{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.18488560203374163,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015407133502811801,
      "grad_norm": 48.20575104273089,
      "learning_rate": 4.615384615384616e-06,
      "loss": 1.3971,
      "step": 10
    },
    {
      "epoch": 0.0030814267005623602,
      "grad_norm": 33.11975747134839,
      "learning_rate": 9.230769230769232e-06,
      "loss": 1.4053,
      "step": 20
    },
    {
      "epoch": 0.004622140050843541,
      "grad_norm": 39.826606299507084,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 1.3472,
      "step": 30
    },
    {
      "epoch": 0.0061628534011247205,
      "grad_norm": 6.773742739301677,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 1.1311,
      "step": 40
    },
    {
      "epoch": 0.007703566751405901,
      "grad_norm": 12.278712041952108,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.9715,
      "step": 50
    },
    {
      "epoch": 0.009244280101687081,
      "grad_norm": 3.776870082439811,
      "learning_rate": 2.7692307692307694e-05,
      "loss": 0.8937,
      "step": 60
    },
    {
      "epoch": 0.010784993451968261,
      "grad_norm": 6.812660145408396,
      "learning_rate": 2.9999955171465948e-05,
      "loss": 0.8472,
      "step": 70
    },
    {
      "epoch": 0.012325706802249441,
      "grad_norm": 14.1920325479403,
      "learning_rate": 2.9999596544801216e-05,
      "loss": 0.8418,
      "step": 80
    },
    {
      "epoch": 0.013866420152530621,
      "grad_norm": 4.760185564415112,
      "learning_rate": 2.999887930004599e-05,
      "loss": 0.8275,
      "step": 90
    },
    {
      "epoch": 0.015407133502811803,
      "grad_norm": 5.64069685533569,
      "learning_rate": 2.9997803454348518e-05,
      "loss": 0.8085,
      "step": 100
    },
    {
      "epoch": 0.01694784685309298,
      "grad_norm": 8.910755610595423,
      "learning_rate": 2.9996369033430674e-05,
      "loss": 0.8105,
      "step": 110
    },
    {
      "epoch": 0.018488560203374162,
      "grad_norm": 7.128375140746789,
      "learning_rate": 2.9994576071587345e-05,
      "loss": 0.7647,
      "step": 120
    },
    {
      "epoch": 0.020029273553655344,
      "grad_norm": 4.883749519467239,
      "learning_rate": 2.9992424611685575e-05,
      "loss": 0.7472,
      "step": 130
    },
    {
      "epoch": 0.021569986903936522,
      "grad_norm": 6.669698248447361,
      "learning_rate": 2.9989914705163582e-05,
      "loss": 0.7644,
      "step": 140
    },
    {
      "epoch": 0.023110700254217704,
      "grad_norm": 8.814324372744018,
      "learning_rate": 2.9987046412029506e-05,
      "loss": 0.7642,
      "step": 150
    },
    {
      "epoch": 0.024651413604498882,
      "grad_norm": 5.408352128962619,
      "learning_rate": 2.9983819800859976e-05,
      "loss": 0.7506,
      "step": 160
    },
    {
      "epoch": 0.026192126954780064,
      "grad_norm": 4.916006313310609,
      "learning_rate": 2.998023494879848e-05,
      "loss": 0.7086,
      "step": 170
    },
    {
      "epoch": 0.027732840305061242,
      "grad_norm": 6.4968532868316515,
      "learning_rate": 2.9976291941553508e-05,
      "loss": 0.7302,
      "step": 180
    },
    {
      "epoch": 0.029273553655342423,
      "grad_norm": 5.414282856209666,
      "learning_rate": 2.9971990873396512e-05,
      "loss": 0.7389,
      "step": 190
    },
    {
      "epoch": 0.030814267005623605,
      "grad_norm": 35.78019922037886,
      "learning_rate": 2.996733184715964e-05,
