      "epoch": 0.3801087351281092,
      "grad_norm": 0.2591119408607483,
      "learning_rate": 0.003,
      "loss": 3.2349179077148436,
      "step": 174000
    },
    {
      "epoch": 0.38032718842415986,
      "grad_norm": 0.16154177486896515,
      "learning_rate": 0.003,
      "loss": 3.2010772705078123,
      "step": 174100
    },
    {
      "epoch": 0.3805456417202105,
      "grad_norm": 0.19662171602249146,
      "learning_rate": 0.003,
      "loss": 3.1979550170898436,
      "step": 174200
    },
    {
      "epoch": 0.38076409501626113,
      "grad_norm": 0.17070196568965912,
      "learning_rate": 0.003,
      "loss": 3.2065390014648436,
      "step": 174300
    },
    {
      "epoch": 0.38098254831231176,
      "grad_norm": 0.166769877076149,
      "learning_rate": 0.003,
      "loss": 3.196834716796875,
      "step": 174400
    },
    {
      "epoch": 0.3812010016083624,
      "grad_norm": 0.1641005277633667,
      "learning_rate": 0.003,
      "loss": 3.2014871215820313,
      "step": 174500
    },
    {
      "epoch": 0.38141945490441304,
      "grad_norm": 0.16330087184906006,
      "learning_rate": 0.003,
      "loss": 3.1944268798828124,
      "step": 174600
    },
    {
      "epoch": 0.38163790820046367,
      "grad_norm": 0.16005554795265198,
      "learning_rate": 0.003,
      "loss": 3.1742156982421874,
      "step": 174700
    },
    {
      "epoch": 0.3818563614965143,
      "grad_norm": 0.18322737514972687,
      "learning_rate": 0.003,
      "loss": 3.221568908691406,
      "step": 174800
    },
    {
      "epoch": 0.38207481479256494,
      "grad_norm": 0.19929206371307373,
      "learning_rate": 0.003,
      "loss": 3.1643942260742186,
      "step": 174900
    },
    {
      "epoch": 0.3822932680886156,
      "grad_norm": 0.16595686972141266,
      "learning_rate": 0.003,
      "loss": 3.182112731933594,
      "step": 175000
    },
    {
      "epoch": 0.3825117213846662,
      "grad_norm": 0.19006474316120148,
      "learning_rate": 0.003,
      "loss": 3.1701290893554686,
      "step": 175100
    },
    {
      "epoch": 0.38273017468071685,
      "grad_norm": 0.15593139827251434,
      "learning_rate": 0.003,
      "loss": 3.174017333984375,
      "step": 175200
    },
    {
      "epoch": 0.3829486279767675,
      "grad_norm": 0.20773789286613464,
      "learning_rate": 0.003,
      "loss": 3.1538961791992186,
      "step": 175300
    },
    {
      "epoch": 0.3831670812728181,
      "grad_norm": 0.17083348333835602,
      "learning_rate": 0.003,
      "loss": 3.1885342407226562,
      "step": 175400
    },
    {
      "epoch": 0.38338553456886876,
      "grad_norm": 0.2512657344341278,
      "learning_rate": 0.003,
      "loss": 3.14274658203125,
      "step": 175500
    },
    {
      "epoch": 0.3836039878649194,
      "grad_norm": 0.16406364738941193,
      "learning_rate": 0.003,
      "loss": 2.6761962890625,
      "step": 175600
    },
    {
      "epoch": 0.38382244116097003,
      "grad_norm": 0.16905443370342255,
      "learning_rate": 0.003,
      "loss": 3.1923626708984374,
      "step": 175700
    },
    {
      "epoch": 0.38404089445702067,
      "grad_norm": 0.16064132750034332,
      "learning_rate": 0.003,
      "loss": 3.1826531982421873,
      "step": 175800
    },
    {
      "epoch": 0.3842593477530713,
      "grad_norm": 0.2164846956729889,
      "learning_rate": 0.003,
      "loss": 3.1615655517578123,
      "step": 175900
    },
    {
      "epoch": 0.38447780104912194,
      "grad_norm": 0.1583317667245865,
      "learning_rate": 0.003,
      "loss": 3.201859436035156,
      "step": 176000
    },
    {
      "epoch": 0.3846962543451726,
      "grad_norm": 0.16627265512943268,
      "learning_rate": 0.003,
      "loss": 3.1486477661132812,
      "step": 176100
    },
    {
      "epoch": 0.3849147076412232,
      "grad_norm": 0.1639377474784851,
      "learning_rate": 0.003,
      "loss": 3.169761962890625,
      "step": 176200
    },
    {
      "epoch": 0.38513316093727384,
      "grad_norm": 0.19453413784503937,
      "learning_rate": 0.003,
      "loss": 3.1988360595703127,
      "step": 176300
    },
    {
      "epoch": 0.3853516142333245,
      "grad_norm": 0.18382062017917633,
      "learning_rate": 0.003,
      "loss": 3.1751812744140624,
      "step": 176400
    },
    {
      "epoch": 0.3855700675293751,
      "grad_norm": 0.1976117342710495,
      "learning_rate": 0.003,
      "loss": 3.2183651733398437,
      "step": 176500
    },
    {
      "epoch": 0.38578852082542575,
      "grad_norm": 0.18467845022678375,
      "learning_rate": 0.003,
      "loss": 3.192021484375,
      "step": 176600
    },
    {
      "epoch": 0.38600697412147644,
      "grad_norm": 0.19127489626407623,
      "learning_rate": 0.003,
      "loss": 3.1882254028320314,
      "step": 176700
    },
    {
      "epoch": 0.3862254274175271,
      "grad_norm": 0.1888899803161621,
      "learning_rate": 0.003,
      "loss": 3.162183837890625,
      "step": 176800
    },
    {
      "epoch": 0.3864438807135777,
      "grad_norm": 0.1641494482755661,
      "learning_rate": 0.003,
      "loss": 3.1763565063476564,
      "step": 176900
    },
    {
      "epoch": 0.38666233400962835,
      "grad_norm": 0.15415582060813904,
      "learning_rate": 0.003,
      "loss": 3.195016174316406,
      "step": 177000
    },
    {
      "epoch": 0.386880787305679,
      "grad_norm": 0.17659373581409454,
      "learning_rate": 0.003,
      "loss": 3.119770812988281,
      "step": 177100
    },
    {
      "epoch": 0.3870992406017296,
      "grad_norm": 0.16927744448184967,
      "learning_rate": 0.003,
      "loss": 3.176107177734375,
      "step": 177200
    },
    {
      "epoch": 0.38731769389778026,
      "grad_norm": 0.19438721239566803,
      "learning_rate": 0.003,
      "loss": 3.2074679565429687,
      "step": 177300
    },
    {
      "epoch": 0.3875361471938309,
      "grad_norm": 0.15416471660137177,
      "learning_rate": 0.003,
      "loss": 3.2117568969726564,
      "step": 177400
    },
    {
      "epoch": 0.38775460048988153,
      "grad_norm": 0.17606864869594574,
      "learning_rate": 0.003,
      "loss": 3.1845907592773437,
      "step": 177500
    },
    {
      "epoch": 0.38797305378593216,
      "grad_norm": 0.19547538459300995,
      "learning_rate": 0.003,
      "loss": 3.1783538818359376,
      "step": 177600
    },
    {
      "epoch": 0.3881915070819828,
      "grad_norm": 0.18645234405994415,
      "learning_rate": 0.003,
      "loss": 3.2376785278320312,
      "step": 177700
    },
    {
      "epoch": 0.38840996037803344,
      "grad_norm": 0.23108743131160736,
      "learning_rate": 0.003,
      "loss": 3.2205044555664064,
      "step": 177800
    },
    {
      "epoch": 0.38862841367408407,
      "grad_norm": 0.17245976626873016,
      "learning_rate": 0.003,
      "loss": 3.1801324462890626,
      "step": 177900
    },
    {
      "epoch": 0.3888468669701347,
      "grad_norm": 0.19993457198143005,
      "learning_rate": 0.003,
      "loss": 3.218960876464844,
      "step": 178000
    },
    {
      "epoch": 0.38906532026618534,
      "grad_norm": 0.16413789987564087,
      "learning_rate": 0.003,
      "loss": 3.25513916015625,
      "step": 178100
    },
    {
      "epoch": 0.389283773562236,
      "grad_norm": 0.17564861476421356,
      "learning_rate": 0.003,
      "loss": 3.1856689453125,
      "step": 178200
    },
    {
      "epoch": 0.3895022268582866,
      "grad_norm": 0.1771843135356903,
      "learning_rate": 0.003,
      "loss": 3.1699493408203123,
      "step": 178300
    },
    {
      "epoch": 0.38972068015433725,
      "grad_norm": 0.23479892313480377,
      "learning_rate": 0.003,
      "loss": 3.1898736572265625,
      "step": 178400
    },
    {
      "epoch": 0.3899391334503879,
      "grad_norm": 0.22637808322906494,
      "learning_rate": 0.003,
      "loss": 3.2417608642578126,
      "step": 178500
    },
    {
      "epoch": 0.3901575867464385,
      "grad_norm": 0.20749548077583313,
      "learning_rate": 0.003,
      "loss": 3.2173748779296876,
      "step": 178600
    },
    {
      "epoch": 0.39037604004248916,
      "grad_norm": 0.24027517437934875,
      "learning_rate": 0.003,
      "loss": 3.2008792114257814,
      "step": 178700
    },
    {
      "epoch": 0.3905944933385398,
      "grad_norm": 0.2996484041213989,
      "learning_rate": 0.003,
      "loss": 3.2116827392578124,
      "step": 178800
    },
    {
      "epoch": 0.39081294663459043,
      "grad_norm": 0.2518756687641144,
      "learning_rate": 0.003,
      "loss": 3.206076354980469,
      "step": 178900
    },
    {
      "epoch": 0.39103139993064107,
      "grad_norm": 0.16661737859249115,
      "learning_rate": 0.003,
      "loss": 3.210162353515625,
      "step": 179000
    },
    {
      "epoch": 0.3912498532266917,
      "grad_norm": 0.24294422566890717,
      "learning_rate": 0.003,
      "loss": 3.22596923828125,
      "step": 179100
    },
    {
      "epoch": 0.39146830652274234,
      "grad_norm": 0.2290848344564438,
      "learning_rate": 0.003,
      "loss": 3.2135052490234375,
      "step": 179200
    },
    {
      "epoch": 0.391686759818793,
      "grad_norm": 0.20530222356319427,
      "learning_rate": 0.003,
      "loss": 3.175398254394531,
      "step": 179300
    },
    {
      "epoch": 0.3919052131148436,
      "grad_norm": 0.155564546585083,
      "learning_rate": 0.003,
      "loss": 3.2350369262695313,
      "step": 179400
    },
    {
      "epoch": 0.39212366641089424,
      "grad_norm": 0.1554679423570633,
      "learning_rate": 0.003,
      "loss": 3.1975277709960936,
      "step": 179500
    },
    {
      "epoch": 0.3923421197069449,
      "grad_norm": 0.18789929151535034,
      "learning_rate": 0.003,
      "loss": 3.2127108764648438,
      "step": 179600
    },
    {
      "epoch": 0.3925605730029955,
      "grad_norm": 0.15663255751132965,
      "learning_rate": 0.003,
      "loss": 3.192061462402344,
      "step": 179700
    },
    {
      "epoch": 0.39277902629904615,
      "grad_norm": 0.18579837679862976,
      "learning_rate": 0.003,
      "loss": 3.209206237792969,
      "step": 179800
    },
    {
      "epoch": 0.3929974795950968,
      "grad_norm": 0.20511704683303833,
      "learning_rate": 0.003,
      "loss": 3.171172790527344,
      "step": 179900
    },
    {
      "epoch": 0.3932159328911475,
      "grad_norm": 0.19241897761821747,
      "learning_rate": 0.003,
      "loss": 3.2022442626953125,
      "step": 180000
    },
    {
      "epoch": 0.3934343861871981,
      "grad_norm": 0.22241468727588654,
      "learning_rate": 0.003,
      "loss": 3.2042965698242187,
      "step": 180100
    },
    {
      "epoch": 0.39365283948324875,
      "grad_norm": 0.17366726696491241,
      "learning_rate": 0.003,
      "loss": 3.2068716430664064,
      "step": 180200
    },
    {
      "epoch": 0.3938712927792994,
      "grad_norm": 0.15627704560756683,
      "learning_rate": 0.003,
      "loss": 3.175196228027344,
      "step": 180300
    },
    {
      "epoch": 0.39408974607535,
      "grad_norm": 0.15205363929271698,
      "learning_rate": 0.003,
      "loss": 3.1975534057617185,
      "step": 180400
    },
    {
      "epoch": 0.39430819937140066,
      "grad_norm": 0.16736654937267303,
      "learning_rate": 0.003,
      "loss": 3.187356262207031,
      "step": 180500
    },
    {
      "epoch": 0.3945266526674513,
      "grad_norm": 0.19624421000480652,
      "learning_rate": 0.003,
      "loss": 3.2102737426757812,
      "step": 180600
    },
    {
      "epoch": 0.39474510596350193,
      "grad_norm": 0.1805698722600937,
      "learning_rate": 0.003,
      "loss": 3.180150146484375,
      "step": 180700
    },
    {
      "epoch": 0.39496355925955257,
      "grad_norm": 0.18465137481689453,
      "learning_rate": 0.003,
      "loss": 3.1614202880859374,
      "step": 180800
    },
    {
      "epoch": 0.3951820125556032,
      "grad_norm": 0.16542978584766388,
      "learning_rate": 0.003,
      "loss": 3.1504254150390625,
      "step": 180900
    },
    {
      "epoch": 0.39540046585165384,
      "grad_norm": 0.1758163422346115,
      "learning_rate": 0.003,
      "loss": 3.1490249633789062,
      "step": 181000
    },
    {
      "epoch": 0.3956189191477045,
      "grad_norm": 0.18850696086883545,
      "learning_rate": 0.003,
      "loss": 3.1426467895507812,
      "step": 181100
    },
    {
      "epoch": 0.3958373724437551,
      "grad_norm": 0.17692168056964874,
      "learning_rate": 0.003,
      "loss": 3.1734588623046873,
      "step": 181200
    },
    {
      "epoch": 0.39605582573980574,
      "grad_norm": 0.16410307586193085,
      "learning_rate": 0.003,
      "loss": 3.1863198852539063,
      "step": 181300
    },
    {
      "epoch": 0.3962742790358564,
      "grad_norm": 0.25289323925971985,
      "learning_rate": 0.003,
      "loss": 3.1587969970703127,
      "step": 181400
    },
    {
      "epoch": 0.396492732331907,
      "grad_norm": 0.19366581737995148,
      "learning_rate": 0.003,
      "loss": 3.211064758300781,
      "step": 181500
    },
    {
      "epoch": 0.39671118562795765,
      "grad_norm": 0.2294604331254959,
      "learning_rate": 0.003,
      "loss": 3.2051434326171875,
      "step": 181600
    },
    {
      "epoch": 0.3969296389240083,
      "grad_norm": 0.17076918482780457,
      "learning_rate": 0.003,
      "loss": 3.193789367675781,
      "step": 181700
    },
    {
      "epoch": 0.3971480922200589,
      "grad_norm": 0.17950652539730072,
      "learning_rate": 0.003,
      "loss": 3.2237493896484377,
      "step": 181800
    },
    {
      "epoch": 0.39736654551610956,
      "grad_norm": 0.24848604202270508,
      "learning_rate": 0.003,
      "loss": 3.241496887207031,
      "step": 181900
    },
    {
      "epoch": 0.3975849988121602,
      "grad_norm": 0.1843125969171524,
      "learning_rate": 0.003,
      "loss": 3.196874694824219,
      "step": 182000
    },
    {
      "epoch": 0.39780345210821083,
      "grad_norm": 0.32231807708740234,
      "learning_rate": 0.003,
      "loss": 3.22003662109375,
      "step": 182100
    },
    {
      "epoch": 0.39802190540426147,
      "grad_norm": 0.19519482553005219,
      "learning_rate": 0.003,
      "loss": 3.2470156860351564,
      "step": 182200
    },
    {
      "epoch": 0.3982403587003121,
      "grad_norm": 0.1507253795862198,
      "learning_rate": 0.003,
      "loss": 3.1745220947265627,
      "step": 182300
    },
    {
      "epoch": 0.39845881199636274,
      "grad_norm": 0.1799633651971817,
      "learning_rate": 0.003,
      "loss": 3.2416131591796873,
      "step": 182400
    },
    {
      "epoch": 0.3986772652924134,
      "grad_norm": 0.20338909327983856,
      "learning_rate": 0.003,
      "loss": 3.237012939453125,
      "step": 182500
    },
    {
      "epoch": 0.398895718588464,
      "grad_norm": 0.1542854607105255,
      "learning_rate": 0.003,
      "loss": 3.200860900878906,
      "step": 182600
    },
    {
      "epoch": 0.39911417188451465,
      "grad_norm": 0.1492144614458084,
      "learning_rate": 0.003,
      "loss": 3.2179913330078125,
      "step": 182700
    },
    {
      "epoch": 0.3993326251805653,
      "grad_norm": 0.2120392918586731,
      "learning_rate": 0.003,
      "loss": 3.2081158447265623,
      "step": 182800
    },
    {
      "epoch": 0.3995510784766159,
      "grad_norm": 0.1635083109140396,
      "learning_rate": 0.003,
      "loss": 3.18388671875,
      "step": 182900
    },
    {
      "epoch": 0.39976953177266655,
      "grad_norm": 0.19470767676830292,
      "learning_rate": 0.003,
      "loss": 3.1972232055664063,
      "step": 183000
    },
    {
      "epoch": 0.3999879850687172,
      "grad_norm": 0.16689738631248474,
      "learning_rate": 0.003,
      "loss": 3.18633056640625,
      "step": 183100
    },
    {
      "epoch": 0.4002064383647678,
      "grad_norm": 0.1567814201116562,
      "learning_rate": 0.003,
      "loss": 3.235396423339844,
      "step": 183200
    },
    {
      "epoch": 0.4004248916608185,
      "grad_norm": 0.24050599336624146,
      "learning_rate": 0.003,
      "loss": 3.2023196411132813,
      "step": 183300
    },
    {
      "epoch": 0.40064334495686915,
      "grad_norm": 0.17390838265419006,
      "learning_rate": 0.003,
      "loss": 3.172646179199219,
      "step": 183400
    },
    {
      "epoch": 0.4008617982529198,
      "grad_norm": 0.16362504661083221,
      "learning_rate": 0.003,
      "loss": 3.209514465332031,
      "step": 183500
    },
    {
      "epoch": 0.4010802515489704,
      "grad_norm": 0.16981935501098633,
      "learning_rate": 0.003,
      "loss": 3.1907998657226564,
      "step": 183600
    },
    {
      "epoch": 0.40129870484502106,
      "grad_norm": 0.14561162889003754,
      "learning_rate": 0.003,
      "loss": 3.2126455688476563,
      "step": 183700
    },
    {
      "epoch": 0.4015171581410717,
      "grad_norm": 0.17461787164211273,
      "learning_rate": 0.003,
      "loss": 3.2027932739257814,
      "step": 183800
    },
    {
      "epoch": 0.40173561143712233,
      "grad_norm": 0.15372994542121887,
      "learning_rate": 0.003,
      "loss": 3.1723883056640627,
      "step": 183900
    },
    {
      "epoch": 0.40195406473317297,
      "grad_norm": 0.18105415999889374,
      "learning_rate": 0.003,
      "loss": 3.20320556640625,
      "step": 184000
    },
    {
      "epoch": 0.4021725180292236,
      "grad_norm": 0.19322223961353302,
      "learning_rate": 0.003,
      "loss": 3.20916259765625,
      "step": 184100
    },
    {
      "epoch": 0.40239097132527424,
      "grad_norm": 0.1999669075012207,
      "learning_rate": 0.003,
      "loss": 3.16731689453125,
      "step": 184200
    },
    {
      "epoch": 0.4026094246213249,
      "grad_norm": 0.190158411860466,
      "learning_rate": 0.003,
      "loss": 3.164765625,
      "step": 184300
    },
    {
      "epoch": 0.4028278779173755,
      "grad_norm": 0.17766131460666656,
      "learning_rate": 0.003,
      "loss": 3.1693936157226563,
      "step": 184400
    },
    {
      "epoch": 0.40304633121342615,
      "grad_norm": 0.20510916411876678,
      "learning_rate": 0.003,
      "loss": 3.127689208984375,
      "step": 184500
    },
    {
      "epoch": 0.4032647845094768,
      "grad_norm": 0.2135549932718277,
      "learning_rate": 0.003,
      "loss": 3.1676290893554686,
      "step": 184600
    },
    {
      "epoch": 0.4034832378055274,
      "grad_norm": 0.20256055891513824,
      "learning_rate": 0.003,
      "loss": 3.1806484985351564,
      "step": 184700
    },
    {
      "epoch": 0.40370169110157805,
      "grad_norm": 0.1929985135793686,
      "learning_rate": 0.003,
      "loss": 3.1799490356445315,
      "step": 184800
    },
    {
      "epoch": 0.4039201443976287,
      "grad_norm": 0.17259716987609863,
      "learning_rate": 0.003,
      "loss": 3.163272705078125,
      "step": 184900
    },
    {
      "epoch": 0.4041385976936793,
      "grad_norm": 0.16638626158237457,
      "learning_rate": 0.003,
      "loss": 3.2002822875976564,
      "step": 185000
    },
    {
      "epoch": 0.40435705098972996,
      "grad_norm": 0.2131744772195816,
      "learning_rate": 0.003,
      "loss": 3.182187194824219,
      "step": 185100
    },
    {
      "epoch": 0.4045755042857806,
      "grad_norm": 0.21150697767734528,
      "learning_rate": 0.003,
      "loss": 3.15331787109375,
      "step": 185200
    },
    {
      "epoch": 0.40479395758183123,
      "grad_norm": 0.22796319425106049,
      "learning_rate": 0.003,
      "loss": 3.1999627685546876,
      "step": 185300
    },
    {
      "epoch": 0.40501241087788187,
      "grad_norm": 0.25316885113716125,
      "learning_rate": 0.003,
      "loss": 3.2177749633789063,
      "step": 185400
    },
    {
      "epoch": 0.4052308641739325,
      "grad_norm": 0.2561890780925751,
      "learning_rate": 0.003,
      "loss": 3.2084869384765624,
      "step": 185500
    },
    {
      "epoch": 0.40544931746998314,
      "grad_norm": 0.23334598541259766,
      "learning_rate": 0.003,
      "loss": 3.3624331665039064,
      "step": 185600
    },
    {
      "epoch": 0.4056677707660338,
      "grad_norm": 0.20088715851306915,
      "learning_rate": 0.003,
      "loss": 3.1659011840820312,
      "step": 185700
    },
    {
      "epoch": 0.4058862240620844,
      "grad_norm": 0.15832436084747314,
      "learning_rate": 0.003,
      "loss": 2.6956158447265626,
      "step": 185800
    },
    {
      "epoch": 0.40610467735813505,
      "grad_norm": 0.22135229408740997,
      "learning_rate": 0.003,
      "loss": 3.165191345214844,
      "step": 185900
    },
    {
      "epoch": 0.4063231306541857,
      "grad_norm": 0.30081579089164734,
      "learning_rate": 0.003,
      "loss": 3.196156005859375,
      "step": 186000
    },
    {
      "epoch": 0.4065415839502363,
      "grad_norm": 0.14421017467975616,
      "learning_rate": 0.003,
      "loss": 3.18418701171875,
      "step": 186100
    },
    {
      "epoch": 0.40676003724628695,
      "grad_norm": 0.19961687922477722,
      "learning_rate": 0.003,
      "loss": 3.1820233154296873,
      "step": 186200
    },
    {
      "epoch": 0.4069784905423376,
      "grad_norm": 0.15882033109664917,
      "learning_rate": 0.003,
      "loss": 3.398824462890625,
      "step": 186300
    },
    {
      "epoch": 0.4071969438383882,
      "grad_norm": 0.23920150101184845,
      "learning_rate": 0.003,
      "loss": 3.1815740966796877,
      "step": 186400
    },
    {
      "epoch": 0.40741539713443886,
      "grad_norm": 0.17135967314243317,
      "learning_rate": 0.003,
      "loss": 3.176737976074219,
      "step": 186500
    },
    {
      "epoch": 0.40763385043048955,
      "grad_norm": 0.19113539159297943,
      "learning_rate": 0.003,
      "loss": 3.183821105957031,
      "step": 186600
    },
    {
      "epoch": 0.4078523037265402,
      "grad_norm": 0.17642919719219208,
      "learning_rate": 0.003,
      "loss": 3.176726989746094,
      "step": 186700
    },
    {
      "epoch": 0.4080707570225908,
      "grad_norm": 0.15663500130176544,
      "learning_rate": 0.003,
      "loss": 3.1614068603515624,
      "step": 186800
    },
    {
      "epoch": 0.40828921031864146,
      "grad_norm": 0.7325788140296936,
      "learning_rate": 0.003,
      "loss": 3.191528015136719,
      "step": 186900
    },
    {
      "epoch": 0.4085076636146921,
      "grad_norm": 0.1820564568042755,
      "learning_rate": 0.003,
      "loss": 3.208664855957031,
      "step": 187000
    },
    {
      "epoch": 0.40872611691074273,
      "grad_norm": 0.15867426991462708,
      "learning_rate": 0.003,
      "loss": 3.1605474853515627,
      "step": 187100
    },
    {
      "epoch": 0.40894457020679337,
      "grad_norm": 0.1883973926305771,
      "learning_rate": 0.003,
      "loss": 3.1736468505859374,
      "step": 187200
    },
    {
      "epoch": 0.409163023502844,
      "grad_norm": 0.19835537672042847,
      "learning_rate": 0.003,
      "loss": 3.2175225830078125,
      "step": 187300
    },
    {
      "epoch": 0.40938147679889464,
      "grad_norm": 0.20899279415607452,
      "learning_rate": 0.003,
      "loss": 3.238639221191406,
      "step": 187400
    },
    {
      "epoch": 0.4095999300949453,
      "grad_norm": 0.17463743686676025,
      "learning_rate": 0.003,
      "loss": 3.21509033203125,
      "step": 187500
    },
    {
      "epoch": 0.4098183833909959,
      "grad_norm": 0.22983255982398987,
      "learning_rate": 0.003,
      "loss": 3.1764312744140626,
      "step": 187600
    },
    {
      "epoch": 0.41003683668704655,
      "grad_norm": 0.1915416270494461,
      "learning_rate": 0.003,
      "loss": 3.1632504272460937,
      "step": 187700
    },
    {
      "epoch": 0.4102552899830972,
      "grad_norm": 0.19094012677669525,
      "learning_rate": 0.003,
      "loss": 3.18535400390625,
      "step": 187800
    },
    {
      "epoch": 0.4104737432791478,
      "grad_norm": 0.46519339084625244,
      "learning_rate": 0.003,
      "loss": 3.2658645629882814,
      "step": 187900
    },
    {
      "epoch": 0.41069219657519845,
      "grad_norm": 0.16349132359027863,
      "learning_rate": 0.003,
      "loss": 3.1646112060546874,
      "step": 188000
    },
    {
      "epoch": 0.4109106498712491,
      "grad_norm": 0.20613685250282288,
      "learning_rate": 0.003,
      "loss": 3.1999017333984376,
      "step": 188100
    },
    {
      "epoch": 0.4111291031672997,
      "grad_norm": 0.2808271646499634,
      "learning_rate": 0.003,
      "loss": 3.148988952636719,
      "step": 188200
    },
    {
      "epoch": 0.41134755646335036,
      "grad_norm": 0.21095828711986542,
      "learning_rate": 0.003,
      "loss": 3.1394580078125,
      "step": 188300
    },
    {
      "epoch": 0.411566009759401,
      "grad_norm": 0.16193212568759918,
      "learning_rate": 0.003,
      "loss": 3.164479064941406,
      "step": 188400
    },
    {
      "epoch": 0.41178446305545163,
      "grad_norm": 0.17273467779159546,
      "learning_rate": 0.003,
      "loss": 3.1684060668945313,
      "step": 188500
    },
    {
      "epoch": 0.41200291635150227,
      "grad_norm": 0.18636715412139893,
      "learning_rate": 0.003,
      "loss": 3.1901651000976563,
      "step": 188600
    },
    {
      "epoch": 0.4122213696475529,
      "grad_norm": 0.19758978486061096,
      "learning_rate": 0.003,
      "loss": 3.213038024902344,
      "step": 188700
    },
    {
      "epoch": 0.41243982294360354,
      "grad_norm": 0.14777310192584991,
      "learning_rate": 0.003,
      "loss": 3.1859469604492188,
      "step": 188800
    },
    {
      "epoch": 0.4126582762396542,
      "grad_norm": 0.17720140516757965,
      "learning_rate": 0.003,
      "loss": 3.211461181640625,
      "step": 188900
    },
    {
      "epoch": 0.4128767295357048,
      "grad_norm": 0.16024065017700195,
      "learning_rate": 0.003,
      "loss": 3.2260513305664062,
      "step": 189000
    },
    {
      "epoch": 0.41309518283175545,
      "grad_norm": 0.2198847234249115,
      "learning_rate": 0.003,
      "loss": 3.200946044921875,
      "step": 189100
    },
    {
      "epoch": 0.4133136361278061,
      "grad_norm": 0.14950239658355713,
      "learning_rate": 0.003,
      "loss": 3.090584716796875,
      "step": 189200
    },
    {
      "epoch": 0.4135320894238567,
      "grad_norm": 0.2859072685241699,
      "learning_rate": 0.003,
      "loss": 3.1644195556640624,
      "step": 189300
    },
    {
      "epoch": 0.41375054271990735,
      "grad_norm": 0.16298578679561615,
      "learning_rate": 0.003,
      "loss": 3.166923828125,
      "step": 189400
    },
    {
      "epoch": 0.413968996015958,
      "grad_norm": 0.15869586169719696,
      "learning_rate": 0.003,
      "loss": 3.1663751220703125,
      "step": 189500
    },
    {
      "epoch": 0.4141874493120086,
      "grad_norm": 0.18599191308021545,
      "learning_rate": 0.003,
      "loss": 3.1800021362304687,
      "step": 189600
    },
    {
      "epoch": 0.41440590260805926,
      "grad_norm": 0.221305251121521,
      "learning_rate": 0.003,
      "loss": 3.185477600097656,
      "step": 189700
    },
    {
      "epoch": 0.4146243559041099,
      "grad_norm": 0.15798625349998474,
      "learning_rate": 0.003,
      "loss": 3.221296691894531,
      "step": 189800
    },
    {
      "epoch": 0.4148428092001606,
      "grad_norm": 0.23340469598770142,
      "learning_rate": 0.003,
      "loss": 3.1689501953125,
      "step": 189900
    },
    {
      "epoch": 0.4150612624962112,
      "grad_norm": 0.3203597366809845,
      "learning_rate": 0.003,
      "loss": 3.203572998046875,
      "step": 190000
    },
    {
      "epoch": 0.41527971579226186,
      "grad_norm": 0.19323056936264038,
      "learning_rate": 0.003,
      "loss": 3.172715759277344,
      "step": 190100
    },
    {
      "epoch": 0.4154981690883125,
      "grad_norm": 0.28456801176071167,
      "learning_rate": 0.003,
      "loss": 3.203382873535156,
      "step": 190200
    },
    {
      "epoch": 0.41571662238436313,
      "grad_norm": 0.17356140911579132,
      "learning_rate": 0.003,
      "loss": 3.1323095703125,
      "step": 190300
    },
    {
      "epoch": 0.41593507568041377,
      "grad_norm": 0.19188471138477325,
      "learning_rate": 0.003,
      "loss": 3.22418701171875,
      "step": 190400
    },
    {
      "epoch": 0.4161535289764644,
      "grad_norm": 0.19762897491455078,
      "learning_rate": 0.003,
      "loss": 3.18052978515625,
      "step": 190500
    },
    {
      "epoch": 0.41637198227251504,
      "grad_norm": 0.17990559339523315,
      "learning_rate": 0.003,
      "loss": 3.2225128173828126,
      "step": 190600
    },
    {
      "epoch": 0.4165904355685657,
      "grad_norm": 0.17433513700962067,
      "learning_rate": 0.003,
      "loss": 3.5059249877929686,
      "step": 190700
    },
    {
      "epoch": 0.4168088888646163,
      "grad_norm": 0.1855400800704956,
      "learning_rate": 0.003,
      "loss": 3.197576904296875,
      "step": 190800
    },
    {
      "epoch": 0.41702734216066695,
      "grad_norm": 0.22566641867160797,
      "learning_rate": 0.003,
      "loss": 3.2001641845703124,
      "step": 190900
    },
    {
      "epoch": 0.4172457954567176,
      "grad_norm": 0.17952874302864075,
      "learning_rate": 0.003,
      "loss": 3.18627685546875,
      "step": 191000
    },
    {
      "epoch": 0.4174642487527682,
      "grad_norm": 0.2208983153104782,
      "learning_rate": 0.003,
      "loss": 3.193293151855469,
      "step": 191100
    },
    {
      "epoch": 0.41768270204881885,
      "grad_norm": 0.1648033708333969,
      "learning_rate": 0.003,
      "loss": 3.1969833374023438,
      "step": 191200
    },
    {
      "epoch": 0.4179011553448695,
      "grad_norm": 0.1829889416694641,
      "learning_rate": 0.003,
      "loss": 3.2138385009765624,
      "step": 191300
    },
    {
      "epoch": 0.4181196086409201,
      "grad_norm": 0.16211101412773132,
      "learning_rate": 0.003,
      "loss": 3.2019476318359374,
      "step": 191400
    },
    {
      "epoch": 0.41833806193697076,
      "grad_norm": 0.24418489634990692,
      "learning_rate": 0.003,
      "loss": 3.1644046020507814,
      "step": 191500
    },
    {
      "epoch": 0.4185565152330214,
      "grad_norm": 0.18671990931034088,
      "learning_rate": 0.003,
      "loss": 3.2010568237304686,
      "step": 191600
    },
    {
      "epoch": 0.41877496852907203,
      "grad_norm": 0.1882808655500412,
      "learning_rate": 0.003,
      "loss": 3.147957763671875,
      "step": 191700
    },
    {
      "epoch": 0.41899342182512267,
      "grad_norm": 0.20930488407611847,
      "learning_rate": 0.003,
      "loss": 3.1639535522460935,
      "step": 191800
    },
    {
      "epoch": 0.4192118751211733,
      "grad_norm": 0.29854610562324524,
      "learning_rate": 0.003,
      "loss": 3.2512847900390627,
      "step": 191900
    },
    {
      "epoch": 0.41943032841722394,
      "grad_norm": 0.21584276854991913,
      "learning_rate": 0.003,
      "loss": 3.2023135375976564,
      "step": 192000
    },
    {
      "epoch": 0.4196487817132746,
      "grad_norm": 0.26711922883987427,
      "learning_rate": 0.003,
      "loss": 3.1593002319335937,
      "step": 192100
    },
    {
      "epoch": 0.4198672350093252,
      "grad_norm": 0.18492016196250916,
      "learning_rate": 0.003,
      "loss": 3.212557067871094,
      "step": 192200
    },
    {
      "epoch": 0.42008568830537585,
      "grad_norm": 0.16737864911556244,
      "learning_rate": 0.003,
