{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16,
  "eval_steps": 250,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016,
      "grad_norm": NaN,
      "learning_rate": 9.574468085106383e-06,
      "loss": 0.6083179950714112,
      "step": 10
    },
    {
      "epoch": 0.0032,
      "grad_norm": 0.2735198438167572,
      "learning_rate": 1.9148936170212766e-05,
      "loss": 0.6088993072509765,
      "step": 20
    },
    {
      "epoch": 0.0048,
      "grad_norm": 0.15276113152503967,
      "learning_rate": 2.9787234042553192e-05,
      "loss": 0.5225989818572998,
      "step": 30
    },
    {
      "epoch": 0.0064,
      "grad_norm": 0.17109858989715576,
      "learning_rate": 4.0425531914893614e-05,
      "loss": 0.4329381942749023,
      "step": 40
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.17585736513137817,
      "learning_rate": 5.1063829787234044e-05,
      "loss": 0.35364015102386476,
      "step": 50
    },
    {
      "epoch": 0.0096,
      "grad_norm": 0.16095905005931854,
      "learning_rate": 6.170212765957447e-05,
      "loss": 0.26982028484344484,
      "step": 60
    },
    {
      "epoch": 0.0112,
      "grad_norm": 0.11053046584129333,
      "learning_rate": 7.23404255319149e-05,
      "loss": 0.20504410266876222,
      "step": 70
    },
    {
      "epoch": 0.0128,
      "grad_norm": 0.12669840455055237,
      "learning_rate": 8.297872340425533e-05,
      "loss": 0.19483240842819213,
      "step": 80
    },
    {
      "epoch": 0.0144,
      "grad_norm": 0.11641468852758408,
      "learning_rate": 9.361702127659576e-05,
      "loss": 0.17770581245422362,
      "step": 90
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.14681392908096313,
      "learning_rate": 0.00010425531914893618,
      "loss": 0.15753360986709594,
      "step": 100
    },
    {
      "epoch": 0.0176,
      "grad_norm": 0.09883147478103638,
      "learning_rate": 0.00011489361702127661,
      "loss": 0.16169432401657105,
      "step": 110
    },
    {
      "epoch": 0.0192,
      "grad_norm": 0.1138603463768959,
      "learning_rate": 0.00012553191489361702,
      "loss": 0.16089822053909303,
      "step": 120
    },
    {
      "epoch": 0.0208,
      "grad_norm": 0.13063949346542358,
      "learning_rate": 0.00013617021276595746,
      "loss": 0.1603950023651123,
      "step": 130
    },
    {
      "epoch": 0.0224,
      "grad_norm": 0.06824357807636261,
      "learning_rate": 0.00014680851063829788,
      "loss": 0.14956578016281127,
      "step": 140
    },
    {
      "epoch": 0.024,
      "grad_norm": 0.12136659771203995,
      "learning_rate": 0.00015744680851063832,
      "loss": 0.1617922306060791,
      "step": 150
    },
    {
      "epoch": 0.0256,
      "grad_norm": 0.10032546520233154,
      "learning_rate": 0.00016808510638297873,
      "loss": 0.1547396659851074,
      "step": 160
    },
    {
      "epoch": 0.0272,
      "grad_norm": 0.07678422331809998,
      "learning_rate": 0.00017872340425531915,
      "loss": 0.14475579261779786,
      "step": 170
    },
    {
      "epoch": 0.0288,
      "grad_norm": 0.10933304578065872,
      "learning_rate": 0.00018936170212765957,
      "loss": 0.1330868124961853,
      "step": 180
    },
    {
      "epoch": 0.0304,
      "grad_norm": 0.12041473388671875,
      "learning_rate": 0.0002,
      "loss": 0.14836544990539552,
      "step": 190
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.0896446481347084,
      "learning_rate": 0.00019967007588254704,
      "loss": 0.14405652284622192,
