{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09811484499300901,
  "eval_steps": 500,
  "global_step": 2035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004821368304324767,
      "grad_norm": 84.9173377406223,
      "learning_rate": 2.910112359550562e-06,
      "loss": 1.5154205322265626,
      "step": 10
    },
    {
      "epoch": 0.0009642736608649534,
      "grad_norm": 57.560206229549436,
      "learning_rate": 3.921348314606742e-06,
      "loss": 0.9048759460449218,
      "step": 20
    },
    {
      "epoch": 0.0014464104912974302,
      "grad_norm": 241.93706017750705,
      "learning_rate": 4.932584269662922e-06,
      "loss": 0.7844394207000732,
      "step": 30
    },
    {
      "epoch": 0.001928547321729907,
      "grad_norm": 635.4867043743025,
      "learning_rate": 5.943820224719102e-06,
      "loss": 0.777440071105957,
      "step": 40
    },
    {
      "epoch": 0.0024106841521623836,
      "grad_norm": 16.70216416699672,
      "learning_rate": 6.955056179775282e-06,
      "loss": 0.7813506126403809,
      "step": 50
    },
    {
      "epoch": 0.0028928209825948605,
      "grad_norm": 104.65219520703347,
      "learning_rate": 7.966292134831462e-06,
      "loss": 0.7643991470336914,
      "step": 60
    },
    {
      "epoch": 0.0033749578130273373,
      "grad_norm": 15.464766046614894,
      "learning_rate": 8.977528089887641e-06,
      "loss": 0.7663109779357911,
      "step": 70
    },
    {
      "epoch": 0.003857094643459814,
      "grad_norm": 11.140861449353931,
      "learning_rate": 9.988764044943822e-06,
      "loss": 0.7194852352142334,
      "step": 80
    },
    {
      "epoch": 0.004339231473892291,
      "grad_norm": 29.54062487849426,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.7484091758728028,
      "step": 90
    },
    {
      "epoch": 0.004821368304324767,
      "grad_norm": 623.2770461417654,
      "learning_rate": 1.2011235955056182e-05,
      "loss": 0.7809892177581788,
      "step": 100
    },
    {
      "epoch": 0.0053035051347572445,
      "grad_norm": 12.453456400945432,
      "learning_rate": 1.3022471910112362e-05,
      "loss": 0.7879758358001709,
      "step": 110
    },
    {
      "epoch": 0.005785641965189721,
      "grad_norm": 15.266718921768598,
      "learning_rate": 1.403370786516854e-05,
      "loss": 0.7485491752624511,
      "step": 120
    },
    {
      "epoch": 0.006267778795622197,
      "grad_norm": 7.765117181857264,
      "learning_rate": 1.504494382022472e-05,
      "loss": 0.7564555168151855,
      "step": 130
    },
    {
      "epoch": 0.006749915626054675,
      "grad_norm": 12.596599218999913,
      "learning_rate": 1.60561797752809e-05,
      "loss": 0.7486157894134522,
      "step": 140
    },
    {
      "epoch": 0.007232052456487151,
      "grad_norm": 4.964019715699265,
      "learning_rate": 1.706741573033708e-05,
      "loss": 0.6995878219604492,
      "step": 150
    },
    {
      "epoch": 0.007714189286919628,
      "grad_norm": 5.34953585002889,
      "learning_rate": 1.8078651685393256e-05,
      "loss": 0.7818653106689453,
      "step": 160
    },
    {
      "epoch": 0.008196326117352104,
      "grad_norm": 13.677128436034314,
      "learning_rate": 1.908988764044944e-05,
      "loss": 0.7409422874450684,
      "step": 170
    },
    {
      "epoch": 0.008678462947784581,
      "grad_norm": 11.253318513799217,
      "learning_rate": 2e-05,
      "loss": 0.7045968532562256,
      "step": 180
    },
    {
      "epoch": 0.009160599778217059,
      "grad_norm": 3.7993902470656638,
      "learning_rate": 2e-05,
      "loss": 0.7415530204772949,
      "step": 190
    },
    {
      "epoch": 0.009642736608649534,
      "grad_norm": 9.932013471995777,
      "learning_rate": 2e-05,
      "loss": 0.7458738327026367,
      "step": 200
    },
    {
      "epoch": 0.010124873439082012,
      "grad_norm": 4.001842841007721,
      "learning_rate": 2e-05,
      "loss": 0.7419017791748047,
      "step": 210
    },
    {
      "epoch": 0.010607010269514489,
      "grad_norm": 5.8081003010500405,
      "learning_rate": 2e-05,
      "loss": 0.727513599395752,
      "step": 220
    },
    {
      "epoch": 0.011089147099946964,
      "grad_norm": 24.899690781901665,
      "learning_rate": 2e-05,
      "loss": 0.7438565731048584,
      "step": 230
    },
    {
      "epoch": 0.011571283930379442,
      "grad_norm": 9.431012313223512,