      "loss": 3.190294189453125,
      "step": 192300
    },
    {
      "epoch": 0.4203041416014265,
      "grad_norm": 0.24325154721736908,
      "learning_rate": 0.003,
      "loss": 3.167086486816406,
      "step": 192400
    },
    {
      "epoch": 0.4205225948974771,
      "grad_norm": 0.18168015778064728,
      "learning_rate": 0.003,
      "loss": 3.2040185546875,
      "step": 192500
    },
    {
      "epoch": 0.42074104819352776,
      "grad_norm": 0.17318503558635712,
      "learning_rate": 0.003,
      "loss": 3.1787591552734376,
      "step": 192600
    },
    {
      "epoch": 0.4209595014895784,
      "grad_norm": 0.16415344178676605,
      "learning_rate": 0.003,
      "loss": 3.19978759765625,
      "step": 192700
    },
    {
      "epoch": 0.421177954785629,
      "grad_norm": 0.15419593453407288,
      "learning_rate": 0.003,
      "loss": 3.2084515380859373,
      "step": 192800
    },
    {
      "epoch": 0.42139640808167966,
      "grad_norm": 0.23044085502624512,
      "learning_rate": 0.003,
      "loss": 3.1947500610351565,
      "step": 192900
    },
    {
      "epoch": 0.4216148613777303,
      "grad_norm": 0.2768518924713135,
      "learning_rate": 0.003,
      "loss": 3.167633361816406,
      "step": 193000
    },
    {
      "epoch": 0.42183331467378093,
      "grad_norm": 0.17717263102531433,
      "learning_rate": 0.003,
      "loss": 3.198765869140625,
      "step": 193100
    },
    {
      "epoch": 0.4220517679698316,
      "grad_norm": 0.17948728799819946,
      "learning_rate": 0.003,
      "loss": 3.162294921875,
      "step": 193200
    },
    {
      "epoch": 0.42227022126588226,
      "grad_norm": 0.2169944941997528,
      "learning_rate": 0.003,
      "loss": 3.1893734741210937,
      "step": 193300
    },
    {
      "epoch": 0.4224886745619329,
      "grad_norm": 0.19639424979686737,
      "learning_rate": 0.003,
      "loss": 3.1738739013671875,
      "step": 193400
    },
    {
      "epoch": 0.42270712785798353,
      "grad_norm": 0.20157811045646667,
      "learning_rate": 0.003,
      "loss": 3.192210998535156,
      "step": 193500
    },
    {
      "epoch": 0.42292558115403417,
      "grad_norm": 0.19461394846439362,
      "learning_rate": 0.003,
      "loss": 3.1514434814453125,
      "step": 193600
    },
    {
      "epoch": 0.4231440344500848,
      "grad_norm": 0.21501785516738892,
      "learning_rate": 0.003,
      "loss": 3.1837368774414063,
      "step": 193700
    },
    {
      "epoch": 0.42336248774613544,
      "grad_norm": 0.19261273741722107,
      "learning_rate": 0.003,
      "loss": 3.1550421142578124,
      "step": 193800
    },
    {
      "epoch": 0.4235809410421861,
      "grad_norm": 0.18213462829589844,
      "learning_rate": 0.003,
      "loss": 3.1901535034179687,
      "step": 193900
    },
    {
      "epoch": 0.4237993943382367,
      "grad_norm": 0.18606354296207428,
      "learning_rate": 0.003,
      "loss": 3.1592898559570313,
      "step": 194000
    },
    {
      "epoch": 0.42401784763428735,
      "grad_norm": 0.18234939873218536,
      "learning_rate": 0.003,
      "loss": 3.185053405761719,
      "step": 194100
    },
    {
      "epoch": 0.424236300930338,
      "grad_norm": 0.18927134573459625,
      "learning_rate": 0.003,
      "loss": 3.1728561401367186,
      "step": 194200
    },
    {
      "epoch": 0.4244547542263886,
      "grad_norm": 0.18319912254810333,
      "learning_rate": 0.003,
      "loss": 3.1678424072265625,
      "step": 194300
    },
    {
      "epoch": 0.42467320752243926,
      "grad_norm": 0.18335697054862976,
      "learning_rate": 0.003,
      "loss": 3.1946209716796874,
      "step": 194400
    },
    {
      "epoch": 0.4248916608184899,
      "grad_norm": 0.17396575212478638,
      "learning_rate": 0.003,
      "loss": 3.205735778808594,
      "step": 194500
    },
    {
      "epoch": 0.4251101141145405,
      "grad_norm": 0.17961376905441284,
      "learning_rate": 0.003,
      "loss": 3.17311279296875,
      "step": 194600
    },
    {
      "epoch": 0.42532856741059116,
      "grad_norm": 0.15825814008712769,
      "learning_rate": 0.003,
      "loss": 3.174876403808594,
      "step": 194700
    },
    {
      "epoch": 0.4255470207066418,
      "grad_norm": 0.18347236514091492,
      "learning_rate": 0.003,
      "loss": 3.1809005737304688,
      "step": 194800
    },
    {
      "epoch": 0.42576547400269243,
      "grad_norm": 0.2542423605918884,
      "learning_rate": 0.003,
      "loss": 3.1792791748046874,
      "step": 194900
    },
    {
      "epoch": 0.42598392729874307,
      "grad_norm": 0.16055554151535034,
      "learning_rate": 0.003,
      "loss": 3.2170816040039063,
      "step": 195000
    },
    {
      "epoch": 0.4262023805947937,
      "grad_norm": 0.1684149205684662,
      "learning_rate": 0.003,
      "loss": 3.2045187377929687,
      "step": 195100
    },
    {
      "epoch": 0.42642083389084434,
      "grad_norm": 0.1769225150346756,
      "learning_rate": 0.003,
      "loss": 3.189585876464844,
      "step": 195200
    },
    {
      "epoch": 0.426639287186895,
      "grad_norm": 0.16583608090877533,
      "learning_rate": 0.003,
      "loss": 3.1739907836914063,
      "step": 195300
    },
    {
      "epoch": 0.4268577404829456,
      "grad_norm": 0.16576716303825378,
      "learning_rate": 0.003,
      "loss": 3.171072692871094,
      "step": 195400
    },
    {
      "epoch": 0.42707619377899625,
      "grad_norm": 0.22751779854297638,
      "learning_rate": 0.003,
      "loss": 3.2072900390625,
      "step": 195500
    },
    {
      "epoch": 0.4272946470750469,
      "grad_norm": 0.26317569613456726,
      "learning_rate": 0.003,
      "loss": 3.2055728149414064,
      "step": 195600
    },
    {
      "epoch": 0.4275131003710975,
      "grad_norm": 0.19651511311531067,
      "learning_rate": 0.003,
      "loss": 3.21059814453125,
      "step": 195700
    },
    {
      "epoch": 0.42773155366714816,
      "grad_norm": 0.1966991275548935,
      "learning_rate": 0.003,
      "loss": 3.1960745239257813,
      "step": 195800
    },
    {
      "epoch": 0.4279500069631988,
      "grad_norm": 0.15497447550296783,
      "learning_rate": 0.003,
      "loss": 3.1767337036132814,
      "step": 195900
    },
    {
      "epoch": 0.42816846025924943,
      "grad_norm": 0.17778752744197845,
      "learning_rate": 0.003,
      "loss": 3.2148617553710936,
      "step": 196000
    },
    {
      "epoch": 0.42838691355530006,
      "grad_norm": 0.16433653235435486,
      "learning_rate": 0.003,
      "loss": 3.228043518066406,
      "step": 196100
    },
    {
      "epoch": 0.4286053668513507,
      "grad_norm": 0.23374071717262268,
      "learning_rate": 0.003,
      "loss": 3.159526672363281,
      "step": 196200
    },
    {
      "epoch": 0.42882382014740134,
      "grad_norm": 0.2345740646123886,
      "learning_rate": 0.003,
      "loss": 3.1858612060546876,
      "step": 196300
    },
    {
      "epoch": 0.42904227344345197,
      "grad_norm": 0.17261254787445068,
      "learning_rate": 0.003,
      "loss": 3.1571005249023436,
      "step": 196400
    },
    {
      "epoch": 0.42926072673950266,
      "grad_norm": 0.4921078085899353,
      "learning_rate": 0.003,
      "loss": 3.1973272705078126,
      "step": 196500
    },
    {
      "epoch": 0.4294791800355533,
      "grad_norm": 0.1977531760931015,
      "learning_rate": 0.003,
      "loss": 3.303300476074219,
      "step": 196600
    },
    {
      "epoch": 0.42969763333160393,
      "grad_norm": 0.18526647984981537,
      "learning_rate": 0.003,
      "loss": 3.1728396606445313,
      "step": 196700
    },
    {
      "epoch": 0.42991608662765457,
      "grad_norm": 0.1589854210615158,
      "learning_rate": 0.003,
      "loss": 3.194491271972656,
      "step": 196800
    },
    {
      "epoch": 0.4301345399237052,
      "grad_norm": 0.2798563241958618,
      "learning_rate": 0.003,
      "loss": 3.1198419189453124,
      "step": 196900
    },
    {
      "epoch": 0.43035299321975584,
      "grad_norm": 0.17101620137691498,
      "learning_rate": 0.003,
      "loss": 3.1847055053710935,
      "step": 197000
    },
    {
      "epoch": 0.4305714465158065,
      "grad_norm": 0.1939271092414856,
      "learning_rate": 0.003,
      "loss": 3.1889215087890626,
      "step": 197100
    },
    {
      "epoch": 0.4307898998118571,
      "grad_norm": 0.16984674334526062,
      "learning_rate": 0.003,
      "loss": 3.137484130859375,
      "step": 197200
    },
    {
      "epoch": 0.43100835310790775,
      "grad_norm": 0.3280338943004608,
      "learning_rate": 0.003,
      "loss": 3.1889242553710937,
      "step": 197300
    },
    {
      "epoch": 0.4312268064039584,
      "grad_norm": 0.6364851593971252,
      "learning_rate": 0.003,
      "loss": 3.4708493041992186,
      "step": 197400
    },
    {
      "epoch": 0.431445259700009,
      "grad_norm": 0.1692935824394226,
      "learning_rate": 0.003,
      "loss": 3.164335021972656,
      "step": 197500
    },
    {
      "epoch": 0.43166371299605966,
      "grad_norm": 0.31458690762519836,
      "learning_rate": 0.003,
      "loss": 3.1413238525390623,
      "step": 197600
    },
    {
      "epoch": 0.4318821662921103,
      "grad_norm": 0.27256762981414795,
      "learning_rate": 0.003,
      "loss": 3.0988259887695313,
      "step": 197700
    },
    {
      "epoch": 0.43210061958816093,
      "grad_norm": 0.17741350829601288,
      "learning_rate": 0.003,
      "loss": 3.161429138183594,
      "step": 197800
    },
    {
      "epoch": 0.43231907288421156,
      "grad_norm": 0.16620120406150818,
      "learning_rate": 0.003,
      "loss": 3.1685031127929686,
      "step": 197900
    },
    {
      "epoch": 0.4325375261802622,
      "grad_norm": 0.14933812618255615,
      "learning_rate": 0.003,
      "loss": 3.169547119140625,
      "step": 198000
    },
    {
      "epoch": 0.43275597947631284,
      "grad_norm": 0.1852118819952011,
      "learning_rate": 0.003,
      "loss": 3.1822409057617187,
      "step": 198100
    },
    {
      "epoch": 0.43297443277236347,
      "grad_norm": 0.2365371733903885,
      "learning_rate": 0.003,
      "loss": 3.150942687988281,
      "step": 198200
    },
    {
      "epoch": 0.4331928860684141,
      "grad_norm": 0.21646462380886078,
      "learning_rate": 0.003,
      "loss": 3.1712240600585937,
      "step": 198300
    },
    {
      "epoch": 0.43341133936446474,
      "grad_norm": 0.3080461323261261,
      "learning_rate": 0.003,
      "loss": 3.1601077270507814,
      "step": 198400
    },
    {
      "epoch": 0.4336297926605154,
      "grad_norm": 0.1867397129535675,
      "learning_rate": 0.003,
      "loss": 3.1351394653320312,
      "step": 198500
    },
    {
      "epoch": 0.433848245956566,
      "grad_norm": 0.2211391031742096,
      "learning_rate": 0.003,
      "loss": 3.138538818359375,
      "step": 198600
    },
    {
      "epoch": 0.43406669925261665,
      "grad_norm": 0.17952261865139008,
      "learning_rate": 0.003,
      "loss": 3.148133544921875,
      "step": 198700
    },
    {
      "epoch": 0.4342851525486673,
      "grad_norm": 0.20710588991641998,
      "learning_rate": 0.003,
      "loss": 3.1607174682617187,
      "step": 198800
    },
    {
      "epoch": 0.4345036058447179,
      "grad_norm": 0.24511949717998505,
      "learning_rate": 0.003,
      "loss": 3.21546630859375,
      "step": 198900
    },
    {
      "epoch": 0.43472205914076856,
      "grad_norm": 0.18444938957691193,
      "learning_rate": 0.003,
      "loss": 3.294717102050781,
      "step": 199000
    },
    {
      "epoch": 0.4349405124368192,
      "grad_norm": 0.20566163957118988,
      "learning_rate": 0.003,
      "loss": 3.147694091796875,
      "step": 199100
    },
    {
      "epoch": 0.43515896573286983,
      "grad_norm": 0.3018874228000641,
      "learning_rate": 0.003,
      "loss": 3.1568942260742188,
      "step": 199200
    },
    {
      "epoch": 0.43537741902892046,
      "grad_norm": 0.18835556507110596,
      "learning_rate": 0.003,
      "loss": 3.1684259033203124,
      "step": 199300
    },
    {
      "epoch": 0.4355958723249711,
      "grad_norm": 0.37234655022621155,
      "learning_rate": 0.003,
      "loss": 3.150151672363281,
      "step": 199400
    },
    {
      "epoch": 0.43581432562102174,
      "grad_norm": 0.19344590604305267,
      "learning_rate": 0.003,
      "loss": 3.1657888793945315,
      "step": 199500
    },
    {
      "epoch": 0.43603277891707237,
      "grad_norm": 0.20414501428604126,
      "learning_rate": 0.003,
      "loss": 3.12616455078125,
      "step": 199600
    },
    {
      "epoch": 0.436251232213123,
      "grad_norm": 0.164936363697052,
      "learning_rate": 0.003,
      "loss": 3.171126708984375,
      "step": 199700
    },
    {
      "epoch": 0.4364696855091737,
      "grad_norm": 0.1484096348285675,
      "learning_rate": 0.003,
      "loss": 3.1562570190429686,
      "step": 199800
    },
    {
      "epoch": 0.43668813880522434,
      "grad_norm": 0.17063280940055847,
      "learning_rate": 0.003,
      "loss": 3.163632507324219,
      "step": 199900
    },
    {
      "epoch": 0.43690659210127497,
      "grad_norm": 0.23969689011573792,
      "learning_rate": 0.003,
      "loss": 3.149070129394531,
      "step": 200000
    },
    {
      "epoch": 0.4371250453973256,
      "grad_norm": 0.2145770639181137,
      "learning_rate": 0.003,
      "loss": 3.1901449584960937,
      "step": 200100
    },
    {
      "epoch": 0.43734349869337624,
      "grad_norm": 0.1567714810371399,
      "learning_rate": 0.003,
      "loss": 3.198854675292969,
      "step": 200200
    },
    {
      "epoch": 0.4375619519894269,
      "grad_norm": 0.1601209193468094,
      "learning_rate": 0.003,
      "loss": 3.1645443725585936,
      "step": 200300
    },
    {
      "epoch": 0.4377804052854775,
      "grad_norm": 0.19364909827709198,
      "learning_rate": 0.003,
      "loss": 3.1427178955078126,
      "step": 200400
    },
    {
      "epoch": 0.43799885858152815,
      "grad_norm": 0.18869169056415558,
      "learning_rate": 0.003,
      "loss": 3.1338534545898438,
      "step": 200500
    },
    {
      "epoch": 0.4382173118775788,
      "grad_norm": 0.1931476891040802,
      "learning_rate": 0.003,
      "loss": 3.1648992919921874,
      "step": 200600
    },
    {
      "epoch": 0.4384357651736294,
      "grad_norm": 0.2133205235004425,
      "learning_rate": 0.003,
      "loss": 3.152872314453125,
      "step": 200700
    },
    {
      "epoch": 0.43865421846968006,
      "grad_norm": 0.17436596751213074,
      "learning_rate": 0.003,
      "loss": 3.154434814453125,
      "step": 200800
    },
    {
      "epoch": 0.4388726717657307,
      "grad_norm": 0.16989195346832275,
      "learning_rate": 0.003,
      "loss": 3.156177673339844,
      "step": 200900
    },
    {
      "epoch": 0.43909112506178133,
      "grad_norm": 0.18729053437709808,
      "learning_rate": 0.003,
      "loss": 3.16497314453125,
      "step": 201000
    },
    {
      "epoch": 0.43930957835783196,
      "grad_norm": 0.180799201130867,
      "learning_rate": 0.003,
      "loss": 3.122683410644531,
      "step": 201100
    },
    {
      "epoch": 0.4395280316538826,
      "grad_norm": 0.15879975259304047,
      "learning_rate": 0.003,
      "loss": 3.1574371337890623,
      "step": 201200
    },
    {
      "epoch": 0.43974648494993324,
      "grad_norm": 0.1638316512107849,
      "learning_rate": 0.003,
      "loss": 3.2139212036132814,
      "step": 201300
    },
    {
      "epoch": 0.43996493824598387,
      "grad_norm": 0.23130196332931519,
      "learning_rate": 0.003,
      "loss": 3.1817987060546873,
      "step": 201400
    },
    {
      "epoch": 0.4401833915420345,
      "grad_norm": 0.16506163775920868,
      "learning_rate": 0.003,
      "loss": 3.1515191650390624,
      "step": 201500
    },
    {
      "epoch": 0.44040184483808514,
      "grad_norm": 0.16108174622058868,
      "learning_rate": 0.003,
      "loss": 3.207608337402344,
      "step": 201600
    },
    {
      "epoch": 0.4406202981341358,
      "grad_norm": 0.16053904592990875,
      "learning_rate": 0.003,
      "loss": 3.1351416015625,
      "step": 201700
    },
    {
      "epoch": 0.4408387514301864,
      "grad_norm": 0.1633559912443161,
      "learning_rate": 0.003,
      "loss": 3.1724652099609374,
      "step": 201800
    },
    {
      "epoch": 0.44105720472623705,
      "grad_norm": 0.168962761759758,
      "learning_rate": 0.003,
      "loss": 3.187872009277344,
      "step": 201900
    },
    {
      "epoch": 0.4412756580222877,
      "grad_norm": 0.2989565134048462,
      "learning_rate": 0.003,
      "loss": 3.1648593139648438,
      "step": 202000
    },
    {
      "epoch": 0.4414941113183383,
      "grad_norm": 0.19677987694740295,
      "learning_rate": 0.003,
      "loss": 3.12785888671875,
      "step": 202100
    },
    {
      "epoch": 0.44171256461438896,
      "grad_norm": 0.19811169803142548,
      "learning_rate": 0.003,
      "loss": 3.090600891113281,
      "step": 202200
    },
    {
      "epoch": 0.4419310179104396,
      "grad_norm": 0.15272833406925201,
      "learning_rate": 0.003,
      "loss": 3.1773712158203127,
      "step": 202300
    },
    {
      "epoch": 0.44214947120649023,
      "grad_norm": 0.19641107320785522,
      "learning_rate": 0.003,
      "loss": 3.1971221923828126,
      "step": 202400
    },
    {
      "epoch": 0.44236792450254087,
      "grad_norm": 0.5620470643043518,
      "learning_rate": 0.003,
      "loss": 3.14832763671875,
      "step": 202500
    },
    {
      "epoch": 0.4425863777985915,
      "grad_norm": 0.18229664862155914,
      "learning_rate": 0.003,
      "loss": 3.180650634765625,
      "step": 202600
    },
    {
      "epoch": 0.44280483109464214,
      "grad_norm": 0.2136525958776474,
      "learning_rate": 0.003,
      "loss": 3.151111755371094,
      "step": 202700
    },
    {
      "epoch": 0.4430232843906928,
      "grad_norm": 0.1700323224067688,
      "learning_rate": 0.003,
      "loss": 3.160267639160156,
      "step": 202800
    },
    {
      "epoch": 0.4432417376867434,
      "grad_norm": 0.25750991702079773,
      "learning_rate": 0.003,
      "loss": 3.09343994140625,
      "step": 202900
    },
    {
      "epoch": 0.44346019098279404,
      "grad_norm": 0.20566947758197784,
      "learning_rate": 0.003,
      "loss": 3.175107116699219,
      "step": 203000
    },
    {
      "epoch": 0.44367864427884474,
      "grad_norm": 0.16463296115398407,
      "learning_rate": 0.003,
      "loss": 3.170555419921875,
      "step": 203100
    },
    {
      "epoch": 0.44389709757489537,
      "grad_norm": 0.2057923525571823,
      "learning_rate": 0.003,
      "loss": 3.1422415161132813,
      "step": 203200
    },
    {
      "epoch": 0.444115550870946,
      "grad_norm": 0.20403887331485748,
      "learning_rate": 0.003,
      "loss": 3.154041442871094,
      "step": 203300
    },
    {
      "epoch": 0.44433400416699664,
      "grad_norm": 0.1620495766401291,
      "learning_rate": 0.003,
      "loss": 3.1455111694335938,
      "step": 203400
    },
    {
      "epoch": 0.4445524574630473,
      "grad_norm": 0.2016565501689911,
      "learning_rate": 0.003,
      "loss": 3.1927203369140624,
      "step": 203500
    },
    {
      "epoch": 0.4447709107590979,
      "grad_norm": 0.23052263259887695,
      "learning_rate": 0.003,
      "loss": 3.1762322998046875,
      "step": 203600
    },
    {
      "epoch": 0.44498936405514855,
      "grad_norm": 0.23547278344631195,
      "learning_rate": 0.003,
      "loss": 3.161244201660156,
      "step": 203700
    },
    {
      "epoch": 0.4452078173511992,
      "grad_norm": 0.17619803547859192,
      "learning_rate": 0.003,
      "loss": 3.1504925537109374,
      "step": 203800
    },
    {
      "epoch": 0.4454262706472498,
      "grad_norm": 0.15786325931549072,
      "learning_rate": 0.003,
      "loss": 3.1679095458984374,
      "step": 203900
    },
    {
      "epoch": 0.44564472394330046,
      "grad_norm": 0.1748770773410797,
      "learning_rate": 0.003,
      "loss": 3.146453552246094,
      "step": 204000
    },
    {
      "epoch": 0.4458631772393511,
      "grad_norm": 0.16151951253414154,
      "learning_rate": 0.003,
      "loss": 3.1801458740234376,
      "step": 204100
    },
    {
      "epoch": 0.44608163053540173,
      "grad_norm": 0.157077357172966,
      "learning_rate": 0.003,
      "loss": 3.1717169189453127,
      "step": 204200
    },
    {
      "epoch": 0.44630008383145237,
      "grad_norm": 0.1605377197265625,
      "learning_rate": 0.003,
      "loss": 3.193360595703125,
      "step": 204300
    },
    {
      "epoch": 0.446518537127503,
      "grad_norm": 0.21394836902618408,
      "learning_rate": 0.003,
      "loss": 3.169910583496094,
      "step": 204400
    },
    {
      "epoch": 0.44673699042355364,
      "grad_norm": 0.16044166684150696,
      "learning_rate": 0.003,
      "loss": 3.132872314453125,
      "step": 204500
    },
    {
      "epoch": 0.4469554437196043,
      "grad_norm": 0.15467199683189392,
      "learning_rate": 0.003,
      "loss": 3.1886727905273435,
      "step": 204600
    },
    {
      "epoch": 0.4471738970156549,
      "grad_norm": 0.15630580484867096,
      "learning_rate": 0.003,
      "loss": 3.175328674316406,
      "step": 204700
    },
    {
      "epoch": 0.44739235031170554,
      "grad_norm": 1.3999574184417725,
      "learning_rate": 0.003,
      "loss": 3.1534478759765623,
      "step": 204800
    },
    {
      "epoch": 0.4476108036077562,
      "grad_norm": 0.277555912733078,
      "learning_rate": 0.003,
      "loss": 3.071371765136719,
      "step": 204900
    },
    {
      "epoch": 0.4478292569038068,
      "grad_norm": 0.17702731490135193,
      "learning_rate": 0.003,
      "loss": 2.936678161621094,
      "step": 205000
    },
    {
      "epoch": 0.44804771019985745,
      "grad_norm": 0.19393837451934814,
      "learning_rate": 0.003,
      "loss": 3.175164794921875,
      "step": 205100
    },
    {
      "epoch": 0.4482661634959081,
      "grad_norm": 0.20200715959072113,
      "learning_rate": 0.003,
      "loss": 3.170127258300781,
      "step": 205200
    },
    {
      "epoch": 0.4484846167919587,
      "grad_norm": 0.24003438651561737,
      "learning_rate": 0.003,
      "loss": 3.12712646484375,
      "step": 205300
    },
    {
      "epoch": 0.44870307008800936,
      "grad_norm": 0.2252911776304245,
      "learning_rate": 0.003,
      "loss": 3.1695208740234375,
      "step": 205400
    },
    {
      "epoch": 0.44892152338406,
      "grad_norm": 0.16646260023117065,
      "learning_rate": 0.003,
      "loss": 3.1475820922851563,
      "step": 205500
    },
    {
      "epoch": 0.44913997668011063,
      "grad_norm": 0.16310742497444153,
      "learning_rate": 0.003,
      "loss": 3.1577783203125,
      "step": 205600
    },
    {
      "epoch": 0.44935842997616127,
      "grad_norm": 0.23147304356098175,
      "learning_rate": 0.003,
      "loss": 3.1667910766601564,
      "step": 205700
    },
    {
      "epoch": 0.4495768832722119,
      "grad_norm": 0.37597811222076416,
      "learning_rate": 0.003,
      "loss": 3.132157287597656,
      "step": 205800
    },
    {
      "epoch": 0.44979533656826254,
      "grad_norm": 0.16955402493476868,
      "learning_rate": 0.003,
      "loss": 3.1531689453125,
      "step": 205900
    },
    {
      "epoch": 0.4500137898643132,
      "grad_norm": 0.216968834400177,
      "learning_rate": 0.003,
      "loss": 3.146459045410156,
      "step": 206000
    },
    {
      "epoch": 0.4502322431603638,
      "grad_norm": 0.16945937275886536,
      "learning_rate": 0.003,
      "loss": 3.129493408203125,
      "step": 206100
    },
    {
      "epoch": 0.45045069645641445,
      "grad_norm": 0.1634141355752945,
      "learning_rate": 0.003,
      "loss": 3.1649295043945314,
      "step": 206200
    },
    {
      "epoch": 0.4506691497524651,
      "grad_norm": 0.22210796177387238,
      "learning_rate": 0.003,
      "loss": 3.1239044189453127,
      "step": 206300
    },
    {
      "epoch": 0.4508876030485158,
      "grad_norm": 0.29906684160232544,
      "learning_rate": 0.003,
      "loss": 3.09810791015625,
      "step": 206400
    },
    {
      "epoch": 0.4511060563445664,
      "grad_norm": 0.18408238887786865,
      "learning_rate": 0.003,
      "loss": 3.1427911376953124,
      "step": 206500
    },
    {
      "epoch": 0.45132450964061704,
      "grad_norm": 0.26075479388237,
      "learning_rate": 0.003,
      "loss": 3.193949890136719,
      "step": 206600
    },
    {
      "epoch": 0.4515429629366677,
      "grad_norm": 0.24402406811714172,
      "learning_rate": 0.003,
      "loss": 3.1403778076171873,
      "step": 206700
    },
    {
      "epoch": 0.4517614162327183,
      "grad_norm": 0.1647372543811798,
      "learning_rate": 0.003,
      "loss": 3.1845187377929687,
      "step": 206800
    },
    {
      "epoch": 0.45197986952876895,
      "grad_norm": 0.22355522215366364,
      "learning_rate": 0.003,
      "loss": 3.1863037109375,
      "step": 206900
    },
    {
      "epoch": 0.4521983228248196,
      "grad_norm": 0.15519294142723083,
      "learning_rate": 0.003,
      "loss": 3.1456622314453124,
      "step": 207000
    },
    {
      "epoch": 0.4524167761208702,
      "grad_norm": 0.19984041154384613,
      "learning_rate": 0.003,
      "loss": 3.1824017333984376,
      "step": 207100
    },
    {
      "epoch": 0.45263522941692086,
      "grad_norm": 0.18676409125328064,
      "learning_rate": 0.003,
      "loss": 3.150601501464844,
      "step": 207200
    },
    {
      "epoch": 0.4528536827129715,
      "grad_norm": 0.21894080936908722,
      "learning_rate": 0.003,
      "loss": 3.1372979736328124,
      "step": 207300
    },
    {
      "epoch": 0.45307213600902213,
      "grad_norm": 0.23746535181999207,
      "learning_rate": 0.003,
      "loss": 3.157814636230469,
      "step": 207400
    },
    {
      "epoch": 0.45329058930507277,
      "grad_norm": 0.16538827121257782,
      "learning_rate": 0.003,
      "loss": 3.1630648803710937,
      "step": 207500
    },
    {
      "epoch": 0.4535090426011234,
      "grad_norm": 0.21920669078826904,
      "learning_rate": 0.003,
      "loss": 3.1670318603515626,
      "step": 207600
    },
    {
      "epoch": 0.45372749589717404,
      "grad_norm": 0.21445763111114502,
      "learning_rate": 0.003,
      "loss": 3.181597900390625,
      "step": 207700
    },
    {
      "epoch": 0.4539459491932247,
      "grad_norm": 0.31932541728019714,
      "learning_rate": 0.003,
      "loss": 3.1186004638671876,
      "step": 207800
    },
    {
      "epoch": 0.4541644024892753,
      "grad_norm": 0.17662931978702545,
      "learning_rate": 0.003,
      "loss": 3.182383728027344,
      "step": 207900
    },
    {
      "epoch": 0.45438285578532595,
      "grad_norm": 0.1909274309873581,
      "learning_rate": 0.003,
      "loss": 3.1328729248046874,
      "step": 208000
    },
    {
      "epoch": 0.4546013090813766,
      "grad_norm": 0.18399013578891754,
      "learning_rate": 0.003,
      "loss": 3.116648864746094,
      "step": 208100
    },
    {
      "epoch": 0.4548197623774272,
      "grad_norm": 0.17121626436710358,
      "learning_rate": 0.003,
      "loss": 3.199187927246094,
      "step": 208200
    },
    {
      "epoch": 0.45503821567347785,
      "grad_norm": 0.3020518124103546,
      "learning_rate": 0.003,
      "loss": 3.231791687011719,
      "step": 208300
    },
    {
      "epoch": 0.4552566689695285,
      "grad_norm": 0.1598193347454071,
      "learning_rate": 0.003,
      "loss": 3.138844299316406,
      "step": 208400
    },
    {
      "epoch": 0.4554751222655791,
      "grad_norm": 0.1910119205713272,
      "learning_rate": 0.003,
      "loss": 3.167586364746094,
      "step": 208500
    },
    {
      "epoch": 0.45569357556162976,
      "grad_norm": 0.1881810426712036,
      "learning_rate": 0.003,
      "loss": 3.1416506958007813,
      "step": 208600
    },
    {
      "epoch": 0.4559120288576804,
      "grad_norm": 0.17203375697135925,
      "learning_rate": 0.003,
      "loss": 3.1579214477539064,
      "step": 208700
    },
    {
      "epoch": 0.45613048215373103,
      "grad_norm": 0.26828309893608093,
      "learning_rate": 0.003,
      "loss": 3.1485159301757815,
      "step": 208800
    },
    {
      "epoch": 0.45634893544978167,
      "grad_norm": 0.19651077687740326,
      "learning_rate": 0.003,
      "loss": 3.1378338623046873,
      "step": 208900
    },
    {
      "epoch": 0.4565673887458323,
      "grad_norm": 0.16316422820091248,
      "learning_rate": 0.003,
      "loss": 3.155181579589844,
      "step": 209000
    },
    {
      "epoch": 0.45678584204188294,
      "grad_norm": 0.18653205037117004,
      "learning_rate": 0.003,
      "loss": 3.1686004638671874,
      "step": 209100
    },
    {
      "epoch": 0.4570042953379336,
      "grad_norm": 0.3053761422634125,
      "learning_rate": 0.003,
      "loss": 3.1448635864257812,
      "step": 209200
    },
    {
      "epoch": 0.4572227486339842,
      "grad_norm": 0.17282266914844513,
      "learning_rate": 0.003,
      "loss": 3.1646148681640627,
      "step": 209300
    },
    {
      "epoch": 0.45744120193003485,
      "grad_norm": 0.17302711308002472,
      "learning_rate": 0.003,
      "loss": 3.1670352172851564,
      "step": 209400
    },
    {
      "epoch": 0.4576596552260855,
      "grad_norm": 0.16899672150611877,
      "learning_rate": 0.003,
      "loss": 3.1867990112304687,
      "step": 209500
    },
    {
      "epoch": 0.4578781085221361,
      "grad_norm": 0.22046208381652832,
      "learning_rate": 0.003,
      "loss": 3.2163922119140627,
      "step": 209600
    },
    {
      "epoch": 0.4580965618181868,
      "grad_norm": 0.14399343729019165,
      "learning_rate": 0.003,
      "loss": 3.1406573486328124,
      "step": 209700
    },
    {
      "epoch": 0.45831501511423745,
      "grad_norm": 0.21815311908721924,
      "learning_rate": 0.003,
      "loss": 2.99076416015625,
      "step": 209800
    },
    {
      "epoch": 0.4585334684102881,
      "grad_norm": 0.20032988488674164,
      "learning_rate": 0.003,
      "loss": 3.134709777832031,
      "step": 209900
    },
    {
      "epoch": 0.4587519217063387,
      "grad_norm": 0.2282021939754486,
      "learning_rate": 0.003,
      "loss": 3.114366455078125,
      "step": 210000
    },
    {
      "epoch": 0.45897037500238935,
      "grad_norm": 0.21151527762413025,
      "learning_rate": 0.003,
      "loss": 3.1238027954101564,
      "step": 210100
    },
    {
      "epoch": 0.45918882829844,
      "grad_norm": 0.14960075914859772,
      "learning_rate": 0.003,
      "loss": 3.159061279296875,
      "step": 210200
    },
    {
      "epoch": 0.4594072815944906,
      "grad_norm": 0.1922806203365326,
      "learning_rate": 0.003,
      "loss": 3.1903143310546875,
      "step": 210300
    },
    {
      "epoch": 0.45962573489054126,
      "grad_norm": 0.16713157296180725,
      "learning_rate": 0.003,
      "loss": 3.1479681396484374,
      "step": 210400
    },
    {
      "epoch": 0.4598441881865919,
      "grad_norm": 0.16104623675346375,
      "learning_rate": 0.003,
      "loss": 3.1393368530273436,
      "step": 210500
    },
    {
      "epoch": 0.46006264148264253,
      "grad_norm": 0.1699758917093277,
      "learning_rate": 0.003,
      "loss": 3.1560064697265626,
      "step": 210600
    },
    {
      "epoch": 0.46028109477869317,
