{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.409985315712188,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011747430249632892,
      "grad_norm": 1.5699902772903442,
      "learning_rate": 0.00027,
      "loss": 3.0983,
      "step": 10
    },
    {
      "epoch": 0.023494860499265784,
      "grad_norm": 1.6029695272445679,
      "learning_rate": 0.00029991523567092526,
      "loss": 2.062,
      "step": 20
    },
    {
      "epoch": 0.03524229074889868,
      "grad_norm": 1.593436360359192,
      "learning_rate": 0.00029962234616583063,
      "loss": 1.2074,
      "step": 30
    },
    {
      "epoch": 0.04698972099853157,
      "grad_norm": 0.5851414799690247,
      "learning_rate": 0.00029912069357315393,
      "loss": 0.888,
      "step": 40
    },
    {
      "epoch": 0.05873715124816446,
      "grad_norm": 0.25992292165756226,
      "learning_rate": 0.0002984109778320875,
      "loss": 0.7685,
      "step": 50
    },
    {
      "epoch": 0.07048458149779736,
      "grad_norm": 0.21082307398319244,
      "learning_rate": 0.00029749418918542057,
      "loss": 0.7096,
      "step": 60
    },
    {
      "epoch": 0.08223201174743025,
      "grad_norm": 0.16843102872371674,
      "learning_rate": 0.0002963716067978866,
      "loss": 0.6901,
      "step": 70
    },
    {
      "epoch": 0.09397944199706314,
      "grad_norm": 0.12076722830533981,
      "learning_rate": 0.000295044796971387,
      "loss": 0.6702,
      "step": 80
    },
    {
      "epoch": 0.10572687224669604,
      "grad_norm": 0.21371866762638092,
      "learning_rate": 0.000293515610959582,
      "loss": 0.6353,
      "step": 90
    },
    {
      "epoch": 0.11747430249632893,
      "grad_norm": 0.13458965718746185,
      "learning_rate": 0.0002917861823848985,
      "loss": 0.6479,
      "step": 100
    },
    {
      "epoch": 0.12922173274596183,
      "grad_norm": 0.265765517950058,
      "learning_rate": 0.0002898589242615568,
      "loss": 0.6244,
      "step": 110
    },
    {
      "epoch": 0.14096916299559473,
      "grad_norm": 0.1473032385110855,
      "learning_rate": 0.0002877365256287728,
      "loss": 0.6217,
      "step": 120
    },
    {
      "epoch": 0.1527165932452276,
      "grad_norm": 0.1591167151927948,
      "learning_rate": 0.00028542194779883047,
      "loss": 0.6022,
      "step": 130
    },
    {
      "epoch": 0.1644640234948605,
      "grad_norm": 0.13270772993564606,
      "learning_rate": 0.00028291842022526133,
      "loss": 0.6098,
      "step": 140
    },
    {
      "epoch": 0.1762114537444934,
      "grad_norm": 0.1444919854402542,
      "learning_rate": 0.0002802294359968954,
      "loss": 0.5971,
      "step": 150
    },
    {
      "epoch": 0.18795888399412627,
      "grad_norm": 0.1571902334690094,
      "learning_rate": 0.0002773587469640702,
      "loss": 0.5937,
      "step": 160
    },
    {
      "epoch": 0.19970631424375918,
      "grad_norm": 0.11585285514593124,
      "learning_rate": 0.0002743103585037989,
      "loss": 0.6054,
      "step": 170
    },
    {
      "epoch": 0.21145374449339208,
      "grad_norm": 0.10303252190351486,
      "learning_rate": 0.0002710885239312008,
      "loss": 0.5708,
      "step": 180
    },
    {
      "epoch": 0.22320117474302498,
      "grad_norm": 0.09355439245700836,
      "learning_rate": 0.00026769773856499167,
      "loss": 0.5806,
      "step": 190
    },
    {
      "epoch": 0.23494860499265785,
      "grad_norm": 0.09288550913333893,
      "learning_rate": 0.0002641427334553158,
