{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9956108266276518,
  "eval_steps": 500,
  "global_step": 1023,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029261155815654718,
      "grad_norm": 14.668970176640238,
      "learning_rate": 3.2467532467532465e-07,
      "loss": 0.8895,
      "step": 10
    },
    {
      "epoch": 0.058522311631309436,
      "grad_norm": 8.496797294755972,
      "learning_rate": 6.493506493506493e-07,
      "loss": 0.8811,
      "step": 20
    },
    {
      "epoch": 0.08778346744696415,
      "grad_norm": 5.273308597570782,
      "learning_rate": 9.740259740259742e-07,
      "loss": 0.8154,
      "step": 30
    },
    {
      "epoch": 0.11704462326261887,
      "grad_norm": 1.433583789015455,
      "learning_rate": 1.2987012987012986e-06,
      "loss": 0.7741,
      "step": 40
    },
    {
      "epoch": 0.14630577907827358,
      "grad_norm": 1.3261000645447931,
      "learning_rate": 1.6233766233766235e-06,
      "loss": 0.75,
      "step": 50
    },
    {
      "epoch": 0.1755669348939283,
      "grad_norm": 1.2156691515832625,
      "learning_rate": 1.9480519480519483e-06,
      "loss": 0.7318,
      "step": 60
    },
    {
      "epoch": 0.20482809070958302,
      "grad_norm": 1.1401188906701956,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.7198,
      "step": 70
    },
    {
      "epoch": 0.23408924652523774,
      "grad_norm": 1.1329393438430202,
      "learning_rate": 2.597402597402597e-06,
      "loss": 0.7105,
      "step": 80
    },
    {
      "epoch": 0.26335040234089246,
      "grad_norm": 1.1907330376838692,
      "learning_rate": 2.922077922077922e-06,
      "loss": 0.7019,
      "step": 90
    },
    {
      "epoch": 0.29261155815654716,
      "grad_norm": 1.1364555929890368,
      "learning_rate": 3.246753246753247e-06,
      "loss": 0.6877,
      "step": 100
    },
    {
      "epoch": 0.3218727139722019,
      "grad_norm": 1.1288685178187858,
      "learning_rate": 3.5714285714285718e-06,
      "loss": 0.6901,
      "step": 110
    },
    {
      "epoch": 0.3511338697878566,
      "grad_norm": 0.8110371303333744,
      "learning_rate": 3.896103896103897e-06,
      "loss": 0.689,
      "step": 120
    },
    {
      "epoch": 0.38039502560351135,
      "grad_norm": 0.5818728259370487,
      "learning_rate": 4.220779220779221e-06,
      "loss": 0.6671,
      "step": 130
    },
    {
      "epoch": 0.40965618141916604,
      "grad_norm": 0.5304327111513184,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.6646,
      "step": 140
    },
    {
      "epoch": 0.4389173372348208,
      "grad_norm": 0.36685425891028794,
      "learning_rate": 4.870129870129871e-06,
      "loss": 0.658,
      "step": 150
    },
    {
      "epoch": 0.4681784930504755,
      "grad_norm": 0.41183157231085515,
      "learning_rate": 4.9994118939080335e-06,
      "loss": 0.6589,
      "step": 160
    },
    {
      "epoch": 0.49743964886613024,
      "grad_norm": 0.4031968246741201,
      "learning_rate": 4.995818914209129e-06,
      "loss": 0.6632,
      "step": 170
    },
    {
      "epoch": 0.5267008046817849,
      "grad_norm": 0.3548947303493851,
      "learning_rate": 4.988964370070926e-06,
      "loss": 0.6621,
      "step": 180
    },
    {
      "epoch": 0.5559619604974396,
      "grad_norm": 0.3686485941331636,
      "learning_rate": 4.978857219089375e-06,
      "loss": 0.6499,
      "step": 190
    },
    {
      "epoch": 0.5852231163130943,
      "grad_norm": 0.35209709708441134,
      "learning_rate": 4.965510669403914e-06,
      "loss": 0.6505,
      "step": 200
    },
    {
      "epoch": 0.6144842721287491,
      "grad_norm": 0.37518333436501056,
      "learning_rate": 4.948942162436912e-06,
      "loss": 0.6568,
      "step": 210
    },
    {