      "step": 200
    },
    {
      "epoch": 0.0336,
      "grad_norm": 0.0876811295747757,
      "learning_rate": 0.00019934015176509403,
      "loss": 0.14646297693252563,
      "step": 210
    },
    {
      "epoch": 0.0352,
      "grad_norm": 0.09327778220176697,
      "learning_rate": 0.00019901022764764106,
      "loss": 0.14419257640838623,
      "step": 220
    },
    {
      "epoch": 0.0368,
      "grad_norm": 0.08388442546129227,
      "learning_rate": 0.00019868030353018806,
      "loss": 0.15150091648101807,
      "step": 230
    },
    {
      "epoch": 0.0384,
      "grad_norm": 0.09979762881994247,
      "learning_rate": 0.00019835037941273509,
      "loss": 0.14006744623184203,
      "step": 240
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.0845855325460434,
      "learning_rate": 0.0001980204552952821,
      "loss": 0.15045372247695923,
      "step": 250
    },
    {
      "epoch": 0.0416,
      "grad_norm": 0.09481288492679596,
      "learning_rate": 0.0001976905311778291,
      "loss": 0.15042688846588134,
      "step": 260
    },
    {
      "epoch": 0.0432,
      "grad_norm": 0.10349375009536743,
      "learning_rate": 0.0001973606070603761,
      "loss": 0.13992291688919067,
      "step": 270
    },
    {
      "epoch": 0.0448,
      "grad_norm": 0.07897678017616272,
      "learning_rate": 0.00019703068294292314,
      "loss": 0.13927781581878662,
      "step": 280
    },
    {
      "epoch": 0.0464,
      "grad_norm": 0.08341789990663528,
      "learning_rate": 0.00019670075882547014,
      "loss": 0.14076149463653564,
      "step": 290
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.10565593093633652,
      "learning_rate": 0.00019637083470801716,
      "loss": 0.14325612783432007,
      "step": 300
    },
    {
      "epoch": 0.0496,
      "grad_norm": 0.07861499488353729,
      "learning_rate": 0.0001960409105905642,
      "loss": 0.1343199133872986,
      "step": 310
    },
    {
      "epoch": 0.0512,
      "grad_norm": 0.09252545982599258,
      "learning_rate": 0.0001957109864731112,
      "loss": 0.12891001701354982,
      "step": 320
    },
    {
      "epoch": 0.0528,
      "grad_norm": 0.08716761320829391,
      "learning_rate": 0.0001953810623556582,
      "loss": 0.1449826717376709,
      "step": 330
    },
    {
      "epoch": 0.0544,
      "grad_norm": 0.07750111818313599,
      "learning_rate": 0.0001950511382382052,
      "loss": 0.1274427056312561,
      "step": 340
    },
    {
      "epoch": 0.056,
      "grad_norm": 0.07396410405635834,
      "learning_rate": 0.00019472121412075224,
      "loss": 0.12241615056991577,
      "step": 350
    },
    {
      "epoch": 0.0576,
      "grad_norm": 0.07157568633556366,
      "learning_rate": 0.00019439129000329926,
      "loss": 0.14313431978225707,
      "step": 360
    },
    {
      "epoch": 0.0592,
      "grad_norm": 0.08780192583799362,
      "learning_rate": 0.00019406136588584626,
      "loss": 0.13534088134765626,
      "step": 370
    },
    {
      "epoch": 0.0608,
      "grad_norm": 0.09394513815641403,
      "learning_rate": 0.0001937314417683933,
      "loss": 0.1249586820602417,
      "step": 380
    },
    {
      "epoch": 0.0624,
      "grad_norm": 0.0853569507598877,
      "learning_rate": 0.0001934015176509403,
      "loss": 0.13353261947631836,
      "step": 390
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.08356380462646484,
      "learning_rate": 0.00019307159353348731,
      "loss": 0.12304072380065918,
      "step": 400
    },
    {
      "epoch": 0.0656,