      "learning_rate": 2e-05,
      "loss": 0.7601432800292969,
      "step": 240
    },
    {
      "epoch": 0.012053420760811919,
      "grad_norm": 9.9069654154098,
      "learning_rate": 2e-05,
      "loss": 0.7237838268280029,
      "step": 250
    },
    {
      "epoch": 0.012535557591244395,
      "grad_norm": 6.065436761140742,
      "learning_rate": 2e-05,
      "loss": 0.7469722747802734,
      "step": 260
    },
    {
      "epoch": 0.013017694421676872,
      "grad_norm": 47.854432068582106,
      "learning_rate": 2e-05,
      "loss": 0.7887792587280273,
      "step": 270
    },
    {
      "epoch": 0.01349983125210935,
      "grad_norm": 7.739139876114809,
      "learning_rate": 2e-05,
      "loss": 0.8068546295166016,
      "step": 280
    },
    {
      "epoch": 0.013981968082541825,
      "grad_norm": 6.596407728810894,
      "learning_rate": 2e-05,
      "loss": 0.7717693328857422,
      "step": 290
    },
    {
      "epoch": 0.014464104912974302,
      "grad_norm": 2.821767608514682,
      "learning_rate": 2e-05,
      "loss": 0.762939453125,
      "step": 300
    },
    {
      "epoch": 0.01494624174340678,
      "grad_norm": 12.92389489442801,
      "learning_rate": 2e-05,
      "loss": 0.7905154705047608,
      "step": 310
    },
    {
      "epoch": 0.015428378573839255,
      "grad_norm": 4.45893615790758,
      "learning_rate": 2e-05,
      "loss": 0.8191452026367188,
      "step": 320
    },
    {
      "epoch": 0.01591051540427173,
      "grad_norm": 2.719882613980345,
      "learning_rate": 2e-05,
      "loss": 0.7672964096069336,
      "step": 330
    },
    {
      "epoch": 0.016392652234704208,
      "grad_norm": 9.433039678311145,
      "learning_rate": 2e-05,
      "loss": 0.7420453548431396,
      "step": 340
    },
    {
      "epoch": 0.016874789065136685,
      "grad_norm": 4.012690253492805,
      "learning_rate": 2e-05,
      "loss": 0.7563004493713379,
      "step": 350
    },
    {
      "epoch": 0.017356925895569163,
      "grad_norm": 11.624966196988954,
      "learning_rate": 2e-05,
      "loss": 0.7373766899108887,
      "step": 360
    },
    {
      "epoch": 0.01783906272600164,
      "grad_norm": 2.7344222258766258,
      "learning_rate": 2e-05,
      "loss": 0.7051375389099122,
      "step": 370
    },
    {
      "epoch": 0.018321199556434117,
      "grad_norm": 4.539182866411412,
      "learning_rate": 2e-05,
      "loss": 0.7277828216552734,
      "step": 380
    },
    {
      "epoch": 0.01880333638686659,
      "grad_norm": 4.87684609900965,
      "learning_rate": 2e-05,
      "loss": 0.7499900817871094,
      "step": 390
    },
    {
      "epoch": 0.01928547321729907,
      "grad_norm": 2.305121309654471,
      "learning_rate": 2e-05,
      "loss": 0.7218913078308106,
      "step": 400
    },
    {
      "epoch": 0.019767610047731546,
      "grad_norm": 2.637730882882061,
      "learning_rate": 2e-05,
      "loss": 0.7323745250701904,
      "step": 410
    },
    {
      "epoch": 0.020249746878164023,
      "grad_norm": 2.9314732121215092,
      "learning_rate": 2e-05,
      "loss": 0.7070964336395263,
      "step": 420
    },
    {
      "epoch": 0.0207318837085965,
      "grad_norm": 4.051033736245248,
      "learning_rate": 2e-05,
      "loss": 0.7526719570159912,
      "step": 430
    },
    {
      "epoch": 0.021214020539028978,
      "grad_norm": 2.737987761268551,
      "learning_rate": 2e-05,
      "loss": 0.7400177001953125,
      "step": 440
    },
    {
      "epoch": 0.02169615736946145,
      "grad_norm": 2.002819925510059,
      "learning_rate": 2e-05,
      "loss": 0.7192610740661621,
      "step": 450
    },
    {
      "epoch": 0.02217829419989393,
      "grad_norm": 3.7426192848860755,
      "learning_rate": 2e-05,
      "loss": 0.7366347312927246,
      "step": 460
    },
    {
      "epoch": 0.022660431030326406,
      "grad_norm": 1.1926626716478357,
      "learning_rate": 2e-05,
      "loss": 0.7299184322357177,
      "step": 470
    },
    {
      "epoch": 0.023142567860758884,
      "grad_norm": 3.367060431673956,
      "learning_rate": 2e-05,
      "loss": 0.7061259269714355,
      "step": 480
    },
    {
      "epoch": 0.02362470469119136,
      "grad_norm": 1.0695774993776388,
      "learning_rate": 2e-05,
      "loss": 0.7048762321472168,
      "step": 490
    },
    {
      "epoch": 0.024106841521623838,
