{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1175,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 0.4270687699317932,
      "learning_rate": 0.00019999602855426865,
      "loss": 1.013,
      "step": 10
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 0.4152718782424927,
      "learning_rate": 0.00019998411453252217,
      "loss": 0.8289,
      "step": 20
    },
    {
      "epoch": 0.1276595744680851,
      "grad_norm": 0.7277560234069824,
      "learning_rate": 0.0001999642588810784,
      "loss": 0.5959,
      "step": 30
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 0.5505673885345459,
      "learning_rate": 0.00019993646317705016,
      "loss": 0.459,
      "step": 40
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 0.528052031993866,
      "learning_rate": 0.00019990072962822007,
      "loss": 0.3775,
      "step": 50
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 0.6307681202888489,
      "learning_rate": 0.00019985706107286514,
      "loss": 0.3285,
      "step": 60
    },
    {
      "epoch": 0.2978723404255319,
      "grad_norm": 0.6954013109207153,
      "learning_rate": 0.00019980546097953132,
      "loss": 0.2855,
      "step": 70
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 0.6790465116500854,
      "learning_rate": 0.000199745933446758,
      "loss": 0.2782,
      "step": 80
    },
    {
      "epoch": 0.3829787234042553,
      "grad_norm": 1.324937105178833,
      "learning_rate": 0.0001996784832027525,
      "loss": 0.2635,
      "step": 90
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.8779314756393433,
      "learning_rate": 0.00019960311560501454,
      "loss": 0.1861,
      "step": 100
    },
    {
      "epoch": 0.46808510638297873,
      "grad_norm": 0.693745493888855,
      "learning_rate": 0.00019951983663991056,
      "loss": 0.2001,
      "step": 110
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 1.0649502277374268,
      "learning_rate": 0.00019942865292219838,
      "loss": 0.1378,
      "step": 120
    },
    {
      "epoch": 0.5531914893617021,
      "grad_norm": 0.6962260007858276,
      "learning_rate": 0.0001993295716945017,
      "loss": 0.1579,
      "step": 130
    },
    {
      "epoch": 0.5957446808510638,
      "grad_norm": 0.7934479713439941,
      "learning_rate": 0.00019922260082673497,
      "loss": 0.092,
      "step": 140
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 1.1331907510757446,
      "learning_rate": 0.000199107748815478,
      "loss": 0.1208,
      "step": 150
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 1.3689247369766235,
      "learning_rate": 0.00019898502478330152,
      "loss": 0.0874,
      "step": 160
    },
    {
      "epoch": 0.723404255319149,
      "grad_norm": 0.5304535031318665,
      "learning_rate": 0.00019885443847804211,
      "loss": 0.0881,
      "step": 170
    },
    {
      "epoch": 0.7659574468085106,
      "grad_norm": 0.6805845499038696,
      "learning_rate": 0.0001987160002720283,
      "loss": 0.0584,
      "step": 180
    },
    {
      "epoch": 0.8085106382978723,
      "grad_norm": 0.2527499198913574,
      "learning_rate": 0.00019856972116125653,
      "loss": 0.08,
      "step": 190
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.799462616443634,
      "learning_rate": 0.0001984156127645178,
      "loss": 0.0556,
      "step": 200
    },
    {
      "epoch": 0.8936170212765957,
      "grad_norm": 0.936975359916687,
      "learning_rate": 0.0001982536873224748,
      "loss": 0.0945,
      "step": 210
    },
    {
      "epoch": 0.9361702127659575,
      "grad_norm": 0.8067993521690369,
      "learning_rate": 0.00019808395769668963,
      "loss": 0.0495,
      "step": 220
    },
    {
      "epoch": 0.9787234042553191,
      "grad_norm": 0.45767834782600403,
      "learning_rate": 0.00019790643736860227,
      "loss": 0.0617,
      "step": 230
    },
    {
      "epoch": 1.0212765957446808,
      "grad_norm": 0.9198794364929199,
      "learning_rate": 0.00019772114043845965,