      "grad_norm": 0.15945173799991608,
      "learning_rate": 0.003,
      "loss": 3.159805908203125,
      "step": 210700
    },
    {
      "epoch": 0.4604995480747438,
      "grad_norm": 0.22266627848148346,
      "learning_rate": 0.003,
      "loss": 3.179281921386719,
      "step": 210800
    },
    {
      "epoch": 0.46071800137079444,
      "grad_norm": 0.14309744536876678,
      "learning_rate": 0.003,
      "loss": 3.167117004394531,
      "step": 210900
    },
    {
      "epoch": 0.4609364546668451,
      "grad_norm": 0.15980547666549683,
      "learning_rate": 0.003,
      "loss": 3.1486465454101564,
      "step": 211000
    },
    {
      "epoch": 0.4611549079628957,
      "grad_norm": 0.18198712170124054,
      "learning_rate": 0.003,
      "loss": 3.1594610595703125,
      "step": 211100
    },
    {
      "epoch": 0.46137336125894635,
      "grad_norm": 0.26559925079345703,
      "learning_rate": 0.003,
      "loss": 3.125909423828125,
      "step": 211200
    },
    {
      "epoch": 0.461591814554997,
      "grad_norm": 0.5364328622817993,
      "learning_rate": 0.003,
      "loss": 3.161825866699219,
      "step": 211300
    },
    {
      "epoch": 0.4618102678510476,
      "grad_norm": 0.2357628047466278,
      "learning_rate": 0.003,
      "loss": 3.152314453125,
      "step": 211400
    },
    {
      "epoch": 0.46202872114709825,
      "grad_norm": 0.1753907948732376,
      "learning_rate": 0.003,
      "loss": 3.083882141113281,
      "step": 211500
    },
    {
      "epoch": 0.4622471744431489,
      "grad_norm": 0.22157512605190277,
      "learning_rate": 0.003,
      "loss": 3.1507366943359374,
      "step": 211600
    },
    {
      "epoch": 0.4624656277391995,
      "grad_norm": 0.18353408575057983,
      "learning_rate": 0.003,
      "loss": 3.1736688232421875,
      "step": 211700
    },
    {
      "epoch": 0.46268408103525016,
      "grad_norm": 0.15600447356700897,
      "learning_rate": 0.003,
      "loss": 3.1443942260742186,
      "step": 211800
    },
    {
      "epoch": 0.4629025343313008,
      "grad_norm": 0.1614781767129898,
      "learning_rate": 0.003,
      "loss": 3.1579415893554685,
      "step": 211900
    },
    {
      "epoch": 0.46312098762735143,
      "grad_norm": 0.20539352297782898,
      "learning_rate": 0.003,
      "loss": 3.128978576660156,
      "step": 212000
    },
    {
      "epoch": 0.46333944092340207,
      "grad_norm": 0.2934597432613373,
      "learning_rate": 0.003,
      "loss": 3.1663763427734377,
      "step": 212100
    },
    {
      "epoch": 0.4635578942194527,
      "grad_norm": 0.3008079528808594,
      "learning_rate": 0.003,
      "loss": 3.1361923217773438,
      "step": 212200
    },
    {
      "epoch": 0.46377634751550334,
      "grad_norm": 0.1944027841091156,
      "learning_rate": 0.003,
      "loss": 3.147728271484375,
      "step": 212300
    },
    {
      "epoch": 0.463994800811554,
      "grad_norm": 0.19676056504249573,
      "learning_rate": 0.003,
      "loss": 3.138658447265625,
      "step": 212400
    },
    {
      "epoch": 0.4642132541076046,
      "grad_norm": 0.1711074709892273,
      "learning_rate": 0.003,
      "loss": 3.1354574584960937,
      "step": 212500
    },
    {
      "epoch": 0.46443170740365525,
      "grad_norm": 0.18143917620182037,
      "learning_rate": 0.003,
      "loss": 3.19213134765625,
      "step": 212600
    },
    {
      "epoch": 0.4646501606997059,
      "grad_norm": 0.17058663070201874,
      "learning_rate": 0.003,
      "loss": 3.198305358886719,
      "step": 212700
    },
    {
      "epoch": 0.4648686139957565,
      "grad_norm": 0.166835218667984,
      "learning_rate": 0.003,
      "loss": 3.180174560546875,
      "step": 212800
    },
    {
      "epoch": 0.46508706729180715,
      "grad_norm": 0.21350142359733582,
      "learning_rate": 0.003,
      "loss": 3.12016357421875,
      "step": 212900
    },
    {
      "epoch": 0.46530552058785785,
      "grad_norm": 0.3394431173801422,
      "learning_rate": 0.003,
      "loss": 3.1741342163085937,
      "step": 213000
    },
    {
      "epoch": 0.4655239738839085,
      "grad_norm": 0.25171831250190735,
      "learning_rate": 0.003,
      "loss": 3.1526889038085937,
      "step": 213100
    },
    {
      "epoch": 0.4657424271799591,
      "grad_norm": 0.17684683203697205,
      "learning_rate": 0.003,
      "loss": 3.2026043701171876,
      "step": 213200
    },
    {
      "epoch": 0.46596088047600975,
      "grad_norm": 0.19386181235313416,
      "learning_rate": 0.003,
      "loss": 3.134582214355469,
      "step": 213300
    },
    {
      "epoch": 0.4661793337720604,
      "grad_norm": 0.21524786949157715,
      "learning_rate": 0.003,
      "loss": 3.0955670166015623,
      "step": 213400
    },
    {
      "epoch": 0.466397787068111,
      "grad_norm": 0.15787705779075623,
      "learning_rate": 0.003,
      "loss": 3.1583438110351563,
      "step": 213500
    },
    {
      "epoch": 0.46661624036416166,
      "grad_norm": 0.3695271909236908,
      "learning_rate": 0.003,
      "loss": 3.106593017578125,
      "step": 213600
    },
    {
      "epoch": 0.4668346936602123,
      "grad_norm": 0.16117428243160248,
      "learning_rate": 0.003,
      "loss": 3.150995788574219,
      "step": 213700
    },
    {
      "epoch": 0.46705314695626293,
      "grad_norm": 0.18444766104221344,
      "learning_rate": 0.003,
      "loss": 3.183512878417969,
      "step": 213800
    },
    {
      "epoch": 0.46727160025231357,
      "grad_norm": 0.15636524558067322,
      "learning_rate": 0.003,
      "loss": 3.1030828857421877,
      "step": 213900
    },
    {
      "epoch": 0.4674900535483642,
      "grad_norm": 0.17310112714767456,
      "learning_rate": 0.003,
      "loss": 3.2202767944335937,
      "step": 214000
    },
    {
      "epoch": 0.46770850684441484,
      "grad_norm": 0.19174368679523468,
      "learning_rate": 0.003,
      "loss": 3.1042364501953124,
      "step": 214100
    },
    {
      "epoch": 0.4679269601404655,
      "grad_norm": 0.21445919573307037,
      "learning_rate": 0.003,
      "loss": 3.153455810546875,
      "step": 214200
    },
    {
      "epoch": 0.4681454134365161,
      "grad_norm": 0.2191775143146515,
      "learning_rate": 0.003,
      "loss": 3.1314501953125,
      "step": 214300
    },
    {
      "epoch": 0.46836386673256675,
      "grad_norm": 0.21473421156406403,
      "learning_rate": 0.003,
      "loss": 3.1436236572265623,
      "step": 214400
    },
    {
      "epoch": 0.4685823200286174,
      "grad_norm": 0.17324420809745789,
      "learning_rate": 0.003,
      "loss": 3.159870910644531,
      "step": 214500
    },
    {
      "epoch": 0.468800773324668,
      "grad_norm": 0.17562781274318695,
      "learning_rate": 0.003,
      "loss": 3.1309463500976564,
      "step": 214600
    },
    {
      "epoch": 0.46901922662071865,
      "grad_norm": 0.17903006076812744,
      "learning_rate": 0.003,
      "loss": 3.1418161010742187,
      "step": 214700
    },
    {
      "epoch": 0.4692376799167693,
      "grad_norm": 0.16592048108577728,
      "learning_rate": 0.003,
      "loss": 3.1326254272460936,
      "step": 214800
    },
    {
      "epoch": 0.4694561332128199,
      "grad_norm": 0.1632029116153717,
      "learning_rate": 0.003,
      "loss": 3.133851318359375,
      "step": 214900
    },
    {
      "epoch": 0.46967458650887056,
      "grad_norm": 0.16100339591503143,
      "learning_rate": 0.003,
      "loss": 3.1411593627929686,
      "step": 215000
    },
    {
      "epoch": 0.4698930398049212,
      "grad_norm": 0.16473691165447235,
      "learning_rate": 0.003,
      "loss": 3.1777252197265624,
      "step": 215100
    },
    {
      "epoch": 0.47011149310097183,
      "grad_norm": 0.16993452608585358,
      "learning_rate": 0.003,
      "loss": 3.1630010986328125,
      "step": 215200
    },
    {
      "epoch": 0.47032994639702247,
      "grad_norm": 0.22841015458106995,
      "learning_rate": 0.003,
      "loss": 3.0239453125,
      "step": 215300
    },
    {
      "epoch": 0.4705483996930731,
      "grad_norm": 0.3482697606086731,
      "learning_rate": 0.003,
      "loss": 3.216066589355469,
      "step": 215400
    },
    {
      "epoch": 0.47076685298912374,
      "grad_norm": 0.26118969917297363,
      "learning_rate": 0.003,
      "loss": 3.1262786865234373,
      "step": 215500
    },
    {
      "epoch": 0.4709853062851744,
      "grad_norm": 0.1813250035047531,
      "learning_rate": 0.003,
      "loss": 3.167774963378906,
      "step": 215600
    },
    {
      "epoch": 0.471203759581225,
      "grad_norm": 0.18028207123279572,
      "learning_rate": 0.003,
      "loss": 3.16726806640625,
      "step": 215700
    },
    {
      "epoch": 0.47142221287727565,
      "grad_norm": 0.18035469949245453,
      "learning_rate": 0.003,
      "loss": 3.159013366699219,
      "step": 215800
    },
    {
      "epoch": 0.4716406661733263,
      "grad_norm": 0.14654624462127686,
      "learning_rate": 0.003,
      "loss": 2.8070077514648437,
      "step": 215900
    },
    {
      "epoch": 0.4718591194693769,
      "grad_norm": 0.18744167685508728,
      "learning_rate": 0.003,
      "loss": 3.17054931640625,
      "step": 216000
    },
    {
      "epoch": 0.47207757276542756,
      "grad_norm": 0.3383685350418091,
      "learning_rate": 0.003,
      "loss": 3.165613708496094,
      "step": 216100
    },
    {
      "epoch": 0.4722960260614782,
      "grad_norm": 0.17463649809360504,
      "learning_rate": 0.003,
      "loss": 3.1798410034179687,
      "step": 216200
    },
    {
      "epoch": 0.4725144793575289,
      "grad_norm": 0.14807528257369995,
      "learning_rate": 0.003,
      "loss": 3.147523193359375,
      "step": 216300
    },
    {
      "epoch": 0.4727329326535795,
      "grad_norm": 0.16796840727329254,
      "learning_rate": 0.003,
      "loss": 3.2063772583007815,
      "step": 216400
    },
    {
      "epoch": 0.47295138594963015,
      "grad_norm": 0.16152361035346985,
      "learning_rate": 0.003,
      "loss": 3.1491717529296874,
      "step": 216500
    },
    {
      "epoch": 0.4731698392456808,
      "grad_norm": 0.2170737385749817,
      "learning_rate": 0.003,
      "loss": 3.155273742675781,
      "step": 216600
    },
    {
      "epoch": 0.4733882925417314,
      "grad_norm": 0.21074289083480835,
      "learning_rate": 0.003,
      "loss": 3.1802407836914064,
      "step": 216700
    },
    {
      "epoch": 0.47360674583778206,
      "grad_norm": 0.1617479771375656,
      "learning_rate": 0.003,
      "loss": 3.1486907958984376,
      "step": 216800
    },
    {
      "epoch": 0.4738251991338327,
      "grad_norm": 0.18184621632099152,
      "learning_rate": 0.003,
      "loss": 3.150770263671875,
      "step": 216900
    },
    {
      "epoch": 0.47404365242988333,
      "grad_norm": 0.3051496744155884,
      "learning_rate": 0.003,
      "loss": 3.1770388793945314,
      "step": 217000
    },
    {
      "epoch": 0.47426210572593397,
      "grad_norm": 0.26827648282051086,
      "learning_rate": 0.003,
      "loss": 3.1692233276367188,
      "step": 217100
    },
    {
      "epoch": 0.4744805590219846,
      "grad_norm": 0.24766795337200165,
      "learning_rate": 0.003,
      "loss": 3.161100158691406,
      "step": 217200
    },
    {
      "epoch": 0.47469901231803524,
      "grad_norm": 0.17308169603347778,
      "learning_rate": 0.003,
      "loss": 3.131328125,
      "step": 217300
    },
    {
      "epoch": 0.4749174656140859,
      "grad_norm": 0.23382170498371124,
      "learning_rate": 0.003,
      "loss": 3.14703857421875,
      "step": 217400
    },
    {
      "epoch": 0.4751359189101365,
      "grad_norm": 0.19710423052310944,
      "learning_rate": 0.003,
      "loss": 3.1825299072265625,
      "step": 217500
    },
    {
      "epoch": 0.47535437220618715,
      "grad_norm": 0.1638881415128708,
      "learning_rate": 0.003,
      "loss": 3.1460092163085935,
      "step": 217600
    },
    {
      "epoch": 0.4755728255022378,
      "grad_norm": 0.1962563544511795,
      "learning_rate": 0.003,
      "loss": 3.074509582519531,
      "step": 217700
    },
    {
      "epoch": 0.4757912787982884,
      "grad_norm": 0.18982835114002228,
      "learning_rate": 0.003,
      "loss": 3.1882479858398436,
      "step": 217800
    },
    {
      "epoch": 0.47600973209433906,
      "grad_norm": 0.2274264693260193,
      "learning_rate": 0.003,
      "loss": 3.09603271484375,
      "step": 217900
    },
    {
      "epoch": 0.4762281853903897,
      "grad_norm": 0.17432497441768646,
      "learning_rate": 0.003,
      "loss": 3.1754559326171874,
      "step": 218000
    },
    {
      "epoch": 0.4764466386864403,
      "grad_norm": 0.2855411767959595,
      "learning_rate": 0.003,
      "loss": 3.1634857177734377,
      "step": 218100
    },
    {
      "epoch": 0.47666509198249096,
      "grad_norm": 0.38714003562927246,
      "learning_rate": 0.003,
      "loss": 3.0960037231445314,
      "step": 218200
    },
    {
      "epoch": 0.4768835452785416,
      "grad_norm": 0.26118314266204834,
      "learning_rate": 0.003,
      "loss": 3.1505917358398436,
      "step": 218300
    },
    {
      "epoch": 0.47710199857459223,
      "grad_norm": 0.18455421924591064,
      "learning_rate": 0.003,
      "loss": 3.140816955566406,
      "step": 218400
    },
    {
      "epoch": 0.47732045187064287,
      "grad_norm": 0.1687876135110855,
      "learning_rate": 0.003,
      "loss": 3.1302886962890626,
      "step": 218500
    },
    {
      "epoch": 0.4775389051666935,
      "grad_norm": 0.17909392714500427,
      "learning_rate": 0.003,
      "loss": 3.197586975097656,
      "step": 218600
    },
    {
      "epoch": 0.47775735846274414,
      "grad_norm": 0.18116098642349243,
      "learning_rate": 0.003,
      "loss": 3.1819522094726564,
      "step": 218700
    },
    {
      "epoch": 0.4779758117587948,
      "grad_norm": 0.1612115502357483,
      "learning_rate": 0.003,
      "loss": 3.1049078369140624,
      "step": 218800
    },
    {
      "epoch": 0.4781942650548454,
      "grad_norm": 0.1840500384569168,
      "learning_rate": 0.003,
      "loss": 3.162522888183594,
      "step": 218900
    },
    {
      "epoch": 0.47841271835089605,
      "grad_norm": 0.20502878725528717,
      "learning_rate": 0.003,
      "loss": 3.1762603759765624,
      "step": 219000
    },
    {
      "epoch": 0.4786311716469467,
      "grad_norm": 0.2547864615917206,
      "learning_rate": 0.003,
      "loss": 3.1093701171875,
      "step": 219100
    },
    {
      "epoch": 0.4788496249429973,
      "grad_norm": 0.2429780811071396,
      "learning_rate": 0.003,
      "loss": 3.1750225830078125,
      "step": 219200
    },
    {
      "epoch": 0.47906807823904796,
      "grad_norm": 0.22146986424922943,
      "learning_rate": 0.003,
      "loss": 3.167830505371094,
      "step": 219300
    },
    {
      "epoch": 0.4792865315350986,
      "grad_norm": 0.16268104314804077,
      "learning_rate": 0.003,
      "loss": 3.158450927734375,
      "step": 219400
    },
    {
      "epoch": 0.47950498483114923,
      "grad_norm": 0.26226094365119934,
      "learning_rate": 0.003,
      "loss": 3.1244711303710937,
      "step": 219500
    },
    {
      "epoch": 0.4797234381271999,
      "grad_norm": 0.17874610424041748,
      "learning_rate": 0.003,
      "loss": 3.11212158203125,
      "step": 219600
    },
    {
      "epoch": 0.47994189142325056,
      "grad_norm": 0.2803521752357483,
      "learning_rate": 0.003,
      "loss": 3.143751525878906,
      "step": 219700
    },
    {
      "epoch": 0.4801603447193012,
      "grad_norm": 0.18600259721279144,
      "learning_rate": 0.003,
      "loss": 3.18244140625,
      "step": 219800
    },
    {
      "epoch": 0.4803787980153518,
      "grad_norm": 0.19180288910865784,
      "learning_rate": 0.003,
      "loss": 3.145629577636719,
      "step": 219900
    },
    {
      "epoch": 0.48059725131140246,
      "grad_norm": 0.24468694627285004,
      "learning_rate": 0.003,
      "loss": 3.1552133178710937,
      "step": 220000
    },
    {
      "epoch": 0.4808157046074531,
      "grad_norm": 0.18709078431129456,
      "learning_rate": 0.003,
      "loss": 3.2035125732421874,
      "step": 220100
    },
    {
      "epoch": 0.48103415790350373,
      "grad_norm": 0.15144896507263184,
      "learning_rate": 0.003,
      "loss": 3.1047967529296874,
      "step": 220200
    },
    {
      "epoch": 0.48125261119955437,
      "grad_norm": 0.1488223671913147,
      "learning_rate": 0.003,
      "loss": 3.1655563354492187,
      "step": 220300
    },
    {
      "epoch": 0.481471064495605,
      "grad_norm": 0.18173527717590332,
      "learning_rate": 0.003,
      "loss": 3.1892333984375,
      "step": 220400
    },
    {
      "epoch": 0.48168951779165564,
      "grad_norm": 0.220792755484581,
      "learning_rate": 0.003,
      "loss": 3.1455557250976565,
      "step": 220500
    },
    {
      "epoch": 0.4819079710877063,
      "grad_norm": 0.22935664653778076,
      "learning_rate": 0.003,
      "loss": 3.1949893188476564,
      "step": 220600
    },
    {
      "epoch": 0.4821264243837569,
      "grad_norm": 0.16736885905265808,
      "learning_rate": 0.003,
      "loss": 3.1827288818359376,
      "step": 220700
    },
    {
      "epoch": 0.48234487767980755,
      "grad_norm": 0.19127635657787323,
      "learning_rate": 0.003,
      "loss": 3.1608261108398437,
      "step": 220800
    },
    {
      "epoch": 0.4825633309758582,
      "grad_norm": 0.14843328297138214,
      "learning_rate": 0.003,
      "loss": 3.1346920776367186,
      "step": 220900
    },
    {
      "epoch": 0.4827817842719088,
      "grad_norm": 0.23333857953548431,
      "learning_rate": 0.003,
      "loss": 3.0843185424804687,
      "step": 221000
    },
    {
      "epoch": 0.48300023756795946,
      "grad_norm": 0.2727338969707489,
      "learning_rate": 0.003,
      "loss": 3.1308114624023435,
      "step": 221100
    },
    {
      "epoch": 0.4832186908640101,
      "grad_norm": 0.2478320598602295,
      "learning_rate": 0.003,
      "loss": 3.1406036376953126,
      "step": 221200
    },
    {
      "epoch": 0.48343714416006073,
      "grad_norm": 0.27126774191856384,
      "learning_rate": 0.003,
      "loss": 3.1255056762695315,
      "step": 221300
    },
    {
      "epoch": 0.48365559745611136,
      "grad_norm": 0.21170471608638763,
      "learning_rate": 0.003,
      "loss": 3.1168563842773436,
      "step": 221400
    },
    {
      "epoch": 0.483874050752162,
      "grad_norm": 0.1838824450969696,
      "learning_rate": 0.003,
      "loss": 3.0979623413085937,
      "step": 221500
    },
    {
      "epoch": 0.48409250404821264,
      "grad_norm": 0.16253533959388733,
      "learning_rate": 0.003,
      "loss": 3.1662173461914063,
      "step": 221600
    },
    {
      "epoch": 0.48431095734426327,
      "grad_norm": 0.18137215077877045,
      "learning_rate": 0.003,
      "loss": 3.1684259033203124,
      "step": 221700
    },
    {
      "epoch": 0.4845294106403139,
      "grad_norm": 0.22282999753952026,
      "learning_rate": 0.003,
      "loss": 3.1648019409179686,
      "step": 221800
    },
    {
      "epoch": 0.48474786393636454,
      "grad_norm": 0.2163437306880951,
      "learning_rate": 0.003,
      "loss": 3.150612487792969,
      "step": 221900
    },
    {
      "epoch": 0.4849663172324152,
      "grad_norm": 0.22172391414642334,
      "learning_rate": 0.003,
      "loss": 3.2086767578125,
      "step": 222000
    },
    {
      "epoch": 0.4851847705284658,
      "grad_norm": 0.28733405470848083,
      "learning_rate": 0.003,
      "loss": 3.166444091796875,
      "step": 222100
    },
    {
      "epoch": 0.48540322382451645,
      "grad_norm": 0.16185955703258514,
      "learning_rate": 0.003,
      "loss": 3.2030029296875,
      "step": 222200
    },
    {
      "epoch": 0.4856216771205671,
      "grad_norm": 0.1988869458436966,
      "learning_rate": 0.003,
      "loss": 3.202830505371094,
      "step": 222300
    },
    {
      "epoch": 0.4858401304166177,
      "grad_norm": 0.21221868693828583,
      "learning_rate": 0.003,
      "loss": 3.2170611572265626,
      "step": 222400
    },
    {
      "epoch": 0.48605858371266836,
      "grad_norm": 0.1589498668909073,
      "learning_rate": 0.003,
      "loss": 3.16412109375,
      "step": 222500
    },
    {
      "epoch": 0.486277037008719,
      "grad_norm": 0.16693870723247528,
      "learning_rate": 0.003,
      "loss": 3.1169143676757813,
      "step": 222600
    },
    {
      "epoch": 0.48649549030476963,
      "grad_norm": 0.22212928533554077,
      "learning_rate": 0.003,
      "loss": 3.1289138793945312,
      "step": 222700
    },
    {
      "epoch": 0.48671394360082026,
      "grad_norm": 0.2194545865058899,
      "learning_rate": 0.003,
      "loss": 3.1857672119140625,
      "step": 222800
    },
    {
      "epoch": 0.48693239689687096,
      "grad_norm": 0.1598360240459442,
      "learning_rate": 0.003,
      "loss": 3.161907043457031,
      "step": 222900
    },
    {
      "epoch": 0.4871508501929216,
      "grad_norm": 0.14613743126392365,
      "learning_rate": 0.003,
      "loss": 3.16557861328125,
      "step": 223000
    },
    {
      "epoch": 0.4873693034889722,
      "grad_norm": 0.22282785177230835,
      "learning_rate": 0.003,
      "loss": 3.16187744140625,
      "step": 223100
    },
    {
      "epoch": 0.48758775678502286,
      "grad_norm": 0.16894131898880005,
      "learning_rate": 0.003,
      "loss": 3.135314636230469,
      "step": 223200
    },
    {
      "epoch": 0.4878062100810735,
      "grad_norm": 0.23414218425750732,
      "learning_rate": 0.003,
      "loss": 3.134132080078125,
      "step": 223300
    },
    {
      "epoch": 0.48802466337712413,
      "grad_norm": 0.15423694252967834,
      "learning_rate": 0.003,
      "loss": 3.156860046386719,
      "step": 223400
    },
    {
      "epoch": 0.48824311667317477,
      "grad_norm": 0.2406158447265625,
      "learning_rate": 0.003,
      "loss": 3.172440490722656,
      "step": 223500
    },
    {
      "epoch": 0.4884615699692254,
      "grad_norm": 0.19144734740257263,
      "learning_rate": 0.003,
      "loss": 3.167115478515625,
      "step": 223600
    },
    {
      "epoch": 0.48868002326527604,
      "grad_norm": 0.26312723755836487,
      "learning_rate": 0.003,
      "loss": 3.165943298339844,
      "step": 223700
    },
    {
      "epoch": 0.4888984765613267,
      "grad_norm": 0.348233163356781,
      "learning_rate": 0.003,
      "loss": 3.191070861816406,
      "step": 223800
    },
    {
      "epoch": 0.4891169298573773,
      "grad_norm": 0.17921116948127747,
      "learning_rate": 0.003,
      "loss": 3.1445526123046874,
      "step": 223900
    },
    {
      "epoch": 0.48933538315342795,
      "grad_norm": 0.22905179858207703,
      "learning_rate": 0.003,
      "loss": 3.147166748046875,
      "step": 224000
    },
    {
      "epoch": 0.4895538364494786,
      "grad_norm": 0.1956830471754074,
      "learning_rate": 0.003,
      "loss": 3.1890408325195314,
      "step": 224100
    },
    {
      "epoch": 0.4897722897455292,
      "grad_norm": 0.2036634385585785,
      "learning_rate": 0.003,
      "loss": 3.0911279296875,
      "step": 224200
    },
    {
      "epoch": 0.48999074304157986,
      "grad_norm": 0.16970489919185638,
      "learning_rate": 0.003,
      "loss": 3.1214834594726564,
      "step": 224300
    },
    {
      "epoch": 0.4902091963376305,
      "grad_norm": 0.19116955995559692,
      "learning_rate": 0.003,
      "loss": 3.166630859375,
      "step": 224400
    },
    {
      "epoch": 0.49042764963368113,
      "grad_norm": 0.2422357201576233,
      "learning_rate": 0.003,
      "loss": 3.172335205078125,
      "step": 224500
    },
    {
      "epoch": 0.49064610292973176,
      "grad_norm": 0.24891163408756256,
      "learning_rate": 0.003,
      "loss": 3.1474761962890625,
      "step": 224600
    },
    {
      "epoch": 0.4908645562257824,
      "grad_norm": 0.2025931179523468,
      "learning_rate": 0.003,
      "loss": 3.1677899169921875,
      "step": 224700
    },
    {
      "epoch": 0.49108300952183304,
      "grad_norm": 0.27099576592445374,
      "learning_rate": 0.003,
      "loss": 3.1918161010742185,
      "step": 224800
    },
    {
      "epoch": 0.49130146281788367,
      "grad_norm": 0.25545749068260193,
      "learning_rate": 0.003,
      "loss": 3.189544982910156,
      "step": 224900
    },
    {
      "epoch": 0.4915199161139343,
      "grad_norm": 0.2629391551017761,
      "learning_rate": 0.003,
      "loss": 3.168634948730469,
      "step": 225000
    },
    {
      "epoch": 0.49173836940998494,
      "grad_norm": 0.18923765420913696,
      "learning_rate": 0.003,
      "loss": 3.15990966796875,
      "step": 225100
    },
    {
      "epoch": 0.4919568227060356,
      "grad_norm": 0.18892456591129303,
      "learning_rate": 0.003,
      "loss": 3.142034606933594,
      "step": 225200
    },
    {
      "epoch": 0.4921752760020862,
      "grad_norm": 0.2659720778465271,
      "learning_rate": 0.003,
      "loss": 3.1375527954101563,
      "step": 225300
    },
    {
      "epoch": 0.49239372929813685,
      "grad_norm": 0.16647860407829285,
      "learning_rate": 0.003,
      "loss": 3.1746176147460936,
      "step": 225400
    },
    {
      "epoch": 0.4926121825941875,
      "grad_norm": 0.19305846095085144,
      "learning_rate": 0.003,
      "loss": 3.1838333129882814,
      "step": 225500
    },
    {
      "epoch": 0.4928306358902381,
      "grad_norm": 0.17307411134243011,
      "learning_rate": 0.003,
      "loss": 3.1351968383789064,
      "step": 225600
    },
    {
      "epoch": 0.49304908918628876,
      "grad_norm": 0.19500820338726044,
      "learning_rate": 0.003,
      "loss": 3.142611083984375,
      "step": 225700
    },
    {
      "epoch": 0.4932675424823394,
      "grad_norm": 0.20214220881462097,
      "learning_rate": 0.003,
      "loss": 3.176474304199219,
      "step": 225800
    },
    {
      "epoch": 0.49348599577839003,
      "grad_norm": 0.2108156383037567,
      "learning_rate": 0.003,
      "loss": 3.1983517456054686,
      "step": 225900
    },
    {
      "epoch": 0.49370444907444067,
      "grad_norm": 0.18418718874454498,
      "learning_rate": 0.003,
      "loss": 3.1477825927734373,
      "step": 226000
    },
    {
      "epoch": 0.4939229023704913,
      "grad_norm": 0.21230654418468475,
      "learning_rate": 0.003,
      "loss": 3.1417645263671874,
      "step": 226100
    },
    {
      "epoch": 0.494141355666542,
      "grad_norm": 0.20152030885219574,
      "learning_rate": 0.003,
      "loss": 3.137409973144531,
      "step": 226200
    },
    {
      "epoch": 0.49435980896259263,
      "grad_norm": 0.17792752385139465,
      "learning_rate": 0.003,
      "loss": 3.1698428344726564,
      "step": 226300
    },
    {
      "epoch": 0.49457826225864326,
      "grad_norm": 0.2009790539741516,
      "learning_rate": 0.003,
      "loss": 3.174663391113281,
      "step": 226400
    },
    {
      "epoch": 0.4947967155546939,
      "grad_norm": 0.18974316120147705,
      "learning_rate": 0.003,
      "loss": 3.164247741699219,
      "step": 226500
    },
    {
      "epoch": 0.49501516885074454,
      "grad_norm": 0.24179743230342865,
      "learning_rate": 0.003,
      "loss": 3.196055908203125,
      "step": 226600
    },
    {
      "epoch": 0.49523362214679517,
      "grad_norm": 0.23746444284915924,
      "learning_rate": 0.003,
      "loss": 3.174152526855469,
      "step": 226700
    },
    {
      "epoch": 0.4954520754428458,
      "grad_norm": 0.17893211543560028,
      "learning_rate": 0.003,
      "loss": 3.1902334594726565,
      "step": 226800
    },
    {
      "epoch": 0.49567052873889644,
      "grad_norm": 0.19245882332324982,
      "learning_rate": 0.003,
      "loss": 3.136605529785156,
      "step": 226900
    },
    {
      "epoch": 0.4958889820349471,
      "grad_norm": 0.20001903176307678,
      "learning_rate": 0.003,
      "loss": 3.191983947753906,
      "step": 227000
    },
    {
      "epoch": 0.4961074353309977,
      "grad_norm": 0.20897835493087769,
      "learning_rate": 0.003,
      "loss": 3.155872802734375,
      "step": 227100
    },
    {
      "epoch": 0.49632588862704835,
      "grad_norm": 0.18248751759529114,
      "learning_rate": 0.003,
      "loss": 3.1695022583007812,
      "step": 227200
    },
    {
      "epoch": 0.496544341923099,
      "grad_norm": 0.19958429038524628,
      "learning_rate": 0.003,
      "loss": 3.1341552734375,
      "step": 227300
    },
    {
      "epoch": 0.4967627952191496,
      "grad_norm": 0.1883472502231598,
      "learning_rate": 0.003,
      "loss": 3.1790115356445314,
      "step": 227400
    },
    {
      "epoch": 0.49698124851520026,
      "grad_norm": 0.15693897008895874,
      "learning_rate": 0.003,
      "loss": 2.619044189453125,
      "step": 227500
    },
    {
      "epoch": 0.4971997018112509,
      "grad_norm": 0.25166088342666626,
      "learning_rate": 0.003,
      "loss": 3.153711853027344,
      "step": 227600
    },
    {
      "epoch": 0.49741815510730153,
      "grad_norm": 0.24233323335647583,
      "learning_rate": 0.003,
      "loss": 3.1704025268554688,
      "step": 227700
    },
    {
      "epoch": 0.49763660840335217,
      "grad_norm": 0.17404961585998535,
      "learning_rate": 0.003,
      "loss": 3.1235888671875,
      "step": 227800
    },
    {
      "epoch": 0.4978550616994028,
      "grad_norm": 0.20510125160217285,
      "learning_rate": 0.003,
      "loss": 3.1796807861328125,
      "step": 227900
    },
    {
      "epoch": 0.49807351499545344,
      "grad_norm": 0.15112701058387756,
      "learning_rate": 0.003,
      "loss": 3.1262002563476563,
      "step": 228000
    },
    {
      "epoch": 0.4982919682915041,
      "grad_norm": 0.1805305778980255,
      "learning_rate": 0.003,
      "loss": 3.144951171875,
      "step": 228100
    },
    {
      "epoch": 0.4985104215875547,
      "grad_norm": 0.24970218539237976,
      "learning_rate": 0.003,
      "loss": 3.145733642578125,
      "step": 228200
    },
    {
      "epoch": 0.49872887488360534,
      "grad_norm": 0.1671173870563507,
      "learning_rate": 0.003,
      "loss": 3.1498037719726564,
      "step": 228300
    },
    {
      "epoch": 0.498947328179656,
      "grad_norm": 0.2547897398471832,
      "learning_rate": 0.003,
      "loss": 3.1435226440429687,
      "step": 228400
    },
    {
      "epoch": 0.4991657814757066,
      "grad_norm": 0.182900071144104,
      "learning_rate": 0.003,
      "loss": 3.15749755859375,
      "step": 228500
    },
    {
      "epoch": 0.49938423477175725,
      "grad_norm": 0.30519285798072815,
      "learning_rate": 0.003,
      "loss": 3.130207214355469,
      "step": 228600
    },
    {
      "epoch": 0.4996026880678079,
      "grad_norm": 0.18492329120635986,
      "learning_rate": 0.003,
      "loss": 3.151156311035156,
      "step": 228700
    },
    {
      "epoch": 0.4998211413638585,
      "grad_norm": 0.18260130286216736,
      "learning_rate": 0.003,
      "loss": 3.130478515625,
      "step": 228800
    },
    {
      "epoch": 0.5000395946599092,
      "grad_norm": 0.2577711343765259,
      "learning_rate": 0.003,
      "loss": 3.1661395263671874,
      "step": 228900
    },
    {
      "epoch": 0.5002580479559599,
      "grad_norm": 0.19339261949062347,
      "learning_rate": 0.003,
      "loss": 3.1246737670898437,
      "step": 229000
    },