      "epoch": 0.6437454279444038,
      "grad_norm": 0.36805268655746204,
      "learning_rate": 4.929173350101025e-06,
      "loss": 0.6443,
      "step": 220
    },
    {
      "epoch": 0.6730065837600585,
      "grad_norm": 0.3786724277264378,
      "learning_rate": 4.906230066504232e-06,
      "loss": 0.644,
      "step": 230
    },
    {
      "epoch": 0.7022677395757132,
      "grad_norm": 0.45256944433012264,
      "learning_rate": 4.880142294189524e-06,
      "loss": 0.6509,
      "step": 240
    },
    {
      "epoch": 0.731528895391368,
      "grad_norm": 0.3534837053618171,
      "learning_rate": 4.850944124953386e-06,
      "loss": 0.6489,
      "step": 250
    },
    {
      "epoch": 0.7607900512070227,
      "grad_norm": 0.3462376731623333,
      "learning_rate": 4.818673715294245e-06,
      "loss": 0.6512,
      "step": 260
    },
    {
      "epoch": 0.7900512070226774,
      "grad_norm": 0.3659651498084311,
      "learning_rate": 4.783373236549124e-06,
      "loss": 0.6533,
      "step": 270
    },
    {
      "epoch": 0.8193123628383321,
      "grad_norm": 0.3464863446071885,
      "learning_rate": 4.7450888197836705e-06,
      "loss": 0.6519,
      "step": 280
    },
    {
      "epoch": 0.8485735186539868,
      "grad_norm": 0.3446817147136836,
      "learning_rate": 4.703870495507544e-06,
      "loss": 0.6439,
      "step": 290
    },
    {
      "epoch": 0.8778346744696416,
      "grad_norm": 0.3663029532843638,
      "learning_rate": 4.659772128293987e-06,
      "loss": 0.6357,
      "step": 300
    },
    {
      "epoch": 0.9070958302852963,
      "grad_norm": 0.3478317684389932,
      "learning_rate": 4.612851346388991e-06,
      "loss": 0.6487,
      "step": 310
    },
    {
      "epoch": 0.936356986100951,
      "grad_norm": 0.3335766728870111,
      "learning_rate": 4.563169466402049e-06,
      "loss": 0.6405,
      "step": 320
    },
    {
      "epoch": 0.9656181419166057,
      "grad_norm": 0.3761185295308495,
      "learning_rate": 4.510791413176912e-06,
      "loss": 0.6436,
      "step": 330
    },
    {
      "epoch": 0.9948792977322605,
      "grad_norm": 0.35211941336512004,
      "learning_rate": 4.455785634947077e-06,
      "loss": 0.6395,
      "step": 340
    },
    {
      "epoch": 0.9978054133138259,
      "eval_loss": 0.6440162658691406,
      "eval_runtime": 342.2489,
      "eval_samples_per_second": 26.907,
      "eval_steps_per_second": 0.421,
      "step": 341
    },
    {
      "epoch": 1.025237746891002,
      "grad_norm": 0.36200167522916055,
      "learning_rate": 4.39822401388685e-06,
      "loss": 0.6599,
      "step": 350
    },
    {
      "epoch": 1.054498902706657,
      "grad_norm": 0.368658897798918,
      "learning_rate": 4.338181772174911e-06,
      "loss": 0.6147,
      "step": 360
    },
    {
      "epoch": 1.0837600585223117,
      "grad_norm": 0.39675018773491727,
      "learning_rate": 4.275737373693118e-06,
      "loss": 0.6179,
      "step": 370
    },
    {
      "epoch": 1.1130212143379663,
      "grad_norm": 0.31910150452705416,
      "learning_rate": 4.210972421489018e-06,
      "loss": 0.6151,
      "step": 380
    },
    {
      "epoch": 1.142282370153621,
      "grad_norm": 0.4146599554888977,
      "learning_rate": 4.143971551136056e-06,
      "loss": 0.6203,
      "step": 390
    },
    {
      "epoch": 1.1715435259692757,
      "grad_norm": 0.37145656101773866,
      "learning_rate": 4.074822320130852e-06,
      "loss": 0.6219,
      "step": 400
    },
    {
      "epoch": 1.2008046817849305,
      "grad_norm": 0.3369796774780415,
      "learning_rate": 4.003615093472073e-06,
      "loss": 0.6216,
      "step": 410
    },
    {
      "epoch": 1.2300658376005853,
      "grad_norm": 0.3498594570629417,
      "learning_rate": 3.930442925570424e-06,