      "loss": 0.5747,
      "step": 200
    },
    {
      "epoch": 0.24669603524229075,
      "grad_norm": 0.10875760763883591,
      "learning_rate": 0.00026042846878266795,
      "loss": 0.5879,
      "step": 210
    },
    {
      "epoch": 0.25844346549192365,
      "grad_norm": 0.09756477177143097,
      "learning_rate": 0.0002565601269371192,
      "loss": 0.5852,
      "step": 220
    },
    {
      "epoch": 0.2701908957415565,
      "grad_norm": 0.10926368832588196,
      "learning_rate": 0.0002525431052874997,
      "loss": 0.5605,
      "step": 230
    },
    {
      "epoch": 0.28193832599118945,
      "grad_norm": 0.09802033007144928,
      "learning_rate": 0.00024838300865062966,
      "loss": 0.5738,
      "step": 240
    },
    {
      "epoch": 0.2936857562408223,
      "grad_norm": 0.10284294933080673,
      "learning_rate": 0.00024408564147110443,
      "loss": 0.5847,
      "step": 250
    },
    {
      "epoch": 0.3054331864904552,
      "grad_norm": 0.09890703111886978,
      "learning_rate": 0.00023965699972254602,
      "loss": 0.5736,
      "step": 260
    },
    {
      "epoch": 0.31718061674008813,
      "grad_norm": 0.09091509878635406,
      "learning_rate": 0.00023510326254162027,
      "loss": 0.5577,
      "step": 270
    },
    {
      "epoch": 0.328928046989721,
      "grad_norm": 0.0930003970861435,
      "learning_rate": 0.00023043078360649285,
      "loss": 0.5651,
      "step": 280
    },
    {
      "epoch": 0.3406754772393539,
      "grad_norm": 0.0988878533244133,
      "learning_rate": 0.00022564608227175316,
      "loss": 0.548,
      "step": 290
    },
    {
      "epoch": 0.3524229074889868,
      "grad_norm": 0.11749754101037979,
      "learning_rate": 0.0002207558344721757,
      "loss": 0.5587,
      "step": 300
    },
    {
      "epoch": 0.3641703377386197,
      "grad_norm": 0.10936658829450607,
      "learning_rate": 0.00021576686340800985,
      "loss": 0.5694,
      "step": 310
    },
    {
      "epoch": 0.37591776798825255,
      "grad_norm": 0.15082670748233795,
      "learning_rate": 0.00021068613002479553,
      "loss": 0.5688,
      "step": 320
    },
    {
      "epoch": 0.3876651982378855,
      "grad_norm": 0.10255635529756546,
      "learning_rate": 0.00020552072330098716,
      "loss": 0.56,
      "step": 330
    },
    {
      "epoch": 0.39941262848751835,
      "grad_norm": 0.10504507273435593,
      "learning_rate": 0.0002002778503569374,
      "loss": 0.557,
      "step": 340
    },
    {
      "epoch": 0.4111600587371512,
      "grad_norm": 0.1146383211016655,
      "learning_rate": 0.00019496482639904194,
      "loss": 0.5497,
      "step": 350
    },
    {
      "epoch": 0.42290748898678415,
      "grad_norm": 0.09596443176269531,
      "learning_rate": 0.00018958906451307489,
      "loss": 0.556,
      "step": 360
    },
    {
      "epoch": 0.434654919236417,
      "grad_norm": 0.10395421087741852,
      "learning_rate": 0.0001841580653209565,
      "loss": 0.5634,
      "step": 370
    },
    {
      "epoch": 0.44640234948604995,
      "grad_norm": 0.08797866106033325,
      "learning_rate": 0.00017867940651538483,
      "loss": 0.5544,
      "step": 380
    },
    {
      "epoch": 0.4581497797356828,
      "grad_norm": 0.1006847620010376,
      "learning_rate": 0.0001731607322869329,
      "loss": 0.5562,
      "step": 390
    },
    {
      "epoch": 0.4698972099853157,
      "grad_norm": 0.09849337488412857,
      "learning_rate": 0.00016760974265836331,
      "loss": 0.5477,
      "step": 400
    },
