{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16005868818566807,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001333822401547234,
      "grad_norm": 5.80256772259428,
      "learning_rate": 4e-06,
      "loss": 1.0498,
      "step": 10
    },
    {
      "epoch": 0.002667644803094468,
      "grad_norm": 33.895696082107904,
      "learning_rate": 8e-06,
      "loss": 1.0653,
      "step": 20
    },
    {
      "epoch": 0.004001467204641702,
      "grad_norm": 5.523348234283539,
      "learning_rate": 1.2e-05,
      "loss": 1.0341,
      "step": 30
    },
    {
      "epoch": 0.005335289606188936,
      "grad_norm": 11.1556403156453,
      "learning_rate": 1.6e-05,
      "loss": 0.9692,
      "step": 40
    },
    {
      "epoch": 0.00666911200773617,
      "grad_norm": 3.7375231126561825,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.9554,
      "step": 50
    },
    {
      "epoch": 0.008002934409283404,
      "grad_norm": 8.43538339698909,
      "learning_rate": 2.4e-05,
      "loss": 0.8965,
      "step": 60
    },
    {
      "epoch": 0.009336756810830639,
      "grad_norm": 13.403454896011478,
      "learning_rate": 2.8e-05,
      "loss": 0.8273,
      "step": 70
    },
    {
      "epoch": 0.010670579212377872,
      "grad_norm": 3.95522050766088,
      "learning_rate": 2.9999966406213696e-05,
      "loss": 0.7837,
      "step": 80
    },
    {
      "epoch": 0.012004401613925107,
      "grad_norm": 36.799552052300854,
      "learning_rate": 2.9999697656826056e-05,
      "loss": 0.8288,
      "step": 90
    },
    {
      "epoch": 0.01333822401547234,
      "grad_norm": 1.6305479563258536,
      "learning_rate": 2.9999160162865885e-05,
      "loss": 0.7778,
      "step": 100
    },
    {
      "epoch": 0.014672046417019574,
      "grad_norm": 2.159536648784889,
      "learning_rate": 2.9998353933963273e-05,
      "loss": 0.7616,
      "step": 110
    },
    {
      "epoch": 0.016005868818566808,
      "grad_norm": 3.397321425707004,
      "learning_rate": 2.999727898456315e-05,
      "loss": 0.7594,
      "step": 120
    },
    {
      "epoch": 0.017339691220114042,
      "grad_norm": 4.772220837365037,
      "learning_rate": 2.999593533392503e-05,
      "loss": 0.756,
      "step": 130
    },
    {
      "epoch": 0.018673513621661277,
      "grad_norm": 2.4845945633126885,
      "learning_rate": 2.9994323006122654e-05,
      "loss": 0.7601,
      "step": 140
    },
    {
      "epoch": 0.02000733602320851,
      "grad_norm": 3.591682569169127,
      "learning_rate": 2.9992442030043557e-05,
      "loss": 0.7894,
      "step": 150
    },
    {
      "epoch": 0.021341158424755743,
      "grad_norm": 2.5679458807474416,
      "learning_rate": 2.9990292439388565e-05,
      "loss": 0.7093,
      "step": 160
    },
    {
      "epoch": 0.022674980826302978,
      "grad_norm": 1.9412569107551652,
      "learning_rate": 2.9987874272671168e-05,
      "loss": 0.706,
      "step": 170
    },
    {
      "epoch": 0.024008803227850213,
      "grad_norm": 3.2667097270489,
      "learning_rate": 2.9985187573216855e-05,
      "loss": 0.7586,
      "step": 180
    },
    {
      "epoch": 0.025342625629397444,
      "grad_norm": 4.4208737375400675,
      "learning_rate": 2.998223238916232e-05,
      "loss": 0.6985,
      "step": 190
    },
    {
      "epoch": 0.02667644803094468,
      "grad_norm": 5.515966302183704,
      "learning_rate": 2.9979008773454618e-05,
      "loss": 0.7323,
      "step": 200
    },
    {
      "epoch": 0.028010270432491914,