      "grad_norm": 0.08608467876911163,
      "learning_rate": 0.00019274166941603434,
      "loss": 0.13379846811294555,
      "step": 410
    },
    {
      "epoch": 0.0672,
      "grad_norm": 0.07890665531158447,
      "learning_rate": 0.0001924117452985813,
      "loss": 0.11951367855072022,
      "step": 420
    },
    {
      "epoch": 0.0688,
      "grad_norm": 0.08108149468898773,
      "learning_rate": 0.00019208182118112834,
      "loss": 0.12902278900146485,
      "step": 430
    },
    {
      "epoch": 0.0704,
      "grad_norm": 0.09603618830442429,
      "learning_rate": 0.00019175189706367536,
      "loss": 0.12690144777297974,
      "step": 440
    },
    {
      "epoch": 0.072,
      "grad_norm": 0.09471320360898972,
      "learning_rate": 0.00019142197294622236,
      "loss": 0.13802603483200074,
      "step": 450
    },
    {
      "epoch": 0.0736,
      "grad_norm": 0.08374392986297607,
      "learning_rate": 0.0001910920488287694,
      "loss": 0.12328752279281616,
      "step": 460
    },
    {
      "epoch": 0.0752,
      "grad_norm": 0.08944465219974518,
      "learning_rate": 0.00019076212471131642,
      "loss": 0.12756569385528566,
      "step": 470
    },
    {
      "epoch": 0.0768,
      "grad_norm": 0.0898577868938446,
      "learning_rate": 0.00019043220059386341,
      "loss": 0.13218681812286376,
      "step": 480
    },
    {
      "epoch": 0.0784,
      "grad_norm": 0.07767961174249649,
      "learning_rate": 0.00019010227647641044,
      "loss": 0.135015869140625,
      "step": 490
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.0865555852651596,
      "learning_rate": 0.00018977235235895744,
      "loss": 0.128175950050354,
      "step": 500
    },
    {
      "epoch": 0.0816,
      "grad_norm": 0.07919178158044815,
      "learning_rate": 0.00018944242824150447,
      "loss": 0.12430660724639893,
      "step": 510
    },
    {
      "epoch": 0.0832,
      "grad_norm": 0.08649525046348572,
      "learning_rate": 0.0001891125041240515,
      "loss": 0.12590073347091674,
      "step": 520
    },
    {
      "epoch": 0.0848,
      "grad_norm": 0.08704695850610733,
      "learning_rate": 0.0001887825800065985,
      "loss": 0.12156925201416016,
      "step": 530
    },
    {
      "epoch": 0.0864,
      "grad_norm": 0.06752946227788925,
      "learning_rate": 0.00018845265588914552,
      "loss": 0.12604955434799195,
      "step": 540
    },
    {
      "epoch": 0.088,
      "grad_norm": 0.09034618735313416,
      "learning_rate": 0.00018812273177169252,
      "loss": 0.13052459955215454,
      "step": 550
    },
    {
      "epoch": 0.0896,
      "grad_norm": 0.0869947075843811,
      "learning_rate": 0.00018779280765423954,
      "loss": 0.12303999662399293,
      "step": 560
    },
    {
      "epoch": 0.0912,
      "grad_norm": 0.0702558308839798,
      "learning_rate": 0.00018746288353678654,
      "loss": 0.12230894565582276,
      "step": 570
    },
    {
      "epoch": 0.0928,
      "grad_norm": 0.08718933910131454,
      "learning_rate": 0.00018713295941933354,
      "loss": 0.1285646677017212,
      "step": 580
    },
    {
      "epoch": 0.0944,
      "grad_norm": 0.07396125048398972,
      "learning_rate": 0.00018680303530188057,
      "loss": 0.1259121775627136,
      "step": 590
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.10813502222299576,
      "learning_rate": 0.0001864731111844276,
      "loss": 0.12581136226654052,
      "step": 600
    },
    {
      "epoch": 0.0976,
      "grad_norm": 0.07332257181406021,
