{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5971397008330099,
  "eval_steps": 1000,
  "global_step": 20000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.9856985041650495e-05,
      "grad_norm": 8.064935684204102,
      "learning_rate": 0.0,
      "loss": 3.4849,
      "step": 1
    },
    {
      "epoch": 0.0014928492520825246,
      "grad_norm": 3.3433420658111572,
      "learning_rate": 0.00019998742849959144,
      "loss": 1.9038,
      "step": 50
    },
    {
      "epoch": 0.0029856985041650493,
      "grad_norm": 2.907883405685425,
      "learning_rate": 0.0001999731427036726,
      "loss": 1.608,
      "step": 100
    },
    {
      "epoch": 0.004478547756247574,
      "grad_norm": 3.2614288330078125,
      "learning_rate": 0.00019995885690775376,
      "loss": 1.5505,
      "step": 150
    },
    {
      "epoch": 0.005971397008330099,
      "grad_norm": 3.8400654792785645,
      "learning_rate": 0.00019994457111183493,
      "loss": 1.5737,
      "step": 200
    },
    {
      "epoch": 0.007464246260412624,
      "grad_norm": 3.3358442783355713,
      "learning_rate": 0.00019993028531591612,
      "loss": 1.567,
      "step": 250
    },
    {
      "epoch": 0.008957095512495149,
      "grad_norm": 2.131911277770996,
      "learning_rate": 0.00019991599951999726,
      "loss": 1.5208,
      "step": 300
    },
    {
      "epoch": 0.010449944764577673,
      "grad_norm": 3.180992364883423,
      "learning_rate": 0.00019990171372407845,
      "loss": 1.5586,
      "step": 350
    },
    {
      "epoch": 0.011942794016660197,
      "grad_norm": 3.024989128112793,
      "learning_rate": 0.0001998874279281596,
      "loss": 1.5267,
      "step": 400
    },
    {
      "epoch": 0.013435643268742723,
      "grad_norm": 3.4935102462768555,
      "learning_rate": 0.00019987314213224078,
      "loss": 1.5609,
      "step": 450
    },
    {
      "epoch": 0.014928492520825247,
      "grad_norm": 3.565504550933838,
      "learning_rate": 0.00019985885633632194,
      "loss": 1.5112,
      "step": 500
    },
    {
      "epoch": 0.01642134177290777,
      "grad_norm": 2.0692882537841797,
      "learning_rate": 0.00019984457054040308,
      "loss": 1.5087,
      "step": 550
    },
    {
      "epoch": 0.017914191024990297,
      "grad_norm": 4.110323905944824,
      "learning_rate": 0.00019983028474448427,
      "loss": 1.5073,
      "step": 600
    },
    {
      "epoch": 0.01940704027707282,
      "grad_norm": 2.8632736206054688,
      "learning_rate": 0.0001998159989485654,
      "loss": 1.472,
      "step": 650
    },
    {
      "epoch": 0.020899889529155346,
      "grad_norm": 2.629347324371338,
      "learning_rate": 0.0001998017131526466,
      "loss": 1.5236,
      "step": 700
    },
    {
      "epoch": 0.022392738781237872,
      "grad_norm": 3.696873188018799,
      "learning_rate": 0.00019978742735672774,
      "loss": 1.5216,
      "step": 750
    },
    {
      "epoch": 0.023885588033320394,
      "grad_norm": 3.253305435180664,
      "learning_rate": 0.00019977314156080893,
      "loss": 1.5915,
      "step": 800
    },
    {
      "epoch": 0.02537843728540292,
      "grad_norm": 2.9587886333465576,
      "learning_rate": 0.0001997588557648901,
      "loss": 1.4862,
      "step": 850
    },
    {
      "epoch": 0.026871286537485446,
      "grad_norm": 3.3311073780059814,
      "learning_rate": 0.00019974456996897126,
      "loss": 1.4703,
      "step": 900
    },
    {
      "epoch": 0.02836413578956797,
      "grad_norm": 2.5960264205932617,
      "learning_rate": 0.00019973028417305243,
      "loss": 1.4818,
      "step": 950
    },
    {
      "epoch": 0.029856985041650495,
      "grad_norm": 3.3142144680023193,
      "learning_rate": 0.0001997159983771336,
      "loss": 1.4746,
      "step": 1000
    },
    {
      "epoch": 0.03134983429373302,
      "grad_norm": 3.5049827098846436,
      "learning_rate": 0.00019970171258121476,
      "loss": 1.442,
      "step": 1050
    },
    {
      "epoch": 0.03284268354581554,
      "grad_norm": 3.0218605995178223,
      "learning_rate": 0.00019968742678529592,
      "loss": 1.5265,
      "step": 1100
    },
    {
      "epoch": 0.03433553279789807,
      "grad_norm": 2.936182975769043,
      "learning_rate": 0.00019967314098937709,
      "loss": 1.5174,
      "step": 1150
    },
    {
      "epoch": 0.035828382049980595,
      "grad_norm": 2.877253293991089,
      "learning_rate": 0.00019965885519345825,
      "loss": 1.4499,
      "step": 1200
    },
    {
      "epoch": 0.03732123130206312,
      "grad_norm": 6.07016658782959,
      "learning_rate": 0.00019964456939753941,
      "loss": 1.4542,
      "step": 1250
    },
    {
      "epoch": 0.03881408055414564,
      "grad_norm": 2.1618189811706543,
      "learning_rate": 0.0001996302836016206,
      "loss": 1.4343,
      "step": 1300
    },
    {
      "epoch": 0.040306929806228166,
      "grad_norm": 2.8267719745635986,
      "learning_rate": 0.00019961599780570174,
      "loss": 1.463,
      "step": 1350
    },
    {
      "epoch": 0.04179977905831069,
      "grad_norm": 2.6036462783813477,
      "learning_rate": 0.00019960171200978294,
      "loss": 1.4557,
      "step": 1400
    },
    {
      "epoch": 0.04329262831039322,
      "grad_norm": 3.0187127590179443,
      "learning_rate": 0.00019958742621386407,
      "loss": 1.4472,
      "step": 1450
    },
    {
      "epoch": 0.044785477562475744,
      "grad_norm": 3.9822633266448975,
      "learning_rate": 0.00019957314041794526,
      "loss": 1.4384,
      "step": 1500
    },
    {
      "epoch": 0.04627832681455826,
      "grad_norm": 2.919654607772827,
      "learning_rate": 0.0001995588546220264,
      "loss": 1.4969,
      "step": 1550
    },
    {
      "epoch": 0.04777117606664079,
      "grad_norm": 2.922963857650757,
      "learning_rate": 0.0001995445688261076,
      "loss": 1.4987,
      "step": 1600
    },
    {
      "epoch": 0.049264025318723315,
      "grad_norm": 2.9638512134552,
      "learning_rate": 0.00019953028303018876,
      "loss": 1.4722,
      "step": 1650
    },
    {
      "epoch": 0.05075687457080584,
      "grad_norm": 3.408391237258911,
      "learning_rate": 0.00019951599723426992,
      "loss": 1.4723,
      "step": 1700
    },
    {
      "epoch": 0.052249723822888366,
      "grad_norm": 3.023597240447998,
      "learning_rate": 0.0001995017114383511,
      "loss": 1.4478,
      "step": 1750
    },
    {
      "epoch": 0.05374257307497089,
      "grad_norm": 2.1655213832855225,
      "learning_rate": 0.00019948742564243225,
      "loss": 1.4071,
      "step": 1800
    },
    {
      "epoch": 0.05523542232705341,
      "grad_norm": 3.796663999557495,
      "learning_rate": 0.00019947313984651342,
      "loss": 1.446,
      "step": 1850
    },
    {
      "epoch": 0.05672827157913594,
      "grad_norm": 3.0415594577789307,
      "learning_rate": 0.00019945885405059458,
      "loss": 1.4324,
      "step": 1900
    },
    {
      "epoch": 0.05822112083121846,
      "grad_norm": 2.524627685546875,
      "learning_rate": 0.00019944456825467575,
      "loss": 1.3963,
      "step": 1950
    },
    {
      "epoch": 0.05971397008330099,
      "grad_norm": 3.2881991863250732,
      "learning_rate": 0.0001994302824587569,
      "loss": 1.4522,
      "step": 2000
    },
    {
      "epoch": 0.061206819335383515,
      "grad_norm": 3.392430067062378,
      "learning_rate": 0.00019941599666283808,
      "loss": 1.4329,
      "step": 2050
    },
    {
      "epoch": 0.06269966858746603,
      "grad_norm": 3.9426393508911133,
      "learning_rate": 0.00019940171086691927,
      "loss": 1.5203,
      "step": 2100
    },
    {
      "epoch": 0.06419251783954856,
      "grad_norm": 3.3737235069274902,
      "learning_rate": 0.0001993874250710004,
      "loss": 1.3674,
      "step": 2150
    },
    {
      "epoch": 0.06568536709163109,
      "grad_norm": 3.783085346221924,
      "learning_rate": 0.0001993731392750816,
      "loss": 1.4339,
      "step": 2200
    },
    {
      "epoch": 0.06717821634371361,
      "grad_norm": 3.4819202423095703,
      "learning_rate": 0.00019935885347916273,
      "loss": 1.4436,
      "step": 2250
    },
    {
      "epoch": 0.06867106559579614,
      "grad_norm": 3.141775608062744,
      "learning_rate": 0.00019934456768324393,
      "loss": 1.4683,
      "step": 2300
    },
    {
      "epoch": 0.07016391484787866,
      "grad_norm": 3.2881035804748535,
      "learning_rate": 0.00019933028188732506,
      "loss": 1.4395,
      "step": 2350
    },
    {
      "epoch": 0.07165676409996119,
      "grad_norm": 3.718122959136963,
      "learning_rate": 0.00019931599609140626,
      "loss": 1.4396,
      "step": 2400
    },
    {
      "epoch": 0.07314961335204372,
      "grad_norm": 4.3829474449157715,