      "loss": 0.7247,
      "step": 200
    },
    {
      "epoch": 0.03235498035590478,
      "grad_norm": 4.344484335761467,
      "learning_rate": 2.9962314974233306e-05,
      "loss": 0.7239,
      "step": 210
    },
    {
      "epoch": 0.03389569370618596,
      "grad_norm": 4.761393885682967,
      "learning_rate": 2.995694037456349e-05,
      "loss": 0.7219,
      "step": 220
    },
    {
      "epoch": 0.03543640705646715,
      "grad_norm": 6.082748106236669,
      "learning_rate": 2.995120817664889e-05,
      "loss": 0.7036,
      "step": 230
    },
    {
      "epoch": 0.036977120406748325,
      "grad_norm": 7.925002223835823,
      "learning_rate": 2.9945118517537857e-05,
      "loss": 0.6795,
      "step": 240
    },
    {
      "epoch": 0.0385178337570295,
      "grad_norm": 4.33748938479485,
      "learning_rate": 2.9938671542825102e-05,
      "loss": 0.6894,
      "step": 250
    },
    {
      "epoch": 0.04005854710731069,
      "grad_norm": 3.419861222736367,
      "learning_rate": 2.993186740664821e-05,
      "loss": 0.674,
      "step": 260
    },
    {
      "epoch": 0.041599260457591866,
      "grad_norm": 4.418012569894865,
      "learning_rate": 2.9924706271683993e-05,
      "loss": 0.7091,
      "step": 270
    },
    {
      "epoch": 0.043139973807873044,
      "grad_norm": 5.5535932232942065,
      "learning_rate": 2.9917188309144548e-05,
      "loss": 0.7114,
      "step": 280
    },
    {
      "epoch": 0.04468068715815422,
      "grad_norm": 5.346051172390458,
      "learning_rate": 2.990931369877321e-05,
      "loss": 0.7092,
      "step": 290
    },
    {
      "epoch": 0.04622140050843541,
      "grad_norm": 5.04585392782648,
      "learning_rate": 2.9901082628840216e-05,
      "loss": 0.7079,
      "step": 300
    },
    {
      "epoch": 0.047762113858716586,
      "grad_norm": 5.3108067226217095,
      "learning_rate": 2.989249529613823e-05,
      "loss": 0.7044,
      "step": 310
    },
    {
      "epoch": 0.049302827208997764,
      "grad_norm": 12.936374781230974,
      "learning_rate": 2.9883551905977647e-05,
      "loss": 0.6795,
      "step": 320
    },
    {
      "epoch": 0.05084354055927895,
      "grad_norm": 4.969368758151501,
      "learning_rate": 2.987425267218164e-05,
      "loss": 0.7365,
      "step": 330
    },
    {
      "epoch": 0.05238425390956013,
      "grad_norm": 17.59963354249395,
      "learning_rate": 2.9864597817081083e-05,
      "loss": 0.6459,
      "step": 340
    },
    {
      "epoch": 0.053924967259841305,
      "grad_norm": 4.287709062556245,
      "learning_rate": 2.985458757150924e-05,
      "loss": 0.7151,
      "step": 350
    },
    {
      "epoch": 0.055465680610122484,
      "grad_norm": 2.353889201419343,
      "learning_rate": 2.9844222174796224e-05,
      "loss": 0.6982,
      "step": 360
    },
    {
      "epoch": 0.05700639396040367,
      "grad_norm": 6.487203178892158,
      "learning_rate": 2.983350187476328e-05,
      "loss": 0.6946,
      "step": 370
    },
    {
      "epoch": 0.05854710731068485,
      "grad_norm": 8.604226568596971,
      "learning_rate": 2.982242692771688e-05,
      "loss": 0.7024,
      "step": 380
    },
    {
      "epoch": 0.060087820660966025,
      "grad_norm": 3.7381224404208107,
      "learning_rate": 2.9810997598442558e-05,
      "loss": 0.6813,
      "step": 390
    },
    {
      "epoch": 0.06162853401124721,
      "grad_norm": 7.21302363512955,
      "learning_rate": 2.9799214160198622e-05,
      "loss": 0.6572,
      "step": 400
    },