      "grad_norm": 1.9484852417237744,
      "learning_rate": 2e-05,
      "loss": 0.7045268058776856,
      "step": 500
    },
    {
      "epoch": 0.024588978352056312,
      "grad_norm": 1.7161008623305876,
      "learning_rate": 2e-05,
      "loss": 0.7366765022277832,
      "step": 510
    },
    {
      "epoch": 0.02507111518248879,
      "grad_norm": 2.7468813266571335,
      "learning_rate": 2e-05,
      "loss": 0.7303312301635743,
      "step": 520
    },
    {
      "epoch": 0.025553252012921267,
      "grad_norm": 8.640342170047546,
      "learning_rate": 2e-05,
      "loss": 0.76505126953125,
      "step": 530
    },
    {
      "epoch": 0.026035388843353744,
      "grad_norm": 14.403207471659123,
      "learning_rate": 2e-05,
      "loss": 0.7315347194671631,
      "step": 540
    },
    {
      "epoch": 0.02651752567378622,
      "grad_norm": 4.9187469514726025,
      "learning_rate": 2e-05,
      "loss": 0.7313735961914063,
      "step": 550
    },
    {
      "epoch": 0.0269996625042187,
      "grad_norm": 21.09742751886116,
      "learning_rate": 2e-05,
      "loss": 0.7265950679779053,
      "step": 560
    },
    {
      "epoch": 0.027481799334651173,
      "grad_norm": 9.120234530490755,
      "learning_rate": 2e-05,
      "loss": 0.752630615234375,
      "step": 570
    },
    {
      "epoch": 0.02796393616508365,
      "grad_norm": 39.217881534027256,
      "learning_rate": 2e-05,
      "loss": 0.7522613048553467,
      "step": 580
    },
    {
      "epoch": 0.028446072995516127,
      "grad_norm": 15.15469395513839,
      "learning_rate": 2e-05,
      "loss": 0.7306804656982422,
      "step": 590
    },
    {
      "epoch": 0.028928209825948605,
      "grad_norm": 2.229860272443176,
      "learning_rate": 2e-05,
      "loss": 0.7174323081970215,
      "step": 600
    },
    {
      "epoch": 0.029410346656381082,
      "grad_norm": 28.87034725965148,
      "learning_rate": 2e-05,
      "loss": 0.7655416488647461,
      "step": 610
    },
    {
      "epoch": 0.02989248348681356,
      "grad_norm": 2.85440650717933,
      "learning_rate": 2e-05,
      "loss": 0.7155353546142578,
      "step": 620
    },
    {
      "epoch": 0.030374620317246033,
      "grad_norm": 4.824295325677904,
      "learning_rate": 2e-05,
      "loss": 0.7334116935729981,
      "step": 630
    },
    {
      "epoch": 0.03085675714767851,
      "grad_norm": 6.533365855916318,
      "learning_rate": 2e-05,
      "loss": 0.7016949653625488,
      "step": 640
    },
    {
      "epoch": 0.03133889397811099,
      "grad_norm": 16.877036489930155,
      "learning_rate": 2e-05,
      "loss": 0.7247958660125733,
      "step": 650
    },
    {
      "epoch": 0.03182103080854346,
      "grad_norm": 329.2790796078927,
      "learning_rate": 2e-05,
      "loss": 0.7393420219421387,
      "step": 660
    },
    {
      "epoch": 0.03230316763897594,
      "grad_norm": 3.076950012733951,
      "learning_rate": 2e-05,
      "loss": 0.762078857421875,
      "step": 670
    },
    {
      "epoch": 0.032785304469408416,
      "grad_norm": 4.030194347977115,
      "learning_rate": 2e-05,
      "loss": 0.7703542232513427,
      "step": 680
    },
    {
      "epoch": 0.0332674412998409,
      "grad_norm": 1.813412222853007,
      "learning_rate": 2e-05,
      "loss": 0.7255609035491943,
      "step": 690
    },
    {
      "epoch": 0.03374957813027337,
      "grad_norm": 3.3819806682901143,
      "learning_rate": 2e-05,
      "loss": 0.7121047973632812,
      "step": 700
    },
    {
      "epoch": 0.03423171496070585,
      "grad_norm": 2.3872601241148304,
      "learning_rate": 2e-05,
      "loss": 0.706441068649292,
      "step": 710
    },
    {
      "epoch": 0.034713851791138325,
      "grad_norm": 3.5426833842605157,
      "learning_rate": 2e-05,
      "loss": 0.7012114524841309,
      "step": 720
    },
    {
      "epoch": 0.0351959886215708,
      "grad_norm": 4.564258584135792,
      "learning_rate": 2e-05,
      "loss": 0.723219633102417,
      "step": 730
    },
    {
      "epoch": 0.03567812545200328,
      "grad_norm": 3.4441825412487086,
      "learning_rate": 2e-05,
      "loss": 0.6977805137634278,
      "step": 740
    },
    {
      "epoch": 0.036160262282435754,
      "grad_norm": 3.8546226650995714,
      "learning_rate": 2e-05,
      "loss": 0.7184113979339599,
      "step": 750
    },
    {
      "epoch": 0.036642399112868235,