    {
      "epoch": 0.48164464023494863,
      "grad_norm": 0.0988384336233139,
      "learning_rate": 0.00016203418274104278,
      "loss": 0.5459,
      "step": 410
    },
    {
      "epoch": 0.4933920704845815,
      "grad_norm": 0.09625212848186493,
      "learning_rate": 0.0001564418319284454,
      "loss": 0.5516,
      "step": 420
    },
    {
      "epoch": 0.5051395007342144,
      "grad_norm": 0.09705183655023575,
      "learning_rate": 0.00015084049304182347,
      "loss": 0.5375,
      "step": 430
    },
    {
      "epoch": 0.5168869309838473,
      "grad_norm": 0.17180472612380981,
      "learning_rate": 0.00014523798144319027,
      "loss": 0.539,
      "step": 440
    },
    {
      "epoch": 0.5286343612334802,
      "grad_norm": 0.09553302824497223,
      "learning_rate": 0.00013964211413080522,
      "loss": 0.5418,
      "step": 450
    },
    {
      "epoch": 0.540381791483113,
      "grad_norm": 0.10648112744092941,
      "learning_rate": 0.0001340606988323758,
      "loss": 0.5414,
      "step": 460
    },
    {
      "epoch": 0.5521292217327459,
      "grad_norm": 0.09907692670822144,
      "learning_rate": 0.00012850152311119498,
      "loss": 0.5353,
      "step": 470
    },
    {
      "epoch": 0.5638766519823789,
      "grad_norm": 0.11162377148866653,
      "learning_rate": 0.00012297234350041228,
      "loss": 0.528,
      "step": 480
    },
    {
      "epoch": 0.5756240822320118,
      "grad_norm": 0.10550152510404587,
      "learning_rate": 0.00011748087468060128,
      "loss": 0.533,
      "step": 490
    },
    {
      "epoch": 0.5873715124816447,
      "grad_norm": 0.09718377143144608,
      "learning_rate": 0.0001120347787157222,
      "loss": 0.5409,
      "step": 500
    },
    {
      "epoch": 0.5991189427312775,
      "grad_norm": 0.09185861796140671,
      "learning_rate": 0.0001066416543624984,
      "loss": 0.5354,
      "step": 510
    },
    {
      "epoch": 0.6108663729809104,
      "grad_norm": 0.0927920788526535,
      "learning_rate": 0.00010130902646812369,
      "loss": 0.5454,
      "step": 520
    },
    {
      "epoch": 0.6226138032305433,
      "grad_norm": 0.087093785405159,
      "learning_rate": 9.604433547109344e-05,
      "loss": 0.5295,
      "step": 530
    },
    {
      "epoch": 0.6343612334801763,
      "grad_norm": 0.09994326531887054,
      "learning_rate": 9.085492701980751e-05,
      "loss": 0.5322,
      "step": 540
    },
    {
      "epoch": 0.6461086637298091,
      "grad_norm": 0.09507084637880325,
      "learning_rate": 8.574804172343134e-05,
      "loss": 0.5224,
      "step": 550
    },
    {
      "epoch": 0.657856093979442,
      "grad_norm": 0.08571015298366547,
      "learning_rate": 8.07308050493148e-05,
      "loss": 0.5378,
      "step": 560
    },
    {
      "epoch": 0.6696035242290749,
      "grad_norm": 0.08876761794090271,
      "learning_rate": 7.581021738106408e-05,
      "loss": 0.5265,
      "step": 570
    },
    {
      "epoch": 0.6813509544787077,
      "grad_norm": 0.09467241168022156,
      "learning_rate": 7.099314425113907e-05,
      "loss": 0.5392,
      "step": 580
    },
    {
      "epoch": 0.6930983847283406,
      "grad_norm": 0.08804601430892944,
      "learning_rate": 6.628630676160445e-05,
      "loss": 0.5365,
      "step": 590
    },
    {
      "epoch": 0.7048458149779736,
      "grad_norm": 0.08877623081207275,
      "learning_rate": 6.169627220639871e-05,
      "loss": 0.5354,
      "step": 600
    },
    {
      "epoch": 0.7165932452276065,