      "grad_norm": 2.964165450396077,
      "learning_rate": 2.997551678385019e-05,
      "loss": 0.7603,
      "step": 210
    },
    {
      "epoch": 0.02934409283403915,
      "grad_norm": 3.0952916783456197,
      "learning_rate": 2.997175648291384e-05,
      "loss": 0.7421,
      "step": 220
    },
    {
      "epoch": 0.03067791523558638,
      "grad_norm": 4.213588693904103,
      "learning_rate": 2.996772793801763e-05,
      "loss": 0.7322,
      "step": 230
    },
    {
      "epoch": 0.032011737637133615,
      "grad_norm": 1.8568586103139084,
      "learning_rate": 2.996343122133965e-05,
      "loss": 0.6922,
      "step": 240
    },
    {
      "epoch": 0.033345560038680847,
      "grad_norm": 4.494146778909846,
      "learning_rate": 2.9958866409862745e-05,
      "loss": 0.7244,
      "step": 250
    },
    {
      "epoch": 0.034679382440228085,
      "grad_norm": 7.438170074282725,
      "learning_rate": 2.9954033585373108e-05,
      "loss": 0.7093,
      "step": 260
    },
    {
      "epoch": 0.036013204841775316,
      "grad_norm": 2.3744787346857015,
      "learning_rate": 2.994893283445885e-05,
      "loss": 0.6983,
      "step": 270
    },
    {
      "epoch": 0.037347027243322554,
      "grad_norm": 1.4722011682616383,
      "learning_rate": 2.9943564248508415e-05,
      "loss": 0.6781,
      "step": 280
    },
    {
      "epoch": 0.038680849644869786,
      "grad_norm": 3.3397620832486075,
      "learning_rate": 2.9937927923708966e-05,
      "loss": 0.7399,
      "step": 290
    },
    {
      "epoch": 0.04001467204641702,
      "grad_norm": 5.05063397044549,
      "learning_rate": 2.993202396104465e-05,
      "loss": 0.7671,
      "step": 300
    },
    {
      "epoch": 0.041348494447964255,
      "grad_norm": 3.0128431385936767,
      "learning_rate": 2.9925852466294795e-05,
      "loss": 0.7015,
      "step": 310
    },
    {
      "epoch": 0.04268231684951149,
      "grad_norm": 2.0161342716764237,
      "learning_rate": 2.9919413550032014e-05,
      "loss": 0.7009,
      "step": 320
    },
    {
      "epoch": 0.04401613925105872,
      "grad_norm": 1.3114004070324985,
      "learning_rate": 2.991270732762022e-05,
      "loss": 0.7153,
      "step": 330
    },
    {
      "epoch": 0.045349961652605957,
      "grad_norm": 18.493625676806268,
      "learning_rate": 2.990573391921255e-05,
      "loss": 0.7518,
      "step": 340
    },
    {
      "epoch": 0.04668378405415319,
      "grad_norm": 2.9526764059703567,
      "learning_rate": 2.989849344974924e-05,
      "loss": 0.7133,
      "step": 350
    },
    {
      "epoch": 0.048017606455700426,
      "grad_norm": 5.26274958582726,
      "learning_rate": 2.9890986048955368e-05,
      "loss": 0.7139,
      "step": 360
    },
    {
      "epoch": 0.04935142885724766,
      "grad_norm": 3.5319788357887933,
      "learning_rate": 2.9883211851338516e-05,
      "loss": 0.7084,
      "step": 370
    },
    {
      "epoch": 0.05068525125879489,
      "grad_norm": 7.607269935902469,
      "learning_rate": 2.9875170996186392e-05,
      "loss": 0.7309,
      "step": 380
    },
    {
      "epoch": 0.05201907366034213,
      "grad_norm": 2.3456663308287253,
      "learning_rate": 2.986686362756431e-05,
      "loss": 0.6827,
      "step": 390
    },
    {
      "epoch": 0.05335289606188936,
      "grad_norm": 2.176182050789012,
      "learning_rate": 2.9858289894312617e-05,
      "loss": 0.6995,
      "step": 400
    },
    {
      "epoch": 0.0546867184634366,