    {
      "epoch": 0.06316924736152839,
      "grad_norm": 7.446657585655329,
      "learning_rate": 2.9787076894709592e-05,
      "loss": 0.6612,
      "step": 410
    },
    {
      "epoch": 0.06470996071180957,
      "grad_norm": 16.149479699980372,
      "learning_rate": 2.977458609215946e-05,
      "loss": 0.6823,
      "step": 420
    },
    {
      "epoch": 0.06625067406209074,
      "grad_norm": 3.654646693112352,
      "learning_rate": 2.9761742051184786e-05,
      "loss": 0.6941,
      "step": 430
    },
    {
      "epoch": 0.06779138741237192,
      "grad_norm": 7.468345726914931,
      "learning_rate": 2.9748545078867524e-05,
      "loss": 0.6254,
      "step": 440
    },
    {
      "epoch": 0.06933210076265311,
      "grad_norm": 6.559292545318311,
      "learning_rate": 2.9734995490727696e-05,
      "loss": 0.6977,
      "step": 450
    },
    {
      "epoch": 0.0708728141129343,
      "grad_norm": 8.749994768413615,
      "learning_rate": 2.9721093610715844e-05,
      "loss": 0.6742,
      "step": 460
    },
    {
      "epoch": 0.07241352746321547,
      "grad_norm": 14.746822726186753,
      "learning_rate": 2.9706839771205282e-05,
      "loss": 0.6986,
      "step": 470
    },
    {
      "epoch": 0.07395424081349665,
      "grad_norm": 2.1125271451210494,
      "learning_rate": 2.9692234312984156e-05,
      "loss": 0.6708,
      "step": 480
    },
    {
      "epoch": 0.07549495416377783,
      "grad_norm": 4.191787346884265,
      "learning_rate": 2.9677277585247296e-05,
      "loss": 0.6839,
      "step": 490
    },
    {
      "epoch": 0.077035667514059,
      "grad_norm": 6.099946769106883,
      "learning_rate": 2.9661969945587867e-05,
      "loss": 0.7253,
      "step": 500
    },
    {
      "epoch": 0.07857638086434018,
      "grad_norm": 8.272898482647978,
      "learning_rate": 2.9646311759988804e-05,
      "loss": 0.6972,
      "step": 510
    },
    {
      "epoch": 0.08011709421462138,
      "grad_norm": 12.38761120543235,
      "learning_rate": 2.9630303402814095e-05,
      "loss": 0.7174,
      "step": 520
    },
    {
      "epoch": 0.08165780756490255,
      "grad_norm": 7.826170900143438,
      "learning_rate": 2.961394525679979e-05,
      "loss": 0.7227,
      "step": 530
    },
    {
      "epoch": 0.08319852091518373,
      "grad_norm": 3.926770198625081,
      "learning_rate": 2.9597237713044888e-05,
      "loss": 0.6682,
      "step": 540
    },
    {
      "epoch": 0.08473923426546491,
      "grad_norm": 3.3408474311965692,
      "learning_rate": 2.9580181171001962e-05,
      "loss": 0.6634,
      "step": 550
    },
    {
      "epoch": 0.08627994761574609,
      "grad_norm": 15.954087186336258,
      "learning_rate": 2.956277603846761e-05,
      "loss": 0.7005,
      "step": 560
    },
    {
      "epoch": 0.08782066096602727,
      "grad_norm": 3.3366594091813475,
      "learning_rate": 2.9545022731572723e-05,
      "loss": 0.6752,
      "step": 570
    },
    {
      "epoch": 0.08936137431630845,
      "grad_norm": 4.359220549879328,
      "learning_rate": 2.9526921674772522e-05,
      "loss": 0.6985,
      "step": 580
    },
    {
      "epoch": 0.09090208766658964,
      "grad_norm": 5.585924353950877,
      "learning_rate": 2.95084733008364e-05,
      "loss": 0.6729,
      "step": 590
    },
    {
      "epoch": 0.09244280101687082,
      "grad_norm": 2.5002732127626075,
      "learning_rate": 2.94896780508376e-05,
      "loss": 0.6881,
      "step": 600
    },
    {
      "epoch": 0.093983514367152,