      "grad_norm": 0.09122662246227264,
      "learning_rate": 5.722944490820774e-05,
      "loss": 0.5356,
      "step": 610
    },
    {
      "epoch": 0.7283406754772394,
      "grad_norm": 0.08744510263204575,
      "learning_rate": 5.289205728272586e-05,
      "loss": 0.5424,
      "step": 620
    },
    {
      "epoch": 0.7400881057268722,
      "grad_norm": 0.08927814662456512,
      "learning_rate": 4.869016114277345e-05,
      "loss": 0.5268,
      "step": 630
    },
    {
      "epoch": 0.7518355359765051,
      "grad_norm": 0.09256933629512787,
      "learning_rate": 4.462961925440341e-05,
      "loss": 0.5414,
      "step": 640
    },
    {
      "epoch": 0.7635829662261381,
      "grad_norm": 0.08703339844942093,
      "learning_rate": 4.071609715677899e-05,
      "loss": 0.5376,
      "step": 650
    },
    {
      "epoch": 0.775330396475771,
      "grad_norm": 0.08876251429319382,
      "learning_rate": 3.695505525723465e-05,
      "loss": 0.5307,
      "step": 660
    },
    {
      "epoch": 0.7870778267254038,
      "grad_norm": 0.08702490478754044,
      "learning_rate": 3.3351741212551595e-05,
      "loss": 0.5307,
      "step": 670
    },
    {
      "epoch": 0.7988252569750367,
      "grad_norm": 0.08601511269807816,
      "learning_rate": 2.9911182607076516e-05,
      "loss": 0.5372,
      "step": 680
    },
    {
      "epoch": 0.8105726872246696,
      "grad_norm": 0.0857272818684578,
      "learning_rate": 2.663817993790021e-05,
      "loss": 0.528,
      "step": 690
    },
    {
      "epoch": 0.8223201174743024,
      "grad_norm": 0.08725214004516602,
      "learning_rate": 2.3537299916883512e-05,
      "loss": 0.5378,
      "step": 700
    },
    {
      "epoch": 0.8340675477239354,
      "grad_norm": 0.0845843032002449,
      "learning_rate": 2.0612869098875988e-05,
      "loss": 0.5389,
      "step": 710
    },
    {
      "epoch": 0.8458149779735683,
      "grad_norm": 0.08480172604322433,
      "learning_rate": 1.786896784501778e-05,
      "loss": 0.5244,
      "step": 720
    },
    {
      "epoch": 0.8575624082232012,
      "grad_norm": 0.09265288710594177,
      "learning_rate": 1.5309424629547164e-05,
      "loss": 0.5403,
      "step": 730
    },
    {
      "epoch": 0.869309838472834,
      "grad_norm": 0.08523637801408768,
      "learning_rate": 1.2937810698057921e-05,
      "loss": 0.5332,
      "step": 740
    },
    {
      "epoch": 0.8810572687224669,
      "grad_norm": 0.08431612700223923,
      "learning_rate": 1.0757435084658694e-05,
      "loss": 0.5198,
      "step": 750
    },
    {
      "epoch": 0.8928046989720999,
      "grad_norm": 0.08998807519674301,
      "learning_rate": 8.771339994987953e-06,
      "loss": 0.5251,
      "step": 760
    },
    {
      "epoch": 0.9045521292217328,
      "grad_norm": 0.08884080499410629,
      "learning_rate": 6.98229656152543e-06,
      "loss": 0.5449,
      "step": 770
    },
    {
      "epoch": 0.9162995594713657,
      "grad_norm": 0.08583056926727295,
      "learning_rate": 5.392800977123047e-06,
      "loss": 0.5264,
      "step": 780
    },
    {
      "epoch": 0.9280469897209985,
      "grad_norm": 0.08824951946735382,
      "learning_rate": 4.005071012149952e-06,
      "loss": 0.5306,
      "step": 790
    },
    {
      "epoch": 0.9397944199706314,
      "grad_norm": 0.08726619184017181,
      "learning_rate": 2.821042920111427e-06,
      "loss": 0.5205,
      "step": 800
    },
    {
      "epoch": 0.9515418502202643,
      "grad_norm": 0.08729498088359833,