      "grad_norm": 11.171630173781537,
      "learning_rate": 2.9849449950044036e-05,
      "loss": 0.7335,
      "step": 410
    },
    {
      "epoch": 0.05602054086498383,
      "grad_norm": 6.63441431767892,
      "learning_rate": 2.984034395314088e-05,
      "loss": 0.7031,
      "step": 420
    },
    {
      "epoch": 0.05735436326653106,
      "grad_norm": 2.861620412225736,
      "learning_rate": 2.983097206675227e-05,
      "loss": 0.6559,
      "step": 430
    },
    {
      "epoch": 0.0586881856680783,
      "grad_norm": 5.523165036486206,
      "learning_rate": 2.9821334458791156e-05,
      "loss": 0.726,
      "step": 440
    },
    {
      "epoch": 0.06002200806962553,
      "grad_norm": 3.5602243751368197,
      "learning_rate": 2.9811431301931344e-05,
      "loss": 0.7202,
      "step": 450
    },
    {
      "epoch": 0.06135583047117276,
      "grad_norm": 11.333380381168622,
      "learning_rate": 2.9801262773604377e-05,
      "loss": 0.7189,
      "step": 460
    },
    {
      "epoch": 0.06268965287271999,
      "grad_norm": 14.159758615106613,
      "learning_rate": 2.9790829055996398e-05,
      "loss": 0.7267,
      "step": 470
    },
    {
      "epoch": 0.06402347527426723,
      "grad_norm": 9.009079485918289,
      "learning_rate": 2.978013033604483e-05,
      "loss": 0.748,
      "step": 480
    },
    {
      "epoch": 0.06535729767581447,
      "grad_norm": 1.9682648681675994,
      "learning_rate": 2.976916680543506e-05,
      "loss": 0.7369,
      "step": 490
    },
    {
      "epoch": 0.06669112007736169,
      "grad_norm": 2.9278164598232777,
      "learning_rate": 2.975793866059701e-05,
      "loss": 0.7037,
      "step": 500
    },
    {
      "epoch": 0.06802494247890893,
      "grad_norm": 5.5563562303649885,
      "learning_rate": 2.9746446102701606e-05,
      "loss": 0.6986,
      "step": 510
    },
    {
      "epoch": 0.06935876488045617,
      "grad_norm": 4.036767303783137,
      "learning_rate": 2.9734689337657157e-05,
      "loss": 0.7119,
      "step": 520
    },
    {
      "epoch": 0.07069258728200341,
      "grad_norm": 1.9856990692088847,
      "learning_rate": 2.9722668576105703e-05,
      "loss": 0.7205,
      "step": 530
    },
    {
      "epoch": 0.07202640968355063,
      "grad_norm": 5.200308739226583,
      "learning_rate": 2.971038403341921e-05,
      "loss": 0.6918,
      "step": 540
    },
    {
      "epoch": 0.07336023208509787,
      "grad_norm": 2.237349124701919,
      "learning_rate": 2.9697835929695727e-05,
      "loss": 0.7339,
      "step": 550
    },
    {
      "epoch": 0.07469405448664511,
      "grad_norm": 1.6388680632753365,
      "learning_rate": 2.968502448975544e-05,
      "loss": 0.7086,
      "step": 560
    },
    {
      "epoch": 0.07602787688819233,
      "grad_norm": 2.8545575025135244,
      "learning_rate": 2.967194994313663e-05,
      "loss": 0.678,
      "step": 570
    },
    {
      "epoch": 0.07736169928973957,
      "grad_norm": 2.674647983669599,
      "learning_rate": 2.9658612524091594e-05,
      "loss": 0.7119,
      "step": 580
    },
    {
      "epoch": 0.07869552169128681,
      "grad_norm": 2.489047760330112,
      "learning_rate": 2.9645012471582406e-05,
      "loss": 0.7382,
      "step": 590
    },
    {
      "epoch": 0.08002934409283403,
      "grad_norm": 5.509352102248308,
      "learning_rate": 2.9631150029276662e-05,
      "loss": 0.738,
      "step": 600
    },
    {
      "epoch": 0.08136316649438127,
      "grad_norm": 3.6489235270404015,