      "learning_rate": 0.00019930171029548742,
      "loss": 1.4477,
      "step": 2450
    },
    {
      "epoch": 0.07464246260412624,
      "grad_norm": 3.3698525428771973,
      "learning_rate": 0.00019928742449956858,
      "loss": 1.3529,
      "step": 2500
    },
    {
      "epoch": 0.07613531185620875,
      "grad_norm": 3.7569565773010254,
      "learning_rate": 0.00019927313870364975,
      "loss": 1.4246,
      "step": 2550
    },
    {
      "epoch": 0.07762816110829128,
      "grad_norm": 3.1486406326293945,
      "learning_rate": 0.00019925885290773091,
      "loss": 1.3813,
      "step": 2600
    },
    {
      "epoch": 0.0791210103603738,
      "grad_norm": 4.0635480880737305,
      "learning_rate": 0.00019924456711181208,
      "loss": 1.4259,
      "step": 2650
    },
    {
      "epoch": 0.08061385961245633,
      "grad_norm": 3.2710611820220947,
      "learning_rate": 0.00019923028131589324,
      "loss": 1.3747,
      "step": 2700
    },
    {
      "epoch": 0.08210670886453886,
      "grad_norm": 3.4968345165252686,
      "learning_rate": 0.0001992159955199744,
      "loss": 1.4721,
      "step": 2750
    },
    {
      "epoch": 0.08359955811662138,
      "grad_norm": 4.274214267730713,
      "learning_rate": 0.00019920170972405557,
      "loss": 1.437,
      "step": 2800
    },
    {
      "epoch": 0.08509240736870391,
      "grad_norm": 2.970602512359619,
      "learning_rate": 0.00019918742392813674,
      "loss": 1.3336,
      "step": 2850
    },
    {
      "epoch": 0.08658525662078644,
      "grad_norm": 4.143342971801758,
      "learning_rate": 0.00019917313813221793,
      "loss": 1.4264,
      "step": 2900
    },
    {
      "epoch": 0.08807810587286896,
      "grad_norm": 3.7546920776367188,
      "learning_rate": 0.00019915885233629907,
      "loss": 1.441,
      "step": 2950
    },
    {
      "epoch": 0.08957095512495149,
      "grad_norm": 3.9160516262054443,
      "learning_rate": 0.00019914456654038026,
      "loss": 1.4261,
      "step": 3000
    },
    {
      "epoch": 0.09106380437703401,
      "grad_norm": 3.842073917388916,
      "learning_rate": 0.0001991302807444614,
      "loss": 1.4076,
      "step": 3050
    },
    {
      "epoch": 0.09255665362911653,
      "grad_norm": 4.392395496368408,
      "learning_rate": 0.0001991159949485426,
      "loss": 1.3789,
      "step": 3100
    },
    {
      "epoch": 0.09404950288119905,
      "grad_norm": 3.822425603866577,
      "learning_rate": 0.00019910170915262373,
      "loss": 1.3877,
      "step": 3150
    },
    {
      "epoch": 0.09554235213328158,
      "grad_norm": 3.1348562240600586,
      "learning_rate": 0.0001990874233567049,
      "loss": 1.4081,
      "step": 3200
    },
    {
      "epoch": 0.0970352013853641,
      "grad_norm": 3.453887939453125,
      "learning_rate": 0.00019907313756078608,
      "loss": 1.4143,
      "step": 3250
    },
    {
      "epoch": 0.09852805063744663,
      "grad_norm": 3.5057384967803955,
      "learning_rate": 0.00019905885176486722,
      "loss": 1.4264,
      "step": 3300
    },
    {
      "epoch": 0.10002089988952916,
      "grad_norm": 3.145796060562134,
      "learning_rate": 0.0001990445659689484,
      "loss": 1.4368,
      "step": 3350
    },
    {
      "epoch": 0.10151374914161168,
      "grad_norm": 3.4077043533325195,
      "learning_rate": 0.00019903028017302955,
      "loss": 1.388,
      "step": 3400
    },
    {
      "epoch": 0.10300659839369421,
      "grad_norm": 3.65567946434021,
      "learning_rate": 0.00019901599437711074,
      "loss": 1.42,
      "step": 3450
    },
    {
      "epoch": 0.10449944764577673,
      "grad_norm": 4.460702419281006,
      "learning_rate": 0.0001990017085811919,
      "loss": 1.3991,
      "step": 3500
    },
    {
      "epoch": 0.10599229689785926,
      "grad_norm": 4.155653476715088,
      "learning_rate": 0.00019898742278527307,
      "loss": 1.371,
      "step": 3550
    },
    {
      "epoch": 0.10748514614994178,
      "grad_norm": 3.8904318809509277,
      "learning_rate": 0.00019897313698935423,
      "loss": 1.4378,
      "step": 3600
    },
    {
      "epoch": 0.1089779954020243,
      "grad_norm": 4.0509233474731445,
      "learning_rate": 0.0001989588511934354,
      "loss": 1.3945,
      "step": 3650
    },
    {
      "epoch": 0.11047084465410682,
      "grad_norm": 3.785123109817505,
      "learning_rate": 0.00019894456539751656,
      "loss": 1.436,
      "step": 3700
    },
    {
      "epoch": 0.11196369390618935,
      "grad_norm": 3.4556167125701904,
      "learning_rate": 0.00019893027960159773,
      "loss": 1.3794,
      "step": 3750
    },
    {
      "epoch": 0.11345654315827187,
      "grad_norm": 4.0479559898376465,
      "learning_rate": 0.0001989159938056789,
      "loss": 1.4734,
      "step": 3800
    },
    {
      "epoch": 0.1149493924103544,
      "grad_norm": 3.890805721282959,
      "learning_rate": 0.00019890170800976006,
      "loss": 1.4341,
      "step": 3850
    },
    {
      "epoch": 0.11644224166243693,
      "grad_norm": 3.8178727626800537,
      "learning_rate": 0.00019888742221384122,
      "loss": 1.4754,
      "step": 3900
    },
    {
      "epoch": 0.11793509091451945,
      "grad_norm": 2.456165075302124,
      "learning_rate": 0.00019887313641792241,
      "loss": 1.3887,
      "step": 3950
    },
    {
      "epoch": 0.11942794016660198,
      "grad_norm": 3.5763051509857178,
      "learning_rate": 0.00019885885062200355,
      "loss": 1.3901,
      "step": 4000
    },
    {
      "epoch": 0.1209207894186845,
      "grad_norm": 3.885662317276001,
      "learning_rate": 0.00019884456482608474,
      "loss": 1.3856,
      "step": 4050
    },
    {
      "epoch": 0.12241363867076703,
      "grad_norm": 3.6095409393310547,
      "learning_rate": 0.00019883027903016588,
      "loss": 1.448,
      "step": 4100
    },
    {
      "epoch": 0.12390648792284956,
      "grad_norm": 3.7112534046173096,
      "learning_rate": 0.00019881599323424707,
      "loss": 1.3537,
      "step": 4150
    },
    {
      "epoch": 0.12539933717493207,
      "grad_norm": 3.3566672801971436,
      "learning_rate": 0.0001988017074383282,
      "loss": 1.4389,
      "step": 4200
    },
    {
      "epoch": 0.1268921864270146,
      "grad_norm": 4.570401191711426,
      "learning_rate": 0.0001987874216424094,
      "loss": 1.4191,
      "step": 4250
    },
    {
      "epoch": 0.12838503567909712,
      "grad_norm": 4.455029010772705,
      "learning_rate": 0.00019877313584649057,
      "loss": 1.3677,
      "step": 4300
    },
    {
      "epoch": 0.12987788493117966,
      "grad_norm": 3.0861828327178955,
      "learning_rate": 0.00019875885005057173,
      "loss": 1.3677,
      "step": 4350
    },
    {
      "epoch": 0.13137073418326217,
      "grad_norm": 4.419896602630615,
      "learning_rate": 0.0001987445642546529,
      "loss": 1.4524,
      "step": 4400
    },
    {
      "epoch": 0.1328635834353447,
      "grad_norm": 5.187576770782471,
      "learning_rate": 0.00019873027845873406,
      "loss": 1.3868,
      "step": 4450
    },
    {
      "epoch": 0.13435643268742722,
      "grad_norm": 5.111696243286133,
      "learning_rate": 0.00019871599266281523,
      "loss": 1.4458,
      "step": 4500
    },
    {
      "epoch": 0.13584928193950974,
      "grad_norm": 3.2652997970581055,
      "learning_rate": 0.0001987017068668964,
      "loss": 1.4529,
      "step": 4550
    },
    {
      "epoch": 0.13734213119159228,
      "grad_norm": 4.190273761749268,
      "learning_rate": 0.00019868742107097755,
      "loss": 1.3991,
      "step": 4600
    },
    {
      "epoch": 0.1388349804436748,
      "grad_norm": 4.85620641708374,
      "learning_rate": 0.00019867313527505872,
      "loss": 1.3916,
      "step": 4650
    },
    {
      "epoch": 0.14032782969575733,
      "grad_norm": 3.030954360961914,
      "learning_rate": 0.00019865884947913988,
      "loss": 1.3805,
      "step": 4700
    },
    {
      "epoch": 0.14182067894783984,
      "grad_norm": 3.264406681060791,
      "learning_rate": 0.00019864456368322108,
      "loss": 1.4048,
      "step": 4750
    },
    {
      "epoch": 0.14331352819992238,
      "grad_norm": 3.2138588428497314,
      "learning_rate": 0.0001986302778873022,
      "loss": 1.4092,
      "step": 4800
    },
    {
      "epoch": 0.1448063774520049,
      "grad_norm": 3.847222328186035,
      "learning_rate": 0.0001986159920913834,
      "loss": 1.3871,
      "step": 4850
    },
    {
      "epoch": 0.14629922670408743,
      "grad_norm": 4.004987716674805,
      "learning_rate": 0.00019860170629546454,
      "loss": 1.3845,
      "step": 4900
    },
    {
      "epoch": 0.14779207595616994,
      "grad_norm": 3.5088725090026855,
      "learning_rate": 0.00019858742049954573,
      "loss": 1.379,
      "step": 4950