      "loss": 0.6093,
      "step": 420
    },
    {
      "epoch": 1.2593269934162399,
      "grad_norm": 0.32836497624245026,
      "learning_rate": 3.855401438644094e-06,
      "loss": 0.6195,
      "step": 430
    },
    {
      "epoch": 1.2885881492318947,
      "grad_norm": 0.3837720666133545,
      "learning_rate": 3.7785886977585562e-06,
      "loss": 0.6116,
      "step": 440
    },
    {
      "epoch": 1.3178493050475493,
      "grad_norm": 0.34346193540291065,
      "learning_rate": 3.7001050826740294e-06,
      "loss": 0.6157,
      "step": 450
    },
    {
      "epoch": 1.347110460863204,
      "grad_norm": 0.33632056202086974,
      "learning_rate": 3.6200531566680695e-06,
      "loss": 0.6128,
      "step": 460
    },
    {
      "epoch": 1.3763716166788589,
      "grad_norm": 0.33016686130410977,
      "learning_rate": 3.5385375325047167e-06,
      "loss": 0.6101,
      "step": 470
    },
    {
      "epoch": 1.4056327724945135,
      "grad_norm": 0.3322405360416849,
      "learning_rate": 3.4556647357253485e-06,
      "loss": 0.6107,
      "step": 480
    },
    {
      "epoch": 1.4348939283101683,
      "grad_norm": 0.3766853715733656,
      "learning_rate": 3.3715430654398994e-06,
      "loss": 0.6172,
      "step": 490
    },
    {
      "epoch": 1.464155084125823,
      "grad_norm": 0.3420044761963859,
      "learning_rate": 3.286282452800349e-06,
      "loss": 0.6054,
      "step": 500
    },
    {
      "epoch": 1.4934162399414777,
      "grad_norm": 0.3312255181380896,
      "learning_rate": 3.1999943173414545e-06,
      "loss": 0.6135,
      "step": 510
    },
    {
      "epoch": 1.5226773957571325,
      "grad_norm": 0.34026173676689114,
      "learning_rate": 3.1127914213764365e-06,
      "loss": 0.6158,
      "step": 520
    },
    {
      "epoch": 1.5519385515727873,
      "grad_norm": 0.33625103408517465,
      "learning_rate": 3.0247877226379123e-06,
      "loss": 0.6145,
      "step": 530
    },
    {
      "epoch": 1.5811997073884418,
      "grad_norm": 0.3367264230640958,
      "learning_rate": 2.9360982253566372e-06,
      "loss": 0.621,
      "step": 540
    },
    {
      "epoch": 1.6104608632040964,
      "grad_norm": 0.3508021187615357,
      "learning_rate": 2.8468388299726714e-06,
      "loss": 0.6116,
      "step": 550
    },
    {
      "epoch": 1.6397220190197512,
      "grad_norm": 0.3329430390973009,
      "learning_rate": 2.7571261816753756e-06,
      "loss": 0.6135,
      "step": 560
    },
    {
      "epoch": 1.668983174835406,
      "grad_norm": 0.32493005225042776,
      "learning_rate": 2.667077517970155e-06,
      "loss": 0.6039,
      "step": 570
    },
    {
      "epoch": 1.6982443306510606,
      "grad_norm": 0.3416247340300911,
      "learning_rate": 2.5768105154711563e-06,
      "loss": 0.6134,
      "step": 580
    },
    {
      "epoch": 1.7275054864667154,
      "grad_norm": 0.32203254574334095,
      "learning_rate": 2.4864431361201358e-06,
      "loss": 0.6131,
      "step": 590
    },
    {
      "epoch": 1.7567666422823702,
      "grad_norm": 0.34441300170978906,
      "learning_rate": 2.396093473032457e-06,
      "loss": 0.61,
      "step": 600
    },
    {
      "epoch": 1.7860277980980248,
      "grad_norm": 0.34502988222958175,
      "learning_rate": 2.305879596171672e-06,
      "loss": 0.6126,
      "step": 610
    },
    {
      "epoch": 1.8152889539136796,
      "grad_norm": 0.31129433406639495,
      "learning_rate": 2.2159193980543504e-06,
      "loss": 0.6129,
      "step": 620
    },
    {
      "epoch": 1.8445501097293344,
      "grad_norm": 0.3234044124788837,
      "learning_rate": 2.126330439686806e-06,
      "loss": 0.6121,
      "step": 630
    },
    {
      "epoch": 1.873811265544989,
      "grad_norm": 0.32298142157786064,