    {
      "epoch": 0.5004765012520105,
      "grad_norm": 0.24445314705371857,
      "learning_rate": 0.003,
      "loss": 3.1471392822265627,
      "step": 229100
    },
    {
      "epoch": 0.5006949545480611,
      "grad_norm": 0.19137607514858246,
      "learning_rate": 0.003,
      "loss": 3.11054931640625,
      "step": 229200
    },
    {
      "epoch": 0.5009134078441118,
      "grad_norm": 0.37376224994659424,
      "learning_rate": 0.003,
      "loss": 3.13775146484375,
      "step": 229300
    },
    {
      "epoch": 0.5011318611401624,
      "grad_norm": 0.1882135421037674,
      "learning_rate": 0.003,
      "loss": 3.13549072265625,
      "step": 229400
    },
    {
      "epoch": 0.501350314436213,
      "grad_norm": 0.1807108074426651,
      "learning_rate": 0.003,
      "loss": 3.1788360595703127,
      "step": 229500
    },
    {
      "epoch": 0.5015687677322637,
      "grad_norm": 0.21003921329975128,
      "learning_rate": 0.003,
      "loss": 3.1137765502929686,
      "step": 229600
    },
    {
      "epoch": 0.5017872210283143,
      "grad_norm": 0.28754863142967224,
      "learning_rate": 0.003,
      "loss": 3.148710021972656,
      "step": 229700
    },
    {
      "epoch": 0.5020056743243649,
      "grad_norm": 0.15810799598693848,
      "learning_rate": 0.003,
      "loss": 3.1385040283203125,
      "step": 229800
    },
    {
      "epoch": 0.5022241276204156,
      "grad_norm": 0.21843253076076508,
      "learning_rate": 0.003,
      "loss": 3.134249572753906,
      "step": 229900
    },
    {
      "epoch": 0.5024425809164662,
      "grad_norm": 0.23452652990818024,
      "learning_rate": 0.003,
      "loss": 3.1600860595703124,
      "step": 230000
    },
    {
      "epoch": 0.5026610342125168,
      "grad_norm": 0.18762056529521942,
      "learning_rate": 0.003,
      "loss": 3.135057067871094,
      "step": 230100
    },
    {
      "epoch": 0.5028794875085675,
      "grad_norm": 0.1835620105266571,
      "learning_rate": 0.003,
      "loss": 3.1578103637695314,
      "step": 230200
    },
    {
      "epoch": 0.5030979408046181,
      "grad_norm": 0.28673288226127625,
      "learning_rate": 0.003,
      "loss": 3.1682400512695312,
      "step": 230300
    },
    {
      "epoch": 0.5033163941006688,
      "grad_norm": 0.2580110430717468,
      "learning_rate": 0.003,
      "loss": 3.146380615234375,
      "step": 230400
    },
    {
      "epoch": 0.5035348473967194,
      "grad_norm": 0.22994884848594666,
      "learning_rate": 0.003,
      "loss": 3.1231060791015626,
      "step": 230500
    },
    {
      "epoch": 0.50375330069277,
      "grad_norm": 0.2120271921157837,
      "learning_rate": 0.003,
      "loss": 3.1535516357421876,
      "step": 230600
    },
    {
      "epoch": 0.5039717539888207,
      "grad_norm": 0.33069106936454773,
      "learning_rate": 0.003,
      "loss": 3.14041748046875,
      "step": 230700
    },
    {
      "epoch": 0.5041902072848713,
      "grad_norm": 0.19148114323616028,
      "learning_rate": 0.003,
      "loss": 3.1341156005859374,
      "step": 230800
    },
    {
      "epoch": 0.5044086605809219,
      "grad_norm": 0.1846427470445633,
      "learning_rate": 0.003,
      "loss": 3.172509765625,
      "step": 230900
    },
    {
      "epoch": 0.5046271138769726,
      "grad_norm": 0.21543483436107635,
      "learning_rate": 0.003,
      "loss": 3.1475018310546874,
      "step": 231000
    },
    {
      "epoch": 0.5048455671730232,
      "grad_norm": 0.18862541019916534,
      "learning_rate": 0.003,
      "loss": 3.145285339355469,
      "step": 231100
    },
    {
      "epoch": 0.5050640204690738,
      "grad_norm": 0.1620454639196396,
      "learning_rate": 0.003,
      "loss": 3.1240771484375,
      "step": 231200
    },
    {
      "epoch": 0.5052824737651245,
      "grad_norm": 0.2802674472332001,
      "learning_rate": 0.003,
      "loss": 3.1252215576171873,
      "step": 231300
    },
    {
      "epoch": 0.5055009270611751,
      "grad_norm": 0.16352462768554688,
      "learning_rate": 0.003,
      "loss": 3.1772000122070314,
      "step": 231400
    },
    {
      "epoch": 0.5057193803572257,
      "grad_norm": 0.3073109984397888,
      "learning_rate": 0.003,
      "loss": 3.1345306396484376,
      "step": 231500
    },
    {
      "epoch": 0.5059378336532764,
      "grad_norm": 0.21778486669063568,
      "learning_rate": 0.003,
      "loss": 3.158148193359375,
      "step": 231600
    },
    {
      "epoch": 0.506156286949327,
      "grad_norm": 0.18240179121494293,
      "learning_rate": 0.003,
      "loss": 3.174432373046875,
      "step": 231700
    },
    {
      "epoch": 0.5063747402453777,
      "grad_norm": 0.2050437331199646,
      "learning_rate": 0.003,
      "loss": 3.1414923095703124,
      "step": 231800
    },
    {
      "epoch": 0.5065931935414283,
      "grad_norm": 0.20635361969470978,
      "learning_rate": 0.003,
      "loss": 3.1892770385742186,
      "step": 231900
    },
    {
      "epoch": 0.5068116468374789,
      "grad_norm": 0.18596193194389343,
      "learning_rate": 0.003,
      "loss": 3.1682550048828126,
      "step": 232000
    },
    {
      "epoch": 0.5070301001335296,
      "grad_norm": 0.21535375714302063,
      "learning_rate": 0.003,
      "loss": 3.1380319213867187,
      "step": 232100
    },
    {
      "epoch": 0.5072485534295802,
      "grad_norm": 0.18974469602108002,
      "learning_rate": 0.003,
      "loss": 3.151031188964844,
      "step": 232200
    },
    {
      "epoch": 0.5074670067256308,
      "grad_norm": 0.18541699647903442,
      "learning_rate": 0.003,
      "loss": 2.648902587890625,
      "step": 232300
    },
    {
      "epoch": 0.5076854600216815,
      "grad_norm": 0.1750500649213791,
      "learning_rate": 0.003,
      "loss": 3.1299972534179688,
      "step": 232400
    },
    {
      "epoch": 0.5079039133177321,
      "grad_norm": 0.2742761969566345,
      "learning_rate": 0.003,
      "loss": 3.1311825561523436,
      "step": 232500
    },
    {
      "epoch": 0.5081223666137827,
      "grad_norm": 0.1484217345714569,
      "learning_rate": 0.003,
      "loss": 3.167539367675781,
      "step": 232600
    },
    {
      "epoch": 0.5083408199098334,
      "grad_norm": 0.15970870852470398,
      "learning_rate": 0.003,
      "loss": 3.192563171386719,
      "step": 232700
    },
    {
      "epoch": 0.508559273205884,
      "grad_norm": 0.17326267063617706,
      "learning_rate": 0.003,
      "loss": 3.1337930297851564,
      "step": 232800
    },
    {
      "epoch": 0.5087777265019346,
      "grad_norm": 0.25302037596702576,
      "learning_rate": 0.003,
      "loss": 3.129071044921875,
      "step": 232900
    },
    {
      "epoch": 0.5089961797979853,
      "grad_norm": 0.19493898749351501,
      "learning_rate": 0.003,
      "loss": 3.1151910400390626,
      "step": 233000
    },
    {
      "epoch": 0.5092146330940359,
      "grad_norm": 0.16462492942810059,
      "learning_rate": 0.003,
      "loss": 3.1464138793945313,
      "step": 233100
    },
    {
      "epoch": 0.5094330863900866,
      "grad_norm": 0.21634113788604736,
      "learning_rate": 0.003,
      "loss": 3.169049072265625,
      "step": 233200
    },
    {
      "epoch": 0.5096515396861372,
      "grad_norm": 0.16171379387378693,
      "learning_rate": 0.003,
      "loss": 3.167049560546875,
      "step": 233300
    },
    {
      "epoch": 0.5098699929821878,
      "grad_norm": 0.2584652602672577,
      "learning_rate": 0.003,
      "loss": 3.1503860473632814,
      "step": 233400
    },
    {
      "epoch": 0.5100884462782385,
      "grad_norm": 0.15525685250759125,
      "learning_rate": 0.003,
      "loss": 3.1419476318359374,
      "step": 233500
    },
    {
      "epoch": 0.5103068995742891,
      "grad_norm": 0.18300648033618927,
      "learning_rate": 0.003,
      "loss": 3.117961120605469,
      "step": 233600
    },
    {
      "epoch": 0.5105253528703397,
      "grad_norm": 0.188507080078125,
      "learning_rate": 0.003,
      "loss": 3.1076394653320314,
      "step": 233700
    },
    {
      "epoch": 0.5107438061663904,
      "grad_norm": 0.19418242573738098,
      "learning_rate": 0.003,
      "loss": 3.103826904296875,
      "step": 233800
    },
    {
      "epoch": 0.510962259462441,
      "grad_norm": 0.1586516797542572,
      "learning_rate": 0.003,
      "loss": 3.1146026611328126,
      "step": 233900
    },
    {
      "epoch": 0.5111807127584916,
      "grad_norm": 0.1668419986963272,
      "learning_rate": 0.003,
      "loss": 3.123565368652344,
      "step": 234000
    },
    {
      "epoch": 0.5113991660545423,
      "grad_norm": 0.17394861578941345,
      "learning_rate": 0.003,
      "loss": 3.0764154052734374,
      "step": 234100
    },
    {
      "epoch": 0.5116176193505929,
      "grad_norm": 0.1693863719701767,
      "learning_rate": 0.003,
      "loss": 3.152529296875,
      "step": 234200
    },
    {
      "epoch": 0.5118360726466435,
      "grad_norm": 0.16254021227359772,
      "learning_rate": 0.003,
      "loss": 3.127790832519531,
      "step": 234300
    },
    {
      "epoch": 0.5120545259426943,
      "grad_norm": 0.17051811516284943,
      "learning_rate": 0.003,
      "loss": 3.1331884765625,
      "step": 234400
    },
    {
      "epoch": 0.5122729792387449,
      "grad_norm": 0.1769934743642807,
      "learning_rate": 0.003,
      "loss": 3.158018798828125,
      "step": 234500
    },
    {
      "epoch": 0.5124914325347956,
      "grad_norm": 0.25265613198280334,
      "learning_rate": 0.003,
      "loss": 3.1365432739257812,
      "step": 234600
    },
    {
      "epoch": 0.5127098858308462,
      "grad_norm": 0.17514252662658691,
      "learning_rate": 0.003,
      "loss": 3.13132568359375,
      "step": 234700
    },
    {
      "epoch": 0.5129283391268968,
      "grad_norm": 0.20028243958950043,
      "learning_rate": 0.003,
      "loss": 3.1804779052734373,
      "step": 234800
    },
    {
      "epoch": 0.5131467924229475,
      "grad_norm": 0.2051955610513687,
      "learning_rate": 0.003,
      "loss": 3.1667559814453123,
      "step": 234900
    },
    {
      "epoch": 0.5133652457189981,
      "grad_norm": 0.1758011430501938,
      "learning_rate": 0.003,
      "loss": 3.1924404907226562,
      "step": 235000
    },
    {
      "epoch": 0.5135836990150487,
      "grad_norm": 0.22561368346214294,
      "learning_rate": 0.003,
      "loss": 3.121515808105469,
      "step": 235100
    },
    {
      "epoch": 0.5138021523110994,
      "grad_norm": 0.19689291715621948,
      "learning_rate": 0.003,
      "loss": 3.135845947265625,
      "step": 235200
    },
    {
      "epoch": 0.51402060560715,
      "grad_norm": 0.16265727579593658,
      "learning_rate": 0.003,
      "loss": 3.1251617431640626,
      "step": 235300
    },
    {
      "epoch": 0.5142390589032007,
      "grad_norm": 0.1738608181476593,
      "learning_rate": 0.003,
      "loss": 3.071164855957031,
      "step": 235400
    },
    {
      "epoch": 0.5144575121992513,
      "grad_norm": 0.2156277596950531,
      "learning_rate": 0.003,
      "loss": 3.1412399291992186,
      "step": 235500
    },
    {
      "epoch": 0.5146759654953019,
      "grad_norm": 0.37841665744781494,
      "learning_rate": 0.003,
      "loss": 3.106079406738281,
      "step": 235600
    },
    {
      "epoch": 0.5148944187913526,
      "grad_norm": 0.21702034771442413,
      "learning_rate": 0.003,
      "loss": 3.1581692504882812,
      "step": 235700
    },
    {
      "epoch": 0.5151128720874032,
      "grad_norm": 0.1470261961221695,
      "learning_rate": 0.003,
      "loss": 3.085460205078125,
      "step": 235800
    },
    {
      "epoch": 0.5153313253834538,
      "grad_norm": 0.2099924087524414,
      "learning_rate": 0.003,
      "loss": 3.147344665527344,
      "step": 235900
    },
    {
      "epoch": 0.5155497786795045,
      "grad_norm": 0.17647843062877655,
      "learning_rate": 0.003,
      "loss": 3.11168701171875,
      "step": 236000
    },
    {
      "epoch": 0.5157682319755551,
      "grad_norm": 0.20817279815673828,
      "learning_rate": 0.003,
      "loss": 3.1170843505859374,
      "step": 236100
    },
    {
      "epoch": 0.5159866852716057,
      "grad_norm": 0.19564424455165863,
      "learning_rate": 0.003,
      "loss": 3.1226620483398437,
      "step": 236200
    },
    {
      "epoch": 0.5162051385676564,
      "grad_norm": 0.18542195856571198,
      "learning_rate": 0.003,
      "loss": 3.092498779296875,
      "step": 236300
    },
    {
      "epoch": 0.516423591863707,
      "grad_norm": 0.17026866972446442,
      "learning_rate": 0.003,
      "loss": 3.086933288574219,
      "step": 236400
    },
    {
      "epoch": 0.5166420451597576,
      "grad_norm": 0.21932733058929443,
      "learning_rate": 0.003,
      "loss": 3.128851013183594,
      "step": 236500
    },
    {
      "epoch": 0.5168604984558083,
      "grad_norm": 0.18108494579792023,
      "learning_rate": 0.003,
      "loss": 3.128507080078125,
      "step": 236600
    },
    {
      "epoch": 0.5170789517518589,
      "grad_norm": 0.21168839931488037,
      "learning_rate": 0.003,
      "loss": 3.176746826171875,
      "step": 236700
    },
    {
      "epoch": 0.5172974050479096,
      "grad_norm": 0.15229472517967224,
      "learning_rate": 0.003,
      "loss": 3.123934326171875,
      "step": 236800
    },
    {
      "epoch": 0.5175158583439602,
      "grad_norm": 0.4455394446849823,
      "learning_rate": 0.003,
      "loss": 3.101551208496094,
      "step": 236900
    },
    {
      "epoch": 0.5177343116400108,
      "grad_norm": 0.19681786000728607,
      "learning_rate": 0.003,
      "loss": 3.1094903564453125,
      "step": 237000
    },
    {
      "epoch": 0.5179527649360615,
      "grad_norm": 0.17515911161899567,
      "learning_rate": 0.003,
      "loss": 3.180419616699219,
      "step": 237100
    },
    {
      "epoch": 0.5181712182321121,
      "grad_norm": 0.18159349262714386,
      "learning_rate": 0.003,
      "loss": 3.1235211181640623,
      "step": 237200
    },
    {
      "epoch": 0.5183896715281627,
      "grad_norm": 0.14785555005073547,
      "learning_rate": 0.003,
      "loss": 3.1321286010742186,
      "step": 237300
    },
    {
      "epoch": 0.5186081248242134,
      "grad_norm": 0.1888085901737213,
      "learning_rate": 0.003,
      "loss": 3.1357357788085936,
      "step": 237400
    },
    {
      "epoch": 0.518826578120264,
      "grad_norm": 0.2578486204147339,
      "learning_rate": 0.003,
      "loss": 3.11129150390625,
      "step": 237500
    },
    {
      "epoch": 0.5190450314163146,
      "grad_norm": 0.21361865103244781,
      "learning_rate": 0.003,
      "loss": 3.1505697631835936,
      "step": 237600
    },
    {
      "epoch": 0.5192634847123653,
      "grad_norm": 0.2349197417497635,
      "learning_rate": 0.003,
      "loss": 3.1423828125,
      "step": 237700
    },
    {
      "epoch": 0.5194819380084159,
      "grad_norm": 0.22056037187576294,
      "learning_rate": 0.003,
      "loss": 3.1116253662109377,
      "step": 237800
    },
    {
      "epoch": 0.5197003913044665,
      "grad_norm": 0.35375213623046875,
      "learning_rate": 0.003,
      "loss": 3.107217102050781,
      "step": 237900
    },
    {
      "epoch": 0.5199188446005172,
      "grad_norm": 0.29404938220977783,
      "learning_rate": 0.003,
      "loss": 3.1488226318359374,
      "step": 238000
    },
    {
      "epoch": 0.5201372978965678,
      "grad_norm": 0.20642751455307007,
      "learning_rate": 0.003,
      "loss": 3.117867736816406,
      "step": 238100
    },
    {
      "epoch": 0.5203557511926185,
      "grad_norm": 0.2022472321987152,
      "learning_rate": 0.003,
      "loss": 3.128268127441406,
      "step": 238200
    },
    {
      "epoch": 0.5205742044886691,
      "grad_norm": 0.3263418674468994,
      "learning_rate": 0.003,
      "loss": 3.1254312133789064,
      "step": 238300
    },
    {
      "epoch": 0.5207926577847197,
      "grad_norm": 0.21278858184814453,
      "learning_rate": 0.003,
      "loss": 3.139371032714844,
      "step": 238400
    },
    {
      "epoch": 0.5210111110807704,
      "grad_norm": 0.162919282913208,
      "learning_rate": 0.003,
      "loss": 2.6450790405273437,
      "step": 238500
    },
    {
      "epoch": 0.521229564376821,
      "grad_norm": 0.21057674288749695,
      "learning_rate": 0.003,
      "loss": 3.0988424682617186,
      "step": 238600
    },
    {
      "epoch": 0.5214480176728716,
      "grad_norm": 0.18826709687709808,
      "learning_rate": 0.003,
      "loss": 3.1593002319335937,
      "step": 238700
    },
    {
      "epoch": 0.5216664709689223,
      "grad_norm": 0.24033360183238983,
      "learning_rate": 0.003,
      "loss": 3.085846252441406,
      "step": 238800
    },
    {
      "epoch": 0.5218849242649729,
      "grad_norm": 0.15197022259235382,
      "learning_rate": 0.003,
      "loss": 3.11141357421875,
      "step": 238900
    },
    {
      "epoch": 0.5221033775610235,
      "grad_norm": 0.2142292708158493,
      "learning_rate": 0.003,
      "loss": 3.11074951171875,
      "step": 239000
    },
    {
      "epoch": 0.5223218308570742,
      "grad_norm": 0.16097873449325562,
      "learning_rate": 0.003,
      "loss": 3.106669616699219,
      "step": 239100
    },
    {
      "epoch": 0.5225402841531248,
      "grad_norm": 0.21529777348041534,
      "learning_rate": 0.003,
      "loss": 3.1509161376953125,
      "step": 239200
    },
    {
      "epoch": 0.5227587374491754,
      "grad_norm": 0.27515995502471924,
      "learning_rate": 0.003,
      "loss": 3.1199020385742187,
      "step": 239300
    },
    {
      "epoch": 0.5229771907452261,
      "grad_norm": 0.17017614841461182,
      "learning_rate": 0.003,
      "loss": 3.107218933105469,
      "step": 239400
    },
    {
      "epoch": 0.5231956440412767,
      "grad_norm": 0.24366989731788635,
      "learning_rate": 0.003,
      "loss": 3.1330767822265626,
      "step": 239500
    },
    {
      "epoch": 0.5234140973373274,
      "grad_norm": 0.17527785897254944,
      "learning_rate": 0.003,
      "loss": 3.1184152221679686,
      "step": 239600
    },
    {
      "epoch": 0.523632550633378,
      "grad_norm": 0.19744913280010223,
      "learning_rate": 0.003,
      "loss": 3.135106201171875,
      "step": 239700
    },
    {
      "epoch": 0.5238510039294286,
      "grad_norm": 0.202736958861351,
      "learning_rate": 0.003,
      "loss": 3.1773104858398438,
      "step": 239800
    },
    {
      "epoch": 0.5240694572254793,
      "grad_norm": 0.17386242747306824,
      "learning_rate": 0.003,
      "loss": 3.164744873046875,
      "step": 239900
    },
    {
      "epoch": 0.5242879105215299,
      "grad_norm": 0.18304742872714996,
      "learning_rate": 0.003,
      "loss": 3.1589617919921875,
      "step": 240000
    },
    {
      "epoch": 0.5245063638175805,
      "grad_norm": 0.2101735770702362,
      "learning_rate": 0.003,
      "loss": 3.1398870849609377,
      "step": 240100
    },
    {
      "epoch": 0.5247248171136312,
      "grad_norm": 0.23245501518249512,
      "learning_rate": 0.003,
      "loss": 3.154371643066406,
      "step": 240200
    },
    {
      "epoch": 0.5249432704096818,
      "grad_norm": 0.2745104432106018,
      "learning_rate": 0.003,
      "loss": 3.12414306640625,
      "step": 240300
    },
    {
      "epoch": 0.5251617237057324,
      "grad_norm": 0.18514570593833923,
      "learning_rate": 0.003,
      "loss": 3.176530456542969,
      "step": 240400
    },
    {
      "epoch": 0.5253801770017831,
      "grad_norm": 0.20294037461280823,
      "learning_rate": 0.003,
      "loss": 3.1463330078125,
      "step": 240500
    },
    {
      "epoch": 0.5255986302978337,
      "grad_norm": 0.3588567078113556,
      "learning_rate": 0.003,
      "loss": 3.0707131958007814,
      "step": 240600
    },
    {
      "epoch": 0.5258170835938843,
      "grad_norm": 0.20789752900600433,
      "learning_rate": 0.003,
      "loss": 3.1508062744140624,
      "step": 240700
    },
    {
      "epoch": 0.526035536889935,
      "grad_norm": 0.17802083492279053,
      "learning_rate": 0.003,
      "loss": 3.112729187011719,
      "step": 240800
    },
    {
      "epoch": 0.5262539901859856,
      "grad_norm": 0.21749688684940338,
      "learning_rate": 0.003,
      "loss": 3.1141656494140624,
      "step": 240900
    },
    {
      "epoch": 0.5264724434820364,
      "grad_norm": 0.17815862596035004,
      "learning_rate": 0.003,
      "loss": 3.1264682006835938,
      "step": 241000
    },
    {
      "epoch": 0.526690896778087,
      "grad_norm": 0.18600204586982727,
      "learning_rate": 0.003,
      "loss": 3.0889852905273436,
      "step": 241100
    },
    {
      "epoch": 0.5269093500741376,
      "grad_norm": 0.1708911508321762,
      "learning_rate": 0.003,
      "loss": 3.115555419921875,
      "step": 241200
    },
    {
      "epoch": 0.5271278033701883,
      "grad_norm": 0.20583029091358185,
      "learning_rate": 0.003,
      "loss": 3.1248098754882814,
      "step": 241300
    },
    {
      "epoch": 0.5273462566662389,
      "grad_norm": 0.23500178754329681,
      "learning_rate": 0.003,
      "loss": 3.1504916381835937,
      "step": 241400
    },
    {
      "epoch": 0.5275647099622895,
      "grad_norm": 0.20651696622371674,
      "learning_rate": 0.003,
      "loss": 3.1338641357421877,
      "step": 241500
    },
    {
      "epoch": 0.5277831632583402,
      "grad_norm": 0.1797979325056076,
      "learning_rate": 0.003,
      "loss": 3.1771466064453127,
      "step": 241600
    },
    {
      "epoch": 0.5280016165543908,
      "grad_norm": 0.2010064423084259,
      "learning_rate": 0.003,
      "loss": 3.146392517089844,
      "step": 241700
    },
    {
      "epoch": 0.5282200698504415,
      "grad_norm": 0.21170252561569214,
      "learning_rate": 0.003,
      "loss": 2.6480673217773436,
      "step": 241800
    },
    {
      "epoch": 0.5284385231464921,
      "grad_norm": 0.19016186892986298,
      "learning_rate": 0.003,
      "loss": 3.1313824462890625,
      "step": 241900
    },
    {
      "epoch": 0.5286569764425427,
      "grad_norm": 0.25798410177230835,
      "learning_rate": 0.003,
      "loss": 3.1526840209960936,
      "step": 242000
    },
    {
      "epoch": 0.5288754297385934,
      "grad_norm": 0.22974206507205963,
      "learning_rate": 0.003,
      "loss": 3.1100921630859375,
      "step": 242100
    },
    {
      "epoch": 0.529093883034644,
      "grad_norm": 0.27642637491226196,
      "learning_rate": 0.003,
      "loss": 3.107566223144531,
      "step": 242200
    },
    {
      "epoch": 0.5293123363306946,
      "grad_norm": 0.16707384586334229,
      "learning_rate": 0.003,
      "loss": 3.1245303344726563,
      "step": 242300
    },
    {
      "epoch": 0.5295307896267453,
      "grad_norm": 0.24297451972961426,
      "learning_rate": 0.003,
      "loss": 3.1431069946289063,
      "step": 242400
    },
    {
      "epoch": 0.5297492429227959,
      "grad_norm": 0.20769760012626648,
      "learning_rate": 0.003,
      "loss": 3.1313385009765624,
      "step": 242500
    },
    {
      "epoch": 0.5299676962188465,
      "grad_norm": 0.18473562598228455,
      "learning_rate": 0.003,
      "loss": 3.1169390869140625,
      "step": 242600
    },
    {
      "epoch": 0.5301861495148972,
      "grad_norm": 0.33607473969459534,
      "learning_rate": 0.003,
      "loss": 3.1396173095703124,
      "step": 242700
    },
    {
      "epoch": 0.5304046028109478,
      "grad_norm": 0.18841011822223663,
      "learning_rate": 0.003,
      "loss": 3.1677780151367188,
      "step": 242800
    },
    {
      "epoch": 0.5306230561069984,
      "grad_norm": 0.1925668716430664,
      "learning_rate": 0.003,
      "loss": 3.16513427734375,
      "step": 242900
    },
    {
      "epoch": 0.5308415094030491,
      "grad_norm": 0.21411524713039398,
      "learning_rate": 0.003,
      "loss": 3.182710876464844,
      "step": 243000
    },
    {
      "epoch": 0.5310599626990997,
      "grad_norm": 0.23761388659477234,
      "learning_rate": 0.003,
      "loss": 3.1229791259765625,
      "step": 243100
    },
    {
      "epoch": 0.5312784159951504,
      "grad_norm": 0.189153254032135,
      "learning_rate": 0.003,
      "loss": 3.150081787109375,
      "step": 243200
    },
    {
      "epoch": 0.531496869291201,
      "grad_norm": 0.22847697138786316,
      "learning_rate": 0.003,
      "loss": 3.1227841186523437,
      "step": 243300
    },
    {
      "epoch": 0.5317153225872516,
      "grad_norm": 0.2811618149280548,
      "learning_rate": 0.003,
      "loss": 3.149488525390625,
      "step": 243400
    },
    {
      "epoch": 0.5319337758833023,
      "grad_norm": 0.1922217160463333,
      "learning_rate": 0.003,
      "loss": 3.0970285034179685,
      "step": 243500
    },
    {
      "epoch": 0.5321522291793529,
      "grad_norm": 0.20400716364383698,
      "learning_rate": 0.003,
      "loss": 3.088838806152344,
      "step": 243600
    },
    {
      "epoch": 0.5323706824754035,
      "grad_norm": 0.167266845703125,
      "learning_rate": 0.003,
      "loss": 3.1400494384765625,
      "step": 243700
    },
    {
      "epoch": 0.5325891357714542,
      "grad_norm": 0.2143728882074356,
      "learning_rate": 0.003,
      "loss": 3.1147845458984373,
      "step": 243800
    },
    {
      "epoch": 0.5328075890675048,
      "grad_norm": 0.20438382029533386,
      "learning_rate": 0.003,
      "loss": 3.2136740112304687,
      "step": 243900
    },
    {
      "epoch": 0.5330260423635554,
      "grad_norm": 0.1927761286497116,
      "learning_rate": 0.003,
      "loss": 3.1357626342773437,
      "step": 244000
    },
    {
      "epoch": 0.5332444956596061,
      "grad_norm": 0.25126394629478455,
      "learning_rate": 0.003,
      "loss": 3.1431399536132814,
      "step": 244100
    },
    {
      "epoch": 0.5334629489556567,
      "grad_norm": 0.18891437351703644,
      "learning_rate": 0.003,
      "loss": 3.1622125244140626,
      "step": 244200
    },
    {
      "epoch": 0.5336814022517073,
      "grad_norm": 0.2305135726928711,
      "learning_rate": 0.003,
      "loss": 3.1171194458007814,
      "step": 244300
    },
    {
      "epoch": 0.533899855547758,
      "grad_norm": 0.1918029636144638,
      "learning_rate": 0.003,
      "loss": 3.1366259765625,
      "step": 244400
    },
    {
      "epoch": 0.5341183088438086,
      "grad_norm": 0.3250686526298523,
      "learning_rate": 0.003,
      "loss": 3.1357046508789064,
      "step": 244500
    },
    {
      "epoch": 0.5343367621398593,
      "grad_norm": 0.1797194480895996,
      "learning_rate": 0.003,
      "loss": 3.149069519042969,
      "step": 244600
    },
    {
      "epoch": 0.5345552154359099,
      "grad_norm": 0.17812472581863403,
      "learning_rate": 0.003,
      "loss": 3.1442205810546877,
      "step": 244700
    },
    {
      "epoch": 0.5347736687319605,
      "grad_norm": 0.21778053045272827,
      "learning_rate": 0.003,
      "loss": 3.136746520996094,
      "step": 244800
    },
    {
      "epoch": 0.5349921220280112,
      "grad_norm": 0.22971677780151367,
      "learning_rate": 0.003,
      "loss": 3.1393667602539064,
      "step": 244900
    },
    {
      "epoch": 0.5352105753240618,
      "grad_norm": 0.19162683188915253,
      "learning_rate": 0.003,
      "loss": 3.19802978515625,
      "step": 245000
    },
    {
      "epoch": 0.5354290286201124,
      "grad_norm": 0.2531306743621826,
      "learning_rate": 0.003,
      "loss": 3.1263632202148437,
      "step": 245100
    },
    {
      "epoch": 0.5356474819161631,
      "grad_norm": 0.17510290443897247,
      "learning_rate": 0.003,
      "loss": 3.1374856567382814,
      "step": 245200
    },
    {
      "epoch": 0.5358659352122137,
      "grad_norm": 0.19497226178646088,
      "learning_rate": 0.003,
      "loss": 3.105311279296875,
      "step": 245300
    },
    {
      "epoch": 0.5360843885082643,
      "grad_norm": 0.24567493796348572,
      "learning_rate": 0.003,
      "loss": 3.0898287963867186,
      "step": 245400
    },
    {
      "epoch": 0.536302841804315,
      "grad_norm": 0.15240059792995453,
      "learning_rate": 0.003,
      "loss": 3.1500125122070313,
      "step": 245500
    },
    {
      "epoch": 0.5365212951003656,
      "grad_norm": 0.20908641815185547,
      "learning_rate": 0.003,
      "loss": 3.1202337646484377,
      "step": 245600
    },
    {
      "epoch": 0.5367397483964162,
      "grad_norm": 0.2986869812011719,
      "learning_rate": 0.003,
      "loss": 3.0675833129882815,
      "step": 245700
    },
    {
      "epoch": 0.5369582016924669,
      "grad_norm": 0.19116243720054626,
      "learning_rate": 0.003,
      "loss": 3.114186096191406,
      "step": 245800
    },
    {
      "epoch": 0.5371766549885175,
      "grad_norm": 0.17148825526237488,
      "learning_rate": 0.003,
      "loss": 3.123931884765625,
      "step": 245900
    },
    {
      "epoch": 0.5373951082845682,
      "grad_norm": 0.20180387794971466,
      "learning_rate": 0.003,
      "loss": 3.1113421630859377,
      "step": 246000
    },
    {
      "epoch": 0.5376135615806188,
      "grad_norm": 0.2422924041748047,
      "learning_rate": 0.003,
      "loss": 3.153812255859375,
      "step": 246100
    },
    {
      "epoch": 0.5378320148766694,
      "grad_norm": 0.21342086791992188,
      "learning_rate": 0.003,
      "loss": 3.106568603515625,
      "step": 246200
    },
    {
      "epoch": 0.5380504681727201,
      "grad_norm": 0.17749156057834625,
      "learning_rate": 0.003,
      "loss": 3.1006719970703127,
      "step": 246300
    },
    {
      "epoch": 0.5382689214687707,
      "grad_norm": 0.174751877784729,
      "learning_rate": 0.003,
      "loss": 3.101731262207031,
      "step": 246400
    },
    {
      "epoch": 0.5384873747648213,
      "grad_norm": 0.16365885734558105,
      "learning_rate": 0.003,
      "loss": 3.110872497558594,
      "step": 246500
    },
    {
      "epoch": 0.538705828060872,
      "grad_norm": 0.18931667506694794,
      "learning_rate": 0.003,
      "loss": 3.1217276000976564,
      "step": 246600
    },
    {
      "epoch": 0.5389242813569226,
      "grad_norm": 0.2399245798587799,
      "learning_rate": 0.003,
      "loss": 3.0612939453125,
      "step": 246700
    },
    {
      "epoch": 0.5391427346529732,
      "grad_norm": 0.16774024069309235,
      "learning_rate": 0.003,
      "loss": 3.11084228515625,
      "step": 246800
    },
    {
      "epoch": 0.5393611879490239,
      "grad_norm": 0.384067177772522,
      "learning_rate": 0.003,
      "loss": 3.091241760253906,
      "step": 246900
    },
    {
      "epoch": 0.5395796412450745,
      "grad_norm": 0.16883859038352966,
      "learning_rate": 0.003,
      "loss": 3.0991705322265624,
      "step": 247000
    },
    {
      "epoch": 0.5397980945411252,
      "grad_norm": 0.29548773169517517,
      "learning_rate": 0.003,
      "loss": 3.1065579223632813,
      "step": 247100
    },
    {
      "epoch": 0.5400165478371758,
      "grad_norm": 0.1816398799419403,
      "learning_rate": 0.003,
      "loss": 3.132042236328125,
      "step": 247200
    },
    {
      "epoch": 0.5402350011332264,
      "grad_norm": 0.1755320280790329,
      "learning_rate": 0.003,
      "loss": 3.125732727050781,
      "step": 247300
    },
    {
      "epoch": 0.5404534544292771,
      "grad_norm": 0.24235445261001587,
      "learning_rate": 0.003,
      "loss": 3.1327362060546875,
      "step": 247400
    },
    {
      "epoch": 0.5406719077253277,