    },
    {
      "epoch": 0.14928492520825248,
      "grad_norm": 3.275099277496338,
      "learning_rate": 0.00019857313470362687,
      "loss": 1.3628,
      "step": 5000
    },
    {
      "epoch": 0.150777774460335,
      "grad_norm": 3.7903060913085938,
      "learning_rate": 0.00019855884890770806,
      "loss": 1.3804,
      "step": 5050
    },
    {
      "epoch": 0.1522706237124175,
      "grad_norm": 4.294798374176025,
      "learning_rate": 0.00019854456311178923,
      "loss": 1.3988,
      "step": 5100
    },
    {
      "epoch": 0.15376347296450005,
      "grad_norm": 3.2719295024871826,
      "learning_rate": 0.0001985302773158704,
      "loss": 1.387,
      "step": 5150
    },
    {
      "epoch": 0.15525632221658256,
      "grad_norm": 4.143224239349365,
      "learning_rate": 0.00019851599151995156,
      "loss": 1.393,
      "step": 5200
    },
    {
      "epoch": 0.1567491714686651,
      "grad_norm": 3.404754638671875,
      "learning_rate": 0.00019850170572403272,
      "loss": 1.4205,
      "step": 5250
    },
    {
      "epoch": 0.1582420207207476,
      "grad_norm": 3.607126474380493,
      "learning_rate": 0.0001984874199281139,
      "loss": 1.4239,
      "step": 5300
    },
    {
      "epoch": 0.15973486997283015,
      "grad_norm": 4.140823841094971,
      "learning_rate": 0.00019847313413219505,
      "loss": 1.4204,
      "step": 5350
    },
    {
      "epoch": 0.16122771922491266,
      "grad_norm": 3.893251419067383,
      "learning_rate": 0.00019845884833627622,
      "loss": 1.392,
      "step": 5400
    },
    {
      "epoch": 0.1627205684769952,
      "grad_norm": 4.304211139678955,
      "learning_rate": 0.00019844456254035738,
      "loss": 1.44,
      "step": 5450
    },
    {
      "epoch": 0.16421341772907772,
      "grad_norm": 5.273501873016357,
      "learning_rate": 0.00019843027674443855,
      "loss": 1.445,
      "step": 5500
    },
    {
      "epoch": 0.16570626698116026,
      "grad_norm": 4.787700176239014,
      "learning_rate": 0.00019841599094851974,
      "loss": 1.3668,
      "step": 5550
    },
    {
      "epoch": 0.16719911623324277,
      "grad_norm": 3.7984108924865723,
      "learning_rate": 0.00019840170515260087,
      "loss": 1.3523,
      "step": 5600
    },
    {
      "epoch": 0.16869196548532528,
      "grad_norm": 3.885608673095703,
      "learning_rate": 0.00019838741935668207,
      "loss": 1.3917,
      "step": 5650
    },
    {
      "epoch": 0.17018481473740782,
      "grad_norm": 3.459803342819214,
      "learning_rate": 0.0001983731335607632,
      "loss": 1.3833,
      "step": 5700
    },
    {
      "epoch": 0.17167766398949033,
      "grad_norm": 3.7103006839752197,
      "learning_rate": 0.0001983588477648444,
      "loss": 1.4473,
      "step": 5750
    },
    {
      "epoch": 0.17317051324157287,
      "grad_norm": 6.645928382873535,
      "learning_rate": 0.00019834456196892553,
      "loss": 1.3706,
      "step": 5800
    },
    {
      "epoch": 0.17466336249365538,
      "grad_norm": 3.7201037406921387,
      "learning_rate": 0.0001983302761730067,
      "loss": 1.3733,
      "step": 5850
    },
    {
      "epoch": 0.17615621174573792,
      "grad_norm": 4.050106048583984,
      "learning_rate": 0.0001983159903770879,
      "loss": 1.4096,
      "step": 5900
    },
    {
      "epoch": 0.17764906099782043,
      "grad_norm": 4.190842628479004,
      "learning_rate": 0.00019830170458116903,
      "loss": 1.4404,
      "step": 5950
    },
    {
      "epoch": 0.17914191024990297,
      "grad_norm": 4.393162727355957,
      "learning_rate": 0.00019828741878525022,
      "loss": 1.4443,
      "step": 6000
    },
    {
      "epoch": 0.1806347595019855,
      "grad_norm": 3.597520351409912,
      "learning_rate": 0.00019827313298933136,
      "loss": 1.4063,
      "step": 6050
    },
    {
      "epoch": 0.18212760875406803,
      "grad_norm": 3.608085870742798,
      "learning_rate": 0.00019825884719341255,
      "loss": 1.3857,
      "step": 6100
    },
    {
      "epoch": 0.18362045800615054,
      "grad_norm": 3.7055492401123047,
      "learning_rate": 0.0001982445613974937,
      "loss": 1.3997,
      "step": 6150
    },
    {
      "epoch": 0.18511330725823305,
      "grad_norm": 3.875457763671875,
      "learning_rate": 0.00019823027560157488,
      "loss": 1.4296,
      "step": 6200
    },
    {
      "epoch": 0.1866061565103156,
      "grad_norm": 5.074592590332031,
      "learning_rate": 0.00019821598980565604,
      "loss": 1.3785,
      "step": 6250
    },
    {
      "epoch": 0.1880990057623981,
      "grad_norm": 6.013392448425293,
      "learning_rate": 0.0001982017040097372,
      "loss": 1.4391,
      "step": 6300
    },
    {
      "epoch": 0.18959185501448064,
      "grad_norm": 5.679958820343018,
      "learning_rate": 0.00019818741821381837,
      "loss": 1.367,
      "step": 6350
    },
    {
      "epoch": 0.19108470426656315,
      "grad_norm": 3.6182546615600586,
      "learning_rate": 0.00019817313241789954,
      "loss": 1.4508,
      "step": 6400
    },
    {
      "epoch": 0.1925775535186457,
      "grad_norm": 5.209213733673096,
      "learning_rate": 0.0001981588466219807,
      "loss": 1.3878,
      "step": 6450
    },
    {
      "epoch": 0.1940704027707282,
      "grad_norm": 3.0043230056762695,
      "learning_rate": 0.00019814456082606187,
      "loss": 1.4248,
      "step": 6500
    },
    {
      "epoch": 0.19556325202281075,
      "grad_norm": 3.157851219177246,
      "learning_rate": 0.00019813027503014303,
      "loss": 1.3725,
      "step": 6550
    },
    {
      "epoch": 0.19705610127489326,
      "grad_norm": 3.5292418003082275,
      "learning_rate": 0.0001981159892342242,
      "loss": 1.3932,
      "step": 6600
    },
    {
      "epoch": 0.1985489505269758,
      "grad_norm": 3.2819600105285645,
      "learning_rate": 0.00019810170343830536,
      "loss": 1.3495,
      "step": 6650
    },
    {
      "epoch": 0.2000417997790583,
      "grad_norm": 3.0243399143218994,
      "learning_rate": 0.00019808741764238655,
      "loss": 1.3689,
      "step": 6700
    },
    {
      "epoch": 0.20153464903114082,
      "grad_norm": 3.4495368003845215,
      "learning_rate": 0.0001980731318464677,
      "loss": 1.3725,
      "step": 6750
    },
    {
      "epoch": 0.20302749828322336,
      "grad_norm": 3.538259744644165,
      "learning_rate": 0.00019805884605054888,
      "loss": 1.3905,
      "step": 6800
    },
    {
      "epoch": 0.20452034753530587,
      "grad_norm": 4.162181377410889,
      "learning_rate": 0.00019804456025463002,
      "loss": 1.4129,
      "step": 6850
    },
    {
      "epoch": 0.20601319678738841,
      "grad_norm": 4.592432022094727,
      "learning_rate": 0.0001980302744587112,
      "loss": 1.3634,
      "step": 6900
    },
    {
      "epoch": 0.20750604603947093,
      "grad_norm": 3.45967960357666,
      "learning_rate": 0.00019801598866279237,
      "loss": 1.416,
      "step": 6950
    },
    {
      "epoch": 0.20899889529155347,
      "grad_norm": 4.221930503845215,
      "learning_rate": 0.00019800170286687354,
      "loss": 1.4051,
      "step": 7000
    },
    {
      "epoch": 0.21049174454363598,
      "grad_norm": 4.144239902496338,
      "learning_rate": 0.0001979874170709547,
      "loss": 1.4219,
      "step": 7050
    },
    {
      "epoch": 0.21198459379571852,
      "grad_norm": 4.7492570877075195,
      "learning_rate": 0.00019797313127503587,
      "loss": 1.4028,
      "step": 7100
    },
    {
      "epoch": 0.21347744304780103,
      "grad_norm": 3.5841355323791504,
      "learning_rate": 0.00019795884547911703,
      "loss": 1.4361,
      "step": 7150
    },
    {
      "epoch": 0.21497029229988357,
      "grad_norm": 4.662593364715576,
      "learning_rate": 0.0001979445596831982,
      "loss": 1.3816,
      "step": 7200
    },
    {
      "epoch": 0.21646314155196608,
      "grad_norm": 4.700701713562012,
      "learning_rate": 0.00019793027388727936,
      "loss": 1.4226,
      "step": 7250
    },
    {
      "epoch": 0.2179559908040486,
      "grad_norm": 4.025181293487549,
      "learning_rate": 0.00019791598809136053,
      "loss": 1.4291,
      "step": 7300
    },
    {
      "epoch": 0.21944884005613113,
      "grad_norm": 3.064573049545288,
      "learning_rate": 0.0001979017022954417,
      "loss": 1.4293,
      "step": 7350
    },
    {
      "epoch": 0.22094168930821365,
      "grad_norm": 6.342152118682861,
      "learning_rate": 0.00019788741649952288,
      "loss": 1.4173,
      "step": 7400
    },
    {
      "epoch": 0.22243453856029619,
      "grad_norm": 5.89996337890625,
      "learning_rate": 0.00019787313070360402,
      "loss": 1.396,
      "step": 7450
    },
    {
      "epoch": 0.2239273878123787,
      "grad_norm": 4.462945938110352,