      "learning_rate": 2.037229796935041e-06,
      "loss": 0.6065,
      "step": 640
    },
    {
      "epoch": 1.9030724213606436,
      "grad_norm": 0.33703026308837425,
      "learning_rate": 1.948733907528678e-06,
      "loss": 0.6124,
      "step": 650
    },
    {
      "epoch": 1.9323335771762986,
      "grad_norm": 0.31918477425731495,
      "learning_rate": 1.8609584188988135e-06,
      "loss": 0.6128,
      "step": 660
    },
    {
      "epoch": 1.9615947329919532,
      "grad_norm": 0.3240942780939225,
      "learning_rate": 1.774018037048647e-06,
      "loss": 0.6016,
      "step": 670
    },
    {
      "epoch": 1.9908558888076078,
      "grad_norm": 0.3172940503810845,
      "learning_rate": 1.6880263766543742e-06,
      "loss": 0.6162,
      "step": 680
    },
    {
      "epoch": 1.9967081199707388,
      "eval_loss": 0.6352197527885437,
      "eval_runtime": 341.3485,
      "eval_samples_per_second": 26.978,
      "eval_steps_per_second": 0.422,
      "step": 682
    },
    {
      "epoch": 2.0212143379663496,
      "grad_norm": 0.3175314791094243,
      "learning_rate": 1.6030958125922416e-06,
      "loss": 0.6344,
      "step": 690
    },
    {
      "epoch": 2.050475493782004,
      "grad_norm": 0.31427421868845,
      "learning_rate": 1.5193373330857852e-06,
      "loss": 0.5848,
      "step": 700
    },
    {
      "epoch": 2.0797366495976592,
      "grad_norm": 0.3050138399442785,
      "learning_rate": 1.436860394665161e-06,
      "loss": 0.5869,
      "step": 710
    },
    {
      "epoch": 2.108997805413314,
      "grad_norm": 0.3287719989093099,
      "learning_rate": 1.3557727791281144e-06,
      "loss": 0.588,
      "step": 720
    },
    {
      "epoch": 2.1382589612289684,
      "grad_norm": 0.3211488131597453,
      "learning_rate": 1.2761804526894973e-06,
      "loss": 0.5897,
      "step": 730
    },
    {
      "epoch": 2.1675201170446234,
      "grad_norm": 0.3354985605470603,
      "learning_rate": 1.1981874275034292e-06,
      "loss": 0.5945,
      "step": 740
    },
    {
      "epoch": 2.196781272860278,
      "grad_norm": 0.330245659117232,
      "learning_rate": 1.121895625739026e-06,
      "loss": 0.5931,
      "step": 750
    },
    {
      "epoch": 2.2260424286759326,
      "grad_norm": 0.34341233350847544,
      "learning_rate": 1.0474047463873615e-06,
      "loss": 0.5903,
      "step": 760
    },
    {
      "epoch": 2.255303584491587,
      "grad_norm": 0.30870638315996124,
      "learning_rate": 9.74812134973689e-07,
      "loss": 0.5884,
      "step": 770
    },
    {
      "epoch": 2.284564740307242,
      "grad_norm": 0.31977910069700466,
      "learning_rate": 9.042126563452127e-07,
      "loss": 0.5878,
      "step": 780
    },
    {
      "epoch": 2.313825896122897,
      "grad_norm": 0.3031431539019493,
      "learning_rate": 8.356985707006268e-07,
      "loss": 0.5858,
      "step": 790
    },
    {
      "epoch": 2.3430870519385514,
      "grad_norm": 0.3128129431092359,
      "learning_rate": 7.6935941302344e-07,
      "loss": 0.5935,
      "step": 800
    },
    {
      "epoch": 2.3723482077542064,
      "grad_norm": 0.3086236399140173,
      "learning_rate": 7.052818760766511e-07,
      "loss": 0.5884,
      "step": 810
    },
    {
      "epoch": 2.401609363569861,
      "grad_norm": 0.3209593796492324,
      "learning_rate": 6.435496971116578e-07,
      "loss": 0.5945,
      "step": 820
    },
    {
      "epoch": 2.4308705193855156,
      "grad_norm": 0.2958964862772339,
      "learning_rate": 5.842435484394701e-07,
      "loss": 0.5868,
      "step": 830
    },
    {
      "epoch": 2.4601316752011706,
      "grad_norm": 0.3051666167851246,
      "learning_rate": 5.274409320072202e-07,
      "loss": 0.5872,
      "step": 840