      "grad_norm": 16.213966783350067,
      "learning_rate": 2e-05,
      "loss": 0.7428165435791015,
      "step": 760
    },
    {
      "epoch": 0.03712453594330071,
      "grad_norm": 2.0741210758941913,
      "learning_rate": 2e-05,
      "loss": 0.7358497619628906,
      "step": 770
    },
    {
      "epoch": 0.03760667277373318,
      "grad_norm": 2.5202301046172417,
      "learning_rate": 2e-05,
      "loss": 0.7103074550628662,
      "step": 780
    },
    {
      "epoch": 0.03808880960416566,
      "grad_norm": 4.106110045969379,
      "learning_rate": 2e-05,
      "loss": 0.713107967376709,
      "step": 790
    },
    {
      "epoch": 0.03857094643459814,
      "grad_norm": 3.088072216074999,
      "learning_rate": 2e-05,
      "loss": 0.7298454284667969,
      "step": 800
    },
    {
      "epoch": 0.03905308326503062,
      "grad_norm": 2.171527717000864,
      "learning_rate": 2e-05,
      "loss": 0.7251861095428467,
      "step": 810
    },
    {
      "epoch": 0.03953522009546309,
      "grad_norm": 2.0872404223379406,
      "learning_rate": 2e-05,
      "loss": 0.7178170680999756,
      "step": 820
    },
    {
      "epoch": 0.04001735692589557,
      "grad_norm": 2.085406019030795,
      "learning_rate": 2e-05,
      "loss": 0.6847468376159668,
      "step": 830
    },
    {
      "epoch": 0.040499493756328046,
      "grad_norm": 6.295654776698936,
      "learning_rate": 2e-05,
      "loss": 0.7038663387298584,
      "step": 840
    },
    {
      "epoch": 0.04098163058676052,
      "grad_norm": 2.454918336179734,
      "learning_rate": 2e-05,
      "loss": 0.7551318645477295,
      "step": 850
    },
    {
      "epoch": 0.041463767417193,
      "grad_norm": 2.5362213989256044,
      "learning_rate": 2e-05,
      "loss": 0.7268366813659668,
      "step": 860
    },
    {
      "epoch": 0.041945904247625475,
      "grad_norm": 2.0309978712081254,
      "learning_rate": 2e-05,
      "loss": 0.725460433959961,
      "step": 870
    },
    {
      "epoch": 0.042428041078057956,
      "grad_norm": 2.726392751612776,
      "learning_rate": 2e-05,
      "loss": 0.7183332443237305,
      "step": 880
    },
    {
      "epoch": 0.04291017790849043,
      "grad_norm": 2.2408894596393836,
      "learning_rate": 2e-05,
      "loss": 0.7466308116912842,
      "step": 890
    },
    {
      "epoch": 0.0433923147389229,
      "grad_norm": 8.581913026001844,
      "learning_rate": 2e-05,
      "loss": 0.67788667678833,
      "step": 900
    },
    {
      "epoch": 0.043874451569355384,
      "grad_norm": 14.329361671424175,
      "learning_rate": 2e-05,
      "loss": 0.6972944259643554,
      "step": 910
    },
    {
      "epoch": 0.04435658839978786,
      "grad_norm": 3.9088010842539327,
      "learning_rate": 2e-05,
      "loss": 0.699748182296753,
      "step": 920
    },
    {
      "epoch": 0.04483872523022034,
      "grad_norm": 2.221525537997574,
      "learning_rate": 2e-05,
      "loss": 0.7268280982971191,
      "step": 930
    },
    {
      "epoch": 0.04532086206065281,
      "grad_norm": 2.273319630076157,
      "learning_rate": 2e-05,
      "loss": 0.7030668258666992,
      "step": 940
    },
    {
      "epoch": 0.04580299889108529,
      "grad_norm": 2.8492569998023027,
      "learning_rate": 2e-05,
      "loss": 0.7284522533416748,
      "step": 950
    },
    {
      "epoch": 0.04628513572151777,
      "grad_norm": 3.6240853365585473,
      "learning_rate": 2e-05,
      "loss": 0.6911632061004639,
      "step": 960
    },
    {
      "epoch": 0.04676727255195024,
      "grad_norm": 4.035089048393918,
      "learning_rate": 2e-05,
      "loss": 0.7237444877624511,
      "step": 970
    },
    {
      "epoch": 0.04724940938238272,
      "grad_norm": 1.7484668255186857,
      "learning_rate": 2e-05,
      "loss": 0.7165475368499756,
      "step": 980
    },
    {
      "epoch": 0.047731546212815196,
      "grad_norm": 3.6565231516157466,
      "learning_rate": 2e-05,
      "loss": 0.7023948669433594,
      "step": 990
    },
    {
      "epoch": 0.048213683043247677,
      "grad_norm": 8.83591745574243,
      "learning_rate": 2e-05,
      "loss": 0.714229679107666,
      "step": 1000
    },
    {
      "epoch": 0.04869581987368015,
      "grad_norm": 1.5477438520033022,
      "learning_rate": 2e-05,
      "loss": 0.6836585998535156,
      "step": 1010
    },
    {
      "epoch": 0.049177956704112624,