      "grad_norm": 8.22666868773466,
      "learning_rate": 2.9470536374142656e-05,
      "loss": 0.6918,
      "step": 610
    },
    {
      "epoch": 0.09552422771743317,
      "grad_norm": 14.050897991765508,
      "learning_rate": 2.9451048728400644e-05,
      "loss": 0.6584,
      "step": 620
    },
    {
      "epoch": 0.09706494106771435,
      "grad_norm": 3.117445397285045,
      "learning_rate": 2.9431215579532253e-05,
      "loss": 0.6495,
      "step": 630
    },
    {
      "epoch": 0.09860565441799553,
      "grad_norm": 7.000286096448409,
      "learning_rate": 2.9411037401718628e-05,
      "loss": 0.6568,
      "step": 640
    },
    {
      "epoch": 0.1001463677682767,
      "grad_norm": 3.09698455955492,
      "learning_rate": 2.939051467739006e-05,
      "loss": 0.7095,
      "step": 650
    },
    {
      "epoch": 0.1016870811185579,
      "grad_norm": 4.163429426840949,
      "learning_rate": 2.936964789721442e-05,
      "loss": 0.6573,
      "step": 660
    },
    {
      "epoch": 0.10322779446883908,
      "grad_norm": 3.282543980811516,
      "learning_rate": 2.934843756008546e-05,
      "loss": 0.6901,
      "step": 670
    },
    {
      "epoch": 0.10476850781912025,
      "grad_norm": 7.4918954929572115,
      "learning_rate": 2.932688417311085e-05,
      "loss": 0.6826,
      "step": 680
    },
    {
      "epoch": 0.10630922116940143,
      "grad_norm": 49.53066344289919,
      "learning_rate": 2.9304988251600084e-05,
      "loss": 0.6668,
      "step": 690
    },
    {
      "epoch": 0.10784993451968261,
      "grad_norm": 23.218366206451197,
      "learning_rate": 2.9282750319052154e-05,
      "loss": 0.6643,
      "step": 700
    },
    {
      "epoch": 0.10939064786996379,
      "grad_norm": 2.59944116748961,
      "learning_rate": 2.9260170907143012e-05,
      "loss": 0.6709,
      "step": 710
    },
    {
      "epoch": 0.11093136122024497,
      "grad_norm": 4.59006482180365,
      "learning_rate": 2.9237250555712887e-05,
      "loss": 0.6878,
      "step": 720
    },
    {
      "epoch": 0.11247207457052616,
      "grad_norm": 3.1508976338573507,
      "learning_rate": 2.9213989812753366e-05,
      "loss": 0.6512,
      "step": 730
    },
    {
      "epoch": 0.11401278792080734,
      "grad_norm": 4.5342197552006835,
      "learning_rate": 2.9190389234394285e-05,
      "loss": 0.6687,
      "step": 740
    },
    {
      "epoch": 0.11555350127108852,
      "grad_norm": 6.514898099534209,
      "learning_rate": 2.9166449384890446e-05,
      "loss": 0.6868,
      "step": 750
    },
    {
      "epoch": 0.1170942146213697,
      "grad_norm": 5.1251296980659005,
      "learning_rate": 2.9142170836608115e-05,
      "loss": 0.6869,
      "step": 760
    },
    {
      "epoch": 0.11863492797165087,
      "grad_norm": 5.896478552497953,
      "learning_rate": 2.9117554170011352e-05,
      "loss": 0.667,
      "step": 770
    },
    {
      "epoch": 0.12017564132193205,
      "grad_norm": 3.4672489526983483,
      "learning_rate": 2.909259997364811e-05,
      "loss": 0.6674,
      "step": 780
    },
    {
      "epoch": 0.12171635467221323,
      "grad_norm": 5.413662982418376,
      "learning_rate": 2.9067308844136193e-05,
      "loss": 0.6891,
      "step": 790
    },
    {
      "epoch": 0.12325706802249442,
      "grad_norm": 5.807164850831801,
      "learning_rate": 2.9041681386148966e-05,
      "loss": 0.6447,
      "step": 800
    },
    {
      "epoch": 0.1247977813727756,
      "grad_norm": 5.542855195057769,