      "learning_rate": 2.9617025445543114e-05,
      "loss": 0.7018,
      "step": 610
    },
    {
      "epoch": 0.08269698889592851,
      "grad_norm": 2.7813651243235697,
      "learning_rate": 2.9602638973447218e-05,
      "loss": 0.7381,
      "step": 620
    },
    {
      "epoch": 0.08403081129747574,
      "grad_norm": 8.271390523006518,
      "learning_rate": 2.9587990870746574e-05,
      "loss": 0.7168,
      "step": 630
    },
    {
      "epoch": 0.08536463369902297,
      "grad_norm": 1.2460611751687307,
      "learning_rate": 2.9573081399886356e-05,
      "loss": 0.7004,
      "step": 640
    },
    {
      "epoch": 0.08669845610057021,
      "grad_norm": 1.704626418994062,
      "learning_rate": 2.9557910827994568e-05,
      "loss": 0.738,
      "step": 650
    },
    {
      "epoch": 0.08803227850211744,
      "grad_norm": 3.275051693107957,
      "learning_rate": 2.9542479426877283e-05,
      "loss": 0.7017,
      "step": 660
    },
    {
      "epoch": 0.08936610090366467,
      "grad_norm": 11.389990685570503,
      "learning_rate": 2.9526787473013753e-05,
      "loss": 0.7107,
      "step": 670
    },
    {
      "epoch": 0.09069992330521191,
      "grad_norm": 5.591277359184055,
      "learning_rate": 2.9510835247551485e-05,
      "loss": 0.7141,
      "step": 680
    },
    {
      "epoch": 0.09203374570675915,
      "grad_norm": 3.180111568581053,
      "learning_rate": 2.949462303630116e-05,
      "loss": 0.6987,
      "step": 690
    },
    {
      "epoch": 0.09336756810830638,
      "grad_norm": 3.8428068166831753,
      "learning_rate": 2.9478151129731567e-05,
      "loss": 0.7373,
      "step": 700
    },
    {
      "epoch": 0.09470139050985361,
      "grad_norm": 2.231397231771392,
      "learning_rate": 2.9461419822964348e-05,
      "loss": 0.6962,
      "step": 710
    },
    {
      "epoch": 0.09603521291140085,
      "grad_norm": 18.287201889017563,
      "learning_rate": 2.9444429415768726e-05,
      "loss": 0.6723,
      "step": 720
    },
    {
      "epoch": 0.09736903531294808,
      "grad_norm": 4.340932687135137,
      "learning_rate": 2.942718021255617e-05,
      "loss": 0.7151,
      "step": 730
    },
    {
      "epoch": 0.09870285771449532,
      "grad_norm": 2.7813821825484446,
      "learning_rate": 2.940967252237488e-05,
      "loss": 0.7332,
      "step": 740
    },
    {
      "epoch": 0.10003668011604255,
      "grad_norm": 2.3251782912937475,
      "learning_rate": 2.9391906658904296e-05,
      "loss": 0.6751,
      "step": 750
    },
    {
      "epoch": 0.10137050251758978,
      "grad_norm": 8.123799866292751,
      "learning_rate": 2.937388294044946e-05,
      "loss": 0.6886,
      "step": 760
    },
    {
      "epoch": 0.10270432491913702,
      "grad_norm": 1.528579329214318,
      "learning_rate": 2.9355601689935315e-05,
      "loss": 0.7146,
      "step": 770
    },
    {
      "epoch": 0.10403814732068425,
      "grad_norm": 2.0278953433974825,
      "learning_rate": 2.933706323490092e-05,
      "loss": 0.7453,
      "step": 780
    },
    {
      "epoch": 0.10537196972223148,
      "grad_norm": 1.4306270659678864,
      "learning_rate": 2.9318267907493583e-05,
      "loss": 0.6702,
      "step": 790
    },
    {
      "epoch": 0.10670579212377872,
      "grad_norm": 1.5178081087799355,
      "learning_rate": 2.9299216044462903e-05,
      "loss": 0.7346,
      "step": 800
    },
    {
      "epoch": 0.10803961452532596,
      "grad_norm": 9.506616797760028,
      "learning_rate": 2.927990798715475e-05,
