{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.29856985041650497,
  "eval_steps": 1000,
  "global_step": 10000,
  "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
    }
  ],
  "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": 2.535695686786089e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}