      "learning_rate": 0.0001978588449076852,
      "loss": 1.3868,
      "step": 7500
    },
    {
      "epoch": 0.22542023706446124,
      "grad_norm": 3.6449055671691895,
      "learning_rate": 0.00019784455911176635,
      "loss": 1.396,
      "step": 7550
    },
    {
      "epoch": 0.22691308631654375,
      "grad_norm": 4.674243927001953,
      "learning_rate": 0.00019783027331584754,
      "loss": 1.395,
      "step": 7600
    },
    {
      "epoch": 0.2284059355686263,
      "grad_norm": 3.6160385608673096,
      "learning_rate": 0.00019781598751992868,
      "loss": 1.3918,
      "step": 7650
    },
    {
      "epoch": 0.2298987848207088,
      "grad_norm": 4.326193332672119,
      "learning_rate": 0.00019780170172400987,
      "loss": 1.3947,
      "step": 7700
    },
    {
      "epoch": 0.23139163407279134,
      "grad_norm": 5.4003777503967285,
      "learning_rate": 0.00019778741592809104,
      "loss": 1.344,
      "step": 7750
    },
    {
      "epoch": 0.23288448332487385,
      "grad_norm": 4.711580753326416,
      "learning_rate": 0.0001977731301321722,
      "loss": 1.3959,
      "step": 7800
    },
    {
      "epoch": 0.23437733257695637,
      "grad_norm": 3.4752814769744873,
      "learning_rate": 0.00019775884433625337,
      "loss": 1.3722,
      "step": 7850
    },
    {
      "epoch": 0.2358701818290389,
      "grad_norm": 4.028527736663818,
      "learning_rate": 0.00019774455854033453,
      "loss": 1.3683,
      "step": 7900
    },
    {
      "epoch": 0.23736303108112142,
      "grad_norm": 4.094334602355957,
      "learning_rate": 0.0001977302727444157,
      "loss": 1.3607,
      "step": 7950
    },
    {
      "epoch": 0.23885588033320396,
      "grad_norm": 5.232580661773682,
      "learning_rate": 0.00019771598694849686,
      "loss": 1.4354,
      "step": 8000
    },
    {
      "epoch": 0.24034872958528647,
      "grad_norm": 4.269852161407471,
      "learning_rate": 0.00019770170115257802,
      "loss": 1.4372,
      "step": 8050
    },
    {
      "epoch": 0.241841578837369,
      "grad_norm": 3.312541961669922,
      "learning_rate": 0.0001976874153566592,
      "loss": 1.3826,
      "step": 8100
    },
    {
      "epoch": 0.24333442808945152,
      "grad_norm": 3.8900692462921143,
      "learning_rate": 0.00019767312956074035,
      "loss": 1.4189,
      "step": 8150
    },
    {
      "epoch": 0.24482727734153406,
      "grad_norm": 3.894512414932251,
      "learning_rate": 0.00019765884376482155,
      "loss": 1.3365,
      "step": 8200
    },
    {
      "epoch": 0.24632012659361657,
      "grad_norm": 4.644411563873291,
      "learning_rate": 0.00019764455796890268,
      "loss": 1.4311,
      "step": 8250
    },
    {
      "epoch": 0.2478129758456991,
      "grad_norm": 8.174029350280762,
      "learning_rate": 0.00019763027217298387,
      "loss": 1.361,
      "step": 8300
    },
    {
      "epoch": 0.24930582509778162,
      "grad_norm": 4.615732192993164,
      "learning_rate": 0.000197615986377065,
      "loss": 1.4552,
      "step": 8350
    },
    {
      "epoch": 0.25079867434986414,
      "grad_norm": 4.421249866485596,
      "learning_rate": 0.0001976017005811462,
      "loss": 1.3463,
      "step": 8400
    },
    {
      "epoch": 0.2522915236019467,
      "grad_norm": 2.8386716842651367,
      "learning_rate": 0.00019758741478522734,
      "loss": 1.348,
      "step": 8450
    },
    {
      "epoch": 0.2537843728540292,
      "grad_norm": 4.3141703605651855,
      "learning_rate": 0.0001975731289893085,
      "loss": 1.4306,
      "step": 8500
    },
    {
      "epoch": 0.2552772221061117,
      "grad_norm": 3.947331428527832,
      "learning_rate": 0.0001975588431933897,
      "loss": 1.3823,
      "step": 8550
    },
    {
      "epoch": 0.25677007135819424,
      "grad_norm": 3.2268636226654053,
      "learning_rate": 0.00019754455739747084,
      "loss": 1.4199,
      "step": 8600
    },
    {
      "epoch": 0.2582629206102768,
      "grad_norm": 4.0353102684021,
      "learning_rate": 0.00019753027160155203,
      "loss": 1.3927,
      "step": 8650
    },
    {
      "epoch": 0.2597557698623593,
      "grad_norm": 3.490560293197632,
      "learning_rate": 0.00019751598580563316,
      "loss": 1.401,
      "step": 8700
    },
    {
      "epoch": 0.2612486191144418,
      "grad_norm": 5.577207088470459,
      "learning_rate": 0.00019750170000971436,
      "loss": 1.3586,
      "step": 8750
    },
    {
      "epoch": 0.26274146836652434,
      "grad_norm": 4.168467998504639,
      "learning_rate": 0.0001974874142137955,
      "loss": 1.3303,
      "step": 8800
    },
    {
      "epoch": 0.2642343176186069,
      "grad_norm": 3.812627077102661,
      "learning_rate": 0.00019747312841787669,
      "loss": 1.3717,
      "step": 8850
    },
    {
      "epoch": 0.2657271668706894,
      "grad_norm": 4.875237464904785,
      "learning_rate": 0.00019745884262195785,
      "loss": 1.3873,
      "step": 8900
    },
    {
      "epoch": 0.2672200161227719,
      "grad_norm": 4.048189163208008,
      "learning_rate": 0.00019744455682603902,
      "loss": 1.3775,
      "step": 8950
    },
    {
      "epoch": 0.26871286537485445,
      "grad_norm": 3.9090261459350586,
      "learning_rate": 0.00019743027103012018,
      "loss": 1.4296,
      "step": 9000
    },
    {
      "epoch": 0.270205714626937,
      "grad_norm": 2.8476953506469727,
      "learning_rate": 0.00019741598523420134,
      "loss": 1.4175,
      "step": 9050
    },
    {
      "epoch": 0.2716985638790195,
      "grad_norm": 5.782102584838867,
      "learning_rate": 0.0001974016994382825,
      "loss": 1.3835,
      "step": 9100
    },
    {
      "epoch": 0.273191413131102,
      "grad_norm": 4.640264987945557,
      "learning_rate": 0.00019738741364236367,
      "loss": 1.4524,
      "step": 9150
    },
    {
      "epoch": 0.27468426238318455,
      "grad_norm": 4.81790828704834,
      "learning_rate": 0.00019737312784644484,
      "loss": 1.3183,
      "step": 9200
    },
    {
      "epoch": 0.2761771116352671,
      "grad_norm": 2.685009717941284,
      "learning_rate": 0.000197358842050526,
      "loss": 1.3243,
      "step": 9250
    },
    {
      "epoch": 0.2776699608873496,
      "grad_norm": 5.321321487426758,
      "learning_rate": 0.00019734455625460717,
      "loss": 1.4086,
      "step": 9300
    },
    {
      "epoch": 0.2791628101394321,
      "grad_norm": 3.065791368484497,
      "learning_rate": 0.00019733027045868836,
      "loss": 1.337,
      "step": 9350
    },
    {
      "epoch": 0.28065565939151466,
      "grad_norm": 4.3569817543029785,
      "learning_rate": 0.0001973159846627695,
      "loss": 1.4082,
      "step": 9400
    },
    {
      "epoch": 0.2821485086435972,
      "grad_norm": 4.67582368850708,
      "learning_rate": 0.0001973016988668507,
      "loss": 1.3832,
      "step": 9450
    },
    {
      "epoch": 0.2836413578956797,
      "grad_norm": 4.942144870758057,
      "learning_rate": 0.00019728741307093183,
      "loss": 1.3734,
      "step": 9500
    },
    {
      "epoch": 0.2851342071477622,
      "grad_norm": 4.853246688842773,
      "learning_rate": 0.00019727312727501302,
      "loss": 1.4111,
      "step": 9550
    },
    {
      "epoch": 0.28662705639984476,
      "grad_norm": 3.071237325668335,
      "learning_rate": 0.00019725884147909418,
      "loss": 1.3746,
      "step": 9600
    },
    {
      "epoch": 0.28811990565192724,
      "grad_norm": 4.844615459442139,
      "learning_rate": 0.00019724455568317535,
      "loss": 1.3051,
      "step": 9650
    },
    {
      "epoch": 0.2896127549040098,
      "grad_norm": 5.954223155975342,
      "learning_rate": 0.0001972302698872565,
      "loss": 1.4131,
      "step": 9700
    },
    {
      "epoch": 0.2911056041560923,
      "grad_norm": 3.6717801094055176,
      "learning_rate": 0.00019721598409133768,
      "loss": 1.4166,
      "step": 9750
    },
    {
      "epoch": 0.29259845340817486,
      "grad_norm": 3.6257095336914062,
      "learning_rate": 0.00019720169829541884,
      "loss": 1.3679,
      "step": 9800
    },
    {
      "epoch": 0.29409130266025735,
      "grad_norm": 4.245635032653809,
      "learning_rate": 0.0001971874124995,
      "loss": 1.3171,
      "step": 9850
    },
    {
      "epoch": 0.2955841519123399,
      "grad_norm": 5.362602710723877,
      "learning_rate": 0.00019717312670358117,
      "loss": 1.3932,
      "step": 9900
    },
    {
      "epoch": 0.2970770011644224,
      "grad_norm": 4.6283721923828125,
      "learning_rate": 0.00019715884090766234,
      "loss": 1.3757,
      "step": 9950
    },
    {
      "epoch": 0.29856985041650497,
      "grad_norm": 4.299574851989746,
      "learning_rate": 0.0001971445551117435,
      "loss": 1.4018,
      "step": 10000
    },
    {