      "grad_norm": 0.2918884754180908,
      "learning_rate": 0.003,
      "loss": 3.108415222167969,
      "step": 247500
    },
    {
      "epoch": 0.5408903610213784,
      "grad_norm": 0.18328259885311127,
      "learning_rate": 0.003,
      "loss": 3.1481494140625,
      "step": 247600
    },
    {
      "epoch": 0.5411088143174291,
      "grad_norm": 0.20819595456123352,
      "learning_rate": 0.003,
      "loss": 3.1106536865234373,
      "step": 247700
    },
    {
      "epoch": 0.5413272676134797,
      "grad_norm": 0.22284214198589325,
      "learning_rate": 0.003,
      "loss": 3.088614807128906,
      "step": 247800
    },
    {
      "epoch": 0.5415457209095303,
      "grad_norm": 0.17495346069335938,
      "learning_rate": 0.003,
      "loss": 3.1115994262695312,
      "step": 247900
    },
    {
      "epoch": 0.541764174205581,
      "grad_norm": 0.35663121938705444,
      "learning_rate": 0.003,
      "loss": 3.12347900390625,
      "step": 248000
    },
    {
      "epoch": 0.5419826275016316,
      "grad_norm": 0.19235268235206604,
      "learning_rate": 0.003,
      "loss": 3.1116098022460936,
      "step": 248100
    },
    {
      "epoch": 0.5422010807976823,
      "grad_norm": 0.2285211831331253,
      "learning_rate": 0.003,
      "loss": 3.140888671875,
      "step": 248200
    },
    {
      "epoch": 0.5424195340937329,
      "grad_norm": 0.18105089664459229,
      "learning_rate": 0.003,
      "loss": 3.031875,
      "step": 248300
    },
    {
      "epoch": 0.5426379873897835,
      "grad_norm": 0.25545111298561096,
      "learning_rate": 0.003,
      "loss": 3.1165667724609376,
      "step": 248400
    },
    {
      "epoch": 0.5428564406858342,
      "grad_norm": 0.3303847908973694,
      "learning_rate": 0.003,
      "loss": 3.12045654296875,
      "step": 248500
    },
    {
      "epoch": 0.5430748939818848,
      "grad_norm": 1.9979333877563477,
      "learning_rate": 0.003,
      "loss": 3.006357421875,
      "step": 248600
    },
    {
      "epoch": 0.5432933472779354,
      "grad_norm": 0.24649471044540405,
      "learning_rate": 0.003,
      "loss": 2.939325866699219,
      "step": 248700
    },
    {
      "epoch": 0.5435118005739861,
      "grad_norm": 0.17547515034675598,
      "learning_rate": 0.003,
      "loss": 3.125332946777344,
      "step": 248800
    },
    {
      "epoch": 0.5437302538700367,
      "grad_norm": 0.3249010145664215,
      "learning_rate": 0.003,
      "loss": 3.121671447753906,
      "step": 248900
    },
    {
      "epoch": 0.5439487071660873,
      "grad_norm": 0.3345842957496643,
      "learning_rate": 0.003,
      "loss": 3.0678668212890625,
      "step": 249000
    },
    {
      "epoch": 0.544167160462138,
      "grad_norm": 0.17194406688213348,
      "learning_rate": 0.003,
      "loss": 3.1369476318359375,
      "step": 249100
    },
    {
      "epoch": 0.5443856137581886,
      "grad_norm": 0.1988215148448944,
      "learning_rate": 0.003,
      "loss": 3.0596624755859376,
      "step": 249200
    },
    {
      "epoch": 0.5446040670542392,
      "grad_norm": 0.22032035887241364,
      "learning_rate": 0.003,
      "loss": 3.0960577392578124,
      "step": 249300
    },
    {
      "epoch": 0.5448225203502899,
      "grad_norm": 0.27398282289505005,
      "learning_rate": 0.003,
      "loss": 3.071913146972656,
      "step": 249400
    },
    {
      "epoch": 0.5450409736463405,
      "grad_norm": 0.16967016458511353,
      "learning_rate": 0.003,
      "loss": 3.0751873779296877,
      "step": 249500
    },
    {
      "epoch": 0.5452594269423912,
      "grad_norm": 0.19359983503818512,
      "learning_rate": 0.003,
      "loss": 2.5894769287109374,
      "step": 249600
    },
    {
      "epoch": 0.5454778802384418,
      "grad_norm": 0.18907172977924347,
      "learning_rate": 0.003,
      "loss": 3.058880615234375,
      "step": 249700
    },
    {
      "epoch": 0.5456963335344924,
      "grad_norm": 0.1952255368232727,
      "learning_rate": 0.003,
      "loss": 2.988880310058594,
      "step": 249800
    },
    {
      "epoch": 0.5459147868305431,
      "grad_norm": 0.23794367909431458,
      "learning_rate": 0.003,
      "loss": 3.109373779296875,
      "step": 249900
    },
    {
      "epoch": 0.5461332401265937,
      "grad_norm": 0.24245142936706543,
      "learning_rate": 0.003,
      "loss": 3.0831268310546873,
      "step": 250000
    },
    {
      "epoch": 0.5463516934226443,
      "grad_norm": 0.23193468153476715,
      "learning_rate": 0.003,
      "loss": 3.0596722412109374,
      "step": 250100
    },
    {
      "epoch": 0.546570146718695,
      "grad_norm": 0.181810662150383,
      "learning_rate": 0.003,
      "loss": 2.9878759765625,
      "step": 250200
    },
    {
      "epoch": 0.5467886000147456,
      "grad_norm": 0.22600685060024261,
      "learning_rate": 0.003,
      "loss": 3.1013568115234373,
      "step": 250300
    },
    {
      "epoch": 0.5470070533107962,
      "grad_norm": 0.19996309280395508,
      "learning_rate": 0.003,
      "loss": 3.119810791015625,
      "step": 250400
    },
    {
      "epoch": 0.5472255066068469,
      "grad_norm": 0.19088006019592285,
      "learning_rate": 0.003,
      "loss": 3.053364562988281,
      "step": 250500
    },
    {
      "epoch": 0.5474439599028975,
      "grad_norm": 0.20620650053024292,
      "learning_rate": 0.003,
      "loss": 3.0581118774414064,
      "step": 250600
    },
    {
      "epoch": 0.5476624131989482,
      "grad_norm": 0.16485771536827087,
      "learning_rate": 0.003,
      "loss": 3.116041564941406,
      "step": 250700
    },
    {
      "epoch": 0.5478808664949988,
      "grad_norm": 0.23952528834342957,
      "learning_rate": 0.003,
      "loss": 3.2115054321289063,
      "step": 250800
    },
    {
      "epoch": 0.5480993197910494,
      "grad_norm": 0.1942622810602188,
      "learning_rate": 0.003,
      "loss": 3.1068685913085936,
      "step": 250900
    },
    {
      "epoch": 0.5483177730871001,
      "grad_norm": 0.21066008508205414,
      "learning_rate": 0.003,
      "loss": 3.170329895019531,
      "step": 251000
    },
    {
      "epoch": 0.5485362263831507,
      "grad_norm": 0.2221982181072235,
      "learning_rate": 0.003,
      "loss": 3.202665100097656,
      "step": 251100
    },
    {
      "epoch": 0.5487546796792013,
      "grad_norm": 0.2604394853115082,
      "learning_rate": 0.003,
      "loss": 3.224049377441406,
      "step": 251200
    },
    {
      "epoch": 0.548973132975252,
      "grad_norm": 0.16383622586727142,
      "learning_rate": 0.003,
      "loss": 3.1751327514648438,
      "step": 251300
    },
    {
      "epoch": 0.5491915862713026,
      "grad_norm": 0.19338476657867432,
      "learning_rate": 0.003,
      "loss": 3.1967984008789063,
      "step": 251400
    },
    {
      "epoch": 0.5494100395673532,
      "grad_norm": 0.1987430900335312,
      "learning_rate": 0.003,
      "loss": 3.2133343505859373,
      "step": 251500
    },
    {
      "epoch": 0.5496284928634039,
      "grad_norm": 0.2706131935119629,
      "learning_rate": 0.003,
      "loss": 3.164719543457031,
      "step": 251600
    },
    {
      "epoch": 0.5498469461594545,
      "grad_norm": 0.23942150175571442,
      "learning_rate": 0.003,
      "loss": 3.1530642700195313,
      "step": 251700
    },
    {
      "epoch": 0.5500653994555051,
      "grad_norm": 0.2501784861087799,
      "learning_rate": 0.003,
      "loss": 3.2306134033203127,
      "step": 251800
    },
    {
      "epoch": 0.5502838527515558,
      "grad_norm": 0.1774197220802307,
      "learning_rate": 0.003,
      "loss": 3.156993408203125,
      "step": 251900
    },
    {
      "epoch": 0.5505023060476064,
      "grad_norm": 0.14495019614696503,
      "learning_rate": 0.003,
      "loss": 3.1755682373046876,
      "step": 252000
    },
    {
      "epoch": 0.550720759343657,
      "grad_norm": 0.18338289856910706,
      "learning_rate": 0.003,
      "loss": 3.1817282104492186,
      "step": 252100
    },
    {
      "epoch": 0.5509392126397077,
      "grad_norm": 0.21700529754161835,
      "learning_rate": 0.003,
      "loss": 3.175777587890625,
      "step": 252200
    },
    {
      "epoch": 0.5511576659357583,
      "grad_norm": 0.22416061162948608,
      "learning_rate": 0.003,
      "loss": 3.1836798095703127,
      "step": 252300
    },
    {
      "epoch": 0.551376119231809,
      "grad_norm": 0.15657584369182587,
      "learning_rate": 0.003,
      "loss": 3.169625244140625,
      "step": 252400
    },
    {
      "epoch": 0.5515945725278596,
      "grad_norm": 0.2528873085975647,
      "learning_rate": 0.003,
      "loss": 3.177945556640625,
      "step": 252500
    },
    {
      "epoch": 0.5518130258239102,
      "grad_norm": 0.19377070665359497,
      "learning_rate": 0.003,
      "loss": 3.1807077026367185,
      "step": 252600
    },
    {
      "epoch": 0.5520314791199609,
      "grad_norm": 0.18612059950828552,
      "learning_rate": 0.003,
      "loss": 3.1565374755859374,
      "step": 252700
    },
    {
      "epoch": 0.5522499324160115,
      "grad_norm": 0.22834192216396332,
      "learning_rate": 0.003,
      "loss": 3.1967193603515627,
      "step": 252800
    },
    {
      "epoch": 0.5524683857120621,
      "grad_norm": 0.18935230374336243,
      "learning_rate": 0.003,
      "loss": 3.178858337402344,
      "step": 252900
    },
    {
      "epoch": 0.5526868390081128,
      "grad_norm": 0.18500447273254395,
      "learning_rate": 0.003,
      "loss": 3.156472473144531,
      "step": 253000
    },
    {
      "epoch": 0.5529052923041634,
      "grad_norm": 0.1837243139743805,
      "learning_rate": 0.003,
      "loss": 3.1233340454101564,
      "step": 253100
    },
    {
      "epoch": 0.553123745600214,
      "grad_norm": 0.19835516810417175,
      "learning_rate": 0.003,
      "loss": 3.171439514160156,
      "step": 253200
    },
    {
      "epoch": 0.5533421988962647,
      "grad_norm": 0.18996329605579376,
      "learning_rate": 0.003,
      "loss": 3.168174133300781,
      "step": 253300
    },
    {
      "epoch": 0.5535606521923153,
      "grad_norm": 0.2210487574338913,
      "learning_rate": 0.003,
      "loss": 3.144681091308594,
      "step": 253400
    },
    {
      "epoch": 0.553779105488366,
      "grad_norm": 0.22074343264102936,
      "learning_rate": 0.003,
      "loss": 3.1972406005859373,
      "step": 253500
    },
    {
      "epoch": 0.5539975587844166,
      "grad_norm": 0.19968971610069275,
      "learning_rate": 0.003,
      "loss": 3.178372497558594,
      "step": 253600
    },
    {
      "epoch": 0.5542160120804672,
      "grad_norm": 0.17793087661266327,
      "learning_rate": 0.003,
      "loss": 3.187338562011719,
      "step": 253700
    },
    {
      "epoch": 0.5544344653765179,
      "grad_norm": 0.22516945004463196,
      "learning_rate": 0.003,
      "loss": 3.1575631713867187,
      "step": 253800
    },
    {
      "epoch": 0.5546529186725685,
      "grad_norm": 0.16395944356918335,
      "learning_rate": 0.003,
      "loss": 3.1541357421875,
      "step": 253900
    },
    {
      "epoch": 0.5548713719686191,
      "grad_norm": 0.1603235900402069,
      "learning_rate": 0.003,
      "loss": 3.167360534667969,
      "step": 254000
    },
    {
      "epoch": 0.5550898252646698,
      "grad_norm": 0.1909872442483902,
      "learning_rate": 0.003,
      "loss": 3.1436895751953124,
      "step": 254100
    },
    {
      "epoch": 0.5553082785607205,
      "grad_norm": 0.165199875831604,
      "learning_rate": 0.003,
      "loss": 3.1625765991210937,
      "step": 254200
    },
    {
      "epoch": 0.5555267318567711,
      "grad_norm": 0.1849849820137024,
      "learning_rate": 0.003,
      "loss": 3.10090087890625,
      "step": 254300
    },
    {
      "epoch": 0.5557451851528218,
      "grad_norm": 0.15752363204956055,
      "learning_rate": 0.003,
      "loss": 3.186132507324219,
      "step": 254400
    },
    {
      "epoch": 0.5559636384488724,
      "grad_norm": 0.17930150032043457,
      "learning_rate": 0.003,
      "loss": 3.1598056030273436,
      "step": 254500
    },
    {
      "epoch": 0.5561820917449231,
      "grad_norm": 0.287249892950058,
      "learning_rate": 0.003,
      "loss": 3.1511129760742187,
      "step": 254600
    },
    {
      "epoch": 0.5564005450409737,
      "grad_norm": 0.18981009721755981,
      "learning_rate": 0.003,
      "loss": 3.16507080078125,
      "step": 254700
    },
    {
      "epoch": 0.5566189983370243,
      "grad_norm": 0.22329869866371155,
      "learning_rate": 0.003,
      "loss": 3.180391845703125,
      "step": 254800
    },
    {
      "epoch": 0.556837451633075,
      "grad_norm": 0.26614412665367126,
      "learning_rate": 0.003,
      "loss": 3.1664962768554688,
      "step": 254900
    },
    {
      "epoch": 0.5570559049291256,
      "grad_norm": 0.20086081326007843,
      "learning_rate": 0.003,
      "loss": 3.196507873535156,
      "step": 255000
    },
    {
      "epoch": 0.5572743582251762,
      "grad_norm": 0.24198859930038452,
      "learning_rate": 0.003,
      "loss": 3.149208984375,
      "step": 255100
    },
    {
      "epoch": 0.5574928115212269,
      "grad_norm": 0.8339245319366455,
      "learning_rate": 0.003,
      "loss": 3.16517578125,
      "step": 255200
    },
    {
      "epoch": 0.5577112648172775,
      "grad_norm": 0.15990374982357025,
      "learning_rate": 0.003,
      "loss": 3.1802182006835937,
      "step": 255300
    },
    {
      "epoch": 0.5579297181133281,
      "grad_norm": 0.1920757293701172,
      "learning_rate": 0.003,
      "loss": 3.121871032714844,
      "step": 255400
    },
    {
      "epoch": 0.5581481714093788,
      "grad_norm": 0.21573621034622192,
      "learning_rate": 0.003,
      "loss": 3.1677496337890627,
      "step": 255500
    },
    {
      "epoch": 0.5583666247054294,
      "grad_norm": 0.223190575838089,
      "learning_rate": 0.003,
      "loss": 3.141965026855469,
      "step": 255600
    },
    {
      "epoch": 0.55858507800148,
      "grad_norm": 0.1965768039226532,
      "learning_rate": 0.003,
      "loss": 3.152959899902344,
      "step": 255700
    },
    {
      "epoch": 0.5588035312975307,
      "grad_norm": 0.27002525329589844,
      "learning_rate": 0.003,
      "loss": 3.126148681640625,
      "step": 255800
    },
    {
      "epoch": 0.5590219845935813,
      "grad_norm": 0.171179860830307,
      "learning_rate": 0.003,
      "loss": 3.15204833984375,
      "step": 255900
    },
    {
      "epoch": 0.559240437889632,
      "grad_norm": 0.1975022256374359,
      "learning_rate": 0.003,
      "loss": 3.153853759765625,
      "step": 256000
    },
    {
      "epoch": 0.5594588911856826,
      "grad_norm": 0.24146713316440582,
      "learning_rate": 0.003,
      "loss": 3.134126892089844,
      "step": 256100
    },
    {
      "epoch": 0.5596773444817332,
      "grad_norm": 0.16798879206180573,
      "learning_rate": 0.003,
      "loss": 3.136510009765625,
      "step": 256200
    },
    {
      "epoch": 0.5598957977777839,
      "grad_norm": 0.15690313279628754,
      "learning_rate": 0.003,
      "loss": 3.1510736083984376,
      "step": 256300
    },
    {
      "epoch": 0.5601142510738345,
      "grad_norm": 0.2220565527677536,
      "learning_rate": 0.003,
      "loss": 3.17812255859375,
      "step": 256400
    },
    {
      "epoch": 0.5603327043698851,
      "grad_norm": 0.2009710967540741,
      "learning_rate": 0.003,
      "loss": 3.1844436645507814,
      "step": 256500
    },
    {
      "epoch": 0.5605511576659358,
      "grad_norm": 0.1586998850107193,
      "learning_rate": 0.003,
      "loss": 3.1865557861328124,
      "step": 256600
    },
    {
      "epoch": 0.5607696109619864,
      "grad_norm": 0.22759851813316345,
      "learning_rate": 0.003,
      "loss": 3.185194091796875,
      "step": 256700
    },
    {
      "epoch": 0.560988064258037,
      "grad_norm": 0.27934470772743225,
      "learning_rate": 0.003,
      "loss": 3.214924011230469,
      "step": 256800
    },
    {
      "epoch": 0.5612065175540877,
      "grad_norm": 0.20744450390338898,
      "learning_rate": 0.003,
      "loss": 3.1844833374023436,
      "step": 256900
    },
    {
      "epoch": 0.5614249708501383,
      "grad_norm": 0.17596977949142456,
      "learning_rate": 0.003,
      "loss": 3.1917510986328126,
      "step": 257000
    },
    {
      "epoch": 0.561643424146189,
      "grad_norm": 0.22972305119037628,
      "learning_rate": 0.003,
      "loss": 3.2035333251953126,
      "step": 257100
    },
    {
      "epoch": 0.5618618774422396,
      "grad_norm": 0.16426095366477966,
      "learning_rate": 0.003,
      "loss": 3.2284320068359373,
      "step": 257200
    },
    {
      "epoch": 0.5620803307382902,
      "grad_norm": 0.1638544797897339,
      "learning_rate": 0.003,
      "loss": 3.175955810546875,
      "step": 257300
    },
    {
      "epoch": 0.5622987840343409,
      "grad_norm": 0.21203406155109406,
      "learning_rate": 0.003,
      "loss": 3.183658447265625,
      "step": 257400
    },
    {
      "epoch": 0.5625172373303915,
      "grad_norm": 0.31586337089538574,
      "learning_rate": 0.003,
      "loss": 3.1725201416015625,
      "step": 257500
    },
    {
      "epoch": 0.5627356906264421,
      "grad_norm": 0.20102480053901672,
      "learning_rate": 0.003,
      "loss": 3.1598605346679687,
      "step": 257600
    },
    {
      "epoch": 0.5629541439224928,
      "grad_norm": 0.14764681458473206,
      "learning_rate": 0.003,
      "loss": 3.1617782592773436,
      "step": 257700
    },
    {
      "epoch": 0.5631725972185434,
      "grad_norm": 0.31521499156951904,
      "learning_rate": 0.003,
      "loss": 3.188521423339844,
      "step": 257800
    },
    {
      "epoch": 0.563391050514594,
      "grad_norm": 0.200342059135437,
      "learning_rate": 0.003,
      "loss": 3.173264465332031,
      "step": 257900
    },
    {
      "epoch": 0.5636095038106447,
      "grad_norm": 0.20925523340702057,
      "learning_rate": 0.003,
      "loss": 3.2293099975585937,
      "step": 258000
    },
    {
      "epoch": 0.5638279571066953,
      "grad_norm": 0.1502397656440735,
      "learning_rate": 0.003,
      "loss": 3.1891845703125,
      "step": 258100
    },
    {
      "epoch": 0.564046410402746,
      "grad_norm": 0.2136542946100235,
      "learning_rate": 0.003,
      "loss": 3.184232177734375,
      "step": 258200
    },
    {
      "epoch": 0.5642648636987966,
      "grad_norm": 0.18147513270378113,
      "learning_rate": 0.003,
      "loss": 3.17119873046875,
      "step": 258300
    },
    {
      "epoch": 0.5644833169948472,
      "grad_norm": 0.20932716131210327,
      "learning_rate": 0.003,
      "loss": 3.191925354003906,
      "step": 258400
    },
    {
      "epoch": 0.5647017702908979,
      "grad_norm": 0.20567169785499573,
      "learning_rate": 0.003,
      "loss": 3.1673004150390627,
      "step": 258500
    },
    {
      "epoch": 0.5649202235869485,
      "grad_norm": 0.2012886106967926,
      "learning_rate": 0.003,
      "loss": 3.1739007568359376,
      "step": 258600
    },
    {
      "epoch": 0.5651386768829991,
      "grad_norm": 0.20023569464683533,
      "learning_rate": 0.003,
      "loss": 3.1683779907226564,
      "step": 258700
    },
    {
      "epoch": 0.5653571301790498,
      "grad_norm": 0.20082633197307587,
      "learning_rate": 0.003,
      "loss": 3.231328125,
      "step": 258800
    },
    {
      "epoch": 0.5655755834751004,
      "grad_norm": 0.2716951072216034,
      "learning_rate": 0.003,
      "loss": 3.1710861206054686,
      "step": 258900
    },
    {
      "epoch": 0.565794036771151,
      "grad_norm": 0.2101980745792389,
      "learning_rate": 0.003,
      "loss": 3.1972970581054687,
      "step": 259000
    },
    {
      "epoch": 0.5660124900672017,
      "grad_norm": 0.20938672125339508,
      "learning_rate": 0.003,
      "loss": 3.1853192138671873,
      "step": 259100
    },
    {
      "epoch": 0.5662309433632523,
      "grad_norm": 0.1563986837863922,
      "learning_rate": 0.003,
      "loss": 3.2237539672851563,
      "step": 259200
    },
    {
      "epoch": 0.5664493966593029,
      "grad_norm": 0.21248815953731537,
      "learning_rate": 0.003,
      "loss": 3.1737774658203124,
      "step": 259300
    },
    {
      "epoch": 0.5666678499553536,
      "grad_norm": 0.19710727035999298,
      "learning_rate": 0.003,
      "loss": 3.1830462646484374,
      "step": 259400
    },
    {
      "epoch": 0.5668863032514042,
      "grad_norm": 0.22061745822429657,
      "learning_rate": 0.003,
      "loss": 3.2029315185546876,
      "step": 259500
    },
    {
      "epoch": 0.5671047565474548,
      "grad_norm": 0.2873390018939972,
      "learning_rate": 0.003,
      "loss": 3.1696243286132812,
      "step": 259600
    },
    {
      "epoch": 0.5673232098435055,
      "grad_norm": 0.2236197143793106,
      "learning_rate": 0.003,
      "loss": 3.1654782104492187,
      "step": 259700
    },
    {
      "epoch": 0.5675416631395561,
      "grad_norm": 0.20394811034202576,
      "learning_rate": 0.003,
      "loss": 3.166907958984375,
      "step": 259800
    },
    {
      "epoch": 0.5677601164356068,
      "grad_norm": 0.1608564853668213,
      "learning_rate": 0.003,
      "loss": 3.1740591430664065,
      "step": 259900
    },
    {
      "epoch": 0.5679785697316574,
      "grad_norm": 0.2079930305480957,
      "learning_rate": 0.003,
      "loss": 3.182764587402344,
      "step": 260000
    },
    {
      "epoch": 0.568197023027708,
      "grad_norm": 0.22330689430236816,
      "learning_rate": 0.003,
      "loss": 3.1629937744140624,
      "step": 260100
    },
    {
      "epoch": 0.5684154763237587,
      "grad_norm": 0.2734830677509308,
      "learning_rate": 0.003,
      "loss": 3.22568603515625,
      "step": 260200
    },
    {
      "epoch": 0.5686339296198093,
      "grad_norm": 0.19939808547496796,
      "learning_rate": 0.003,
      "loss": 3.1989947509765626,
      "step": 260300
    },
    {
      "epoch": 0.5688523829158599,
      "grad_norm": 0.18888352811336517,
      "learning_rate": 0.003,
      "loss": 3.165388488769531,
      "step": 260400
    },
    {
      "epoch": 0.5690708362119106,
      "grad_norm": 0.18465003371238708,
      "learning_rate": 0.003,
      "loss": 3.1980856323242186,
      "step": 260500
    },
    {
      "epoch": 0.5692892895079612,
      "grad_norm": 0.2567843794822693,
      "learning_rate": 0.003,
      "loss": 3.183458251953125,
      "step": 260600
    },
    {
      "epoch": 0.5695077428040118,
      "grad_norm": 0.3008464574813843,
      "learning_rate": 0.003,
      "loss": 3.1996310424804686,
      "step": 260700
    },
    {
      "epoch": 0.5697261961000626,
      "grad_norm": 0.1615452766418457,
      "learning_rate": 0.003,
      "loss": 3.1967535400390625,
      "step": 260800
    },
    {
      "epoch": 0.5699446493961132,
      "grad_norm": 0.16338762640953064,
      "learning_rate": 0.003,
      "loss": 3.1748931884765623,
      "step": 260900
    },
    {
      "epoch": 0.5701631026921639,
      "grad_norm": 0.16161572933197021,
      "learning_rate": 0.003,
      "loss": 3.1754446411132813,
      "step": 261000
    },
    {
      "epoch": 0.5703815559882145,
      "grad_norm": 0.20569346845149994,
      "learning_rate": 0.003,
      "loss": 3.1739178466796876,
      "step": 261100
    },
    {
      "epoch": 0.5706000092842651,
      "grad_norm": 0.1979573369026184,
      "learning_rate": 0.003,
      "loss": 3.228049621582031,
      "step": 261200
    },
    {
      "epoch": 0.5708184625803158,
      "grad_norm": 0.18235380947589874,
      "learning_rate": 0.003,
      "loss": 3.2047845458984376,
      "step": 261300
    },
    {
      "epoch": 0.5710369158763664,
      "grad_norm": 0.1901075392961502,
      "learning_rate": 0.003,
      "loss": 3.1973870849609374,
      "step": 261400
    },
    {
      "epoch": 0.571255369172417,
      "grad_norm": 0.1609690636396408,
      "learning_rate": 0.003,
      "loss": 3.1882559204101564,
      "step": 261500
    },
    {
      "epoch": 0.5714738224684677,
      "grad_norm": 0.17356561124324799,
      "learning_rate": 0.003,
      "loss": 3.19646240234375,
      "step": 261600
    },
    {
      "epoch": 0.5716922757645183,
      "grad_norm": 0.19353534281253815,
      "learning_rate": 0.003,
      "loss": 3.160430603027344,
      "step": 261700
    },
    {
      "epoch": 0.571910729060569,
      "grad_norm": 0.16725818812847137,
      "learning_rate": 0.003,
      "loss": 3.2259771728515627,
      "step": 261800
    },
    {
      "epoch": 0.5721291823566196,
      "grad_norm": 0.19310921430587769,
      "learning_rate": 0.003,
      "loss": 3.170102233886719,
      "step": 261900
    },
    {
      "epoch": 0.5723476356526702,
      "grad_norm": 0.3168920874595642,
      "learning_rate": 0.003,
      "loss": 3.194738464355469,
      "step": 262000
    },
    {
      "epoch": 0.5725660889487209,
      "grad_norm": 0.19824889302253723,
      "learning_rate": 0.003,
      "loss": 3.223552551269531,
      "step": 262100
    },
    {
      "epoch": 0.5727845422447715,
      "grad_norm": 0.17245273292064667,
      "learning_rate": 0.003,
      "loss": 3.1947427368164063,
      "step": 262200
    },
    {
      "epoch": 0.5730029955408221,
      "grad_norm": 0.18719570338726044,
      "learning_rate": 0.003,
      "loss": 3.2099346923828125,
      "step": 262300
    },
    {
      "epoch": 0.5732214488368728,
      "grad_norm": 0.25440147519111633,
      "learning_rate": 0.003,
      "loss": 3.1818728637695313,
      "step": 262400
    },
    {
      "epoch": 0.5734399021329234,
      "grad_norm": 0.2570394277572632,
      "learning_rate": 0.003,
      "loss": 3.229093322753906,
      "step": 262500
    },
    {
      "epoch": 0.573658355428974,
      "grad_norm": 0.22535084187984467,
      "learning_rate": 0.003,
      "loss": 3.2349734497070313,
      "step": 262600
    },
    {
      "epoch": 0.5738768087250247,
      "grad_norm": 0.19186465442180634,
      "learning_rate": 0.003,
      "loss": 3.2272515869140626,
      "step": 262700
    },
    {
      "epoch": 0.5740952620210753,
      "grad_norm": 0.21436728537082672,
      "learning_rate": 0.003,
      "loss": 3.1864599609375,
      "step": 262800
    },
    {
      "epoch": 0.5743137153171259,
      "grad_norm": 0.16038323938846588,
      "learning_rate": 0.003,
      "loss": 3.1863629150390627,
      "step": 262900
    },
    {
      "epoch": 0.5745321686131766,
      "grad_norm": 0.24044932425022125,
      "learning_rate": 0.003,
      "loss": 3.2025311279296873,
      "step": 263000
    },
    {
      "epoch": 0.5747506219092272,
      "grad_norm": 0.17561674118041992,
      "learning_rate": 0.003,
      "loss": 3.2181951904296877,
      "step": 263100
    },
    {
      "epoch": 0.5749690752052778,
      "grad_norm": 0.17075251042842865,
      "learning_rate": 0.003,
      "loss": 3.2026907348632814,
      "step": 263200
    },
    {
      "epoch": 0.5751875285013285,
      "grad_norm": 0.16710202395915985,
      "learning_rate": 0.003,
      "loss": 3.2038815307617186,
      "step": 263300
    },
    {
      "epoch": 0.5754059817973791,
      "grad_norm": 0.308967649936676,
      "learning_rate": 0.003,
      "loss": 3.1787957763671875,
      "step": 263400
    },
    {
      "epoch": 0.5756244350934298,
      "grad_norm": 0.20793256163597107,
      "learning_rate": 0.003,
      "loss": 3.1722677612304686,
      "step": 263500
    },
    {
      "epoch": 0.5758428883894804,
      "grad_norm": 0.16182377934455872,
      "learning_rate": 0.003,
      "loss": 3.220724792480469,
      "step": 263600
    },
    {
      "epoch": 0.576061341685531,
      "grad_norm": 0.19249974191188812,
      "learning_rate": 0.003,
      "loss": 3.22536865234375,
      "step": 263700
    },
    {
      "epoch": 0.5762797949815817,
      "grad_norm": 0.22193986177444458,
      "learning_rate": 0.003,
      "loss": 3.1873681640625,
      "step": 263800
    },
    {
      "epoch": 0.5764982482776323,
      "grad_norm": 0.18515698611736298,
      "learning_rate": 0.003,
      "loss": 3.1928271484375,
      "step": 263900
    },
    {
      "epoch": 0.5767167015736829,
      "grad_norm": 0.24966979026794434,
      "learning_rate": 0.003,
      "loss": 3.162454833984375,
      "step": 264000
    },
    {
      "epoch": 0.5769351548697336,
      "grad_norm": 0.26115745306015015,
      "learning_rate": 0.003,
      "loss": 3.1905889892578125,
      "step": 264100
    },
    {
      "epoch": 0.5771536081657842,
      "grad_norm": 0.2683042883872986,
      "learning_rate": 0.003,
      "loss": 3.1746005249023437,
      "step": 264200
    },
    {
      "epoch": 0.5773720614618348,
      "grad_norm": 0.3153984248638153,
      "learning_rate": 0.003,
      "loss": 3.2391842651367186,
      "step": 264300
    },
    {
      "epoch": 0.5775905147578855,
      "grad_norm": 0.16122107207775116,
      "learning_rate": 0.003,
      "loss": 3.20578857421875,
      "step": 264400
    },
    {
      "epoch": 0.5778089680539361,
      "grad_norm": 0.17334873974323273,
      "learning_rate": 0.003,
      "loss": 3.2292019653320314,
      "step": 264500
    },
    {
      "epoch": 0.5780274213499867,
      "grad_norm": 0.16419857740402222,
      "learning_rate": 0.003,
      "loss": 3.173647155761719,
      "step": 264600
    },
    {
      "epoch": 0.5782458746460374,
      "grad_norm": 0.2015664428472519,
      "learning_rate": 0.003,
      "loss": 3.1929666137695314,
      "step": 264700
    },
    {
      "epoch": 0.578464327942088,
      "grad_norm": 0.259512335062027,
      "learning_rate": 0.003,
      "loss": 3.199881286621094,
      "step": 264800
    },
    {
      "epoch": 0.5786827812381387,
      "grad_norm": 0.29203203320503235,
      "learning_rate": 0.003,
      "loss": 3.1710882568359375,
      "step": 264900
    },
    {
      "epoch": 0.5789012345341893,
      "grad_norm": 0.14998146891593933,
      "learning_rate": 0.003,
      "loss": 3.188811950683594,
      "step": 265000
    },
    {
      "epoch": 0.5791196878302399,
      "grad_norm": 0.19076985120773315,
      "learning_rate": 0.003,
      "loss": 3.2168939208984373,
      "step": 265100
    },
    {
      "epoch": 0.5793381411262906,
      "grad_norm": 0.42967578768730164,
      "learning_rate": 0.003,
      "loss": 3.1713546752929687,
      "step": 265200
    },
    {
      "epoch": 0.5795565944223412,
      "grad_norm": 0.27276602387428284,
      "learning_rate": 0.003,
      "loss": 3.195423583984375,
      "step": 265300
    },
    {
      "epoch": 0.5797750477183918,
      "grad_norm": 0.22074908018112183,
      "learning_rate": 0.003,
      "loss": 3.1816372680664062,
      "step": 265400
    },
    {
      "epoch": 0.5799935010144425,
      "grad_norm": 0.1695699393749237,
      "learning_rate": 0.003,
      "loss": 3.16842041015625,
      "step": 265500
    },
    {
      "epoch": 0.5802119543104931,
      "grad_norm": 0.2297377586364746,
      "learning_rate": 0.003,
      "loss": 3.170928649902344,
      "step": 265600
    },
    {
      "epoch": 0.5804304076065437,
      "grad_norm": 0.23917090892791748,
      "learning_rate": 0.003,
      "loss": 3.1946395874023437,
      "step": 265700
    },
    {
      "epoch": 0.5806488609025944,
      "grad_norm": 0.2362290620803833,
      "learning_rate": 0.003,
      "loss": 3.2047683715820314,
      "step": 265800
    },
    {
      "epoch": 0.580867314198645,
      "grad_norm": 0.25489068031311035,