      "learning_rate": 1.8423687360584137e-06,
      "loss": 0.5217,
      "step": 810
    },
    {
      "epoch": 0.9632892804698973,
      "grad_norm": 0.08497074991464615,
      "learning_rate": 1.070413971558115e-06,
      "loss": 0.534,
      "step": 820
    },
    {
      "epoch": 0.9750367107195301,
      "grad_norm": 0.08497001975774765,
      "learning_rate": 5.062557094410058e-07,
      "loss": 0.5241,
      "step": 830
    },
    {
      "epoch": 0.986784140969163,
      "grad_norm": 0.08295251429080963,
      "learning_rate": 1.5068110098296338e-07,
      "loss": 0.5337,
      "step": 840
    },
    {
      "epoch": 0.9985315712187959,
      "grad_norm": 0.10860061645507812,
      "learning_rate": 0.00022638651575377874,
      "loss": 0.5227,
      "step": 850
    },
    {
      "epoch": 1.0105726872246696,
      "grad_norm": 0.11796294897794724,
      "learning_rate": 0.00022478592280680777,
      "loss": 0.588,
      "step": 860
    },
    {
      "epoch": 1.0223201174743024,
      "grad_norm": 0.1594405323266983,
      "learning_rate": 0.0002231739162937319,
      "loss": 0.5307,
      "step": 870
    },
    {
      "epoch": 1.0340675477239354,
      "grad_norm": 0.10787333548069,
      "learning_rate": 0.0002215507422333499,
      "loss": 0.5359,
      "step": 880
    },
    {
      "epoch": 1.0458149779735684,
      "grad_norm": 0.10763130336999893,
      "learning_rate": 0.0002199166483488127,
      "loss": 0.5407,
      "step": 890
    },
    {
      "epoch": 1.0575624082232011,
      "grad_norm": 0.13658902049064636,
      "learning_rate": 0.00021827188402981652,
      "loss": 0.5255,
      "step": 900
    },
    {
      "epoch": 1.0693098384728341,
      "grad_norm": 0.10522827506065369,
      "learning_rate": 0.00021661670029454207,
      "loss": 0.5276,
      "step": 910
    },
    {
      "epoch": 1.0810572687224669,
      "grad_norm": 0.1422538459300995,
      "learning_rate": 0.0002149513497513448,
      "loss": 0.5245,
      "step": 920
    },
    {
      "epoch": 1.0928046989720999,
      "grad_norm": 0.10326780378818512,
      "learning_rate": 0.00021327608656020305,
      "loss": 0.5294,
      "step": 930
    },
    {
      "epoch": 1.1045521292217328,
      "grad_norm": 0.11100132018327713,
      "learning_rate": 0.00021159116639392868,
      "loss": 0.52,
      "step": 940
    },
    {
      "epoch": 1.1162995594713656,
      "grad_norm": 0.09583411365747452,
      "learning_rate": 0.00020989684639914738,
      "loss": 0.5247,
      "step": 950
    },
    {
      "epoch": 1.1280469897209986,
      "grad_norm": 0.10812857002019882,
      "learning_rate": 0.00020819338515705378,
      "loss": 0.5236,
      "step": 960
    },
    {
      "epoch": 1.1397944199706314,
      "grad_norm": 0.12208293378353119,
      "learning_rate": 0.00020648104264394784,
      "loss": 0.5217,
      "step": 970
    },
    {
      "epoch": 1.1515418502202643,
      "grad_norm": 0.11540035158395767,
      "learning_rate": 0.00020476008019155794,
      "loss": 0.5387,
      "step": 980
    },
    {
      "epoch": 1.1632892804698973,
      "grad_norm": 0.10755149275064468,
      "learning_rate": 0.00020303076044715738,
      "loss": 0.5057,
      "step": 990
    },
    {
      "epoch": 1.17503671071953,
      "grad_norm": 0.10145018994808197,
      "learning_rate": 0.0002012933473334804,
      "loss": 0.5202,
      "step": 1000
    },
    {
      "epoch": 1.186784140969163,
      "grad_norm": 0.11095395684242249,
      "learning_rate": 0.00019954810600844277,
      "loss": 0.5314,