      "epoch": 0.30006269966858745,
      "grad_norm": 4.7913641929626465,
      "learning_rate": 0.0001971302693158247,
      "loss": 1.4228,
      "step": 10050
    },
    {
      "epoch": 0.30155554892067,
      "grad_norm": 5.312823295593262,
      "learning_rate": 0.00019711598351990583,
      "loss": 1.3866,
      "step": 10100
    },
    {
      "epoch": 0.30304839817275253,
      "grad_norm": 4.099662780761719,
      "learning_rate": 0.00019710169772398702,
      "loss": 1.454,
      "step": 10150
    },
    {
      "epoch": 0.304541247424835,
      "grad_norm": 4.254878520965576,
      "learning_rate": 0.00019708741192806816,
      "loss": 1.3526,
      "step": 10200
    },
    {
      "epoch": 0.30603409667691756,
      "grad_norm": 4.056606292724609,
      "learning_rate": 0.00019707312613214935,
      "loss": 1.4167,
      "step": 10250
    },
    {
      "epoch": 0.3075269459290001,
      "grad_norm": 3.790809154510498,
      "learning_rate": 0.0001970588403362305,
      "loss": 1.3536,
      "step": 10300
    },
    {
      "epoch": 0.30901979518108263,
      "grad_norm": 4.46298360824585,
      "learning_rate": 0.00019704455454031168,
      "loss": 1.3613,
      "step": 10350
    },
    {
      "epoch": 0.3105126444331651,
      "grad_norm": 4.52452278137207,
      "learning_rate": 0.00019703026874439284,
      "loss": 1.4591,
      "step": 10400
    },
    {
      "epoch": 0.31200549368524766,
      "grad_norm": 4.735177040100098,
      "learning_rate": 0.000197015982948474,
      "loss": 1.4617,
      "step": 10450
    },
    {
      "epoch": 0.3134983429373302,
      "grad_norm": 4.48261833190918,
      "learning_rate": 0.00019700169715255517,
      "loss": 1.4072,
      "step": 10500
    },
    {
      "epoch": 0.31499119218941274,
      "grad_norm": 3.3441503047943115,
      "learning_rate": 0.00019698741135663634,
      "loss": 1.4082,
      "step": 10550
    },
    {
      "epoch": 0.3164840414414952,
      "grad_norm": 3.9771218299865723,
      "learning_rate": 0.0001969731255607175,
      "loss": 1.4184,
      "step": 10600
    },
    {
      "epoch": 0.31797689069357776,
      "grad_norm": 6.366194725036621,
      "learning_rate": 0.00019695883976479867,
      "loss": 1.387,
      "step": 10650
    },
    {
      "epoch": 0.3194697399456603,
      "grad_norm": 5.072678089141846,
      "learning_rate": 0.00019694455396887983,
      "loss": 1.3996,
      "step": 10700
    },
    {
      "epoch": 0.3209625891977428,
      "grad_norm": 3.7204978466033936,
      "learning_rate": 0.000196930268172961,
      "loss": 1.3774,
      "step": 10750
    },
    {
      "epoch": 0.3224554384498253,
      "grad_norm": 4.47731351852417,
      "learning_rate": 0.00019691598237704216,
      "loss": 1.3552,
      "step": 10800
    },
    {
      "epoch": 0.32394828770190787,
      "grad_norm": 3.4569220542907715,
      "learning_rate": 0.00019690169658112335,
      "loss": 1.3794,
      "step": 10850
    },
    {
      "epoch": 0.3254411369539904,
      "grad_norm": 4.344145774841309,
      "learning_rate": 0.0001968874107852045,
      "loss": 1.4419,
      "step": 10900
    },
    {
      "epoch": 0.3269339862060729,
      "grad_norm": 4.089848041534424,
      "learning_rate": 0.00019687312498928568,
      "loss": 1.4116,
      "step": 10950
    },
    {
      "epoch": 0.32842683545815543,
      "grad_norm": 3.995945930480957,
      "learning_rate": 0.00019685883919336682,
      "loss": 1.3532,
      "step": 11000
    },
    {
      "epoch": 0.32991968471023797,
      "grad_norm": 3.8309378623962402,
      "learning_rate": 0.00019684455339744798,
      "loss": 1.3957,
      "step": 11050
    },
    {
      "epoch": 0.3314125339623205,
      "grad_norm": 4.386235237121582,
      "learning_rate": 0.00019683026760152915,
      "loss": 1.3616,
      "step": 11100
    },
    {
      "epoch": 0.332905383214403,
      "grad_norm": 5.133239269256592,
      "learning_rate": 0.00019681598180561031,
      "loss": 1.3959,
      "step": 11150
    },
    {
      "epoch": 0.33439823246648553,
      "grad_norm": 4.216183662414551,
      "learning_rate": 0.0001968016960096915,
      "loss": 1.3446,
      "step": 11200
    },
    {
      "epoch": 0.3358910817185681,
      "grad_norm": 3.631131172180176,
      "learning_rate": 0.00019678741021377264,
      "loss": 1.3779,
      "step": 11250
    },
    {
      "epoch": 0.33738393097065056,
      "grad_norm": 4.603448390960693,
      "learning_rate": 0.00019677312441785384,
      "loss": 1.3962,
      "step": 11300
    },
    {
      "epoch": 0.3388767802227331,
      "grad_norm": 3.6482913494110107,
      "learning_rate": 0.00019675883862193497,
      "loss": 1.3931,
      "step": 11350
    },
    {
      "epoch": 0.34036962947481564,
      "grad_norm": 5.040388107299805,
      "learning_rate": 0.00019674455282601616,
      "loss": 1.3465,
      "step": 11400
    },
    {
      "epoch": 0.3418624787268982,
      "grad_norm": 5.762825012207031,
      "learning_rate": 0.0001967302670300973,
      "loss": 1.3577,
      "step": 11450
    },
    {
      "epoch": 0.34335532797898066,
      "grad_norm": 4.941501617431641,
      "learning_rate": 0.0001967159812341785,
      "loss": 1.3676,
      "step": 11500
    },
    {
      "epoch": 0.3448481772310632,
      "grad_norm": 5.368370532989502,
      "learning_rate": 0.00019670169543825966,
      "loss": 1.4265,
      "step": 11550
    },
    {
      "epoch": 0.34634102648314574,
      "grad_norm": 4.931522369384766,
      "learning_rate": 0.00019668740964234082,
      "loss": 1.3551,
      "step": 11600
    },
    {
      "epoch": 0.3478338757352283,
      "grad_norm": 3.9685990810394287,
      "learning_rate": 0.000196673123846422,
      "loss": 1.402,
      "step": 11650
    },
    {
      "epoch": 0.34932672498731077,
      "grad_norm": 5.771200656890869,
      "learning_rate": 0.00019665883805050315,
      "loss": 1.3596,
      "step": 11700
    },
    {
      "epoch": 0.3508195742393933,
      "grad_norm": 5.142852306365967,
      "learning_rate": 0.00019664455225458432,
      "loss": 1.385,
      "step": 11750
    },
    {
      "epoch": 0.35231242349147585,
      "grad_norm": 3.295628786087036,
      "learning_rate": 0.00019663026645866548,
      "loss": 1.3454,
      "step": 11800
    },
    {
      "epoch": 0.35380527274355833,
      "grad_norm": 4.34658145904541,
      "learning_rate": 0.00019661598066274665,
      "loss": 1.3976,
      "step": 11850
    },
    {
      "epoch": 0.35529812199564087,
      "grad_norm": 4.032591819763184,
      "learning_rate": 0.0001966016948668278,
      "loss": 1.3571,
      "step": 11900
    },
    {
      "epoch": 0.3567909712477234,
      "grad_norm": 3.9286158084869385,
      "learning_rate": 0.00019658740907090898,
      "loss": 1.398,
      "step": 11950
    },
    {
      "epoch": 0.35828382049980595,
      "grad_norm": 5.184597492218018,
      "learning_rate": 0.00019657312327499017,
      "loss": 1.3827,
      "step": 12000
    },
    {
      "epoch": 0.35977666975188843,
      "grad_norm": 4.4749226570129395,
      "learning_rate": 0.0001965588374790713,
      "loss": 1.373,
      "step": 12050
    },
    {
      "epoch": 0.361269519003971,
      "grad_norm": 3.5633764266967773,
      "learning_rate": 0.0001965445516831525,
      "loss": 1.3704,
      "step": 12100
    },
    {
      "epoch": 0.3627623682560535,
      "grad_norm": 7.570897102355957,
      "learning_rate": 0.00019653026588723363,
      "loss": 1.3515,
      "step": 12150
    },
    {
      "epoch": 0.36425521750813605,
      "grad_norm": 4.239411354064941,
      "learning_rate": 0.00019651598009131483,
      "loss": 1.3813,
      "step": 12200
    },
    {
      "epoch": 0.36574806676021854,
      "grad_norm": 3.8941049575805664,
      "learning_rate": 0.00019650169429539596,
      "loss": 1.3954,
      "step": 12250
    },
    {
      "epoch": 0.3672409160123011,
      "grad_norm": 4.8694586753845215,
      "learning_rate": 0.00019648740849947716,
      "loss": 1.3531,
      "step": 12300
    },
    {
      "epoch": 0.3687337652643836,
      "grad_norm": 3.914964437484741,
      "learning_rate": 0.00019647312270355832,
      "loss": 1.3954,
      "step": 12350
    },
    {
      "epoch": 0.3702266145164661,
      "grad_norm": 3.4050538539886475,
      "learning_rate": 0.00019645883690763948,
      "loss": 1.3498,
      "step": 12400
    },
    {
      "epoch": 0.37171946376854864,
      "grad_norm": 4.436797618865967,
      "learning_rate": 0.00019644455111172065,
      "loss": 1.3889,
      "step": 12450
    },
    {
      "epoch": 0.3732123130206312,
      "grad_norm": 2.7660670280456543,
      "learning_rate": 0.00019643026531580181,
      "loss": 1.3392,
      "step": 12500
    },
    {
      "epoch": 0.3747051622727137,