      "learning_rate": 0.0001861431870669746,
      "loss": 0.120159912109375,
      "step": 610
    },
    {
      "epoch": 0.0992,
      "grad_norm": 0.08529425412416458,
      "learning_rate": 0.00018581326294952162,
      "loss": 0.1297559142112732,
      "step": 620
    },
    {
      "epoch": 0.1008,
      "grad_norm": 0.09605136513710022,
      "learning_rate": 0.00018548333883206864,
      "loss": 0.12067115306854248,
      "step": 630
    },
    {
      "epoch": 0.1024,
      "grad_norm": 0.08586304634809494,
      "learning_rate": 0.00018515341471461564,
      "loss": 0.12730380296707153,
      "step": 640
    },
    {
      "epoch": 0.104,
      "grad_norm": 0.06986010074615479,
      "learning_rate": 0.00018482349059716267,
      "loss": 0.12864140272140503,
      "step": 650
    },
    {
      "epoch": 0.1056,
      "grad_norm": 0.08565957844257355,
      "learning_rate": 0.00018449356647970967,
      "loss": 0.13535914421081544,
      "step": 660
    },
    {
      "epoch": 0.1072,
      "grad_norm": 0.07841351628303528,
      "learning_rate": 0.0001841636423622567,
      "loss": 0.12447234392166137,
      "step": 670
    },
    {
      "epoch": 0.1088,
      "grad_norm": 0.07424665987491608,
      "learning_rate": 0.00018383371824480372,
      "loss": 0.12037907838821411,
      "step": 680
    },
    {
      "epoch": 0.1104,
      "grad_norm": 0.0957612544298172,
      "learning_rate": 0.00018350379412735072,
      "loss": 0.11919810771942138,
      "step": 690
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.07862170785665512,
      "learning_rate": 0.00018317387000989775,
      "loss": 0.12414863109588622,
      "step": 700
    },
    {
      "epoch": 0.1136,
      "grad_norm": 0.12410055845975876,
      "learning_rate": 0.00018284394589244474,
      "loss": 0.12083030939102173,
      "step": 710
    },
    {
      "epoch": 0.1152,
      "grad_norm": 0.07692275941371918,
      "learning_rate": 0.00018251402177499174,
      "loss": 0.11559462547302246,
      "step": 720
    },
    {
      "epoch": 0.1168,
      "grad_norm": 0.07810766994953156,
      "learning_rate": 0.00018218409765753877,
      "loss": 0.12092136144638062,
      "step": 730
    },
    {
      "epoch": 0.1184,
      "grad_norm": 0.08475863188505173,
      "learning_rate": 0.00018185417354008577,
      "loss": 0.12225215435028076,
      "step": 740
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.09497244656085968,
      "learning_rate": 0.0001815242494226328,
      "loss": 0.12478446960449219,
      "step": 750
    },
    {
      "epoch": 0.1216,
      "grad_norm": 0.07779653370380402,
      "learning_rate": 0.00018119432530517982,
      "loss": 0.11081166267395019,
      "step": 760
    },
    {
      "epoch": 0.1232,
      "grad_norm": 0.08435814827680588,
      "learning_rate": 0.00018086440118772682,
      "loss": 0.10844987630844116,
      "step": 770
    },
    {
      "epoch": 0.1248,
      "grad_norm": 0.07567104697227478,
      "learning_rate": 0.00018053447707027385,
      "loss": 0.11887184381484986,
      "step": 780
    },
    {
      "epoch": 0.1264,
      "grad_norm": 0.07750700414180756,
      "learning_rate": 0.00018020455295282087,
      "loss": 0.11811846494674683,
      "step": 790
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.09390198439359665,
      "learning_rate": 0.00017987462883536787,
      "loss": 0.11379201412200927,
      "step": 800
    },
    {
      "epoch": 0.1296,
      "grad_norm": 0.08400580286979675,
      "learning_rate": 0.0001795447047179149,