      "learning_rate": 0.003,
      "loss": 3.1955880737304687,
      "step": 265900
    },
    {
      "epoch": 0.5810857674946956,
      "grad_norm": 0.17693288624286652,
      "learning_rate": 0.003,
      "loss": 3.183690490722656,
      "step": 266000
    },
    {
      "epoch": 0.5813042207907463,
      "grad_norm": 0.21266834437847137,
      "learning_rate": 0.003,
      "loss": 3.245302734375,
      "step": 266100
    },
    {
      "epoch": 0.5815226740867969,
      "grad_norm": 0.18541201949119568,
      "learning_rate": 0.003,
      "loss": 3.1921737670898436,
      "step": 266200
    },
    {
      "epoch": 0.5817411273828476,
      "grad_norm": 0.2655397057533264,
      "learning_rate": 0.003,
      "loss": 3.1956341552734373,
      "step": 266300
    },
    {
      "epoch": 0.5819595806788982,
      "grad_norm": 0.17718522250652313,
      "learning_rate": 0.003,
      "loss": 3.197523193359375,
      "step": 266400
    },
    {
      "epoch": 0.5821780339749488,
      "grad_norm": 0.17110799252986908,
      "learning_rate": 0.003,
      "loss": 3.204190673828125,
      "step": 266500
    },
    {
      "epoch": 0.5823964872709995,
      "grad_norm": 0.2140788435935974,
      "learning_rate": 0.003,
      "loss": 3.1643112182617186,
      "step": 266600
    },
    {
      "epoch": 0.5826149405670501,
      "grad_norm": 0.32044583559036255,
      "learning_rate": 0.003,
      "loss": 3.166121826171875,
      "step": 266700
    },
    {
      "epoch": 0.5828333938631007,
      "grad_norm": 0.2647723853588104,
      "learning_rate": 0.003,
      "loss": 3.2100494384765623,
      "step": 266800
    },
    {
      "epoch": 0.5830518471591514,
      "grad_norm": 0.1704663336277008,
      "learning_rate": 0.003,
      "loss": 3.1646957397460938,
      "step": 266900
    },
    {
      "epoch": 0.583270300455202,
      "grad_norm": 0.1819402575492859,
      "learning_rate": 0.003,
      "loss": 3.176807861328125,
      "step": 267000
    },
    {
      "epoch": 0.5834887537512526,
      "grad_norm": 0.20062623918056488,
      "learning_rate": 0.003,
      "loss": 3.180963134765625,
      "step": 267100
    },
    {
      "epoch": 0.5837072070473033,
      "grad_norm": 0.18052946031093597,
      "learning_rate": 0.003,
      "loss": 3.170113830566406,
      "step": 267200
    },
    {
      "epoch": 0.5839256603433539,
      "grad_norm": 0.1635192632675171,
      "learning_rate": 0.003,
      "loss": 3.2039035034179686,
      "step": 267300
    },
    {
      "epoch": 0.5841441136394047,
      "grad_norm": 0.19927239418029785,
      "learning_rate": 0.003,
      "loss": 3.1917520141601563,
      "step": 267400
    },
    {
      "epoch": 0.5843625669354553,
      "grad_norm": 0.198630228638649,
      "learning_rate": 0.003,
      "loss": 3.1945529174804688,
      "step": 267500
    },
    {
      "epoch": 0.5845810202315059,
      "grad_norm": 0.16243672370910645,
      "learning_rate": 0.003,
      "loss": 3.183653564453125,
      "step": 267600
    },
    {
      "epoch": 0.5847994735275566,
      "grad_norm": 0.20302021503448486,
      "learning_rate": 0.003,
      "loss": 3.158987731933594,
      "step": 267700
    },
    {
      "epoch": 0.5850179268236072,
      "grad_norm": 0.18480262160301208,
      "learning_rate": 0.003,
      "loss": 3.166141357421875,
      "step": 267800
    },
    {
      "epoch": 0.5852363801196578,
      "grad_norm": 0.15348458290100098,
      "learning_rate": 0.003,
      "loss": 3.1704611206054687,
      "step": 267900
    },
    {
      "epoch": 0.5854548334157085,
      "grad_norm": 0.24076738953590393,
      "learning_rate": 0.003,
      "loss": 3.1471682739257814,
      "step": 268000
    },
    {
      "epoch": 0.5856732867117591,
      "grad_norm": 0.1548558622598648,
      "learning_rate": 0.003,
      "loss": 3.1621478271484373,
      "step": 268100
    },
    {
      "epoch": 0.5858917400078097,
      "grad_norm": 0.2089904099702835,
      "learning_rate": 0.003,
      "loss": 3.185433349609375,
      "step": 268200
    },
    {
      "epoch": 0.5861101933038604,
      "grad_norm": 0.17434892058372498,
      "learning_rate": 0.003,
      "loss": 3.1716778564453123,
      "step": 268300
    },
    {
      "epoch": 0.586328646599911,
      "grad_norm": 0.18791651725769043,
      "learning_rate": 0.003,
      "loss": 3.211730651855469,
      "step": 268400
    },
    {
      "epoch": 0.5865470998959617,
      "grad_norm": 0.2201097160577774,
      "learning_rate": 0.003,
      "loss": 3.15764892578125,
      "step": 268500
    },
    {
      "epoch": 0.5867655531920123,
      "grad_norm": 0.17530202865600586,
      "learning_rate": 0.003,
      "loss": 3.146661682128906,
      "step": 268600
    },
    {
      "epoch": 0.5869840064880629,
      "grad_norm": 0.23692193627357483,
      "learning_rate": 0.003,
      "loss": 3.1638949584960936,
      "step": 268700
    },
    {
      "epoch": 0.5872024597841136,
      "grad_norm": 0.16665300726890564,
      "learning_rate": 0.003,
      "loss": 3.195250244140625,
      "step": 268800
    },
    {
      "epoch": 0.5874209130801642,
      "grad_norm": 0.25573283433914185,
      "learning_rate": 0.003,
      "loss": 3.191344909667969,
      "step": 268900
    },
    {
      "epoch": 0.5876393663762148,
      "grad_norm": 0.22903670370578766,
      "learning_rate": 0.003,
      "loss": 3.181047058105469,
      "step": 269000
    },
    {
      "epoch": 0.5878578196722655,
      "grad_norm": 0.18855856359004974,
      "learning_rate": 0.003,
      "loss": 3.2052536010742188,
      "step": 269100
    },
    {
      "epoch": 0.5880762729683161,
      "grad_norm": 0.18793243169784546,
      "learning_rate": 0.003,
      "loss": 3.1892074584960937,
      "step": 269200
    },
    {
      "epoch": 0.5882947262643667,
      "grad_norm": 0.16603167355060577,
      "learning_rate": 0.003,
      "loss": 3.16753662109375,
      "step": 269300
    },
    {
      "epoch": 0.5885131795604174,
      "grad_norm": 0.18323567509651184,
      "learning_rate": 0.003,
      "loss": 3.1971942138671876,
      "step": 269400
    },
    {
      "epoch": 0.588731632856468,
      "grad_norm": 0.15336167812347412,
      "learning_rate": 0.003,
      "loss": 3.1921792602539063,
      "step": 269500
    },
    {
      "epoch": 0.5889500861525186,
      "grad_norm": 0.18619868159294128,
      "learning_rate": 0.003,
      "loss": 3.1913888549804685,
      "step": 269600
    },
    {
      "epoch": 0.5891685394485693,
      "grad_norm": 0.1950242519378662,
      "learning_rate": 0.003,
      "loss": 3.195780944824219,
      "step": 269700
    },
    {
      "epoch": 0.5893869927446199,
      "grad_norm": 0.17987596988677979,
      "learning_rate": 0.003,
      "loss": 3.1521151733398436,
      "step": 269800
    },
    {
      "epoch": 0.5896054460406706,
      "grad_norm": 0.21784746646881104,
      "learning_rate": 0.003,
      "loss": 3.171282958984375,
      "step": 269900
    },
    {
      "epoch": 0.5898238993367212,
      "grad_norm": 0.14519715309143066,
      "learning_rate": 0.003,
      "loss": 3.140666198730469,
      "step": 270000
    },
    {
      "epoch": 0.5900423526327718,
      "grad_norm": 0.26620376110076904,
      "learning_rate": 0.003,
      "loss": 3.159576721191406,
      "step": 270100
    },
    {
      "epoch": 0.5902608059288225,
      "grad_norm": 0.21485473215579987,
      "learning_rate": 0.003,
      "loss": 3.1531576538085937,
      "step": 270200
    },
    {
      "epoch": 0.5904792592248731,
      "grad_norm": 0.2193589061498642,
      "learning_rate": 0.003,
      "loss": 3.1774224853515625,
      "step": 270300
    },
    {
      "epoch": 0.5906977125209237,
      "grad_norm": 0.22787240147590637,
      "learning_rate": 0.003,
      "loss": 3.2377490234375,
      "step": 270400
    },
    {
      "epoch": 0.5909161658169744,
      "grad_norm": 0.37484413385391235,
      "learning_rate": 0.003,
      "loss": 3.154388122558594,
      "step": 270500
    },
    {
      "epoch": 0.591134619113025,
      "grad_norm": 0.18989340960979462,
      "learning_rate": 0.003,
      "loss": 3.168203125,
      "step": 270600
    },
    {
      "epoch": 0.5913530724090756,
      "grad_norm": 0.24385006725788116,
      "learning_rate": 0.003,
      "loss": 3.1889215087890626,
      "step": 270700
    },
    {
      "epoch": 0.5915715257051263,
      "grad_norm": 0.3026793897151947,
      "learning_rate": 0.003,
      "loss": 3.2030523681640624,
      "step": 270800
    },
    {
      "epoch": 0.5917899790011769,
      "grad_norm": 0.2936710715293884,
      "learning_rate": 0.003,
      "loss": 3.1885992431640626,
      "step": 270900
    },
    {
      "epoch": 0.5920084322972275,
      "grad_norm": 0.21619591116905212,
      "learning_rate": 0.003,
      "loss": 3.2202764892578126,
      "step": 271000
    },
    {
      "epoch": 0.5922268855932782,
      "grad_norm": 0.1867588460445404,
      "learning_rate": 0.003,
      "loss": 3.1881610107421876,
      "step": 271100
    },
    {
      "epoch": 0.5924453388893288,
      "grad_norm": 0.4097394049167633,
      "learning_rate": 0.003,
      "loss": 3.2200140380859374,
      "step": 271200
    },
    {
      "epoch": 0.5926637921853795,
      "grad_norm": 0.20535510778427124,
      "learning_rate": 0.003,
      "loss": 3.240670471191406,
      "step": 271300
    },
    {
      "epoch": 0.5928822454814301,
      "grad_norm": 0.45737725496292114,
      "learning_rate": 0.003,
      "loss": 3.1828558349609377,
      "step": 271400
    },
    {
      "epoch": 0.5931006987774807,
      "grad_norm": 0.18356703221797943,
      "learning_rate": 0.003,
      "loss": 3.184310302734375,
      "step": 271500
    },
    {
      "epoch": 0.5933191520735314,
      "grad_norm": 0.26878026127815247,
      "learning_rate": 0.003,
      "loss": 3.1623074340820314,
      "step": 271600
    },
    {
      "epoch": 0.593537605369582,
      "grad_norm": 0.2153097242116928,
      "learning_rate": 0.003,
      "loss": 3.200213623046875,
      "step": 271700
    },
    {
      "epoch": 0.5937560586656326,
      "grad_norm": 0.16848962008953094,
      "learning_rate": 0.003,
      "loss": 3.1765386962890627,
      "step": 271800
    },
    {
      "epoch": 0.5939745119616833,
      "grad_norm": 0.17778430879116058,
      "learning_rate": 0.003,
      "loss": 3.1835791015625,
      "step": 271900
    },
    {
      "epoch": 0.5941929652577339,
      "grad_norm": 0.16753341257572174,
      "learning_rate": 0.003,
      "loss": 3.1610943603515627,
      "step": 272000
    },
    {
      "epoch": 0.5944114185537845,
      "grad_norm": 0.3433186113834381,
      "learning_rate": 0.003,
      "loss": 3.181799011230469,
      "step": 272100
    },
    {
      "epoch": 0.5946298718498352,
      "grad_norm": 0.29238706827163696,
      "learning_rate": 0.003,
      "loss": 3.195639953613281,
      "step": 272200
    },
    {
      "epoch": 0.5948483251458858,
      "grad_norm": 0.16925358772277832,
      "learning_rate": 0.003,
      "loss": 3.197470397949219,
      "step": 272300
    },
    {
      "epoch": 0.5950667784419365,
      "grad_norm": 0.17997771501541138,
      "learning_rate": 0.003,
      "loss": 3.15649658203125,
      "step": 272400
    },
    {
      "epoch": 0.5952852317379871,
      "grad_norm": 0.17824098467826843,
      "learning_rate": 0.003,
      "loss": 3.192305908203125,
      "step": 272500
    },
    {
      "epoch": 0.5955036850340377,
      "grad_norm": 0.1786663681268692,
      "learning_rate": 0.003,
      "loss": 3.1702398681640624,
      "step": 272600
    },
    {
      "epoch": 0.5957221383300884,
      "grad_norm": 0.20062538981437683,
      "learning_rate": 0.003,
      "loss": 3.1737811279296877,
      "step": 272700
    },
    {
      "epoch": 0.595940591626139,
      "grad_norm": 0.20446963608264923,
      "learning_rate": 0.003,
      "loss": 3.16707763671875,
      "step": 272800
    },
    {
      "epoch": 0.5961590449221896,
      "grad_norm": 0.2239767611026764,
      "learning_rate": 0.003,
      "loss": 3.1751089477539063,
      "step": 272900
    },
    {
      "epoch": 0.5963774982182403,
      "grad_norm": 0.1851469725370407,
      "learning_rate": 0.003,
      "loss": 3.2574285888671874,
      "step": 273000
    },
    {
      "epoch": 0.5965959515142909,
      "grad_norm": 0.19188979268074036,
      "learning_rate": 0.003,
      "loss": 3.1535552978515624,
      "step": 273100
    },
    {
      "epoch": 0.5968144048103415,
      "grad_norm": 0.22704674303531647,
      "learning_rate": 0.003,
      "loss": 3.1976223754882813,
      "step": 273200
    },
    {
      "epoch": 0.5970328581063922,
      "grad_norm": 0.22671857476234436,
      "learning_rate": 0.003,
      "loss": 3.175836486816406,
      "step": 273300
    },
    {
      "epoch": 0.5972513114024428,
      "grad_norm": 0.24379031360149384,
      "learning_rate": 0.003,
      "loss": 3.1869796752929687,
      "step": 273400
    },
    {
      "epoch": 0.5974697646984934,
      "grad_norm": 0.16013966500759125,
      "learning_rate": 0.003,
      "loss": 3.212471618652344,
      "step": 273500
    },
    {
      "epoch": 0.5976882179945441,
      "grad_norm": 0.20620028674602509,
      "learning_rate": 0.003,
      "loss": 3.193661804199219,
      "step": 273600
    },
    {
      "epoch": 0.5979066712905947,
      "grad_norm": 0.18357396125793457,
      "learning_rate": 0.003,
      "loss": 3.14890380859375,
      "step": 273700
    },
    {
      "epoch": 0.5981251245866454,
      "grad_norm": 0.16118085384368896,
      "learning_rate": 0.003,
      "loss": 3.181595764160156,
      "step": 273800
    },
    {
      "epoch": 0.598343577882696,
      "grad_norm": 0.22084209322929382,
      "learning_rate": 0.003,
      "loss": 3.1745721435546876,
      "step": 273900
    },
    {
      "epoch": 0.5985620311787467,
      "grad_norm": 0.19982588291168213,
      "learning_rate": 0.003,
      "loss": 3.210919189453125,
      "step": 274000
    },
    {
      "epoch": 0.5987804844747974,
      "grad_norm": 0.21388833224773407,
      "learning_rate": 0.003,
      "loss": 3.1929397583007812,
      "step": 274100
    },
    {
      "epoch": 0.598998937770848,
      "grad_norm": 0.1559390127658844,
      "learning_rate": 0.003,
      "loss": 3.210037841796875,
      "step": 274200
    },
    {
      "epoch": 0.5992173910668986,
      "grad_norm": 0.35150784254074097,
      "learning_rate": 0.003,
      "loss": 3.179581298828125,
      "step": 274300
    },
    {
      "epoch": 0.5994358443629493,
      "grad_norm": 0.18898102641105652,
      "learning_rate": 0.003,
      "loss": 3.17751953125,
      "step": 274400
    },
    {
      "epoch": 0.5996542976589999,
      "grad_norm": 0.17562362551689148,
      "learning_rate": 0.003,
      "loss": 3.197981262207031,
      "step": 274500
    },
    {
      "epoch": 0.5998727509550505,
      "grad_norm": 0.16491129994392395,
      "learning_rate": 0.003,
      "loss": 3.1793768310546877,
      "step": 274600
    },
    {
      "epoch": 0.6000912042511012,
      "grad_norm": 0.2157270461320877,
      "learning_rate": 0.003,
      "loss": 3.21033447265625,
      "step": 274700
    },
    {
      "epoch": 0.6003096575471518,
      "grad_norm": 0.31318947672843933,
      "learning_rate": 0.003,
      "loss": 3.2078704833984375,
      "step": 274800
    },
    {
      "epoch": 0.6005281108432025,
      "grad_norm": 0.565285325050354,
      "learning_rate": 0.003,
      "loss": 3.1789505004882814,
      "step": 274900
    },
    {
      "epoch": 0.6007465641392531,
      "grad_norm": 0.1992669701576233,
      "learning_rate": 0.003,
      "loss": 3.188543701171875,
      "step": 275000
    },
    {
      "epoch": 0.6009650174353037,
      "grad_norm": 0.19401922821998596,
      "learning_rate": 0.003,
      "loss": 3.18631591796875,
      "step": 275100
    },
    {
      "epoch": 0.6011834707313544,
      "grad_norm": 0.20895209908485413,
      "learning_rate": 0.003,
      "loss": 3.196438903808594,
      "step": 275200
    },
    {
      "epoch": 0.601401924027405,
      "grad_norm": 0.20434080064296722,
      "learning_rate": 0.003,
      "loss": 3.1825244140625,
      "step": 275300
    },
    {
      "epoch": 0.6016203773234556,
      "grad_norm": 0.18119269609451294,
      "learning_rate": 0.003,
      "loss": 3.1607196044921877,
      "step": 275400
    },
    {
      "epoch": 0.6018388306195063,
      "grad_norm": 0.27453410625457764,
      "learning_rate": 0.003,
      "loss": 3.2045904541015626,
      "step": 275500
    },
    {
      "epoch": 0.6020572839155569,
      "grad_norm": 0.24531832337379456,
      "learning_rate": 0.003,
      "loss": 3.188206787109375,
      "step": 275600
    },
    {
      "epoch": 0.6022757372116075,
      "grad_norm": 0.15990878641605377,
      "learning_rate": 0.003,
      "loss": 3.164237060546875,
      "step": 275700
    },
    {
      "epoch": 0.6024941905076582,
      "grad_norm": 0.17023086547851562,
      "learning_rate": 0.003,
      "loss": 3.1978045654296876,
      "step": 275800
    },
    {
      "epoch": 0.6027126438037088,
      "grad_norm": 0.23108148574829102,
      "learning_rate": 0.003,
      "loss": 3.183524169921875,
      "step": 275900
    },
    {
      "epoch": 0.6029310970997594,
      "grad_norm": 0.17994177341461182,
      "learning_rate": 0.003,
      "loss": 3.2128466796875,
      "step": 276000
    },
    {
      "epoch": 0.6031495503958101,
      "grad_norm": 0.22104574739933014,
      "learning_rate": 0.003,
      "loss": 3.20671875,
      "step": 276100
    },
    {
      "epoch": 0.6033680036918607,
      "grad_norm": 0.19002124667167664,
      "learning_rate": 0.003,
      "loss": 3.185667724609375,
      "step": 276200
    },
    {
      "epoch": 0.6035864569879114,
      "grad_norm": 0.2765943109989166,
      "learning_rate": 0.003,
      "loss": 3.171270751953125,
      "step": 276300
    },
    {
      "epoch": 0.603804910283962,
      "grad_norm": 0.16902455687522888,
      "learning_rate": 0.003,
      "loss": 3.2092041015625,
      "step": 276400
    },
    {
      "epoch": 0.6040233635800126,
      "grad_norm": 0.17837058007717133,
      "learning_rate": 0.003,
      "loss": 3.1959469604492186,
      "step": 276500
    },
    {
      "epoch": 0.6042418168760633,
      "grad_norm": 0.24306359887123108,
      "learning_rate": 0.003,
      "loss": 3.2038369750976563,
      "step": 276600
    },
    {
      "epoch": 0.6044602701721139,
      "grad_norm": 0.2769904136657715,
      "learning_rate": 0.003,
      "loss": 3.1780706787109376,
      "step": 276700
    },
    {
      "epoch": 0.6046787234681645,
      "grad_norm": 0.18594355881214142,
      "learning_rate": 0.003,
      "loss": 3.2014263916015624,
      "step": 276800
    },
    {
      "epoch": 0.6048971767642152,
      "grad_norm": 0.18026407063007355,
      "learning_rate": 0.003,
      "loss": 3.1773760986328123,
      "step": 276900
    },
    {
      "epoch": 0.6051156300602658,
      "grad_norm": 0.16951219737529755,
      "learning_rate": 0.003,
      "loss": 3.1456723022460937,
      "step": 277000
    },
    {
      "epoch": 0.6053340833563164,
      "grad_norm": 0.30202338099479675,
      "learning_rate": 0.003,
      "loss": 3.2171600341796873,
      "step": 277100
    },
    {
      "epoch": 0.6055525366523671,
      "grad_norm": 0.1839420050382614,
      "learning_rate": 0.003,
      "loss": 3.1722723388671876,
      "step": 277200
    },
    {
      "epoch": 0.6057709899484177,
      "grad_norm": 0.19461020827293396,
      "learning_rate": 0.003,
      "loss": 3.2344781494140626,
      "step": 277300
    },
    {
      "epoch": 0.6059894432444684,
      "grad_norm": 0.16227911412715912,
      "learning_rate": 0.003,
      "loss": 3.207802429199219,
      "step": 277400
    },
    {
      "epoch": 0.606207896540519,
      "grad_norm": 0.2340696156024933,
      "learning_rate": 0.003,
      "loss": 3.1534237670898437,
      "step": 277500
    },
    {
      "epoch": 0.6064263498365696,
      "grad_norm": 0.20139533281326294,
      "learning_rate": 0.003,
      "loss": 3.1860809326171875,
      "step": 277600
    },
    {
      "epoch": 0.6066448031326203,
      "grad_norm": 0.22579284012317657,
      "learning_rate": 0.003,
      "loss": 3.1737384033203124,
      "step": 277700
    },
    {
      "epoch": 0.6068632564286709,
      "grad_norm": 0.17872489988803864,
      "learning_rate": 0.003,
      "loss": 3.177811279296875,
      "step": 277800
    },
    {
      "epoch": 0.6070817097247215,
      "grad_norm": 0.17154665291309357,
      "learning_rate": 0.003,
      "loss": 3.2129522705078126,
      "step": 277900
    },
    {
      "epoch": 0.6073001630207722,
      "grad_norm": 0.20345716178417206,
      "learning_rate": 0.003,
      "loss": 3.194685974121094,
      "step": 278000
    },
    {
      "epoch": 0.6075186163168228,
      "grad_norm": 0.19972197711467743,
      "learning_rate": 0.003,
      "loss": 3.1683172607421874,
      "step": 278100
    },
    {
      "epoch": 0.6077370696128734,
      "grad_norm": 0.24639728665351868,
      "learning_rate": 0.003,
      "loss": 3.1975643920898436,
      "step": 278200
    },
    {
      "epoch": 0.6079555229089241,
      "grad_norm": 0.1678711324930191,
      "learning_rate": 0.003,
      "loss": 3.163349609375,
      "step": 278300
    },
    {
      "epoch": 0.6081739762049747,
      "grad_norm": 0.1582835465669632,
      "learning_rate": 0.003,
      "loss": 3.1676669311523438,
      "step": 278400
    },
    {
      "epoch": 0.6083924295010253,
      "grad_norm": 0.1776084303855896,
      "learning_rate": 0.003,
      "loss": 3.188576354980469,
      "step": 278500
    },
    {
      "epoch": 0.608610882797076,
      "grad_norm": 0.17008942365646362,
      "learning_rate": 0.003,
      "loss": 3.2235638427734377,
      "step": 278600
    },
    {
      "epoch": 0.6088293360931266,
      "grad_norm": 0.15058891475200653,
      "learning_rate": 0.003,
      "loss": 3.218577880859375,
      "step": 278700
    },
    {
      "epoch": 0.6090477893891773,
      "grad_norm": 0.22054730355739594,
      "learning_rate": 0.003,
      "loss": 3.2290777587890624,
      "step": 278800
    },
    {
      "epoch": 0.6092662426852279,
      "grad_norm": 0.20505490899085999,
      "learning_rate": 0.003,
      "loss": 3.2360345458984376,
      "step": 278900
    },
    {
      "epoch": 0.6094846959812785,
      "grad_norm": 0.16889184713363647,
      "learning_rate": 0.003,
      "loss": 3.2322161865234373,
      "step": 279000
    },
    {
      "epoch": 0.6097031492773292,
      "grad_norm": 0.14906372129917145,
      "learning_rate": 0.003,
      "loss": 3.200885009765625,
      "step": 279100
    },
    {
      "epoch": 0.6099216025733798,
      "grad_norm": 0.23367558419704437,
      "learning_rate": 0.003,
      "loss": 3.281402587890625,
      "step": 279200
    },
    {
      "epoch": 0.6101400558694304,
      "grad_norm": 0.19567924737930298,
      "learning_rate": 0.003,
      "loss": 3.251478576660156,
      "step": 279300
    },
    {
      "epoch": 0.6103585091654811,
      "grad_norm": 0.2576897144317627,
      "learning_rate": 0.003,
      "loss": 3.219094543457031,
      "step": 279400
    },
    {
      "epoch": 0.6105769624615317,
      "grad_norm": 0.20338435471057892,
      "learning_rate": 0.003,
      "loss": 3.2011016845703124,
      "step": 279500
    },
    {
      "epoch": 0.6107954157575823,
      "grad_norm": 0.19842180609703064,
      "learning_rate": 0.003,
      "loss": 3.224814147949219,
      "step": 279600
    },
    {
      "epoch": 0.611013869053633,
      "grad_norm": 0.1748685985803604,
      "learning_rate": 0.003,
      "loss": 3.1903311157226564,
      "step": 279700
    },
    {
      "epoch": 0.6112323223496836,
      "grad_norm": 0.20952138304710388,
      "learning_rate": 0.003,
      "loss": 3.186549072265625,
      "step": 279800
    },
    {
      "epoch": 0.6114507756457342,
      "grad_norm": 0.17591659724712372,
      "learning_rate": 0.003,
      "loss": 3.2390841674804687,
      "step": 279900
    },
    {
      "epoch": 0.6116692289417849,
      "grad_norm": 0.17997194826602936,
      "learning_rate": 0.003,
      "loss": 3.22374267578125,
      "step": 280000
    },
    {
      "epoch": 0.6118876822378355,
      "grad_norm": 0.2298325151205063,
      "learning_rate": 0.003,
      "loss": 3.218565673828125,
      "step": 280100
    },
    {
      "epoch": 0.6121061355338862,
      "grad_norm": 0.29981234669685364,
      "learning_rate": 0.003,
      "loss": 3.2290170288085935,
      "step": 280200
    },
    {
      "epoch": 0.6123245888299368,
      "grad_norm": 0.1893419772386551,
      "learning_rate": 0.003,
      "loss": 3.2608001708984373,
      "step": 280300
    },
    {
      "epoch": 0.6125430421259874,
      "grad_norm": 0.21723315119743347,
      "learning_rate": 0.003,
      "loss": 3.2499896240234376,
      "step": 280400
    },
    {
      "epoch": 0.6127614954220381,
      "grad_norm": 0.2760069966316223,
      "learning_rate": 0.003,
      "loss": 3.210706787109375,
      "step": 280500
    },
    {
      "epoch": 0.6129799487180888,
      "grad_norm": 0.18448935449123383,
      "learning_rate": 0.003,
      "loss": 3.2539251708984374,
      "step": 280600
    },
    {
      "epoch": 0.6131984020141394,
      "grad_norm": 0.17874455451965332,
      "learning_rate": 0.003,
      "loss": 3.204296875,
      "step": 280700
    },
    {
      "epoch": 0.6134168553101901,
      "grad_norm": 0.17619864642620087,
      "learning_rate": 0.003,
      "loss": 3.207901611328125,
      "step": 280800
    },
    {
      "epoch": 0.6136353086062407,
      "grad_norm": 0.15697738528251648,
      "learning_rate": 0.003,
      "loss": 3.193507080078125,
      "step": 280900
    },
    {
      "epoch": 0.6138537619022914,
      "grad_norm": 0.16789767146110535,
      "learning_rate": 0.003,
      "loss": 3.2187896728515626,
      "step": 281000
    },
    {
      "epoch": 0.614072215198342,
      "grad_norm": 0.15810124576091766,
      "learning_rate": 0.003,
      "loss": 3.226168212890625,
      "step": 281100
    },
    {
      "epoch": 0.6142906684943926,
      "grad_norm": 0.16084574162960052,
      "learning_rate": 0.003,
      "loss": 3.2249624633789065,
      "step": 281200
    },
    {
      "epoch": 0.6145091217904433,
      "grad_norm": 0.2734839618206024,
      "learning_rate": 0.003,
      "loss": 3.214705810546875,
      "step": 281300
    },
    {
      "epoch": 0.6147275750864939,
      "grad_norm": 0.1650455743074417,
      "learning_rate": 0.003,
      "loss": 3.200811767578125,
      "step": 281400
    },
    {
      "epoch": 0.6149460283825445,
      "grad_norm": 0.20756572484970093,
      "learning_rate": 0.003,
      "loss": 3.2253350830078125,
      "step": 281500
    },
    {
      "epoch": 0.6151644816785952,
      "grad_norm": 0.27218082547187805,
      "learning_rate": 0.003,
      "loss": 3.224010314941406,
      "step": 281600
    },
    {
      "epoch": 0.6153829349746458,
      "grad_norm": 0.18597164750099182,
      "learning_rate": 0.003,
      "loss": 3.2408602905273436,
      "step": 281700
    },
    {
      "epoch": 0.6156013882706964,
      "grad_norm": 0.3097550570964813,
      "learning_rate": 0.003,
      "loss": 3.2364547729492186,
      "step": 281800
    },
    {
      "epoch": 0.6158198415667471,
      "grad_norm": 0.14957626163959503,
      "learning_rate": 0.003,
      "loss": 3.2118701171875,
      "step": 281900
    },
    {
      "epoch": 0.6160382948627977,
      "grad_norm": 0.173723965883255,
      "learning_rate": 0.003,
      "loss": 3.1995144653320313,
      "step": 282000
    },
    {
      "epoch": 0.6162567481588483,
      "grad_norm": 0.2679918110370636,
      "learning_rate": 0.003,
      "loss": 3.21077880859375,
      "step": 282100
    },
    {
      "epoch": 0.616475201454899,
      "grad_norm": 0.20013374090194702,
      "learning_rate": 0.003,
      "loss": 3.21534423828125,
      "step": 282200
    },
    {
      "epoch": 0.6166936547509496,
      "grad_norm": 0.19734624028205872,
      "learning_rate": 0.003,
      "loss": 3.2249191284179686,
      "step": 282300
    },
    {
      "epoch": 0.6169121080470003,
      "grad_norm": 0.17574071884155273,
      "learning_rate": 0.003,
      "loss": 3.247730407714844,
      "step": 282400
    },
    {
      "epoch": 0.6171305613430509,
      "grad_norm": 0.2526727020740509,
      "learning_rate": 0.003,
      "loss": 3.2391473388671876,
      "step": 282500
    },
    {
      "epoch": 0.6173490146391015,
      "grad_norm": 0.2336476743221283,
      "learning_rate": 0.003,
      "loss": 3.253121643066406,
      "step": 282600
    },
    {
      "epoch": 0.6175674679351522,
      "grad_norm": 0.20967942476272583,
      "learning_rate": 0.003,
      "loss": 3.2355526733398436,
      "step": 282700
    },
    {
      "epoch": 0.6177859212312028,
      "grad_norm": 0.1525416374206543,
      "learning_rate": 0.003,
      "loss": 3.2273519897460936,
      "step": 282800
    },
    {
      "epoch": 0.6180043745272534,
      "grad_norm": 0.25935304164886475,
      "learning_rate": 0.003,
      "loss": 3.194563293457031,
      "step": 282900
    },
    {
      "epoch": 0.6182228278233041,
      "grad_norm": 0.19603733718395233,
      "learning_rate": 0.003,
      "loss": 3.2104449462890625,
      "step": 283000
    },
    {
      "epoch": 0.6184412811193547,
      "grad_norm": 0.17551939189434052,
      "learning_rate": 0.003,
      "loss": 3.217191467285156,
      "step": 283100
    },
    {
      "epoch": 0.6186597344154053,
      "grad_norm": 0.21156436204910278,
      "learning_rate": 0.003,
      "loss": 3.221127624511719,
      "step": 283200
    },
    {
      "epoch": 0.618878187711456,
      "grad_norm": 0.16724392771720886,
      "learning_rate": 0.003,
      "loss": 3.2321722412109377,
      "step": 283300
    },
    {
      "epoch": 0.6190966410075066,
      "grad_norm": 0.186121866106987,
      "learning_rate": 0.003,
      "loss": 3.204158935546875,
      "step": 283400
    },
    {
      "epoch": 0.6193150943035572,
      "grad_norm": 0.31068140268325806,
      "learning_rate": 0.003,
      "loss": 3.20711181640625,
      "step": 283500
    },
    {
      "epoch": 0.6195335475996079,
      "grad_norm": 0.2943353056907654,
      "learning_rate": 0.003,
      "loss": 3.2226220703125,
      "step": 283600
    },
    {
      "epoch": 0.6197520008956585,
      "grad_norm": 0.17843976616859436,
      "learning_rate": 0.003,
      "loss": 3.2084176635742185,
      "step": 283700
    },
    {
      "epoch": 0.6199704541917092,
      "grad_norm": 0.1970898061990738,
      "learning_rate": 0.003,
      "loss": 3.2124114990234376,
      "step": 283800
    },
    {
      "epoch": 0.6201889074877598,
      "grad_norm": 0.22497090697288513,
      "learning_rate": 0.003,
      "loss": 3.2032244873046873,
      "step": 283900
    },
    {
      "epoch": 0.6204073607838104,
      "grad_norm": 0.21933315694332123,
      "learning_rate": 0.003,
      "loss": 3.2039813232421874,
      "step": 284000
    },
    {
      "epoch": 0.6206258140798611,
      "grad_norm": 0.18281668424606323,
      "learning_rate": 0.003,
      "loss": 3.2014804077148438,
      "step": 284100
    },
    {
      "epoch": 0.6208442673759117,
      "grad_norm": 0.17093998193740845,
      "learning_rate": 0.003,
      "loss": 3.257895812988281,
      "step": 284200
    },
    {
      "epoch": 0.6210627206719623,
      "grad_norm": 0.5414712429046631,
      "learning_rate": 0.003,
      "loss": 3.2131463623046876,