      "loss": 0.6558,
      "step": 810
    },
    {
      "epoch": 0.1093734369268732,
      "grad_norm": 2.4597311302505767,
      "learning_rate": 2.926034408150513e-05,
      "loss": 0.726,
      "step": 820
    },
    {
      "epoch": 0.11070725932842042,
      "grad_norm": 12.372180964422007,
      "learning_rate": 2.9240524678034016e-05,
      "loss": 0.7308,
      "step": 830
    },
    {
      "epoch": 0.11204108172996766,
      "grad_norm": 1.4488469801164658,
      "learning_rate": 2.9220450131839037e-05,
      "loss": 0.7072,
      "step": 840
    },
    {
      "epoch": 0.1133749041315149,
      "grad_norm": 8.602946960846197,
      "learning_rate": 2.920012080258912e-05,
      "loss": 0.7234,
      "step": 850
    },
    {
      "epoch": 0.11470872653306212,
      "grad_norm": 1.441195423452674,
      "learning_rate": 2.9179537054518085e-05,
      "loss": 0.6934,
      "step": 860
    },
    {
      "epoch": 0.11604254893460936,
      "grad_norm": 4.318952956999577,
      "learning_rate": 2.9158699256418056e-05,
      "loss": 0.6534,
      "step": 870
    },
    {
      "epoch": 0.1173763713361566,
      "grad_norm": 9.733179695623866,
      "learning_rate": 2.9137607781632913e-05,
      "loss": 0.71,
      "step": 880
    },
    {
      "epoch": 0.11871019373770382,
      "grad_norm": 7.397049093836735,
      "learning_rate": 2.911626300805155e-05,
      "loss": 0.7386,
      "step": 890
    },
    {
      "epoch": 0.12004401613925106,
      "grad_norm": 2.920812240139869,
      "learning_rate": 2.9094665318101155e-05,
      "loss": 0.6789,
      "step": 900
    },
    {
      "epoch": 0.1213778385407983,
      "grad_norm": 1.7031296196271206,
      "learning_rate": 2.9072815098740326e-05,
      "loss": 0.715,
      "step": 910
    },
    {
      "epoch": 0.12271166094234552,
      "grad_norm": 1.5630656172291801,
      "learning_rate": 2.9050712741452136e-05,
      "loss": 0.7136,
      "step": 920
    },
    {
      "epoch": 0.12404548334389276,
      "grad_norm": 7.870543414771234,
      "learning_rate": 2.902835864223715e-05,
      "loss": 0.6669,
      "step": 930
    },
    {
      "epoch": 0.12537930574543998,
      "grad_norm": 4.843671834991794,
      "learning_rate": 2.9005753201606287e-05,
      "loss": 0.7281,
      "step": 940
    },
    {
      "epoch": 0.12671312814698724,
      "grad_norm": 3.010503818258016,
      "learning_rate": 2.8982896824573678e-05,
      "loss": 0.7018,
      "step": 950
    },
    {
      "epoch": 0.12804695054853446,
      "grad_norm": 2.5552186559589654,
      "learning_rate": 2.8959789920649394e-05,
      "loss": 0.7338,
      "step": 960
    },
    {
      "epoch": 0.12938077295008168,
      "grad_norm": 12.306055851495117,
      "learning_rate": 2.893643290383212e-05,
      "loss": 0.6732,
      "step": 970
    },
    {
      "epoch": 0.13071459535162894,
      "grad_norm": 2.16185926525944,
      "learning_rate": 2.891282619260172e-05,
      "loss": 0.7108,
      "step": 980
    },
    {
      "epoch": 0.13204841775317616,
      "grad_norm": 5.992378798792086,
      "learning_rate": 2.8888970209911754e-05,
      "loss": 0.6525,
      "step": 990
    },
    {
      "epoch": 0.13338224015472339,
      "grad_norm": 2.986272238787896,
      "learning_rate": 2.8864865383181893e-05,
      "loss": 0.6655,
      "step": 1000
    },
    {
      "epoch": 0.13471606255627064,
      "grad_norm": 12.855377354582437,
      "learning_rate": 2.8840512144290273e-05,
      "loss": 0.6826,