      "grad_norm": 1.7108650020940415,
      "learning_rate": 2e-05,
      "loss": 0.6963685512542724,
      "step": 1020
    },
    {
      "epoch": 0.049660093534545105,
      "grad_norm": 3.8025775202775516,
      "learning_rate": 2e-05,
      "loss": 0.7289498329162598,
      "step": 1030
    },
    {
      "epoch": 0.05014223036497758,
      "grad_norm": 1.6346781298258524,
      "learning_rate": 2e-05,
      "loss": 0.7262353897094727,
      "step": 1040
    },
    {
      "epoch": 0.05062436719541006,
      "grad_norm": 3.386679850071031,
      "learning_rate": 2e-05,
      "loss": 0.6808836936950684,
      "step": 1050
    },
    {
      "epoch": 0.051106504025842533,
      "grad_norm": 2.3953301062602854,
      "learning_rate": 2e-05,
      "loss": 0.7089850425720214,
      "step": 1060
    },
    {
      "epoch": 0.051588640856275014,
      "grad_norm": 2.5139615513318763,
      "learning_rate": 2e-05,
      "loss": 0.7181517601013183,
      "step": 1070
    },
    {
      "epoch": 0.05207077768670749,
      "grad_norm": 2.8534620949787053,
      "learning_rate": 2e-05,
      "loss": 0.6958971977233886,
      "step": 1080
    },
    {
      "epoch": 0.05255291451713996,
      "grad_norm": 1.9564028862046592,
      "learning_rate": 2e-05,
      "loss": 0.7039243698120117,
      "step": 1090
    },
    {
      "epoch": 0.05303505134757244,
      "grad_norm": 1.557897571396239,
      "learning_rate": 2e-05,
      "loss": 0.7114754676818847,
      "step": 1100
    },
    {
      "epoch": 0.05351718817800492,
      "grad_norm": 2.930498345415913,
      "learning_rate": 2e-05,
      "loss": 0.7031359672546387,
      "step": 1110
    },
    {
      "epoch": 0.0539993250084374,
      "grad_norm": 1.4602419678677463,
      "learning_rate": 2e-05,
      "loss": 0.7077861785888672,
      "step": 1120
    },
    {
      "epoch": 0.05448146183886987,
      "grad_norm": 1.7319226933333385,
      "learning_rate": 2e-05,
      "loss": 0.7047904968261719,
      "step": 1130
    },
    {
      "epoch": 0.054963598669302345,
      "grad_norm": 2.520611756871299,
      "learning_rate": 2e-05,
      "loss": 0.7063097953796387,
      "step": 1140
    },
    {
      "epoch": 0.055445735499734826,
      "grad_norm": 3.214756094588082,
      "learning_rate": 2e-05,
      "loss": 0.6928376197814942,
      "step": 1150
    },
    {
      "epoch": 0.0559278723301673,
      "grad_norm": 2.1913033139614546,
      "learning_rate": 2e-05,
      "loss": 0.7101710319519043,
      "step": 1160
    },
    {
      "epoch": 0.05641000916059978,
      "grad_norm": 5.747581126680708,
      "learning_rate": 2e-05,
      "loss": 0.7223403453826904,
      "step": 1170
    },
    {
      "epoch": 0.056892145991032254,
      "grad_norm": 1.478178600197385,
      "learning_rate": 2e-05,
      "loss": 0.7083209991455078,
      "step": 1180
    },
    {
      "epoch": 0.05737428282146473,
      "grad_norm": 3.1153048058866166,
      "learning_rate": 2e-05,
      "loss": 0.7255118370056153,
      "step": 1190
    },
    {
      "epoch": 0.05785641965189721,
      "grad_norm": 6.6985613434510975,
      "learning_rate": 2e-05,
      "loss": 0.726648473739624,
      "step": 1200
    },
    {
      "epoch": 0.05833855648232968,
      "grad_norm": 5.377966618368178,
      "learning_rate": 2e-05,
      "loss": 0.7175424575805665,
      "step": 1210
    },
    {
      "epoch": 0.058820693312762164,
      "grad_norm": 3.838988528518626,
      "learning_rate": 2e-05,
      "loss": 0.7453009605407714,
      "step": 1220
    },
    {
      "epoch": 0.05930283014319464,
      "grad_norm": 2.6228691909450834,
      "learning_rate": 2e-05,
      "loss": 0.7184647560119629,
      "step": 1230
    },
    {
      "epoch": 0.05978496697362712,
      "grad_norm": 2.6612776295017615,
      "learning_rate": 2e-05,
      "loss": 0.7309318542480469,
      "step": 1240
    },
    {
      "epoch": 0.06026710380405959,
      "grad_norm": 1.8845329907929567,
      "learning_rate": 2e-05,
      "loss": 0.725009822845459,
      "step": 1250
    },
    {
      "epoch": 0.060749240634492066,
      "grad_norm": 10.28021708941531,
      "learning_rate": 2e-05,
      "loss": 0.7213550567626953,
      "step": 1260
    },
    {
      "epoch": 0.06123137746492455,
      "grad_norm": 1.7751708481039612,
      "learning_rate": 2e-05,
      "loss": 0.6989108562469483,