      "learning_rate": 2.9015718212400918e-05,
      "loss": 0.6486,
      "step": 810
    },
    {
      "epoch": 0.12633849472305678,
      "grad_norm": 3.60243198052599,
      "learning_rate": 2.8989419943632992e-05,
      "loss": 0.6552,
      "step": 820
    },
    {
      "epoch": 0.12787920807333797,
      "grad_norm": 10.54124596601907,
      "learning_rate": 2.896278720859776e-05,
      "loss": 0.667,
      "step": 830
    },
    {
      "epoch": 0.12941992142361913,
      "grad_norm": 8.542824965925352,
      "learning_rate": 2.8935820644044398e-05,
      "loss": 0.697,
      "step": 840
    },
    {
      "epoch": 0.13096063477390033,
      "grad_norm": 6.327341591650607,
      "learning_rate": 2.890852089470343e-05,
      "loss": 0.65,
      "step": 850
    },
    {
      "epoch": 0.1325013481241815,
      "grad_norm": 7.687827002540841,
      "learning_rate": 2.888088861327135e-05,
      "loss": 0.6435,
      "step": 860
    },
    {
      "epoch": 0.13404206147446268,
      "grad_norm": 3.356453126127434,
      "learning_rate": 2.885292446039499e-05,
      "loss": 0.6721,
      "step": 870
    },
    {
      "epoch": 0.13558277482474385,
      "grad_norm": 8.406402473059597,
      "learning_rate": 2.8824629104655736e-05,
      "loss": 0.6694,
      "step": 880
    },
    {
      "epoch": 0.13712348817502504,
      "grad_norm": 11.653019434398818,
      "learning_rate": 2.8796003222553558e-05,
      "loss": 0.6531,
      "step": 890
    },
    {
      "epoch": 0.13866420152530623,
      "grad_norm": 6.371551478518258,
      "learning_rate": 2.8767047498490798e-05,
      "loss": 0.6568,
      "step": 900
    },
    {
      "epoch": 0.1402049148755874,
      "grad_norm": 26.71523757066426,
      "learning_rate": 2.8737762624755846e-05,
      "loss": 0.6857,
      "step": 910
    },
    {
      "epoch": 0.1417456282258686,
      "grad_norm": 4.417578021376778,
      "learning_rate": 2.8708149301506573e-05,
      "loss": 0.665,
      "step": 920
    },
    {
      "epoch": 0.14328634157614975,
      "grad_norm": 5.335327649767265,
      "learning_rate": 2.8678208236753577e-05,
      "loss": 0.7014,
      "step": 930
    },
    {
      "epoch": 0.14482705492643094,
      "grad_norm": 4.155520038033631,
      "learning_rate": 2.8647940146343278e-05,
      "loss": 0.6767,
      "step": 940
    },
    {
      "epoch": 0.1463677682767121,
      "grad_norm": 3.815046866792752,
      "learning_rate": 2.86173457539408e-05,
      "loss": 0.6557,
      "step": 950
    },
    {
      "epoch": 0.1479084816269933,
      "grad_norm": 3.7651811393538552,
      "learning_rate": 2.8586425791012648e-05,
      "loss": 0.675,
      "step": 960
    },
    {
      "epoch": 0.1494491949772745,
      "grad_norm": 4.382966553943605,
      "learning_rate": 2.8555180996809246e-05,
      "loss": 0.6313,
      "step": 970
    },
    {
      "epoch": 0.15098990832755566,
      "grad_norm": 10.103890347717131,
      "learning_rate": 2.8523612118347245e-05,
      "loss": 0.645,
      "step": 980
    },
    {
      "epoch": 0.15253062167783685,
      "grad_norm": 6.294074332584702,
      "learning_rate": 2.8491719910391685e-05,
      "loss": 0.659,
      "step": 990
    },
    {
      "epoch": 0.154071335028118,
      "grad_norm": 2.5808531227457565,
      "learning_rate": 2.845950513543791e-05,
      "loss": 0.6688,
      "step": 1000
    },
    {
      "epoch": 0.1556120483783992,
      "grad_norm": 2.927888770737132,
      "learning_rate": 2.842696856369338e-05,
      "loss": 0.6381,