      "grad_norm": 5.364072799682617,
      "learning_rate": 0.00019641597951988298,
      "loss": 1.3157,
      "step": 12550
    },
    {
      "epoch": 0.3761980115247962,
      "grad_norm": 5.123339653015137,
      "learning_rate": 0.00019640169372396414,
      "loss": 1.3523,
      "step": 12600
    },
    {
      "epoch": 0.37769086077687875,
      "grad_norm": 3.4495439529418945,
      "learning_rate": 0.0001963874079280453,
      "loss": 1.3331,
      "step": 12650
    },
    {
      "epoch": 0.3791837100289613,
      "grad_norm": 4.613680362701416,
      "learning_rate": 0.00019637312213212647,
      "loss": 1.3707,
      "step": 12700
    },
    {
      "epoch": 0.3806765592810438,
      "grad_norm": 3.5819404125213623,
      "learning_rate": 0.00019635883633620764,
      "loss": 1.4023,
      "step": 12750
    },
    {
      "epoch": 0.3821694085331263,
      "grad_norm": 3.5075576305389404,
      "learning_rate": 0.00019634455054028883,
      "loss": 1.3815,
      "step": 12800
    },
    {
      "epoch": 0.38366225778520885,
      "grad_norm": 4.425256729125977,
      "learning_rate": 0.00019633026474436997,
      "loss": 1.3801,
      "step": 12850
    },
    {
      "epoch": 0.3851551070372914,
      "grad_norm": 3.5711112022399902,
      "learning_rate": 0.00019631597894845116,
      "loss": 1.3375,
      "step": 12900
    },
    {
      "epoch": 0.3866479562893739,
      "grad_norm": 5.728016376495361,
      "learning_rate": 0.0001963016931525323,
      "loss": 1.3914,
      "step": 12950
    },
    {
      "epoch": 0.3881408055414564,
      "grad_norm": 4.294504642486572,
      "learning_rate": 0.0001962874073566135,
      "loss": 1.4561,
      "step": 13000
    },
    {
      "epoch": 0.38963365479353895,
      "grad_norm": 5.329941749572754,
      "learning_rate": 0.00019627312156069465,
      "loss": 1.4018,
      "step": 13050
    },
    {
      "epoch": 0.3911265040456215,
      "grad_norm": 4.166362762451172,
      "learning_rate": 0.00019625883576477582,
      "loss": 1.4334,
      "step": 13100
    },
    {
      "epoch": 0.392619353297704,
      "grad_norm": 3.3922691345214844,
      "learning_rate": 0.00019624454996885698,
      "loss": 1.3956,
      "step": 13150
    },
    {
      "epoch": 0.3941122025497865,
      "grad_norm": 4.340898036956787,
      "learning_rate": 0.00019623026417293815,
      "loss": 1.3643,
      "step": 13200
    },
    {
      "epoch": 0.39560505180186906,
      "grad_norm": 6.623823165893555,
      "learning_rate": 0.0001962159783770193,
      "loss": 1.362,
      "step": 13250
    },
    {
      "epoch": 0.3970979010539516,
      "grad_norm": 4.490639686584473,
      "learning_rate": 0.00019620169258110048,
      "loss": 1.3742,
      "step": 13300
    },
    {
      "epoch": 0.3985907503060341,
      "grad_norm": 4.179808139801025,
      "learning_rate": 0.00019618740678518164,
      "loss": 1.4191,
      "step": 13350
    },
    {
      "epoch": 0.4000835995581166,
      "grad_norm": 5.623187065124512,
      "learning_rate": 0.0001961731209892628,
      "loss": 1.3793,
      "step": 13400
    },
    {
      "epoch": 0.40157644881019916,
      "grad_norm": 3.9650678634643555,
      "learning_rate": 0.00019615883519334397,
      "loss": 1.3917,
      "step": 13450
    },
    {
      "epoch": 0.40306929806228164,
      "grad_norm": 5.047702312469482,
      "learning_rate": 0.00019614454939742516,
      "loss": 1.4501,
      "step": 13500
    },
    {
      "epoch": 0.4045621473143642,
      "grad_norm": 3.46647310256958,
      "learning_rate": 0.0001961302636015063,
      "loss": 1.4091,
      "step": 13550
    },
    {
      "epoch": 0.4060549965664467,
      "grad_norm": 3.2203481197357178,
      "learning_rate": 0.0001961159778055875,
      "loss": 1.4003,
      "step": 13600
    },
    {
      "epoch": 0.40754784581852926,
      "grad_norm": 3.727679967880249,
      "learning_rate": 0.00019610169200966863,
      "loss": 1.4004,
      "step": 13650
    },
    {
      "epoch": 0.40904069507061175,
      "grad_norm": 4.469257831573486,
      "learning_rate": 0.0001960874062137498,
      "loss": 1.4061,
      "step": 13700
    },
    {
      "epoch": 0.4105335443226943,
      "grad_norm": 4.041538715362549,
      "learning_rate": 0.00019607312041783096,
      "loss": 1.411,
      "step": 13750
    },
    {
      "epoch": 0.41202639357477683,
      "grad_norm": 5.2691779136657715,
      "learning_rate": 0.00019605883462191212,
      "loss": 1.3396,
      "step": 13800
    },
    {
      "epoch": 0.41351924282685937,
      "grad_norm": 6.236726760864258,
      "learning_rate": 0.00019604454882599331,
      "loss": 1.4295,
      "step": 13850
    },
    {
      "epoch": 0.41501209207894185,
      "grad_norm": 6.703745365142822,
      "learning_rate": 0.00019603026303007445,
      "loss": 1.4105,
      "step": 13900
    },
    {
      "epoch": 0.4165049413310244,
      "grad_norm": 3.997664451599121,
      "learning_rate": 0.00019601597723415564,
      "loss": 1.347,
      "step": 13950
    },
    {
      "epoch": 0.41799779058310693,
      "grad_norm": 5.311407566070557,
      "learning_rate": 0.00019600169143823678,
      "loss": 1.4546,
      "step": 14000
    },
    {
      "epoch": 0.4194906398351894,
      "grad_norm": 4.0283098220825195,
      "learning_rate": 0.00019598740564231797,
      "loss": 1.4513,
      "step": 14050
    },
    {
      "epoch": 0.42098348908727196,
      "grad_norm": 7.345764636993408,
      "learning_rate": 0.0001959731198463991,
      "loss": 1.3832,
      "step": 14100
    },
    {
      "epoch": 0.4224763383393545,
      "grad_norm": 4.324542045593262,
      "learning_rate": 0.0001959588340504803,
      "loss": 1.3751,
      "step": 14150
    },
    {
      "epoch": 0.42396918759143704,
      "grad_norm": 3.8322675228118896,
      "learning_rate": 0.00019594454825456147,
      "loss": 1.344,
      "step": 14200
    },
    {
      "epoch": 0.4254620368435195,
      "grad_norm": 4.62548303604126,
      "learning_rate": 0.00019593026245864263,
      "loss": 1.4346,
      "step": 14250
    },
    {
      "epoch": 0.42695488609560206,
      "grad_norm": 4.585489273071289,
      "learning_rate": 0.0001959159766627238,
      "loss": 1.4145,
      "step": 14300
    },
    {
      "epoch": 0.4284477353476846,
      "grad_norm": 3.64227557182312,
      "learning_rate": 0.00019590169086680496,
      "loss": 1.367,
      "step": 14350
    },
    {
      "epoch": 0.42994058459976714,
      "grad_norm": 4.730580806732178,
      "learning_rate": 0.00019588740507088613,
      "loss": 1.3653,
      "step": 14400
    },
    {
      "epoch": 0.4314334338518496,
      "grad_norm": 4.4075398445129395,
      "learning_rate": 0.0001958731192749673,
      "loss": 1.4081,
      "step": 14450
    },
    {
      "epoch": 0.43292628310393216,
      "grad_norm": 3.0498785972595215,
      "learning_rate": 0.00019585883347904845,
      "loss": 1.343,
      "step": 14500
    },
    {
      "epoch": 0.4344191323560147,
      "grad_norm": 4.179199695587158,
      "learning_rate": 0.00019584454768312962,
      "loss": 1.3662,
      "step": 14550
    },
    {
      "epoch": 0.4359119816080972,
      "grad_norm": 4.1148786544799805,
      "learning_rate": 0.00019583026188721078,
      "loss": 1.3785,
      "step": 14600
    },
    {
      "epoch": 0.4374048308601797,
      "grad_norm": 4.012060165405273,
      "learning_rate": 0.00019581597609129198,
      "loss": 1.4056,
      "step": 14650
    },
    {
      "epoch": 0.43889768011226227,
      "grad_norm": 7.186342716217041,
      "learning_rate": 0.0001958016902953731,
      "loss": 1.3943,
      "step": 14700
    },
    {
      "epoch": 0.4403905293643448,
      "grad_norm": 3.951267957687378,
      "learning_rate": 0.0001957874044994543,
      "loss": 1.3976,
      "step": 14750
    },
    {
      "epoch": 0.4418833786164273,
      "grad_norm": 5.276801586151123,
      "learning_rate": 0.00019577311870353544,
      "loss": 1.4137,
      "step": 14800
    },
    {
      "epoch": 0.44337622786850983,
      "grad_norm": 4.107429504394531,
      "learning_rate": 0.00019575883290761663,
      "loss": 1.388,
      "step": 14850
    },
    {
      "epoch": 0.44486907712059237,
      "grad_norm": 4.274941444396973,
      "learning_rate": 0.00019574454711169777,
      "loss": 1.3446,
      "step": 14900
    },
    {
      "epoch": 0.4463619263726749,
      "grad_norm": 4.174200534820557,
      "learning_rate": 0.00019573026131577896,
      "loss": 1.3703,
      "step": 14950
    },
    {
      "epoch": 0.4478547756247574,
      "grad_norm": 3.867125988006592,
      "learning_rate": 0.00019571597551986013,
      "loss": 1.3745,
      "step": 15000
    },
    {
      "epoch": 0.44934762487683994,
      "grad_norm": 6.454402923583984,
      "learning_rate": 0.0001957016897239413,