      "step": 1270
    },
    {
      "epoch": 0.06171351429535702,
      "grad_norm": 2.058733549275171,
      "learning_rate": 2e-05,
      "loss": 0.6917882442474366,
      "step": 1280
    },
    {
      "epoch": 0.0621956511257895,
      "grad_norm": 5.491929938751169,
      "learning_rate": 2e-05,
      "loss": 0.6999297142028809,
      "step": 1290
    },
    {
      "epoch": 0.06267778795622198,
      "grad_norm": 6.688351091581926,
      "learning_rate": 2e-05,
      "loss": 0.7235936164855957,
      "step": 1300
    },
    {
      "epoch": 0.06315992478665446,
      "grad_norm": 4.899979463669896,
      "learning_rate": 2e-05,
      "loss": 0.686549711227417,
      "step": 1310
    },
    {
      "epoch": 0.06364206161708692,
      "grad_norm": 2.952614374772642,
      "learning_rate": 2e-05,
      "loss": 0.7102313041687012,
      "step": 1320
    },
    {
      "epoch": 0.0641241984475194,
      "grad_norm": 10.566954823585363,
      "learning_rate": 2e-05,
      "loss": 0.7124320983886718,
      "step": 1330
    },
    {
      "epoch": 0.06460633527795188,
      "grad_norm": 8.873763489301671,
      "learning_rate": 2e-05,
      "loss": 0.7242676734924316,
      "step": 1340
    },
    {
      "epoch": 0.06508847210838437,
      "grad_norm": 3.170822217707811,
      "learning_rate": 2e-05,
      "loss": 0.709017276763916,
      "step": 1350
    },
    {
      "epoch": 0.06557060893881683,
      "grad_norm": 4.133385298753556,
      "learning_rate": 2e-05,
      "loss": 0.7052340507507324,
      "step": 1360
    },
    {
      "epoch": 0.06605274576924931,
      "grad_norm": 2.3980143582956575,
      "learning_rate": 2e-05,
      "loss": 0.7251494884490967,
      "step": 1370
    },
    {
      "epoch": 0.0665348825996818,
      "grad_norm": 1.8149128248978232,
      "learning_rate": 2e-05,
      "loss": 0.6977263450622558,
      "step": 1380
    },
    {
      "epoch": 0.06701701943011426,
      "grad_norm": 3.216048638536296,
      "learning_rate": 2e-05,
      "loss": 0.7132225036621094,
      "step": 1390
    },
    {
      "epoch": 0.06749915626054674,
      "grad_norm": 2.759251898652736,
      "learning_rate": 2e-05,
      "loss": 0.6781229972839355,
      "step": 1400
    },
    {
      "epoch": 0.06798129309097922,
      "grad_norm": 2.1615844816494523,
      "learning_rate": 2e-05,
      "loss": 0.6893566131591797,
      "step": 1410
    },
    {
      "epoch": 0.0684634299214117,
      "grad_norm": 1.269324197852931,
      "learning_rate": 2e-05,
      "loss": 0.7151976585388183,
      "step": 1420
    },
    {
      "epoch": 0.06894556675184417,
      "grad_norm": 2.475140950996921,
      "learning_rate": 2e-05,
      "loss": 0.7208847045898438,
      "step": 1430
    },
    {
      "epoch": 0.06942770358227665,
      "grad_norm": 1.8637431609519701,
      "learning_rate": 2e-05,
      "loss": 0.6920453548431397,
      "step": 1440
    },
    {
      "epoch": 0.06990984041270913,
      "grad_norm": 4.388822465185116,
      "learning_rate": 2e-05,
      "loss": 0.7050337791442871,
      "step": 1450
    },
    {
      "epoch": 0.0703919772431416,
      "grad_norm": 1.7686798808274666,
      "learning_rate": 2e-05,
      "loss": 0.6877009391784668,
      "step": 1460
    },
    {
      "epoch": 0.07087411407357408,
      "grad_norm": 2.1589166054135314,
      "learning_rate": 2e-05,
      "loss": 0.6840052604675293,
      "step": 1470
    },
    {
      "epoch": 0.07135625090400656,
      "grad_norm": 3.4176787553601677,
      "learning_rate": 2e-05,
      "loss": 0.7044760704040527,
      "step": 1480
    },
    {
      "epoch": 0.07183838773443903,
      "grad_norm": 5.058389900187091,
      "learning_rate": 2e-05,
      "loss": 0.7252198219299316,
      "step": 1490
    },
    {
      "epoch": 0.07232052456487151,
      "grad_norm": 3.4902103862821328,
      "learning_rate": 2e-05,
      "loss": 0.7132100582122802,
      "step": 1500
    },
    {
      "epoch": 0.07280266139530399,
      "grad_norm": 6.018184255339297,
      "learning_rate": 2e-05,
      "loss": 0.70932936668396,
      "step": 1510
    },
    {
      "epoch": 0.07328479822573647,
      "grad_norm": 3.5144758180231968,
      "learning_rate": 2e-05,
      "loss": 0.7115926742553711,
      "step": 1520
    },
    {
      "epoch": 0.07376693505616894,
      "grad_norm": 6.3900031796310985,
      "learning_rate": 2e-05,