      "step": 1010
    },
    {
      "epoch": 0.15715276172868037,
      "grad_norm": 14.062433268070832,
      "learning_rate": 2.8394110973059233e-05,
      "loss": 0.6946,
      "step": 1020
    },
    {
      "epoch": 0.15869347507896156,
      "grad_norm": 2.4470437840581054,
      "learning_rate": 2.8360933149111695e-05,
      "loss": 0.6844,
      "step": 1030
    },
    {
      "epoch": 0.16023418842924275,
      "grad_norm": 3.8078577514013343,
      "learning_rate": 2.8327435885083292e-05,
      "loss": 0.64,
      "step": 1040
    },
    {
      "epoch": 0.16177490177952392,
      "grad_norm": 25.680768915471432,
      "learning_rate": 2.8293619981843887e-05,
      "loss": 0.6329,
      "step": 1050
    },
    {
      "epoch": 0.1633156151298051,
      "grad_norm": 5.0369491995422715,
      "learning_rate": 2.8259486247881537e-05,
      "loss": 0.6604,
      "step": 1060
    },
    {
      "epoch": 0.16485632848008627,
      "grad_norm": 3.9026521516961608,
      "learning_rate": 2.8225035499283155e-05,
      "loss": 0.6564,
      "step": 1070
    },
    {
      "epoch": 0.16639704183036746,
      "grad_norm": 4.945417598915296,
      "learning_rate": 2.8190268559715017e-05,
      "loss": 0.6655,
      "step": 1080
    },
    {
      "epoch": 0.16793775518064863,
      "grad_norm": 3.222466850494984,
      "learning_rate": 2.815518626040304e-05,
      "loss": 0.6603,
      "step": 1090
    },
    {
      "epoch": 0.16947846853092982,
      "grad_norm": 6.539136587655263,
      "learning_rate": 2.811978944011293e-05,
      "loss": 0.7036,
      "step": 1100
    },
    {
      "epoch": 0.171019181881211,
      "grad_norm": 8.14211829139052,
      "learning_rate": 2.8084078945130117e-05,
      "loss": 0.6356,
      "step": 1110
    },
    {
      "epoch": 0.17255989523149218,
      "grad_norm": 4.1954200205175605,
      "learning_rate": 2.8048055629239543e-05,
      "loss": 0.6591,
      "step": 1120
    },
    {
      "epoch": 0.17410060858177337,
      "grad_norm": 4.333940585698679,
      "learning_rate": 2.8011720353705224e-05,
      "loss": 0.6575,
      "step": 1130
    },
    {
      "epoch": 0.17564132193205453,
      "grad_norm": 4.2805487065333,
      "learning_rate": 2.797507398724966e-05,
      "loss": 0.6624,
      "step": 1140
    },
    {
      "epoch": 0.17718203528233573,
      "grad_norm": 4.7173213185412,
      "learning_rate": 2.7938117406033086e-05,
      "loss": 0.623,
      "step": 1150
    },
    {
      "epoch": 0.1787227486326169,
      "grad_norm": 99.71383370833006,
      "learning_rate": 2.7900851493632508e-05,
      "loss": 0.6591,
      "step": 1160
    },
    {
      "epoch": 0.18026346198289808,
      "grad_norm": 3.6747989781213954,
      "learning_rate": 2.786327714102058e-05,
      "loss": 0.692,
      "step": 1170
    },
    {
      "epoch": 0.18180417533317927,
      "grad_norm": 2.5009166944220604,
      "learning_rate": 2.78253952465443e-05,
      "loss": 0.6614,
      "step": 1180
    },
    {
      "epoch": 0.18334488868346044,
      "grad_norm": 3.144011687958325,
      "learning_rate": 2.7787206715903543e-05,
      "loss": 0.6406,
      "step": 1190
    },
    {
      "epoch": 0.18488560203374163,
      "grad_norm": 4.063731315051197,
      "learning_rate": 2.7748712462129396e-05,
      "loss": 0.6444,
      "step": 1200
    }
  ],
  "logging_steps": 10,
  "max_steps": 6490,
  "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": 1.0934282360979456e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}