      "step": 284300
    },
    {
      "epoch": 0.621281173968013,
      "grad_norm": 0.24203021824359894,
      "learning_rate": 0.003,
      "loss": 3.208263244628906,
      "step": 284400
    },
    {
      "epoch": 0.6214996272640636,
      "grad_norm": 0.23131752014160156,
      "learning_rate": 0.003,
      "loss": 3.229090270996094,
      "step": 284500
    },
    {
      "epoch": 0.6217180805601142,
      "grad_norm": 0.22036364674568176,
      "learning_rate": 0.003,
      "loss": 3.213861389160156,
      "step": 284600
    },
    {
      "epoch": 0.6219365338561649,
      "grad_norm": 0.21612179279327393,
      "learning_rate": 0.003,
      "loss": 3.150676574707031,
      "step": 284700
    },
    {
      "epoch": 0.6221549871522155,
      "grad_norm": 0.18414941430091858,
      "learning_rate": 0.003,
      "loss": 3.2058514404296874,
      "step": 284800
    },
    {
      "epoch": 0.6223734404482661,
      "grad_norm": 0.23727717995643616,
      "learning_rate": 0.003,
      "loss": 3.201068115234375,
      "step": 284900
    },
    {
      "epoch": 0.6225918937443168,
      "grad_norm": 0.21799902617931366,
      "learning_rate": 0.003,
      "loss": 3.2068130493164064,
      "step": 285000
    },
    {
      "epoch": 0.6228103470403674,
      "grad_norm": 0.22931742668151855,
      "learning_rate": 0.003,
      "loss": 3.19539306640625,
      "step": 285100
    },
    {
      "epoch": 0.623028800336418,
      "grad_norm": 0.182006374001503,
      "learning_rate": 0.003,
      "loss": 3.1844390869140624,
      "step": 285200
    },
    {
      "epoch": 0.6232472536324687,
      "grad_norm": 0.17878194153308868,
      "learning_rate": 0.003,
      "loss": 3.201749572753906,
      "step": 285300
    },
    {
      "epoch": 0.6234657069285193,
      "grad_norm": 0.23979757726192474,
      "learning_rate": 0.003,
      "loss": 3.1891043090820315,
      "step": 285400
    },
    {
      "epoch": 0.62368416022457,
      "grad_norm": 0.21130961179733276,
      "learning_rate": 0.003,
      "loss": 3.223269348144531,
      "step": 285500
    },
    {
      "epoch": 0.6239026135206206,
      "grad_norm": 0.26726633310317993,
      "learning_rate": 0.003,
      "loss": 3.2433599853515624,
      "step": 285600
    },
    {
      "epoch": 0.6241210668166712,
      "grad_norm": 0.20099696516990662,
      "learning_rate": 0.003,
      "loss": 3.2557061767578124,
      "step": 285700
    },
    {
      "epoch": 0.6243395201127219,
      "grad_norm": 0.19590891897678375,
      "learning_rate": 0.003,
      "loss": 3.256570129394531,
      "step": 285800
    },
    {
      "epoch": 0.6245579734087725,
      "grad_norm": 0.23263265192508698,
      "learning_rate": 0.003,
      "loss": 3.228614501953125,
      "step": 285900
    },
    {
      "epoch": 0.6247764267048231,
      "grad_norm": 0.1568203568458557,
      "learning_rate": 0.003,
      "loss": 3.2337380981445314,
      "step": 286000
    },
    {
      "epoch": 0.6249948800008738,
      "grad_norm": 0.16980203986167908,
      "learning_rate": 0.003,
      "loss": 3.2243988037109377,
      "step": 286100
    },
    {
      "epoch": 0.6252133332969244,
      "grad_norm": 0.1692260503768921,
      "learning_rate": 0.003,
      "loss": 3.2188507080078126,
      "step": 286200
    },
    {
      "epoch": 0.625431786592975,
      "grad_norm": 0.2141398787498474,
      "learning_rate": 0.003,
      "loss": 3.2453622436523437,
      "step": 286300
    },
    {
      "epoch": 0.6256502398890257,
      "grad_norm": 0.21553441882133484,
      "learning_rate": 0.003,
      "loss": 3.2024435424804687,
      "step": 286400
    },
    {
      "epoch": 0.6258686931850763,
      "grad_norm": 0.23952943086624146,
      "learning_rate": 0.003,
      "loss": 3.216363830566406,
      "step": 286500
    },
    {
      "epoch": 0.626087146481127,
      "grad_norm": 0.1785024106502533,
      "learning_rate": 0.003,
      "loss": 3.2151620483398435,
      "step": 286600
    },
    {
      "epoch": 0.6263055997771776,
      "grad_norm": 0.15831226110458374,
      "learning_rate": 0.003,
      "loss": 3.2485397338867186,
      "step": 286700
    },
    {
      "epoch": 0.6265240530732282,
      "grad_norm": 0.17145226895809174,
      "learning_rate": 0.003,
      "loss": 3.2080877685546874,
      "step": 286800
    },
    {
      "epoch": 0.6267425063692789,
      "grad_norm": 0.2014709711074829,
      "learning_rate": 0.003,
      "loss": 3.2211288452148437,
      "step": 286900
    },
    {
      "epoch": 0.6269609596653295,
      "grad_norm": 0.17480652034282684,
      "learning_rate": 0.003,
      "loss": 3.19992431640625,
      "step": 287000
    },
    {
      "epoch": 0.6271794129613801,
      "grad_norm": 0.5618772506713867,
      "learning_rate": 0.003,
      "loss": 3.2403289794921877,
      "step": 287100
    },
    {
      "epoch": 0.6273978662574309,
      "grad_norm": 0.28726547956466675,
      "learning_rate": 0.003,
      "loss": 3.1722259521484375,
      "step": 287200
    },
    {
      "epoch": 0.6276163195534815,
      "grad_norm": 0.25002768635749817,
      "learning_rate": 0.003,
      "loss": 3.2153179931640623,
      "step": 287300
    },
    {
      "epoch": 0.6278347728495322,
      "grad_norm": 0.28767040371894836,
      "learning_rate": 0.003,
      "loss": 3.21020751953125,
      "step": 287400
    },
    {
      "epoch": 0.6280532261455828,
      "grad_norm": 0.1514800786972046,
      "learning_rate": 0.003,
      "loss": 3.2307974243164064,
      "step": 287500
    },
    {
      "epoch": 0.6282716794416334,
      "grad_norm": 0.1654813289642334,
      "learning_rate": 0.003,
      "loss": 3.217948303222656,
      "step": 287600
    },
    {
      "epoch": 0.6284901327376841,
      "grad_norm": 0.16197553277015686,
      "learning_rate": 0.003,
      "loss": 3.2160372924804688,
      "step": 287700
    },
    {
      "epoch": 0.6287085860337347,
      "grad_norm": 0.2692326009273529,
      "learning_rate": 0.003,
      "loss": 3.226651916503906,
      "step": 287800
    },
    {
      "epoch": 0.6289270393297853,
      "grad_norm": 0.1686079055070877,
      "learning_rate": 0.003,
      "loss": 3.2225408935546875,
      "step": 287900
    },
    {
      "epoch": 0.629145492625836,
      "grad_norm": 0.17967018485069275,
      "learning_rate": 0.003,
      "loss": 3.219140625,
      "step": 288000
    },
    {
      "epoch": 0.6293639459218866,
      "grad_norm": 0.39554107189178467,
      "learning_rate": 0.003,
      "loss": 3.249757080078125,
      "step": 288100
    },
    {
      "epoch": 0.6295823992179372,
      "grad_norm": 0.26681211590766907,
      "learning_rate": 0.003,
      "loss": 3.2215020751953123,
      "step": 288200
    },
    {
      "epoch": 0.6298008525139879,
      "grad_norm": 0.19122950732707977,
      "learning_rate": 0.003,
      "loss": 3.2331497192382814,
      "step": 288300
    },
    {
      "epoch": 0.6300193058100385,
      "grad_norm": 0.22437626123428345,
      "learning_rate": 0.003,
      "loss": 3.2123757934570314,
      "step": 288400
    },
    {
      "epoch": 0.6302377591060891,
      "grad_norm": 0.2811083495616913,
      "learning_rate": 0.003,
      "loss": 3.2272845458984376,
      "step": 288500
    },
    {
      "epoch": 0.6304562124021398,
      "grad_norm": 0.17704203724861145,
      "learning_rate": 0.003,
      "loss": 3.2331854248046876,
      "step": 288600
    },
    {
      "epoch": 0.6306746656981904,
      "grad_norm": 0.19387799501419067,
      "learning_rate": 0.003,
      "loss": 3.268462829589844,
      "step": 288700
    },
    {
      "epoch": 0.630893118994241,
      "grad_norm": 0.1690356284379959,
      "learning_rate": 0.003,
      "loss": 3.246180114746094,
      "step": 288800
    },
    {
      "epoch": 0.6311115722902917,
      "grad_norm": 0.26224347949028015,
      "learning_rate": 0.003,
      "loss": 3.2055258178710937,
      "step": 288900
    },
    {
      "epoch": 0.6313300255863423,
      "grad_norm": 0.16216501593589783,
      "learning_rate": 0.003,
      "loss": 3.2119586181640627,
      "step": 289000
    },
    {
      "epoch": 0.631548478882393,
      "grad_norm": 0.6684026718139648,
      "learning_rate": 0.003,
      "loss": 3.2276852416992186,
      "step": 289100
    },
    {
      "epoch": 0.6317669321784436,
      "grad_norm": 0.16669830679893494,
      "learning_rate": 0.003,
      "loss": 3.2140536499023438,
      "step": 289200
    },
    {
      "epoch": 0.6319853854744942,
      "grad_norm": 0.27438318729400635,
      "learning_rate": 0.003,
      "loss": 3.2338491821289064,
      "step": 289300
    },
    {
      "epoch": 0.6322038387705449,
      "grad_norm": 0.18542805314064026,
      "learning_rate": 0.003,
      "loss": 3.215194091796875,
      "step": 289400
    },
    {
      "epoch": 0.6324222920665955,
      "grad_norm": 0.16285960376262665,
      "learning_rate": 0.003,
      "loss": 3.2204049682617186,
      "step": 289500
    },
    {
      "epoch": 0.6326407453626461,
      "grad_norm": 0.2150706797838211,
      "learning_rate": 0.003,
      "loss": 3.2491799926757814,
      "step": 289600
    },
    {
      "epoch": 0.6328591986586968,
      "grad_norm": 0.16465799510478973,
      "learning_rate": 0.003,
      "loss": 3.229394836425781,
      "step": 289700
    },
    {
      "epoch": 0.6330776519547474,
      "grad_norm": 0.21082794666290283,
      "learning_rate": 0.003,
      "loss": 3.2316717529296874,
      "step": 289800
    },
    {
      "epoch": 0.633296105250798,
      "grad_norm": 0.19099874794483185,
      "learning_rate": 0.003,
      "loss": 3.2224075317382814,
      "step": 289900
    },
    {
      "epoch": 0.6335145585468487,
      "grad_norm": 0.18653811514377594,
      "learning_rate": 0.003,
      "loss": 3.241226806640625,
      "step": 290000
    },
    {
      "epoch": 0.6337330118428993,
      "grad_norm": 0.15790440142154694,
      "learning_rate": 0.003,
      "loss": 3.2193890380859376,
      "step": 290100
    },
    {
      "epoch": 0.63395146513895,
      "grad_norm": 0.17822077870368958,
      "learning_rate": 0.003,
      "loss": 3.233725280761719,
      "step": 290200
    },
    {
      "epoch": 0.6341699184350006,
      "grad_norm": 0.1595640778541565,
      "learning_rate": 0.003,
      "loss": 3.2387994384765624,
      "step": 290300
    },
    {
      "epoch": 0.6343883717310512,
      "grad_norm": 0.20599380135536194,
      "learning_rate": 0.003,
      "loss": 3.230789794921875,
      "step": 290400
    },
    {
      "epoch": 0.6346068250271019,
      "grad_norm": 0.2180960327386856,
      "learning_rate": 0.003,
      "loss": 3.2289505004882812,
      "step": 290500
    },
    {
      "epoch": 0.6348252783231525,
      "grad_norm": 0.19660598039627075,
      "learning_rate": 0.003,
      "loss": 3.2185397338867188,
      "step": 290600
    },
    {
      "epoch": 0.6350437316192031,
      "grad_norm": 0.1990455687046051,
      "learning_rate": 0.003,
      "loss": 3.2131362915039063,
      "step": 290700
    },
    {
      "epoch": 0.6352621849152538,
      "grad_norm": 0.25876370072364807,
      "learning_rate": 0.003,
      "loss": 3.2440533447265625,
      "step": 290800
    },
    {
      "epoch": 0.6354806382113044,
      "grad_norm": 0.15375180542469025,
      "learning_rate": 0.003,
      "loss": 3.2562249755859374,
      "step": 290900
    },
    {
      "epoch": 0.635699091507355,
      "grad_norm": 0.20260626077651978,
      "learning_rate": 0.003,
      "loss": 3.21085693359375,
      "step": 291000
    },
    {
      "epoch": 0.6359175448034057,
      "grad_norm": 0.22221435606479645,
      "learning_rate": 0.003,
      "loss": 3.2080426025390625,
      "step": 291100
    },
    {
      "epoch": 0.6361359980994563,
      "grad_norm": 0.171079620718956,
      "learning_rate": 0.003,
      "loss": 3.2209518432617186,
      "step": 291200
    },
    {
      "epoch": 0.636354451395507,
      "grad_norm": 0.22816050052642822,
      "learning_rate": 0.003,
      "loss": 3.25553955078125,
      "step": 291300
    },
    {
      "epoch": 0.6365729046915576,
      "grad_norm": 0.17978259921073914,
      "learning_rate": 0.003,
      "loss": 3.231046142578125,
      "step": 291400
    },
    {
      "epoch": 0.6367913579876082,
      "grad_norm": 0.16530568897724152,
      "learning_rate": 0.003,
      "loss": 3.2056622314453125,
      "step": 291500
    },
    {
      "epoch": 0.6370098112836589,
      "grad_norm": 0.17650382220745087,
      "learning_rate": 0.003,
      "loss": 3.1861282348632813,
      "step": 291600
    },
    {
      "epoch": 0.6372282645797095,
      "grad_norm": 0.2348802536725998,
      "learning_rate": 0.003,
      "loss": 3.182919616699219,
      "step": 291700
    },
    {
      "epoch": 0.6374467178757601,
      "grad_norm": 0.15267673134803772,
      "learning_rate": 0.003,
      "loss": 3.2105584716796876,
      "step": 291800
    },
    {
      "epoch": 0.6376651711718108,
      "grad_norm": 0.1857692152261734,
      "learning_rate": 0.003,
      "loss": 3.223770751953125,
      "step": 291900
    },
    {
      "epoch": 0.6378836244678614,
      "grad_norm": 0.24901726841926575,
      "learning_rate": 0.003,
      "loss": 3.2155825805664064,
      "step": 292000
    },
    {
      "epoch": 0.638102077763912,
      "grad_norm": 0.1653231978416443,
      "learning_rate": 0.003,
      "loss": 3.232175598144531,
      "step": 292100
    },
    {
      "epoch": 0.6383205310599627,
      "grad_norm": 0.2187768816947937,
      "learning_rate": 0.003,
      "loss": 3.2303228759765625,
      "step": 292200
    },
    {
      "epoch": 0.6385389843560133,
      "grad_norm": 0.1626879870891571,
      "learning_rate": 0.003,
      "loss": 3.2115203857421877,
      "step": 292300
    },
    {
      "epoch": 0.6387574376520639,
      "grad_norm": 0.18992793560028076,
      "learning_rate": 0.003,
      "loss": 3.191268310546875,
      "step": 292400
    },
    {
      "epoch": 0.6389758909481146,
      "grad_norm": 0.2519702911376953,
      "learning_rate": 0.003,
      "loss": 3.2203164672851563,
      "step": 292500
    },
    {
      "epoch": 0.6391943442441652,
      "grad_norm": 0.1607976257801056,
      "learning_rate": 0.003,
      "loss": 3.2437109375,
      "step": 292600
    },
    {
      "epoch": 0.6394127975402158,
      "grad_norm": 0.1860385239124298,
      "learning_rate": 0.003,
      "loss": 3.2113681030273438,
      "step": 292700
    },
    {
      "epoch": 0.6396312508362665,
      "grad_norm": 0.33479562401771545,
      "learning_rate": 0.003,
      "loss": 3.20093017578125,
      "step": 292800
    },
    {
      "epoch": 0.6398497041323171,
      "grad_norm": 0.21903567016124725,
      "learning_rate": 0.003,
      "loss": 3.2004470825195312,
      "step": 292900
    },
    {
      "epoch": 0.6400681574283678,
      "grad_norm": 0.17611242830753326,
      "learning_rate": 0.003,
      "loss": 3.199743347167969,
      "step": 293000
    },
    {
      "epoch": 0.6402866107244184,
      "grad_norm": 0.18022991716861725,
      "learning_rate": 0.003,
      "loss": 3.2054098510742186,
      "step": 293100
    },
    {
      "epoch": 0.640505064020469,
      "grad_norm": 0.168337881565094,
      "learning_rate": 0.003,
      "loss": 3.220614013671875,
      "step": 293200
    },
    {
      "epoch": 0.6407235173165197,
      "grad_norm": 0.209769606590271,
      "learning_rate": 0.003,
      "loss": 3.1769366455078125,
      "step": 293300
    },
    {
      "epoch": 0.6409419706125703,
      "grad_norm": 0.2826310694217682,
      "learning_rate": 0.003,
      "loss": 3.192751159667969,
      "step": 293400
    },
    {
      "epoch": 0.6411604239086209,
      "grad_norm": 0.20993946492671967,
      "learning_rate": 0.003,
      "loss": 3.22356689453125,
      "step": 293500
    },
    {
      "epoch": 0.6413788772046716,
      "grad_norm": 0.18484105169773102,
      "learning_rate": 0.003,
      "loss": 3.1791766357421873,
      "step": 293600
    },
    {
      "epoch": 0.6415973305007222,
      "grad_norm": 0.19068412482738495,
      "learning_rate": 0.003,
      "loss": 3.1897122192382814,
      "step": 293700
    },
    {
      "epoch": 0.641815783796773,
      "grad_norm": 0.3493463695049286,
      "learning_rate": 0.003,
      "loss": 3.2472247314453124,
      "step": 293800
    },
    {
      "epoch": 0.6420342370928236,
      "grad_norm": 0.22216889262199402,
      "learning_rate": 0.003,
      "loss": 3.182608337402344,
      "step": 293900
    },
    {
      "epoch": 0.6422526903888742,
      "grad_norm": 0.17419646680355072,
      "learning_rate": 0.003,
      "loss": 3.232746276855469,
      "step": 294000
    },
    {
      "epoch": 0.6424711436849249,
      "grad_norm": 0.2276816964149475,
      "learning_rate": 0.003,
      "loss": 3.238111572265625,
      "step": 294100
    },
    {
      "epoch": 0.6426895969809755,
      "grad_norm": 0.17274421453475952,
      "learning_rate": 0.003,
      "loss": 3.2163006591796877,
      "step": 294200
    },
    {
      "epoch": 0.6429080502770261,
      "grad_norm": 0.23269233107566833,
      "learning_rate": 0.003,
      "loss": 3.2243466186523437,
      "step": 294300
    },
    {
      "epoch": 0.6431265035730768,
      "grad_norm": 0.32842302322387695,
      "learning_rate": 0.003,
      "loss": 3.2250067138671876,
      "step": 294400
    },
    {
      "epoch": 0.6433449568691274,
      "grad_norm": 0.17886516451835632,
      "learning_rate": 0.003,
      "loss": 3.228027038574219,
      "step": 294500
    },
    {
      "epoch": 0.643563410165178,
      "grad_norm": 0.24313399195671082,
      "learning_rate": 0.003,
      "loss": 3.2058526611328126,
      "step": 294600
    },
    {
      "epoch": 0.6437818634612287,
      "grad_norm": 0.18590319156646729,
      "learning_rate": 0.003,
      "loss": 3.2345791625976563,
      "step": 294700
    },
    {
      "epoch": 0.6440003167572793,
      "grad_norm": 0.22010497748851776,
      "learning_rate": 0.003,
      "loss": 3.2042193603515625,
      "step": 294800
    },
    {
      "epoch": 0.64421877005333,
      "grad_norm": 0.278316468000412,
      "learning_rate": 0.003,
      "loss": 3.216324768066406,
      "step": 294900
    },
    {
      "epoch": 0.6444372233493806,
      "grad_norm": 0.2618716061115265,
      "learning_rate": 0.003,
      "loss": 3.209858703613281,
      "step": 295000
    },
    {
      "epoch": 0.6446556766454312,
      "grad_norm": 0.17413729429244995,
      "learning_rate": 0.003,
      "loss": 3.210880126953125,
      "step": 295100
    },
    {
      "epoch": 0.6448741299414819,
      "grad_norm": 0.22063487768173218,
      "learning_rate": 0.003,
      "loss": 3.2133450317382812,
      "step": 295200
    },
    {
      "epoch": 0.6450925832375325,
      "grad_norm": 0.26703551411628723,
      "learning_rate": 0.003,
      "loss": 3.2113824462890626,
      "step": 295300
    },
    {
      "epoch": 0.6453110365335831,
      "grad_norm": 0.16885654628276825,
      "learning_rate": 0.003,
      "loss": 3.1849456787109376,
      "step": 295400
    },
    {
      "epoch": 0.6455294898296338,
      "grad_norm": 0.1926022619009018,
      "learning_rate": 0.003,
      "loss": 3.2447674560546873,
      "step": 295500
    },
    {
      "epoch": 0.6457479431256844,
      "grad_norm": 0.18120601773262024,
      "learning_rate": 0.003,
      "loss": 3.210369873046875,
      "step": 295600
    },
    {
      "epoch": 0.645966396421735,
      "grad_norm": 0.23647962510585785,
      "learning_rate": 0.003,
      "loss": 3.2169232177734375,
      "step": 295700
    },
    {
      "epoch": 0.6461848497177857,
      "grad_norm": 0.33971190452575684,
      "learning_rate": 0.003,
      "loss": 3.195985107421875,
      "step": 295800
    },
    {
      "epoch": 0.6464033030138363,
      "grad_norm": 0.1742861568927765,
      "learning_rate": 0.003,
      "loss": 3.210167236328125,
      "step": 295900
    },
    {
      "epoch": 0.6466217563098869,
      "grad_norm": 0.16989250481128693,
      "learning_rate": 0.003,
      "loss": 3.2188739013671874,
      "step": 296000
    },
    {
      "epoch": 0.6468402096059376,
      "grad_norm": 0.3357365131378174,
      "learning_rate": 0.003,
      "loss": 3.2032516479492186,
      "step": 296100
    },
    {
      "epoch": 0.6470586629019882,
      "grad_norm": 0.1617504358291626,
      "learning_rate": 0.003,
      "loss": 3.207527770996094,
      "step": 296200
    },
    {
      "epoch": 0.6472771161980388,
      "grad_norm": 0.2176031470298767,
      "learning_rate": 0.003,
      "loss": 3.1994818115234374,
      "step": 296300
    },
    {
      "epoch": 0.6474955694940895,
      "grad_norm": 0.22267164289951324,
      "learning_rate": 0.003,
      "loss": 3.220369873046875,
      "step": 296400
    },
    {
      "epoch": 0.6477140227901401,
      "grad_norm": 0.19282014667987823,
      "learning_rate": 0.003,
      "loss": 3.242883605957031,
      "step": 296500
    },
    {
      "epoch": 0.6479324760861908,
      "grad_norm": 0.35791265964508057,
      "learning_rate": 0.003,
      "loss": 3.1887692260742186,
      "step": 296600
    },
    {
      "epoch": 0.6481509293822414,
      "grad_norm": 0.19347485899925232,
      "learning_rate": 0.003,
      "loss": 3.2010302734375,
      "step": 296700
    },
    {
      "epoch": 0.648369382678292,
      "grad_norm": 0.20703920722007751,
      "learning_rate": 0.003,
      "loss": 3.2091265869140626,
      "step": 296800
    },
    {
      "epoch": 0.6485878359743427,
      "grad_norm": 0.2082105129957199,
      "learning_rate": 0.003,
      "loss": 3.2014584350585937,
      "step": 296900
    },
    {
      "epoch": 0.6488062892703933,
      "grad_norm": 0.2916179299354553,
      "learning_rate": 0.003,
      "loss": 3.2074530029296877,
      "step": 297000
    },
    {
      "epoch": 0.6490247425664439,
      "grad_norm": 0.2831776440143585,
      "learning_rate": 0.003,
      "loss": 3.208277282714844,
      "step": 297100
    },
    {
      "epoch": 0.6492431958624946,
      "grad_norm": 0.17695355415344238,
      "learning_rate": 0.003,
      "loss": 3.222369384765625,
      "step": 297200
    },
    {
      "epoch": 0.6494616491585452,
      "grad_norm": 0.16826608777046204,
      "learning_rate": 0.003,
      "loss": 3.2098590087890626,
      "step": 297300
    },
    {
      "epoch": 0.6496801024545958,
      "grad_norm": 0.1833970993757248,
      "learning_rate": 0.003,
      "loss": 3.216153564453125,
      "step": 297400
    },
    {
      "epoch": 0.6498985557506465,
      "grad_norm": 0.2047235071659088,
      "learning_rate": 0.003,
      "loss": 3.2295458984375,
      "step": 297500
    },
    {
      "epoch": 0.6501170090466971,
      "grad_norm": 0.15343202650547028,
      "learning_rate": 0.003,
      "loss": 3.209427490234375,
      "step": 297600
    },
    {
      "epoch": 0.6503354623427477,
      "grad_norm": 0.17504726350307465,
      "learning_rate": 0.003,
      "loss": 3.216612548828125,
      "step": 297700
    },
    {
      "epoch": 0.6505539156387984,
      "grad_norm": 0.15502938628196716,
      "learning_rate": 0.003,
      "loss": 3.2104006958007814,
      "step": 297800
    },
    {
      "epoch": 0.650772368934849,
      "grad_norm": 0.23066256940364838,
      "learning_rate": 0.003,
      "loss": 3.2003338623046873,
      "step": 297900
    },
    {
      "epoch": 0.6509908222308997,
      "grad_norm": 0.20049090683460236,
      "learning_rate": 0.003,
      "loss": 3.2026025390625,
      "step": 298000
    },
    {
      "epoch": 0.6512092755269503,
      "grad_norm": 0.21652831137180328,
      "learning_rate": 0.003,
      "loss": 3.197514953613281,
      "step": 298100
    },
    {
      "epoch": 0.6514277288230009,
      "grad_norm": 0.17694705724716187,
      "learning_rate": 0.003,
      "loss": 3.211328430175781,
      "step": 298200
    },
    {
      "epoch": 0.6516461821190516,
      "grad_norm": 0.2777915894985199,
      "learning_rate": 0.003,
      "loss": 3.218311462402344,
      "step": 298300
    },
    {
      "epoch": 0.6518646354151022,
      "grad_norm": 0.19759583473205566,
      "learning_rate": 0.003,
      "loss": 3.1718414306640623,
      "step": 298400
    },
    {
      "epoch": 0.6520830887111528,
      "grad_norm": 0.22223566472530365,
      "learning_rate": 0.003,
      "loss": 3.2045233154296877,
      "step": 298500
    },
    {
      "epoch": 0.6523015420072035,
      "grad_norm": 0.1721937507390976,
      "learning_rate": 0.003,
      "loss": 3.225453186035156,
      "step": 298600
    },
    {
      "epoch": 0.6525199953032541,
      "grad_norm": 0.17230795323848724,
      "learning_rate": 0.003,
      "loss": 3.197484436035156,
      "step": 298700
    },
    {
      "epoch": 0.6527384485993047,
      "grad_norm": 0.3072788119316101,
      "learning_rate": 0.003,
      "loss": 3.2088607788085937,
      "step": 298800
    },
    {
      "epoch": 0.6529569018953554,
      "grad_norm": 0.18282048404216766,
      "learning_rate": 0.003,
      "loss": 3.2154412841796876,
      "step": 298900
    },
    {
      "epoch": 0.653175355191406,
      "grad_norm": 0.32448163628578186,
      "learning_rate": 0.003,
      "loss": 3.2090438842773437,
      "step": 299000
    },
    {
      "epoch": 0.6533938084874567,
      "grad_norm": 0.24602174758911133,
      "learning_rate": 0.003,
      "loss": 3.1992950439453125,
      "step": 299100
    },
    {
      "epoch": 0.6536122617835073,
      "grad_norm": 0.20388135313987732,
      "learning_rate": 0.003,
      "loss": 3.232383117675781,
      "step": 299200
    },
    {
      "epoch": 0.6538307150795579,
      "grad_norm": 0.17983829975128174,
      "learning_rate": 0.003,
      "loss": 3.2041424560546874,
      "step": 299300
    },
    {
      "epoch": 0.6540491683756086,
      "grad_norm": 0.24621103703975677,
      "learning_rate": 0.003,
      "loss": 3.2072760009765626,
      "step": 299400
    },
    {
      "epoch": 0.6542676216716592,
      "grad_norm": 0.1693122535943985,
      "learning_rate": 0.003,
      "loss": 3.2283856201171877,
      "step": 299500
    },
    {
      "epoch": 0.6544860749677098,
      "grad_norm": 0.16604112088680267,
      "learning_rate": 0.003,
      "loss": 3.2300738525390624,
      "step": 299600
    },
    {
      "epoch": 0.6547045282637605,
      "grad_norm": 0.1853214055299759,
      "learning_rate": 0.003,
      "loss": 3.2130108642578126,
      "step": 299700
    },
    {
      "epoch": 0.6549229815598111,
      "grad_norm": 0.17625734210014343,
      "learning_rate": 0.003,
      "loss": 3.240780944824219,
      "step": 299800
    },
    {
      "epoch": 0.6551414348558617,
      "grad_norm": 0.23995201289653778,
      "learning_rate": 0.003,
      "loss": 3.1994253540039064,
      "step": 299900
    },
    {
      "epoch": 0.6553598881519124,
      "grad_norm": 0.36196666955947876,
      "learning_rate": 0.003,
      "loss": 3.2601962280273438,
      "step": 300000
    },
    {
      "epoch": 0.655578341447963,
      "grad_norm": 0.22744445502758026,
      "learning_rate": 0.003,
      "loss": 3.2318609619140624,
      "step": 300100
    },
    {
      "epoch": 0.6557967947440136,
      "grad_norm": 0.2668069899082184,
      "learning_rate": 0.003,
      "loss": 3.2366748046875,
      "step": 300200
    },
    {
      "epoch": 0.6560152480400643,
      "grad_norm": 0.20023784041404724,
      "learning_rate": 0.003,
      "loss": 3.2150424194335936,
      "step": 300300
    },
    {
      "epoch": 0.656233701336115,
      "grad_norm": 0.20829899609088898,
      "learning_rate": 0.003,
      "loss": 3.2354595947265623,
      "step": 300400
    },
    {
      "epoch": 0.6564521546321657,
      "grad_norm": 0.17830970883369446,
      "learning_rate": 0.003,
      "loss": 3.2219967651367187,
      "step": 300500
    },
    {
      "epoch": 0.6566706079282163,
      "grad_norm": 0.1684214472770691,
      "learning_rate": 0.003,
      "loss": 3.24798583984375,
      "step": 300600
    },
    {
      "epoch": 0.6568890612242669,
      "grad_norm": 0.15639004111289978,
      "learning_rate": 0.003,
      "loss": 3.1997930908203127,
      "step": 300700
    },
    {
      "epoch": 0.6571075145203176,
      "grad_norm": 0.24520382285118103,
      "learning_rate": 0.003,
      "loss": 3.1876092529296876,
      "step": 300800
    },
    {
      "epoch": 0.6573259678163682,
      "grad_norm": 0.22645990550518036,
      "learning_rate": 0.003,
      "loss": 3.196791687011719,
      "step": 300900
    },
    {
      "epoch": 0.6575444211124188,
      "grad_norm": 0.20528782904148102,
      "learning_rate": 0.003,
      "loss": 3.197469482421875,
      "step": 301000
    },
    {
      "epoch": 0.6577628744084695,
      "grad_norm": 0.21871644258499146,
      "learning_rate": 0.003,
      "loss": 3.2243356323242187,
      "step": 301100
    },
    {
      "epoch": 0.6579813277045201,
      "grad_norm": 0.2103194147348404,
      "learning_rate": 0.003,
      "loss": 3.2315939331054686,
      "step": 301200
    },
    {
      "epoch": 0.6581997810005707,
      "grad_norm": 0.20259596407413483,
      "learning_rate": 0.003,
      "loss": 3.194053955078125,
      "step": 301300
    },
    {
      "epoch": 0.6584182342966214,
      "grad_norm": 0.20097105205059052,
      "learning_rate": 0.003,
      "loss": 3.18394775390625,
      "step": 301400
    },
    {
      "epoch": 0.658636687592672,
      "grad_norm": 0.23157066106796265,
      "learning_rate": 0.003,
      "loss": 3.1934848022460938,
      "step": 301500
    },
    {
      "epoch": 0.6588551408887227,
      "grad_norm": 0.1665690839290619,
      "learning_rate": 0.003,
      "loss": 3.1573736572265627,
      "step": 301600
    },
    {
      "epoch": 0.6590735941847733,
      "grad_norm": 0.22662605345249176,
      "learning_rate": 0.003,
      "loss": 3.205041809082031,
      "step": 301700
    },
    {
      "epoch": 0.6592920474808239,
      "grad_norm": 0.17870958149433136,
      "learning_rate": 0.003,
      "loss": 3.200242004394531,
      "step": 301800
    },
    {
      "epoch": 0.6595105007768746,
      "grad_norm": 0.21168215572834015,
      "learning_rate": 0.003,
      "loss": 3.198275146484375,
      "step": 301900
    },
    {
      "epoch": 0.6597289540729252,
      "grad_norm": 0.17115339636802673,
      "learning_rate": 0.003,
      "loss": 3.2058148193359375,
      "step": 302000
    },
    {
      "epoch": 0.6599474073689758,
      "grad_norm": 0.1780891865491867,
      "learning_rate": 0.003,
      "loss": 3.1999090576171874,
      "step": 302100
    },
    {
      "epoch": 0.6601658606650265,
      "grad_norm": 0.16251401603221893,
      "learning_rate": 0.003,
      "loss": 3.2172247314453126,
      "step": 302200
    },
    {
      "epoch": 0.6603843139610771,
      "grad_norm": 0.19613465666770935,
      "learning_rate": 0.003,
      "loss": 3.265261535644531,
      "step": 302300
    },
    {
      "epoch": 0.6606027672571277,
      "grad_norm": 0.1798177808523178,
      "learning_rate": 0.003,
      "loss": 3.1905667114257814,
      "step": 302400
    },
    {
      "epoch": 0.6608212205531784,
      "grad_norm": 0.24702991545200348,
      "learning_rate": 0.003,
      "loss": 3.225159912109375,
      "step": 302500
    },
    {
      "epoch": 0.661039673849229,
      "grad_norm": 0.2413354516029358,
      "learning_rate": 0.003,
      "loss": 3.2247610473632813,
      "step": 302600
    },
    {
      "epoch": 0.6612581271452797,
      "grad_norm": 0.22546137869358063,
      "learning_rate": 0.003,
      "loss": 3.23873779296875,