      "loss": 1.3081,
      "step": 15050
    },
    {
      "epoch": 0.4508404741289225,
      "grad_norm": 3.8726885318756104,
      "learning_rate": 0.00019568740392802246,
      "loss": 1.3527,
      "step": 15100
    },
    {
      "epoch": 0.45233332338100496,
      "grad_norm": 3.6218361854553223,
      "learning_rate": 0.00019567311813210362,
      "loss": 1.4549,
      "step": 15150
    },
    {
      "epoch": 0.4538261726330875,
      "grad_norm": 5.2475361824035645,
      "learning_rate": 0.0001956588323361848,
      "loss": 1.361,
      "step": 15200
    },
    {
      "epoch": 0.45531902188517004,
      "grad_norm": 4.388748645782471,
      "learning_rate": 0.00019564454654026595,
      "loss": 1.3164,
      "step": 15250
    },
    {
      "epoch": 0.4568118711372526,
      "grad_norm": 4.97973108291626,
      "learning_rate": 0.00019563026074434712,
      "loss": 1.3755,
      "step": 15300
    },
    {
      "epoch": 0.45830472038933506,
      "grad_norm": 4.538138389587402,
      "learning_rate": 0.00019561597494842828,
      "loss": 1.4339,
      "step": 15350
    },
    {
      "epoch": 0.4597975696414176,
      "grad_norm": 4.389719009399414,
      "learning_rate": 0.00019560168915250945,
      "loss": 1.4163,
      "step": 15400
    },
    {
      "epoch": 0.46129041889350014,
      "grad_norm": 4.347919464111328,
      "learning_rate": 0.00019558740335659064,
      "loss": 1.3663,
      "step": 15450
    },
    {
      "epoch": 0.4627832681455827,
      "grad_norm": 4.820595741271973,
      "learning_rate": 0.00019557311756067177,
      "loss": 1.3441,
      "step": 15500
    },
    {
      "epoch": 0.46427611739766517,
      "grad_norm": 2.6965413093566895,
      "learning_rate": 0.00019555883176475297,
      "loss": 1.3657,
      "step": 15550
    },
    {
      "epoch": 0.4657689666497477,
      "grad_norm": 4.741116523742676,
      "learning_rate": 0.0001955445459688341,
      "loss": 1.4414,
      "step": 15600
    },
    {
      "epoch": 0.46726181590183025,
      "grad_norm": 3.9512829780578613,
      "learning_rate": 0.0001955302601729153,
      "loss": 1.354,
      "step": 15650
    },
    {
      "epoch": 0.46875466515391273,
      "grad_norm": 7.704863548278809,
      "learning_rate": 0.00019551597437699646,
      "loss": 1.4107,
      "step": 15700
    },
    {
      "epoch": 0.47024751440599527,
      "grad_norm": 3.502988338470459,
      "learning_rate": 0.00019550168858107763,
      "loss": 1.415,
      "step": 15750
    },
    {
      "epoch": 0.4717403636580778,
      "grad_norm": 4.246065139770508,
      "learning_rate": 0.0001954874027851588,
      "loss": 1.3414,
      "step": 15800
    },
    {
      "epoch": 0.47323321291016035,
      "grad_norm": 3.4039735794067383,
      "learning_rate": 0.00019547311698923995,
      "loss": 1.3303,
      "step": 15850
    },
    {
      "epoch": 0.47472606216224283,
      "grad_norm": 3.279521942138672,
      "learning_rate": 0.00019545883119332112,
      "loss": 1.3447,
      "step": 15900
    },
    {
      "epoch": 0.4762189114143254,
      "grad_norm": 2.9335134029388428,
      "learning_rate": 0.00019544454539740228,
      "loss": 1.3998,
      "step": 15950
    },
    {
      "epoch": 0.4777117606664079,
      "grad_norm": 3.317011833190918,
      "learning_rate": 0.00019543025960148345,
      "loss": 1.3506,
      "step": 16000
    },
    {
      "epoch": 0.47920460991849045,
      "grad_norm": 3.5980935096740723,
      "learning_rate": 0.0001954159738055646,
      "loss": 1.3622,
      "step": 16050
    },
    {
      "epoch": 0.48069745917057294,
      "grad_norm": 4.726743698120117,
      "learning_rate": 0.00019540168800964578,
      "loss": 1.3414,
      "step": 16100
    },
    {
      "epoch": 0.4821903084226555,
      "grad_norm": 5.129758358001709,
      "learning_rate": 0.00019538740221372694,
      "loss": 1.3873,
      "step": 16150
    },
    {
      "epoch": 0.483683157674738,
      "grad_norm": 5.122271537780762,
      "learning_rate": 0.0001953731164178081,
      "loss": 1.428,
      "step": 16200
    },
    {
      "epoch": 0.4851760069268205,
      "grad_norm": 3.359868049621582,
      "learning_rate": 0.0001953588306218893,
      "loss": 1.3111,
      "step": 16250
    },
    {
      "epoch": 0.48666885617890304,
      "grad_norm": 5.066514492034912,
      "learning_rate": 0.00019534454482597044,
      "loss": 1.2961,
      "step": 16300
    },
    {
      "epoch": 0.4881617054309856,
      "grad_norm": 4.902595520019531,
      "learning_rate": 0.0001953302590300516,
      "loss": 1.3682,
      "step": 16350
    },
    {
      "epoch": 0.4896545546830681,
      "grad_norm": 5.0537028312683105,
      "learning_rate": 0.00019531597323413277,
      "loss": 1.315,
      "step": 16400
    },
    {
      "epoch": 0.4911474039351506,
      "grad_norm": 3.7002792358398438,
      "learning_rate": 0.00019530168743821393,
      "loss": 1.3441,
      "step": 16450
    },
    {
      "epoch": 0.49264025318723315,
      "grad_norm": 4.845950603485107,
      "learning_rate": 0.00019528740164229512,
      "loss": 1.3887,
      "step": 16500
    },
    {
      "epoch": 0.4941331024393157,
      "grad_norm": 4.933434963226318,
      "learning_rate": 0.00019527311584637626,
      "loss": 1.3865,
      "step": 16550
    },
    {
      "epoch": 0.4956259516913982,
      "grad_norm": 3.8103625774383545,
      "learning_rate": 0.00019525883005045745,
      "loss": 1.3757,
      "step": 16600
    },
    {
      "epoch": 0.4971188009434807,
      "grad_norm": 4.501999855041504,
      "learning_rate": 0.0001952445442545386,
      "loss": 1.4482,
      "step": 16650
    },
    {
      "epoch": 0.49861165019556325,
      "grad_norm": 5.600002765655518,
      "learning_rate": 0.00019523025845861978,
      "loss": 1.4209,
      "step": 16700
    },
    {
      "epoch": 0.5001044994476458,
      "grad_norm": 5.138682842254639,
      "learning_rate": 0.00019521597266270092,
      "loss": 1.4287,
      "step": 16750
    },
    {
      "epoch": 0.5015973486997283,
      "grad_norm": 5.575449466705322,
      "learning_rate": 0.0001952016868667821,
      "loss": 1.3992,
      "step": 16800
    },
    {
      "epoch": 0.5030901979518109,
      "grad_norm": 3.6443893909454346,
      "learning_rate": 0.00019518740107086327,
      "loss": 1.3661,
      "step": 16850
    },
    {
      "epoch": 0.5045830472038934,
      "grad_norm": 3.904905319213867,
      "learning_rate": 0.00019517311527494444,
      "loss": 1.4448,
      "step": 16900
    },
    {
      "epoch": 0.5060758964559758,
      "grad_norm": 4.380904197692871,
      "learning_rate": 0.0001951588294790256,
      "loss": 1.4076,
      "step": 16950
    },
    {
      "epoch": 0.5075687457080584,
      "grad_norm": 3.5924415588378906,
      "learning_rate": 0.00019514454368310677,
      "loss": 1.3833,
      "step": 17000
    },
    {
      "epoch": 0.5090615949601409,
      "grad_norm": 3.7007193565368652,
      "learning_rate": 0.00019513025788718793,
      "loss": 1.391,
      "step": 17050
    },
    {
      "epoch": 0.5105544442122234,
      "grad_norm": 3.9879095554351807,
      "learning_rate": 0.0001951159720912691,
      "loss": 1.3419,
      "step": 17100
    },
    {
      "epoch": 0.512047293464306,
      "grad_norm": 5.663998126983643,
      "learning_rate": 0.00019510168629535026,
      "loss": 1.3481,
      "step": 17150
    },
    {
      "epoch": 0.5135401427163885,
      "grad_norm": 3.9803707599639893,
      "learning_rate": 0.00019508740049943143,
      "loss": 1.4034,
      "step": 17200
    },
    {
      "epoch": 0.5150329919684711,
      "grad_norm": 3.718477725982666,
      "learning_rate": 0.0001950731147035126,
      "loss": 1.406,
      "step": 17250
    },
    {
      "epoch": 0.5165258412205536,
      "grad_norm": 4.864751815795898,
      "learning_rate": 0.00019505882890759378,
      "loss": 1.375,
      "step": 17300
    },
    {
      "epoch": 0.518018690472636,
      "grad_norm": 3.697645664215088,
      "learning_rate": 0.00019504454311167492,
      "loss": 1.4283,
      "step": 17350
    },
    {
      "epoch": 0.5195115397247186,
      "grad_norm": 4.063074111938477,
      "learning_rate": 0.0001950302573157561,
      "loss": 1.378,
      "step": 17400
    },
    {
      "epoch": 0.5210043889768011,
      "grad_norm": 4.223004341125488,
      "learning_rate": 0.00019501597151983725,
      "loss": 1.3789,
      "step": 17450
    },
    {
      "epoch": 0.5224972382288836,
      "grad_norm": 3.329366683959961,
      "learning_rate": 0.00019500168572391844,
      "loss": 1.346,
      "step": 17500
    },
    {
      "epoch": 0.5239900874809662,
      "grad_norm": 4.774710178375244,
      "learning_rate": 0.00019498739992799958,
      "loss": 1.3895,
      "step": 17550