      "loss": 0.11909257173538208,
      "step": 810
    },
    {
      "epoch": 0.1312,
      "grad_norm": 0.09543855488300323,
      "learning_rate": 0.0001792147806004619,
      "loss": 0.10916774272918701,
      "step": 820
    },
    {
      "epoch": 0.1328,
      "grad_norm": 0.07908441871404648,
      "learning_rate": 0.00017888485648300892,
      "loss": 0.107346510887146,
      "step": 830
    },
    {
      "epoch": 0.1344,
      "grad_norm": 0.1085224449634552,
      "learning_rate": 0.00017855493236555595,
      "loss": 0.12227011919021606,
      "step": 840
    },
    {
      "epoch": 0.136,
      "grad_norm": 0.07472517341375351,
      "learning_rate": 0.00017822500824810295,
      "loss": 0.11575174331665039,
      "step": 850
    },
    {
      "epoch": 0.1376,
      "grad_norm": 0.07198534905910492,
      "learning_rate": 0.00017789508413064997,
      "loss": 0.12281327247619629,
      "step": 860
    },
    {
      "epoch": 0.1392,
      "grad_norm": 0.09142109006643295,
      "learning_rate": 0.00017756516001319697,
      "loss": 0.11497378349304199,
      "step": 870
    },
    {
      "epoch": 0.1408,
      "grad_norm": 0.09548252075910568,
      "learning_rate": 0.00017723523589574397,
      "loss": 0.11615512371063233,
      "step": 880
    },
    {
      "epoch": 0.1424,
      "grad_norm": 0.06250233203172684,
      "learning_rate": 0.000176905311778291,
      "loss": 0.11593252420425415,
      "step": 890
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.08740886300802231,
      "learning_rate": 0.000176575387660838,
      "loss": 0.11546707153320312,
      "step": 900
    },
    {
      "epoch": 0.1456,
      "grad_norm": 0.11061470210552216,
      "learning_rate": 0.00017624546354338502,
      "loss": 0.12130849361419678,
      "step": 910
    },
    {
      "epoch": 0.1472,
      "grad_norm": 0.07824647426605225,
      "learning_rate": 0.00017591553942593205,
      "loss": 0.1188379168510437,
      "step": 920
    },
    {
      "epoch": 0.1488,
      "grad_norm": 0.08214984834194183,
      "learning_rate": 0.00017558561530847905,
      "loss": 0.11806504726409912,
      "step": 930
    },
    {
      "epoch": 0.1504,
      "grad_norm": 0.09313149005174637,
      "learning_rate": 0.00017525569119102607,
      "loss": 0.11112408638000489,
      "step": 940
    },
    {
      "epoch": 0.152,
      "grad_norm": 0.08523363620042801,
      "learning_rate": 0.0001749257670735731,
      "loss": 0.1136185884475708,
      "step": 950
    },
    {
      "epoch": 0.1536,
      "grad_norm": 0.06718438863754272,
      "learning_rate": 0.0001745958429561201,
      "loss": 0.1142117738723755,
      "step": 960
    },
    {
      "epoch": 0.1552,
      "grad_norm": 0.08877789974212646,
      "learning_rate": 0.00017426591883866713,
      "loss": 0.11236680746078491,
      "step": 970
    },
    {
      "epoch": 0.1568,
      "grad_norm": 0.07814772427082062,
      "learning_rate": 0.00017393599472121412,
      "loss": 0.10925638675689697,
      "step": 980
    },
    {
      "epoch": 0.1584,
      "grad_norm": 0.08659686148166656,
      "learning_rate": 0.00017360607060376115,
      "loss": 0.11623308658599854,
      "step": 990
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.08823436498641968,
      "learning_rate": 0.00017327614648630818,
      "loss": 0.11374906301498414,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 6250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.8688917455755264e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}