      "step": 1010
    },
    {
      "epoch": 0.13604988495781786,
      "grad_norm": 2.045979893776702,
      "learning_rate": 2.8815910929565734e-05,
      "loss": 0.6616,
      "step": 1020
    },
    {
      "epoch": 0.1373837073593651,
      "grad_norm": 6.623264301300591,
      "learning_rate": 2.879106217978002e-05,
      "loss": 0.6935,
      "step": 1030
    },
    {
      "epoch": 0.13871752976091234,
      "grad_norm": 2.67990218211766,
      "learning_rate": 2.8765966340139892e-05,
      "loss": 0.6671,
      "step": 1040
    },
    {
      "epoch": 0.14005135216245956,
      "grad_norm": 2.699521523924172,
      "learning_rate": 2.8740623860279116e-05,
      "loss": 0.6763,
      "step": 1050
    },
    {
      "epoch": 0.14138517456400682,
      "grad_norm": 4.1129898011507535,
      "learning_rate": 2.871503519425044e-05,
      "loss": 0.7159,
      "step": 1060
    },
    {
      "epoch": 0.14271899696555404,
      "grad_norm": 2.4592021333659146,
      "learning_rate": 2.8689200800517448e-05,
      "loss": 0.6551,
      "step": 1070
    },
    {
      "epoch": 0.14405281936710126,
      "grad_norm": 5.138500389099849,
      "learning_rate": 2.866312114194634e-05,
      "loss": 0.7214,
      "step": 1080
    },
    {
      "epoch": 0.14538664176864852,
      "grad_norm": 2.822433730666048,
      "learning_rate": 2.8636796685797657e-05,
      "loss": 0.6862,
      "step": 1090
    },
    {
      "epoch": 0.14672046417019574,
      "grad_norm": 3.086468537427806,
      "learning_rate": 2.8610227903717876e-05,
      "loss": 0.6784,
      "step": 1100
    },
    {
      "epoch": 0.14805428657174297,
      "grad_norm": 2.079766793749202,
      "learning_rate": 2.8583415271730994e-05,
      "loss": 0.7065,
      "step": 1110
    },
    {
      "epoch": 0.14938810897329022,
      "grad_norm": 1.659870509072264,
      "learning_rate": 2.855635927022998e-05,
      "loss": 0.7197,
      "step": 1120
    },
    {
      "epoch": 0.15072193137483744,
      "grad_norm": 7.870626779339635,
      "learning_rate": 2.8529060383968175e-05,
      "loss": 0.7305,
      "step": 1130
    },
    {
      "epoch": 0.15205575377638467,
      "grad_norm": 3.0600340899893537,
      "learning_rate": 2.850151910205061e-05,
      "loss": 0.6922,
      "step": 1140
    },
    {
      "epoch": 0.15338957617793192,
      "grad_norm": 3.6147451373702806,
      "learning_rate": 2.847373591792523e-05,
      "loss": 0.7044,
      "step": 1150
    },
    {
      "epoch": 0.15472339857947914,
      "grad_norm": 4.740777951553679,
      "learning_rate": 2.844571132937407e-05,
      "loss": 0.6794,
      "step": 1160
    },
    {
      "epoch": 0.15605722098102637,
      "grad_norm": 3.377522973717319,
      "learning_rate": 2.841744583850431e-05,
      "loss": 0.673,
      "step": 1170
    },
    {
      "epoch": 0.15739104338257362,
      "grad_norm": 4.250656077289992,
      "learning_rate": 2.838893995173932e-05,
      "loss": 0.6975,
      "step": 1180
    },
    {
      "epoch": 0.15872486578412084,
      "grad_norm": 11.73693900915769,
      "learning_rate": 2.836019417980955e-05,
      "loss": 0.6572,
      "step": 1190
    },
    {
      "epoch": 0.16005868818566807,
      "grad_norm": 2.729291714043308,
      "learning_rate": 2.8331209037743387e-05,
      "loss": 0.7247,
      "step": 1200
    }
  ],
  "logging_steps": 10,
  "max_steps": 7497,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.280284708293837e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}