      "loss": 0.7138595581054688,
      "step": 1530
    },
    {
      "epoch": 0.07424907188660142,
      "grad_norm": 1.830421739776605,
      "learning_rate": 2e-05,
      "loss": 0.7291291236877442,
      "step": 1540
    },
    {
      "epoch": 0.0747312087170339,
      "grad_norm": 4.409354344559001,
      "learning_rate": 2e-05,
      "loss": 0.7407273292541504,
      "step": 1550
    },
    {
      "epoch": 0.07521334554746636,
      "grad_norm": 3.4473627534438513,
      "learning_rate": 2e-05,
      "loss": 0.7394618511199951,
      "step": 1560
    },
    {
      "epoch": 0.07569548237789885,
      "grad_norm": 2.6382177594854754,
      "learning_rate": 2e-05,
      "loss": 0.6957945823669434,
      "step": 1570
    },
    {
      "epoch": 0.07617761920833133,
      "grad_norm": 3.999056912619744,
      "learning_rate": 2e-05,
      "loss": 0.6612532615661622,
      "step": 1580
    },
    {
      "epoch": 0.07665975603876381,
      "grad_norm": 3.7247803590530237,
      "learning_rate": 2e-05,
      "loss": 0.7023423194885254,
      "step": 1590
    },
    {
      "epoch": 0.07714189286919627,
      "grad_norm": 1.8337543544271353,
      "learning_rate": 2e-05,
      "loss": 0.7308431148529053,
      "step": 1600
    },
    {
      "epoch": 0.07762402969962875,
      "grad_norm": 4.832144300014454,
      "learning_rate": 2e-05,
      "loss": 0.7019494533538818,
      "step": 1610
    },
    {
      "epoch": 0.07810616653006124,
      "grad_norm": 1.2557192725218083,
      "learning_rate": 2e-05,
      "loss": 0.7272754669189453,
      "step": 1620
    },
    {
      "epoch": 0.0785883033604937,
      "grad_norm": 1.259086888724499,
      "learning_rate": 2e-05,
      "loss": 0.7088966369628906,
      "step": 1630
    },
    {
      "epoch": 0.07907044019092618,
      "grad_norm": 1.4497993722505094,
      "learning_rate": 2e-05,
      "loss": 0.7055980682373046,
      "step": 1640
    },
    {
      "epoch": 0.07955257702135866,
      "grad_norm": 1.9410198139904098,
      "learning_rate": 2e-05,
      "loss": 0.7067210674285889,
      "step": 1650
    },
    {
      "epoch": 0.08003471385179114,
      "grad_norm": 1.8227117633516707,
      "learning_rate": 2e-05,
      "loss": 0.6959988594055175,
      "step": 1660
    },
    {
      "epoch": 0.08051685068222361,
      "grad_norm": 8.864878739103949,
      "learning_rate": 2e-05,
      "loss": 0.7231966018676758,
      "step": 1670
    },
    {
      "epoch": 0.08099898751265609,
      "grad_norm": 5.91600501179535,
      "learning_rate": 2e-05,
      "loss": 0.6998160362243653,
      "step": 1680
    },
    {
      "epoch": 0.08148112434308857,
      "grad_norm": 2.7073467229023582,
      "learning_rate": 2e-05,
      "loss": 0.7311582088470459,
      "step": 1690
    },
    {
      "epoch": 0.08196326117352104,
      "grad_norm": 2.6882475083061217,
      "learning_rate": 2e-05,
      "loss": 0.7005412101745605,
      "step": 1700
    },
    {
      "epoch": 0.08244539800395352,
      "grad_norm": 1.3644811855655996,
      "learning_rate": 2e-05,
      "loss": 0.7040036678314209,
      "step": 1710
    },
    {
      "epoch": 0.082927534834386,
      "grad_norm": 1.707401344240697,
      "learning_rate": 2e-05,
      "loss": 0.7216098308563232,
      "step": 1720
    },
    {
      "epoch": 0.08340967166481847,
      "grad_norm": 2.2473714034468366,
      "learning_rate": 2e-05,
      "loss": 0.7012883186340332,
      "step": 1730
    },
    {
      "epoch": 0.08389180849525095,
      "grad_norm": 3.8729069145758053,
      "learning_rate": 2e-05,
      "loss": 0.7171290397644043,
      "step": 1740
    },
    {
      "epoch": 0.08437394532568343,
      "grad_norm": 2.2548793711676427,
      "learning_rate": 2e-05,
      "loss": 0.6937798976898193,
      "step": 1750
    },
    {
      "epoch": 0.08485608215611591,
      "grad_norm": 3.363398202084773,
      "learning_rate": 2e-05,
      "loss": 0.7099102973937989,
      "step": 1760
    },
    {
      "epoch": 0.08533821898654838,
      "grad_norm": 1.9683460905836172,
      "learning_rate": 2e-05,
      "loss": 0.7375545501708984,
      "step": 1770
    },
    {
      "epoch": 0.08582035581698086,
      "grad_norm": 2.7563303203565104,
      "learning_rate": 2e-05,
      "loss": 0.693428373336792,
      "step": 1780
    },
    {
      "epoch": 0.08630249264741334,
      "grad_norm": 5.488470914545985,