      "step": 1010
    },
    {
      "epoch": 1.1985315712187958,
      "grad_norm": 0.097834512591362,
      "learning_rate": 0.00019779530282467456,
      "loss": 0.5178,
      "step": 1020
    },
    {
      "epoch": 1.2102790014684288,
      "grad_norm": 0.09915532171726227,
      "learning_rate": 0.00019603520528887027,
      "loss": 0.5205,
      "step": 1030
    },
    {
      "epoch": 1.2220264317180616,
      "grad_norm": 0.1107698306441307,
      "learning_rate": 0.00019426808202096298,
      "loss": 0.5268,
      "step": 1040
    },
    {
      "epoch": 1.2337738619676946,
      "grad_norm": 0.11669424921274185,
      "learning_rate": 0.0001924942027131284,
      "loss": 0.53,
      "step": 1050
    },
    {
      "epoch": 1.2455212922173275,
      "grad_norm": 0.11590099334716797,
      "learning_rate": 0.00019071383808862534,
      "loss": 0.5085,
      "step": 1060
    },
    {
      "epoch": 1.2572687224669603,
      "grad_norm": 0.1027660220861435,
      "learning_rate": 0.00018892725986047917,
      "loss": 0.5193,
      "step": 1070
    },
    {
      "epoch": 1.2690161527165933,
      "grad_norm": 0.09436651319265366,
      "learning_rate": 0.00018713474069001354,
      "loss": 0.5002,
      "step": 1080
    },
    {
      "epoch": 1.280763582966226,
      "grad_norm": 0.11379121989011765,
      "learning_rate": 0.00018533655414523808,
      "loss": 0.5212,
      "step": 1090
    },
    {
      "epoch": 1.292511013215859,
      "grad_norm": 0.09809733927249908,
      "learning_rate": 0.00018353297465909717,
      "loss": 0.5124,
      "step": 1100
    },
    {
      "epoch": 1.3042584434654918,
      "grad_norm": 0.1027405858039856,
      "learning_rate": 0.00018172427748758713,
      "loss": 0.5177,
      "step": 1110
    },
    {
      "epoch": 1.3160058737151248,
      "grad_norm": 0.10089763253927231,
      "learning_rate": 0.0001799107386677475,
      "loss": 0.4969,
      "step": 1120
    },
    {
      "epoch": 1.3277533039647578,
      "grad_norm": 0.09994267672300339,
      "learning_rate": 0.0001780926349755332,
      "loss": 0.516,
      "step": 1130
    },
    {
      "epoch": 1.3395007342143905,
      "grad_norm": 0.10974204540252686,
      "learning_rate": 0.00017627024388357416,
      "loss": 0.5035,
      "step": 1140
    },
    {
      "epoch": 1.3512481644640235,
      "grad_norm": 0.09834876656532288,
      "learning_rate": 0.00017444384351882817,
      "loss": 0.5121,
      "step": 1150
    },
    {
      "epoch": 1.3629955947136563,
      "grad_norm": 0.09756341576576233,
      "learning_rate": 0.0001726137126201342,
      "loss": 0.5289,
      "step": 1160
    },
    {
      "epoch": 1.3747430249632893,
      "grad_norm": 0.09796813875436783,
      "learning_rate": 0.0001707801304956723,
      "loss": 0.5054,
      "step": 1170
    },
    {
      "epoch": 1.3864904552129222,
      "grad_norm": 0.09447074681520462,
      "learning_rate": 0.00016894337698033663,
      "loss": 0.5067,
      "step": 1180
    },
    {
      "epoch": 1.398237885462555,
      "grad_norm": 0.10086411237716675,
      "learning_rate": 0.00016710373239302772,
      "loss": 0.5191,
      "step": 1190
    },
    {
      "epoch": 1.409985315712188,
      "grad_norm": 0.10048293322324753,
      "learning_rate": 0.00016526147749387155,
      "loss": 0.5073,
      "step": 1200
    }
  ],
  "logging_steps": 10,
  "max_steps": 2553,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.543416954085966e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}