      "step": 302700
    },
    {
      "epoch": 0.6614765804413303,
      "grad_norm": 0.18609336018562317,
      "learning_rate": 0.003,
      "loss": 3.1911715698242187,
      "step": 302800
    },
    {
      "epoch": 0.6616950337373809,
      "grad_norm": 0.18429632484912872,
      "learning_rate": 0.003,
      "loss": 3.220042419433594,
      "step": 302900
    },
    {
      "epoch": 0.6619134870334316,
      "grad_norm": 0.20843130350112915,
      "learning_rate": 0.003,
      "loss": 3.2080624389648436,
      "step": 303000
    },
    {
      "epoch": 0.6621319403294822,
      "grad_norm": 0.16817250847816467,
      "learning_rate": 0.003,
      "loss": 3.2188449096679688,
      "step": 303100
    },
    {
      "epoch": 0.6623503936255328,
      "grad_norm": 0.17936468124389648,
      "learning_rate": 0.003,
      "loss": 3.2420687866210938,
      "step": 303200
    },
    {
      "epoch": 0.6625688469215835,
      "grad_norm": 0.20911620557308197,
      "learning_rate": 0.003,
      "loss": 3.210085754394531,
      "step": 303300
    },
    {
      "epoch": 0.6627873002176341,
      "grad_norm": 0.16286759078502655,
      "learning_rate": 0.003,
      "loss": 3.2376312255859374,
      "step": 303400
    },
    {
      "epoch": 0.6630057535136847,
      "grad_norm": 0.23707513511180878,
      "learning_rate": 0.003,
      "loss": 3.26609130859375,
      "step": 303500
    },
    {
      "epoch": 0.6632242068097354,
      "grad_norm": 0.17485572397708893,
      "learning_rate": 0.003,
      "loss": 3.218832702636719,
      "step": 303600
    },
    {
      "epoch": 0.663442660105786,
      "grad_norm": 0.16827374696731567,
      "learning_rate": 0.003,
      "loss": 3.210543518066406,
      "step": 303700
    },
    {
      "epoch": 0.6636611134018366,
      "grad_norm": 0.1883353292942047,
      "learning_rate": 0.003,
      "loss": 3.2056118774414064,
      "step": 303800
    },
    {
      "epoch": 0.6638795666978873,
      "grad_norm": 0.2831493020057678,
      "learning_rate": 0.003,
      "loss": 3.22765380859375,
      "step": 303900
    },
    {
      "epoch": 0.6640980199939379,
      "grad_norm": 0.22184669971466064,
      "learning_rate": 0.003,
      "loss": 3.2322592163085937,
      "step": 304000
    },
    {
      "epoch": 0.6643164732899886,
      "grad_norm": 0.18739952147006989,
      "learning_rate": 0.003,
      "loss": 3.2346844482421875,
      "step": 304100
    },
    {
      "epoch": 0.6645349265860392,
      "grad_norm": 0.20169822871685028,
      "learning_rate": 0.003,
      "loss": 3.2142935180664063,
      "step": 304200
    },
    {
      "epoch": 0.6647533798820898,
      "grad_norm": 0.2636165916919708,
      "learning_rate": 0.003,
      "loss": 3.2028262329101564,
      "step": 304300
    },
    {
      "epoch": 0.6649718331781405,
      "grad_norm": 0.19833305478096008,
      "learning_rate": 0.003,
      "loss": 3.194041442871094,
      "step": 304400
    },
    {
      "epoch": 0.6651902864741911,
      "grad_norm": 0.1490991860628128,
      "learning_rate": 0.003,
      "loss": 3.201954040527344,
      "step": 304500
    },
    {
      "epoch": 0.6654087397702417,
      "grad_norm": 0.1889628767967224,
      "learning_rate": 0.003,
      "loss": 3.1885635375976564,
      "step": 304600
    },
    {
      "epoch": 0.6656271930662924,
      "grad_norm": 0.21049557626247406,
      "learning_rate": 0.003,
      "loss": 3.217703552246094,
      "step": 304700
    },
    {
      "epoch": 0.665845646362343,
      "grad_norm": 0.20305891335010529,
      "learning_rate": 0.003,
      "loss": 3.1934417724609374,
      "step": 304800
    },
    {
      "epoch": 0.6660640996583936,
      "grad_norm": 0.2650563418865204,
      "learning_rate": 0.003,
      "loss": 3.217193603515625,
      "step": 304900
    },
    {
      "epoch": 0.6662825529544443,
      "grad_norm": 0.17325250804424286,
      "learning_rate": 0.003,
      "loss": 3.1843994140625,
      "step": 305000
    },
    {
      "epoch": 0.6665010062504949,
      "grad_norm": 0.1646677851676941,
      "learning_rate": 0.003,
      "loss": 3.218613586425781,
      "step": 305100
    },
    {
      "epoch": 0.6667194595465455,
      "grad_norm": 0.24636316299438477,
      "learning_rate": 0.003,
      "loss": 3.202257080078125,
      "step": 305200
    },
    {
      "epoch": 0.6669379128425962,
      "grad_norm": 0.17880240082740784,
      "learning_rate": 0.003,
      "loss": 3.228616027832031,
      "step": 305300
    },
    {
      "epoch": 0.6671563661386468,
      "grad_norm": 0.21487340331077576,
      "learning_rate": 0.003,
      "loss": 3.2378302001953125,
      "step": 305400
    },
    {
      "epoch": 0.6673748194346975,
      "grad_norm": 0.16672925651073456,
      "learning_rate": 0.003,
      "loss": 3.2163931274414064,
      "step": 305500
    },
    {
      "epoch": 0.6675932727307481,
      "grad_norm": 0.20486555993556976,
      "learning_rate": 0.003,
      "loss": 3.19755859375,
      "step": 305600
    },
    {
      "epoch": 0.6678117260267987,
      "grad_norm": 0.19295841455459595,
      "learning_rate": 0.003,
      "loss": 3.2205047607421875,
      "step": 305700
    },
    {
      "epoch": 0.6680301793228494,
      "grad_norm": 0.19123561680316925,
      "learning_rate": 0.003,
      "loss": 3.233076477050781,
      "step": 305800
    },
    {
      "epoch": 0.6682486326189,
      "grad_norm": 0.29945188760757446,
      "learning_rate": 0.003,
      "loss": 3.1701165771484376,
      "step": 305900
    },
    {
      "epoch": 0.6684670859149506,
      "grad_norm": 0.20981299877166748,
      "learning_rate": 0.003,
      "loss": 3.2398284912109374,
      "step": 306000
    },
    {
      "epoch": 0.6686855392110013,
      "grad_norm": 0.1732894629240036,
      "learning_rate": 0.003,
      "loss": 3.195567626953125,
      "step": 306100
    },
    {
      "epoch": 0.6689039925070519,
      "grad_norm": 0.22836065292358398,
      "learning_rate": 0.003,
      "loss": 3.2066104125976564,
      "step": 306200
    },
    {
      "epoch": 0.6691224458031025,
      "grad_norm": 0.36775392293930054,
      "learning_rate": 0.003,
      "loss": 3.2157937622070314,
      "step": 306300
    },
    {
      "epoch": 0.6693408990991532,
      "grad_norm": 0.22865299880504608,
      "learning_rate": 0.003,
      "loss": 3.201554260253906,
      "step": 306400
    },
    {
      "epoch": 0.6695593523952038,
      "grad_norm": 0.18090923130512238,
      "learning_rate": 0.003,
      "loss": 3.250672607421875,
      "step": 306500
    },
    {
      "epoch": 0.6697778056912544,
      "grad_norm": 0.1764441877603531,
      "learning_rate": 0.003,
      "loss": 3.2098574829101563,
      "step": 306600
    },
    {
      "epoch": 0.6699962589873051,
      "grad_norm": 0.1840853989124298,
      "learning_rate": 0.003,
      "loss": 3.2286358642578126,
      "step": 306700
    },
    {
      "epoch": 0.6702147122833557,
      "grad_norm": 0.18044841289520264,
      "learning_rate": 0.003,
      "loss": 3.2066339111328124,
      "step": 306800
    },
    {
      "epoch": 0.6704331655794064,
      "grad_norm": 0.1703362613916397,
      "learning_rate": 0.003,
      "loss": 3.2177169799804686,
      "step": 306900
    },
    {
      "epoch": 0.6706516188754571,
      "grad_norm": 0.20050768554210663,
      "learning_rate": 0.003,
      "loss": 3.2220309448242186,
      "step": 307000
    },
    {
      "epoch": 0.6708700721715077,
      "grad_norm": 0.16470454633235931,
      "learning_rate": 0.003,
      "loss": 3.177530517578125,
      "step": 307100
    },
    {
      "epoch": 0.6710885254675584,
      "grad_norm": 0.1639939844608307,
      "learning_rate": 0.003,
      "loss": 3.2003173828125,
      "step": 307200
    },
    {
      "epoch": 0.671306978763609,
      "grad_norm": 0.16684788465499878,
      "learning_rate": 0.003,
      "loss": 3.2303872680664063,
      "step": 307300
    },
    {
      "epoch": 0.6715254320596596,
      "grad_norm": 0.21592481434345245,
      "learning_rate": 0.003,
      "loss": 3.2202947998046874,
      "step": 307400
    },
    {
      "epoch": 0.6717438853557103,
      "grad_norm": 0.19638244807720184,
      "learning_rate": 0.003,
      "loss": 3.153433837890625,
      "step": 307500
    },
    {
      "epoch": 0.6719623386517609,
      "grad_norm": 0.3065269887447357,
      "learning_rate": 0.003,
      "loss": 3.1862197875976563,
      "step": 307600
    },
    {
      "epoch": 0.6721807919478116,
      "grad_norm": 0.17610310018062592,
      "learning_rate": 0.003,
      "loss": 3.2371859741210938,
      "step": 307700
    },
    {
      "epoch": 0.6723992452438622,
      "grad_norm": 0.31250008940696716,
      "learning_rate": 0.003,
      "loss": 3.2346817016601563,
      "step": 307800
    },
    {
      "epoch": 0.6726176985399128,
      "grad_norm": 0.21141862869262695,
      "learning_rate": 0.003,
      "loss": 3.2095962524414063,
      "step": 307900
    },
    {
      "epoch": 0.6728361518359635,
      "grad_norm": 0.17335063219070435,
      "learning_rate": 0.003,
      "loss": 3.153291015625,
      "step": 308000
    },
    {
      "epoch": 0.6730546051320141,
      "grad_norm": 0.16361065208911896,
      "learning_rate": 0.003,
      "loss": 3.2134439086914064,
      "step": 308100
    },
    {
      "epoch": 0.6732730584280647,
      "grad_norm": 0.1722339391708374,
      "learning_rate": 0.003,
      "loss": 3.1733050537109375,
      "step": 308200
    },
    {
      "epoch": 0.6734915117241154,
      "grad_norm": 0.166559636592865,
      "learning_rate": 0.003,
      "loss": 3.2202078247070314,
      "step": 308300
    },
    {
      "epoch": 0.673709965020166,
      "grad_norm": 0.21635200083255768,
      "learning_rate": 0.003,
      "loss": 3.1822848510742188,
      "step": 308400
    },
    {
      "epoch": 0.6739284183162166,
      "grad_norm": 0.25251302123069763,
      "learning_rate": 0.003,
      "loss": 3.1653387451171877,
      "step": 308500
    },
    {
      "epoch": 0.6741468716122673,
      "grad_norm": 0.18900343775749207,
      "learning_rate": 0.003,
      "loss": 3.1732272338867187,
      "step": 308600
    },
    {
      "epoch": 0.6743653249083179,
      "grad_norm": 0.24745331704616547,
      "learning_rate": 0.003,
      "loss": 3.170323486328125,
      "step": 308700
    },
    {
      "epoch": 0.6745837782043685,
      "grad_norm": 0.18476608395576477,
      "learning_rate": 0.003,
      "loss": 3.173564758300781,
      "step": 308800
    },
    {
      "epoch": 0.6748022315004192,
      "grad_norm": 0.19383637607097626,
      "learning_rate": 0.003,
      "loss": 3.188165588378906,
      "step": 308900
    },
    {
      "epoch": 0.6750206847964698,
      "grad_norm": 0.21646493673324585,
      "learning_rate": 0.003,
      "loss": 3.17208740234375,
      "step": 309000
    },
    {
      "epoch": 0.6752391380925205,
      "grad_norm": 0.1939047873020172,
      "learning_rate": 0.003,
      "loss": 3.2574581909179687,
      "step": 309100
    },
    {
      "epoch": 0.6754575913885711,
      "grad_norm": 0.1980661153793335,
      "learning_rate": 0.003,
      "loss": 3.1932293701171877,
      "step": 309200
    },
    {
      "epoch": 0.6756760446846217,
      "grad_norm": 0.16224496066570282,
      "learning_rate": 0.003,
      "loss": 3.1783511352539064,
      "step": 309300
    },
    {
      "epoch": 0.6758944979806724,
      "grad_norm": 0.202712744474411,
      "learning_rate": 0.003,
      "loss": 3.2093572998046875,
      "step": 309400
    },
    {
      "epoch": 0.676112951276723,
      "grad_norm": 0.17281390726566315,
      "learning_rate": 0.003,
      "loss": 3.189764404296875,
      "step": 309500
    },
    {
      "epoch": 0.6763314045727736,
      "grad_norm": 0.18861469626426697,
      "learning_rate": 0.003,
      "loss": 3.227015380859375,
      "step": 309600
    },
    {
      "epoch": 0.6765498578688243,
      "grad_norm": 0.20320996642112732,
      "learning_rate": 0.003,
      "loss": 3.20105224609375,
      "step": 309700
    },
    {
      "epoch": 0.6767683111648749,
      "grad_norm": 0.2117713838815689,
      "learning_rate": 0.003,
      "loss": 3.196175537109375,
      "step": 309800
    },
    {
      "epoch": 0.6769867644609255,
      "grad_norm": 0.2043059766292572,
      "learning_rate": 0.003,
      "loss": 3.2206787109375,
      "step": 309900
    },
    {
      "epoch": 0.6772052177569762,
      "grad_norm": 0.2059088498353958,
      "learning_rate": 0.003,
      "loss": 3.191325378417969,
      "step": 310000
    },
    {
      "epoch": 0.6774236710530268,
      "grad_norm": 0.16710332036018372,
      "learning_rate": 0.003,
      "loss": 3.2231106567382812,
      "step": 310100
    },
    {
      "epoch": 0.6776421243490774,
      "grad_norm": 0.19772081077098846,
      "learning_rate": 0.003,
      "loss": 3.2278671264648438,
      "step": 310200
    },
    {
      "epoch": 0.6778605776451281,
      "grad_norm": 0.16292034089565277,
      "learning_rate": 0.003,
      "loss": 3.1694876098632814,
      "step": 310300
    },
    {
      "epoch": 0.6780790309411787,
      "grad_norm": 0.24583515524864197,
      "learning_rate": 0.003,
      "loss": 3.192455139160156,
      "step": 310400
    },
    {
      "epoch": 0.6782974842372294,
      "grad_norm": 0.21594125032424927,
      "learning_rate": 0.003,
      "loss": 3.2232330322265623,
      "step": 310500
    },
    {
      "epoch": 0.67851593753328,
      "grad_norm": 0.17762251198291779,
      "learning_rate": 0.003,
      "loss": 3.1636148071289063,
      "step": 310600
    },
    {
      "epoch": 0.6787343908293306,
      "grad_norm": 0.16651715338230133,
      "learning_rate": 0.003,
      "loss": 3.1900933837890624,
      "step": 310700
    },
    {
      "epoch": 0.6789528441253813,
      "grad_norm": 0.17519238591194153,
      "learning_rate": 0.003,
      "loss": 3.19745361328125,
      "step": 310800
    },
    {
      "epoch": 0.6791712974214319,
      "grad_norm": 0.1805468052625656,
      "learning_rate": 0.003,
      "loss": 3.204796142578125,
      "step": 310900
    },
    {
      "epoch": 0.6793897507174825,
      "grad_norm": 0.21922335028648376,
      "learning_rate": 0.003,
      "loss": 3.2320291137695314,
      "step": 311000
    },
    {
      "epoch": 0.6796082040135332,
      "grad_norm": 0.23161950707435608,
      "learning_rate": 0.003,
      "loss": 3.2042828369140626,
      "step": 311100
    },
    {
      "epoch": 0.6798266573095838,
      "grad_norm": 0.1838044375181198,
      "learning_rate": 0.003,
      "loss": 3.19519775390625,
      "step": 311200
    },
    {
      "epoch": 0.6800451106056344,
      "grad_norm": 0.2180398851633072,
      "learning_rate": 0.003,
      "loss": 3.1841470336914064,
      "step": 311300
    },
    {
      "epoch": 0.6802635639016851,
      "grad_norm": 0.24195468425750732,
      "learning_rate": 0.003,
      "loss": 3.1849127197265625,
      "step": 311400
    },
    {
      "epoch": 0.6804820171977357,
      "grad_norm": 0.18009723722934723,
      "learning_rate": 0.003,
      "loss": 3.194149169921875,
      "step": 311500
    },
    {
      "epoch": 0.6807004704937863,
      "grad_norm": 0.1883620321750641,
      "learning_rate": 0.003,
      "loss": 3.210948181152344,
      "step": 311600
    },
    {
      "epoch": 0.680918923789837,
      "grad_norm": 0.23738133907318115,
      "learning_rate": 0.003,
      "loss": 3.1947671508789064,
      "step": 311700
    },
    {
      "epoch": 0.6811373770858876,
      "grad_norm": 0.22023935616016388,
      "learning_rate": 0.003,
      "loss": 3.2093319702148437,
      "step": 311800
    },
    {
      "epoch": 0.6813558303819383,
      "grad_norm": 0.22992876172065735,
      "learning_rate": 0.003,
      "loss": 3.1898150634765625,
      "step": 311900
    },
    {
      "epoch": 0.6815742836779889,
      "grad_norm": 0.1881478726863861,
      "learning_rate": 0.003,
      "loss": 3.2124057006835938,
      "step": 312000
    },
    {
      "epoch": 0.6817927369740395,
      "grad_norm": 0.17735520005226135,
      "learning_rate": 0.003,
      "loss": 3.19234619140625,
      "step": 312100
    },
    {
      "epoch": 0.6820111902700902,
      "grad_norm": 0.18895170092582703,
      "learning_rate": 0.003,
      "loss": 3.2011102294921874,
      "step": 312200
    },
    {
      "epoch": 0.6822296435661408,
      "grad_norm": 0.19253608584403992,
      "learning_rate": 0.003,
      "loss": 3.2125454711914063,
      "step": 312300
    },
    {
      "epoch": 0.6824480968621914,
      "grad_norm": 0.16899695992469788,
      "learning_rate": 0.003,
      "loss": 3.178625183105469,
      "step": 312400
    },
    {
      "epoch": 0.6826665501582421,
      "grad_norm": 0.2261907011270523,
      "learning_rate": 0.003,
      "loss": 3.211822814941406,
      "step": 312500
    },
    {
      "epoch": 0.6828850034542927,
      "grad_norm": 0.20471321046352386,
      "learning_rate": 0.003,
      "loss": 3.1593289184570312,
      "step": 312600
    },
    {
      "epoch": 0.6831034567503433,
      "grad_norm": 0.33698052167892456,
      "learning_rate": 0.003,
      "loss": 3.207825012207031,
      "step": 312700
    },
    {
      "epoch": 0.683321910046394,
      "grad_norm": 0.3978661298751831,
      "learning_rate": 0.003,
      "loss": 3.212341003417969,
      "step": 312800
    },
    {
      "epoch": 0.6835403633424446,
      "grad_norm": 0.25749894976615906,
      "learning_rate": 0.003,
      "loss": 3.1770974731445314,
      "step": 312900
    },
    {
      "epoch": 0.6837588166384952,
      "grad_norm": 0.23231497406959534,
      "learning_rate": 0.003,
      "loss": 3.2088446044921874,
      "step": 313000
    },
    {
      "epoch": 0.6839772699345459,
      "grad_norm": 0.26409631967544556,
      "learning_rate": 0.003,
      "loss": 3.220814514160156,
      "step": 313100
    },
    {
      "epoch": 0.6841957232305965,
      "grad_norm": 0.19819815456867218,
      "learning_rate": 0.003,
      "loss": 3.1851104736328124,
      "step": 313200
    },
    {
      "epoch": 0.6844141765266472,
      "grad_norm": 0.17629215121269226,
      "learning_rate": 0.003,
      "loss": 3.1794815063476562,
      "step": 313300
    },
    {
      "epoch": 0.6846326298226978,
      "grad_norm": 0.16130298376083374,
      "learning_rate": 0.003,
      "loss": 3.18755126953125,
      "step": 313400
    },
    {
      "epoch": 0.6848510831187484,
      "grad_norm": 0.24917210638523102,
      "learning_rate": 0.003,
      "loss": 3.2076016235351563,
      "step": 313500
    },
    {
      "epoch": 0.6850695364147992,
      "grad_norm": 0.311861515045166,
      "learning_rate": 0.003,
      "loss": 3.194355773925781,
      "step": 313600
    },
    {
      "epoch": 0.6852879897108498,
      "grad_norm": 0.20576713979244232,
      "learning_rate": 0.003,
      "loss": 3.1708197021484374,
      "step": 313700
    },
    {
      "epoch": 0.6855064430069004,
      "grad_norm": 0.20043489336967468,
      "learning_rate": 0.003,
      "loss": 3.1926004028320314,
      "step": 313800
    },
    {
      "epoch": 0.6857248963029511,
      "grad_norm": 0.16079092025756836,
      "learning_rate": 0.003,
      "loss": 3.205037841796875,
      "step": 313900
    },
    {
      "epoch": 0.6859433495990017,
      "grad_norm": 0.27777576446533203,
      "learning_rate": 0.003,
      "loss": 3.1588427734375,
      "step": 314000
    },
    {
      "epoch": 0.6861618028950524,
      "grad_norm": 0.21166430413722992,
      "learning_rate": 0.003,
      "loss": 3.192196044921875,
      "step": 314100
    },
    {
      "epoch": 0.686380256191103,
      "grad_norm": 0.18208011984825134,
      "learning_rate": 0.003,
      "loss": 3.204046630859375,
      "step": 314200
    },
    {
      "epoch": 0.6865987094871536,
      "grad_norm": 0.22597776353359222,
      "learning_rate": 0.003,
      "loss": 3.2169879150390623,
      "step": 314300
    },
    {
      "epoch": 0.6868171627832043,
      "grad_norm": 0.17020441591739655,
      "learning_rate": 0.003,
      "loss": 3.2141458129882814,
      "step": 314400
    },
    {
      "epoch": 0.6870356160792549,
      "grad_norm": 0.195199653506279,
      "learning_rate": 0.003,
      "loss": 3.220701904296875,
      "step": 314500
    },
    {
      "epoch": 0.6872540693753055,
      "grad_norm": 0.4784257411956787,
      "learning_rate": 0.003,
      "loss": 3.195270690917969,
      "step": 314600
    },
    {
      "epoch": 0.6874725226713562,
      "grad_norm": 0.18978168070316315,
      "learning_rate": 0.003,
      "loss": 3.2173165893554687,
      "step": 314700
    },
    {
      "epoch": 0.6876909759674068,
      "grad_norm": 0.17206624150276184,
      "learning_rate": 0.003,
      "loss": 3.192900390625,
      "step": 314800
    },
    {
      "epoch": 0.6879094292634574,
      "grad_norm": 0.14735569059848785,
      "learning_rate": 0.003,
      "loss": 3.1904351806640623,
      "step": 314900
    },
    {
      "epoch": 0.6881278825595081,
      "grad_norm": 0.2309851348400116,
      "learning_rate": 0.003,
      "loss": 3.189046630859375,
      "step": 315000
    },
    {
      "epoch": 0.6883463358555587,
      "grad_norm": 0.19177788496017456,
      "learning_rate": 0.003,
      "loss": 3.186983642578125,
      "step": 315100
    },
    {
      "epoch": 0.6885647891516093,
      "grad_norm": 0.17619240283966064,
      "learning_rate": 0.003,
      "loss": 3.1885501098632814,
      "step": 315200
    },
    {
      "epoch": 0.68878324244766,
      "grad_norm": 0.17635206878185272,
      "learning_rate": 0.003,
      "loss": 3.173389892578125,
      "step": 315300
    },
    {
      "epoch": 0.6890016957437106,
      "grad_norm": 0.23111259937286377,
      "learning_rate": 0.003,
      "loss": 3.185491027832031,
      "step": 315400
    },
    {
      "epoch": 0.6892201490397613,
      "grad_norm": 0.22397398948669434,
      "learning_rate": 0.003,
      "loss": 3.165135803222656,
      "step": 315500
    },
    {
      "epoch": 0.6894386023358119,
      "grad_norm": 0.2724665105342865,
      "learning_rate": 0.003,
      "loss": 3.229146728515625,
      "step": 315600
    },
    {
      "epoch": 0.6896570556318625,
      "grad_norm": 0.1591438353061676,
      "learning_rate": 0.003,
      "loss": 3.167120056152344,
      "step": 315700
    },
    {
      "epoch": 0.6898755089279132,
      "grad_norm": 0.21389752626419067,
      "learning_rate": 0.003,
      "loss": 3.14984130859375,
      "step": 315800
    },
    {
      "epoch": 0.6900939622239638,
      "grad_norm": 0.19706067442893982,
      "learning_rate": 0.003,
      "loss": 3.2054876708984374,
      "step": 315900
    },
    {
      "epoch": 0.6903124155200144,
      "grad_norm": 0.21618619561195374,
      "learning_rate": 0.003,
      "loss": 3.16546630859375,
      "step": 316000
    },
    {
      "epoch": 0.6905308688160651,
      "grad_norm": 0.19666269421577454,
      "learning_rate": 0.003,
      "loss": 3.160159912109375,
      "step": 316100
    },
    {
      "epoch": 0.6907493221121157,
      "grad_norm": 0.19777296483516693,
      "learning_rate": 0.003,
      "loss": 3.1843936157226564,
      "step": 316200
    },
    {
      "epoch": 0.6909677754081663,
      "grad_norm": 0.16829274594783783,
      "learning_rate": 0.003,
      "loss": 3.19912841796875,
      "step": 316300
    },
    {
      "epoch": 0.691186228704217,
      "grad_norm": 0.18362608551979065,
      "learning_rate": 0.003,
      "loss": 3.183807067871094,
      "step": 316400
    },
    {
      "epoch": 0.6914046820002676,
      "grad_norm": 0.19064904749393463,
      "learning_rate": 0.003,
      "loss": 3.259541015625,
      "step": 316500
    },
    {
      "epoch": 0.6916231352963182,
      "grad_norm": 0.1538792997598648,
      "learning_rate": 0.003,
      "loss": 3.153006286621094,
      "step": 316600
    },
    {
      "epoch": 0.6918415885923689,
      "grad_norm": 0.20653383433818817,
      "learning_rate": 0.003,
      "loss": 3.1532940673828125,
      "step": 316700
    },
    {
      "epoch": 0.6920600418884195,
      "grad_norm": 0.20320236682891846,
      "learning_rate": 0.003,
      "loss": 3.18331787109375,
      "step": 316800
    },
    {
      "epoch": 0.6922784951844702,
      "grad_norm": 0.19123028218746185,
      "learning_rate": 0.003,
      "loss": 3.1970526123046876,
      "step": 316900
    },
    {
      "epoch": 0.6924969484805208,
      "grad_norm": 0.1722438931465149,
      "learning_rate": 0.003,
      "loss": 3.1723709106445312,
      "step": 317000
    },
    {
      "epoch": 0.6927154017765714,
      "grad_norm": 0.20457300543785095,
      "learning_rate": 0.003,
      "loss": 3.1672207641601564,
      "step": 317100
    },
    {
      "epoch": 0.6929338550726221,
      "grad_norm": 0.2276708036661148,
      "learning_rate": 0.003,
      "loss": 3.172391662597656,
      "step": 317200
    },
    {
      "epoch": 0.6931523083686727,
      "grad_norm": 0.18610015511512756,
      "learning_rate": 0.003,
      "loss": 3.191929931640625,
      "step": 317300
    },
    {
      "epoch": 0.6933707616647233,
      "grad_norm": 0.22656722366809845,
      "learning_rate": 0.003,
      "loss": 3.145940856933594,
      "step": 317400
    },
    {
      "epoch": 0.693589214960774,
      "grad_norm": 0.20406396687030792,
      "learning_rate": 0.003,
      "loss": 3.184013671875,
      "step": 317500
    },
    {
      "epoch": 0.6938076682568246,
      "grad_norm": 0.2138676941394806,
      "learning_rate": 0.003,
      "loss": 3.170304870605469,
      "step": 317600
    },
    {
      "epoch": 0.6940261215528752,
      "grad_norm": 0.17452582716941833,
      "learning_rate": 0.003,
      "loss": 3.167100830078125,
      "step": 317700
    },
    {
      "epoch": 0.6942445748489259,
      "grad_norm": 0.20261573791503906,
      "learning_rate": 0.003,
      "loss": 3.1571185302734377,
      "step": 317800
    },
    {
      "epoch": 0.6944630281449765,
      "grad_norm": 0.17396317422389984,
      "learning_rate": 0.003,
      "loss": 3.1535577392578125,
      "step": 317900
    },
    {
      "epoch": 0.6946814814410271,
      "grad_norm": 0.2003057599067688,
      "learning_rate": 0.003,
      "loss": 3.1768923950195314,
      "step": 318000
    },
    {
      "epoch": 0.6948999347370778,
      "grad_norm": 0.1776229590177536,
      "learning_rate": 0.003,
      "loss": 3.188221435546875,
      "step": 318100
    },
    {
      "epoch": 0.6951183880331284,
      "grad_norm": 0.20265789330005646,
      "learning_rate": 0.003,
      "loss": 3.150877685546875,
      "step": 318200
    },
    {
      "epoch": 0.6953368413291791,
      "grad_norm": 0.2165839672088623,
      "learning_rate": 0.003,
      "loss": 3.1912600708007814,
      "step": 318300
    },
    {
      "epoch": 0.6955552946252297,
      "grad_norm": 0.27685219049453735,
      "learning_rate": 0.003,
      "loss": 3.1503460693359373,
      "step": 318400
    },
    {
      "epoch": 0.6957737479212803,
      "grad_norm": 0.20882809162139893,
      "learning_rate": 0.003,
      "loss": 3.170815734863281,
      "step": 318500
    },
    {
      "epoch": 0.695992201217331,
      "grad_norm": 0.18048788607120514,
      "learning_rate": 0.003,
      "loss": 3.1511822509765626,
      "step": 318600
    },
    {
      "epoch": 0.6962106545133816,
      "grad_norm": 0.17725111544132233,
      "learning_rate": 0.003,
      "loss": 3.1877651977539063,
      "step": 318700
    },
    {
      "epoch": 0.6964291078094322,
      "grad_norm": 0.2627936899662018,
      "learning_rate": 0.003,
      "loss": 3.19096435546875,
      "step": 318800
    },
    {
      "epoch": 0.6966475611054829,
      "grad_norm": 0.23302951455116272,
      "learning_rate": 0.003,
      "loss": 3.1538189697265624,
      "step": 318900
    },
    {
      "epoch": 0.6968660144015335,
      "grad_norm": 0.2152089923620224,
      "learning_rate": 0.003,
      "loss": 3.152620849609375,
      "step": 319000
    },
    {
      "epoch": 0.6970844676975841,
      "grad_norm": 0.17498676478862762,
      "learning_rate": 0.003,
      "loss": 3.183999328613281,
      "step": 319100
    },
    {
      "epoch": 0.6973029209936348,
      "grad_norm": 0.22293367981910706,
      "learning_rate": 0.003,
      "loss": 3.1645278930664062,
      "step": 319200
    },
    {
      "epoch": 0.6975213742896854,
      "grad_norm": 0.1807529777288437,
      "learning_rate": 0.003,
      "loss": 3.2114324951171875,
      "step": 319300
    },
    {
      "epoch": 0.697739827585736,
      "grad_norm": 0.19182415306568146,
      "learning_rate": 0.003,
      "loss": 3.200361633300781,
      "step": 319400
    },
    {
      "epoch": 0.6979582808817867,
      "grad_norm": 0.16125787794589996,
      "learning_rate": 0.003,
      "loss": 3.169613952636719,
      "step": 319500
    },
    {
      "epoch": 0.6981767341778373,
      "grad_norm": 0.22501985728740692,
      "learning_rate": 0.003,
      "loss": 3.1691400146484376,
      "step": 319600
    },
    {
      "epoch": 0.698395187473888,
      "grad_norm": 0.19499929249286652,
      "learning_rate": 0.003,
      "loss": 3.198096923828125,
      "step": 319700
    },
    {
      "epoch": 0.6986136407699386,
      "grad_norm": 0.1918955147266388,
      "learning_rate": 0.003,
      "loss": 3.188798828125,
      "step": 319800
    },
    {
      "epoch": 0.6988320940659892,
      "grad_norm": 0.16118286550045013,
      "learning_rate": 0.003,
      "loss": 3.201631774902344,
      "step": 319900
    },
    {
      "epoch": 0.6990505473620399,
      "grad_norm": 0.21022526919841766,
      "learning_rate": 0.003,
      "loss": 3.144825134277344,
      "step": 320000
    },
    {
      "epoch": 0.6992690006580905,
      "grad_norm": 0.22314117848873138,
      "learning_rate": 0.003,
      "loss": 3.191007385253906,
      "step": 320100
    },
    {
      "epoch": 0.6994874539541412,
      "grad_norm": 0.23611965775489807,
      "learning_rate": 0.003,
      "loss": 3.170477294921875,
      "step": 320200
    },
    {
      "epoch": 0.6997059072501919,
      "grad_norm": 0.2463647872209549,
      "learning_rate": 0.003,
      "loss": 3.1666204833984377,
      "step": 320300
    },
    {
      "epoch": 0.6999243605462425,
      "grad_norm": 0.2318897247314453,
      "learning_rate": 0.003,
      "loss": 3.2137435913085937,
      "step": 320400
    },
    {
      "epoch": 0.7001428138422932,
      "grad_norm": 0.22850576043128967,
      "learning_rate": 0.003,
      "loss": 3.1795953369140624,
      "step": 320500
    },
    {
      "epoch": 0.7003612671383438,
      "grad_norm": 0.22884884476661682,
      "learning_rate": 0.003,
      "loss": 3.162303466796875,
      "step": 320600
    },
    {
      "epoch": 0.7005797204343944,
      "grad_norm": 0.24036118388175964,
      "learning_rate": 0.003,
      "loss": 3.176139221191406,
      "step": 320700
    },
    {
      "epoch": 0.7007981737304451,
      "grad_norm": 0.22533559799194336,
      "learning_rate": 0.003,
      "loss": 3.19075439453125,
      "step": 320800
    },
    {
      "epoch": 0.7010166270264957,
      "grad_norm": 0.22212982177734375,
      "learning_rate": 0.003,
      "loss": 3.141514892578125,
      "step": 320900
    },
    {
      "epoch": 0.7012350803225463,
      "grad_norm": 0.39769884943962097,
      "learning_rate": 0.003,
      "loss": 3.169114685058594,
      "step": 321000
    }
  ],
  "logging_steps": 100,
  "max_steps": 457764,
  "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": 6.29100200853504e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}