    },
    {
      "epoch": 0.5254829367330487,
      "grad_norm": 6.2145490646362305,
      "learning_rate": 0.00019497311413208077,
      "loss": 1.3715,
      "step": 17600
    },
    {
      "epoch": 0.5269757859851312,
      "grad_norm": 3.9069626331329346,
      "learning_rate": 0.00019495882833616194,
      "loss": 1.4572,
      "step": 17650
    },
    {
      "epoch": 0.5284686352372138,
      "grad_norm": 3.347576141357422,
      "learning_rate": 0.0001949445425402431,
      "loss": 1.359,
      "step": 17700
    },
    {
      "epoch": 0.5299614844892963,
      "grad_norm": 5.305202484130859,
      "learning_rate": 0.00019493025674432427,
      "loss": 1.4038,
      "step": 17750
    },
    {
      "epoch": 0.5314543337413788,
      "grad_norm": 3.865619659423828,
      "learning_rate": 0.00019491597094840543,
      "loss": 1.3913,
      "step": 17800
    },
    {
      "epoch": 0.5329471829934613,
      "grad_norm": 4.791336536407471,
      "learning_rate": 0.0001949016851524866,
      "loss": 1.3852,
      "step": 17850
    },
    {
      "epoch": 0.5344400322455438,
      "grad_norm": 3.7827060222625732,
      "learning_rate": 0.00019488739935656776,
      "loss": 1.3108,
      "step": 17900
    },
    {
      "epoch": 0.5359328814976264,
      "grad_norm": 4.945117473602295,
      "learning_rate": 0.00019487311356064892,
      "loss": 1.346,
      "step": 17950
    },
    {
      "epoch": 0.5374257307497089,
      "grad_norm": 4.561169147491455,
      "learning_rate": 0.0001948588277647301,
      "loss": 1.3904,
      "step": 18000
    },
    {
      "epoch": 0.5389185800017914,
      "grad_norm": 4.608798027038574,
      "learning_rate": 0.00019484454196881125,
      "loss": 1.4133,
      "step": 18050
    },
    {
      "epoch": 0.540411429253874,
      "grad_norm": 4.303143501281738,
      "learning_rate": 0.00019483025617289245,
      "loss": 1.3994,
      "step": 18100
    },
    {
      "epoch": 0.5419042785059565,
      "grad_norm": 5.815835952758789,
      "learning_rate": 0.00019481597037697358,
      "loss": 1.392,
      "step": 18150
    },
    {
      "epoch": 0.543397127758039,
      "grad_norm": 5.349491596221924,
      "learning_rate": 0.00019480168458105477,
      "loss": 1.418,
      "step": 18200
    },
    {
      "epoch": 0.5448899770101215,
      "grad_norm": 3.7407824993133545,
      "learning_rate": 0.0001947873987851359,
      "loss": 1.3747,
      "step": 18250
    },
    {
      "epoch": 0.546382826262204,
      "grad_norm": 5.2810163497924805,
      "learning_rate": 0.0001947731129892171,
      "loss": 1.4023,
      "step": 18300
    },
    {
      "epoch": 0.5478756755142866,
      "grad_norm": 4.417948246002197,
      "learning_rate": 0.00019475882719329824,
      "loss": 1.4005,
      "step": 18350
    },
    {
      "epoch": 0.5493685247663691,
      "grad_norm": 5.287749290466309,
      "learning_rate": 0.00019474454139737943,
      "loss": 1.4211,
      "step": 18400
    },
    {
      "epoch": 0.5508613740184516,
      "grad_norm": 4.0996809005737305,
      "learning_rate": 0.0001947302556014606,
      "loss": 1.3559,
      "step": 18450
    },
    {
      "epoch": 0.5523542232705342,
      "grad_norm": 5.229327201843262,
      "learning_rate": 0.00019471596980554176,
      "loss": 1.4549,
      "step": 18500
    },
    {
      "epoch": 0.5538470725226167,
      "grad_norm": 4.409546852111816,
      "learning_rate": 0.00019470168400962293,
      "loss": 1.3683,
      "step": 18550
    },
    {
      "epoch": 0.5553399217746992,
      "grad_norm": 5.4077229499816895,
      "learning_rate": 0.0001946873982137041,
      "loss": 1.398,
      "step": 18600
    },
    {
      "epoch": 0.5568327710267817,
      "grad_norm": 5.208966255187988,
      "learning_rate": 0.00019467311241778526,
      "loss": 1.3276,
      "step": 18650
    },
    {
      "epoch": 0.5583256202788642,
      "grad_norm": 4.8162617683410645,
      "learning_rate": 0.00019465882662186642,
      "loss": 1.3314,
      "step": 18700
    },
    {
      "epoch": 0.5598184695309467,
      "grad_norm": 5.04697322845459,
      "learning_rate": 0.00019464454082594759,
      "loss": 1.3883,
      "step": 18750
    },
    {
      "epoch": 0.5613113187830293,
      "grad_norm": 4.038108825683594,
      "learning_rate": 0.00019463025503002875,
      "loss": 1.4377,
      "step": 18800
    },
    {
      "epoch": 0.5628041680351118,
      "grad_norm": 4.910576820373535,
      "learning_rate": 0.00019461596923410992,
      "loss": 1.3713,
      "step": 18850
    },
    {
      "epoch": 0.5642970172871944,
      "grad_norm": 5.3433756828308105,
      "learning_rate": 0.00019460168343819108,
      "loss": 1.4359,
      "step": 18900
    },
    {
      "epoch": 0.5657898665392769,
      "grad_norm": 3.9515552520751953,
      "learning_rate": 0.00019458739764227224,
      "loss": 1.3608,
      "step": 18950
    },
    {
      "epoch": 0.5672827157913594,
      "grad_norm": 4.515705108642578,
      "learning_rate": 0.0001945731118463534,
      "loss": 1.3274,
      "step": 19000
    },
    {
      "epoch": 0.568775565043442,
      "grad_norm": 4.434077262878418,
      "learning_rate": 0.00019455882605043457,
      "loss": 1.3681,
      "step": 19050
    },
    {
      "epoch": 0.5702684142955244,
      "grad_norm": 4.534008979797363,
      "learning_rate": 0.00019454454025451574,
      "loss": 1.3863,
      "step": 19100
    },
    {
      "epoch": 0.5717612635476069,
      "grad_norm": 4.200322151184082,
      "learning_rate": 0.00019453025445859693,
      "loss": 1.3743,
      "step": 19150
    },
    {
      "epoch": 0.5732541127996895,
      "grad_norm": 5.686845779418945,
      "learning_rate": 0.00019451596866267807,
      "loss": 1.3225,
      "step": 19200
    },
    {
      "epoch": 0.574746962051772,
      "grad_norm": 7.821211814880371,
      "learning_rate": 0.00019450168286675926,
      "loss": 1.3775,
      "step": 19250
    },
    {
      "epoch": 0.5762398113038545,
      "grad_norm": 5.200834274291992,
      "learning_rate": 0.0001944873970708404,
      "loss": 1.3423,
      "step": 19300
    },
    {
      "epoch": 0.5777326605559371,
      "grad_norm": 5.26302433013916,
      "learning_rate": 0.0001944731112749216,
      "loss": 1.3813,
      "step": 19350
    },
    {
      "epoch": 0.5792255098080196,
      "grad_norm": 3.3207719326019287,
      "learning_rate": 0.00019445882547900273,
      "loss": 1.3922,
      "step": 19400
    },
    {
      "epoch": 0.5807183590601022,
      "grad_norm": 4.619020938873291,
      "learning_rate": 0.00019444453968308392,
      "loss": 1.3533,
      "step": 19450
    },
    {
      "epoch": 0.5822112083121846,
      "grad_norm": 5.780002593994141,
      "learning_rate": 0.00019443025388716508,
      "loss": 1.4035,
      "step": 19500
    },
    {
      "epoch": 0.5837040575642671,
      "grad_norm": 4.961215496063232,
      "learning_rate": 0.00019441596809124625,
      "loss": 1.3687,
      "step": 19550
    },
    {
      "epoch": 0.5851969068163497,
      "grad_norm": 4.50115442276001,
      "learning_rate": 0.0001944016822953274,
      "loss": 1.342,
      "step": 19600
    },
    {
      "epoch": 0.5866897560684322,
      "grad_norm": 3.9477944374084473,
      "learning_rate": 0.00019438739649940858,
      "loss": 1.394,
      "step": 19650
    },
    {
      "epoch": 0.5881826053205147,
      "grad_norm": 3.7466814517974854,
      "learning_rate": 0.00019437311070348974,
      "loss": 1.3414,
      "step": 19700
    },
    {
      "epoch": 0.5896754545725973,
      "grad_norm": 4.382058143615723,
      "learning_rate": 0.0001943588249075709,
      "loss": 1.3669,
      "step": 19750
    },
    {
      "epoch": 0.5911683038246798,
      "grad_norm": 3.7016665935516357,
      "learning_rate": 0.00019434453911165207,
      "loss": 1.4548,
      "step": 19800
    },
    {
      "epoch": 0.5926611530767623,
      "grad_norm": 4.4738030433654785,
      "learning_rate": 0.00019433025331573324,
      "loss": 1.4273,
      "step": 19850
    },
    {
      "epoch": 0.5941540023288449,
      "grad_norm": 5.2445454597473145,
      "learning_rate": 0.0001943159675198144,
      "loss": 1.3746,
      "step": 19900
    },
    {
      "epoch": 0.5956468515809273,
      "grad_norm": 3.766219139099121,
      "learning_rate": 0.0001943016817238956,
      "loss": 1.4391,
      "step": 19950
    },
    {
      "epoch": 0.5971397008330099,
      "grad_norm": 6.310808181762695,
      "learning_rate": 0.00019428739592797673,
      "loss": 1.3316,
      "step": 20000
    }
  ],
  "logging_steps": 50,
  "max_steps": 700001,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 21,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.04693160210858e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}