      "learning_rate": 2e-05,
      "loss": 0.6957249641418457,
      "step": 1790
    },
    {
      "epoch": 0.0867846294778458,
      "grad_norm": 2.09336496768559,
      "learning_rate": 2e-05,
      "loss": 0.6892104148864746,
      "step": 1800
    },
    {
      "epoch": 0.08726676630827829,
      "grad_norm": 1.5894667449541344,
      "learning_rate": 2e-05,
      "loss": 0.6863278388977051,
      "step": 1810
    },
    {
      "epoch": 0.08774890313871077,
      "grad_norm": 2.351872874716584,
      "learning_rate": 2e-05,
      "loss": 0.6925557136535645,
      "step": 1820
    },
    {
      "epoch": 0.08823103996914325,
      "grad_norm": 5.709628555644903,
      "learning_rate": 2e-05,
      "loss": 0.7161927223205566,
      "step": 1830
    },
    {
      "epoch": 0.08871317679957572,
      "grad_norm": 2.3637395099075658,
      "learning_rate": 2e-05,
      "loss": 0.6833971977233887,
      "step": 1840
    },
    {
      "epoch": 0.0891953136300082,
      "grad_norm": 3.0782660457463638,
      "learning_rate": 2e-05,
      "loss": 0.6962731838226318,
      "step": 1850
    },
    {
      "epoch": 0.08967745046044068,
      "grad_norm": 3.0074368386337524,
      "learning_rate": 2e-05,
      "loss": 0.6978533744812012,
      "step": 1860
    },
    {
      "epoch": 0.09015958729087314,
      "grad_norm": 2.887814419604526,
      "learning_rate": 2e-05,
      "loss": 0.7000442504882812,
      "step": 1870
    },
    {
      "epoch": 0.09064172412130563,
      "grad_norm": 3.6280575625203513,
      "learning_rate": 2e-05,
      "loss": 0.7079222679138184,
      "step": 1880
    },
    {
      "epoch": 0.0911238609517381,
      "grad_norm": 1.3557511666014126,
      "learning_rate": 2e-05,
      "loss": 0.6967864036560059,
      "step": 1890
    },
    {
      "epoch": 0.09160599778217059,
      "grad_norm": 1.403629260906539,
      "learning_rate": 2e-05,
      "loss": 0.7130854606628418,
      "step": 1900
    },
    {
      "epoch": 0.09208813461260305,
      "grad_norm": 1.8739359959248085,
      "learning_rate": 2e-05,
      "loss": 0.6871781826019288,
      "step": 1910
    },
    {
      "epoch": 0.09257027144303553,
      "grad_norm": 2.824655544812341,
      "learning_rate": 2e-05,
      "loss": 0.6981027126312256,
      "step": 1920
    },
    {
      "epoch": 0.09305240827346802,
      "grad_norm": 1.4828172680841498,
      "learning_rate": 2e-05,
      "loss": 0.6929860591888428,
      "step": 1930
    },
    {
      "epoch": 0.09353454510390048,
      "grad_norm": 7.2089191719005425,
      "learning_rate": 2e-05,
      "loss": 0.7134679794311524,
      "step": 1940
    },
    {
      "epoch": 0.09401668193433296,
      "grad_norm": 2.1889125436919574,
      "learning_rate": 2e-05,
      "loss": 0.7014190196990967,
      "step": 1950
    },
    {
      "epoch": 0.09449881876476544,
      "grad_norm": 6.312627812926516,
      "learning_rate": 2e-05,
      "loss": 0.7476691722869873,
      "step": 1960
    },
    {
      "epoch": 0.09498095559519791,
      "grad_norm": 1.2052636178685785,
      "learning_rate": 2e-05,
      "loss": 0.7070323944091796,
      "step": 1970
    },
    {
      "epoch": 0.09546309242563039,
      "grad_norm": 1.1645089780675213,
      "learning_rate": 2e-05,
      "loss": 0.6702715873718261,
      "step": 1980
    },
    {
      "epoch": 0.09594522925606287,
      "grad_norm": 3.612031603825751,
      "learning_rate": 2e-05,
      "loss": 0.6985786437988282,
      "step": 1990
    },
    {
      "epoch": 0.09642736608649535,
      "grad_norm": 1.2061047374120728,
      "learning_rate": 2e-05,
      "loss": 0.6996285915374756,
      "step": 2000
    },
    {
      "epoch": 0.09690950291692782,
      "grad_norm": 1.319276109312496,
      "learning_rate": 2e-05,
      "loss": 0.693095588684082,
      "step": 2010
    },
    {
      "epoch": 0.0973916397473603,
      "grad_norm": 1.358389710976587,
      "learning_rate": 2e-05,
      "loss": 0.7233096122741699,
      "step": 2020
    },
    {
      "epoch": 0.09787377657779278,
      "grad_norm": 2.29102697168753,
      "learning_rate": 2e-05,
      "loss": 0.699147367477417,
      "step": 2030
    }
  ],
  "logging_steps": 10,
  "max_steps": 5935,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2035,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 963613493821440.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}