    },
    {
      "epoch": 2.489392831016825,
      "grad_norm": 0.3116559897212902,
      "learning_rate": 4.7321607811774056e-07,
      "loss": 0.5889,
      "step": 850
    },
    {
      "epoch": 2.5186539868324798,
      "grad_norm": 0.3162392315755417,
      "learning_rate": 4.2163984842456043e-07,
      "loss": 0.5821,
      "step": 860
    },
    {
      "epoch": 2.547915142648135,
      "grad_norm": 0.3108046500670305,
      "learning_rate": 3.7277964332909645e-07,
      "loss": 0.5844,
      "step": 870
    },
    {
      "epoch": 2.5771762984637894,
      "grad_norm": 0.2946758208140416,
      "learning_rate": 3.266993139010438e-07,
      "loss": 0.5885,
      "step": 880
    },
    {
      "epoch": 2.606437454279444,
      "grad_norm": 0.30055832996790277,
      "learning_rate": 2.8345907843707304e-07,
      "loss": 0.5881,
      "step": 890
    },
    {
      "epoch": 2.6356986100950985,
      "grad_norm": 0.30952781379566374,
      "learning_rate": 2.4311544376688035e-07,
      "loss": 0.5925,
      "step": 900
    },
    {
      "epoch": 2.6649597659107536,
      "grad_norm": 0.3047050770609814,
      "learning_rate": 2.0572113140941985e-07,
      "loss": 0.5929,
      "step": 910
    },
    {
      "epoch": 2.694220921726408,
      "grad_norm": 0.31153516958982186,
      "learning_rate": 1.7132500867582695e-07,
      "loss": 0.5868,
      "step": 920
    },
    {
      "epoch": 2.723482077542063,
      "grad_norm": 0.3185842923901254,
      "learning_rate": 1.399720248090608e-07,
      "loss": 0.5901,
      "step": 930
    },
    {
      "epoch": 2.7527432333577178,
      "grad_norm": 0.3109345062558724,
      "learning_rate": 1.1170315224372507e-07,
      "loss": 0.589,
      "step": 940
    },
    {
      "epoch": 2.7820043891733723,
      "grad_norm": 0.29604620944870486,
      "learning_rate": 8.655533306282687e-08,
      "loss": 0.5876,
      "step": 950
    },
    {
      "epoch": 2.811265544989027,
      "grad_norm": 0.36359227990850435,
      "learning_rate": 6.456143072144261e-08,
      "loss": 0.5915,
      "step": 960
    },
    {
      "epoch": 2.840526700804682,
      "grad_norm": 0.2960058344228556,
      "learning_rate": 4.5750187100383204e-08,
      "loss": 0.5872,
      "step": 970
    },
    {
      "epoch": 2.8697878566203365,
      "grad_norm": 0.30121823974621786,
      "learning_rate": 3.0146184945978595e-08,
      "loss": 0.5873,
      "step": 980
    },
    {
      "epoch": 2.899049012435991,
      "grad_norm": 0.2997640067590943,
      "learning_rate": 1.7769815745066476e-08,
      "loss": 0.5799,
      "step": 990
    },
    {
      "epoch": 2.928310168251646,
      "grad_norm": 0.3145839088496146,
      "learning_rate": 8.637253077165287e-09,
      "loss": 0.5878,
      "step": 1000
    },
    {
      "epoch": 2.9575713240673007,
      "grad_norm": 0.30040451461060846,
      "learning_rate": 2.760431478658343e-09,
      "loss": 0.5791,
      "step": 1010
    },
    {
      "epoch": 2.9868324798829553,
      "grad_norm": 0.30168448002353826,
      "learning_rate": 1.470308466056114e-10,
      "loss": 0.591,
      "step": 1020
    },
    {
      "epoch": 2.9956108266276518,
      "eval_loss": 0.6357085704803467,
      "eval_runtime": 340.5768,
      "eval_samples_per_second": 27.039,
      "eval_steps_per_second": 0.423,
      "step": 1023
    },
    {
      "epoch": 2.9956108266276518,
      "step": 1023,
      "total_flos": 2144987064041472.0,
      "train_loss": 0.6305035024094792,
      "train_runtime": 54804.0253,
      "train_samples_per_second": 9.577,
      "train_steps_per_second": 0.019
    }
  ],
  "logging_steps": 10,
  "max_steps": 1023,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2144987064041472.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}