      "loss": 0.0467,
      "step": 240
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 0.7327796816825867,
      "learning_rate": 0.0001975280816241959,
      "loss": 0.0391,
      "step": 250
    },
    {
      "epoch": 1.1063829787234043,
      "grad_norm": 0.8003076910972595,
      "learning_rate": 0.00019732727626026305,
      "loss": 0.0428,
      "step": 260
    },
    {
      "epoch": 1.148936170212766,
      "grad_norm": 0.10251367837190628,
      "learning_rate": 0.0001971187402964132,
      "loss": 0.032,
      "step": 270
    },
    {
      "epoch": 1.1914893617021276,
      "grad_norm": 0.45093855261802673,
      "learning_rate": 0.00019690249029643162,
      "loss": 0.0673,
      "step": 280
    },
    {
      "epoch": 1.2340425531914894,
      "grad_norm": 0.4845767915248871,
      "learning_rate": 0.0001966785434368211,
      "loss": 0.033,
      "step": 290
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 0.31195056438446045,
      "learning_rate": 0.00019644691750543767,
      "loss": 0.0261,
      "step": 300
    },
    {
      "epoch": 1.3191489361702127,
      "grad_norm": 0.14839951694011688,
      "learning_rate": 0.00019620763090007762,
      "loss": 0.0298,
      "step": 310
    },
    {
      "epoch": 1.3617021276595744,
      "grad_norm": 0.20573872327804565,
      "learning_rate": 0.00019596070262701626,
      "loss": 0.0155,
      "step": 320
    },
    {
      "epoch": 1.4042553191489362,
      "grad_norm": 0.47702595591545105,
      "learning_rate": 0.00019570615229949842,
      "loss": 0.0369,
      "step": 330
    },
    {
      "epoch": 1.4468085106382977,
      "grad_norm": 0.7073186039924622,
      "learning_rate": 0.00019544400013618023,
      "loss": 0.0302,
      "step": 340
    },
    {
      "epoch": 1.4893617021276595,
      "grad_norm": 0.1539478451013565,
      "learning_rate": 0.00019517426695952358,
      "loss": 0.0223,
      "step": 350
    },
    {
      "epoch": 1.5319148936170213,
      "grad_norm": 0.5202814340591431,
      "learning_rate": 0.00019489697419414182,
      "loss": 0.0263,
      "step": 360
    },
    {
      "epoch": 1.574468085106383,
      "grad_norm": 0.968192458152771,
      "learning_rate": 0.00019461214386509842,
      "loss": 0.044,
      "step": 370
    },
    {
      "epoch": 1.6170212765957448,
      "grad_norm": 0.5662522912025452,
      "learning_rate": 0.00019431979859615726,
      "loss": 0.0421,
      "step": 380
    },
    {
      "epoch": 1.6595744680851063,
      "grad_norm": 0.42925137281417847,
      "learning_rate": 0.00019401996160798573,
      "loss": 0.0606,
      "step": 390
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 0.5803830027580261,
      "learning_rate": 0.00019371265671631037,
      "loss": 0.0392,
      "step": 400
    },
    {
      "epoch": 1.7446808510638299,
      "grad_norm": 0.4235450327396393,
      "learning_rate": 0.00019339790833002515,
      "loss": 0.0286,
      "step": 410
    },
    {
      "epoch": 1.7872340425531914,
      "grad_norm": 0.519207775592804,
      "learning_rate": 0.00019307574144925287,
      "loss": 0.0522,
      "step": 420
    },
    {
      "epoch": 1.8297872340425532,
      "grad_norm": 0.2344844490289688,
      "learning_rate": 0.00019274618166335912,
      "loss": 0.0281,
      "step": 430
    },
    {
      "epoch": 1.872340425531915,
      "grad_norm": 0.1990007758140564,
      "learning_rate": 0.00019240925514892,
      "loss": 0.0229,
      "step": 440
    },
    {
      "epoch": 1.9148936170212765,
      "grad_norm": 0.10929415374994278,
      "learning_rate": 0.00019206498866764288,
      "loss": 0.0258,
      "step": 450
    },
    {
      "epoch": 1.9574468085106385,
      "grad_norm": 0.4308103024959564,
      "learning_rate": 0.00019171340956424074,
      "loss": 0.0167,
      "step": 460
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.46525439620018005,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0283,
      "step": 470
    },
    {
      "epoch": 2.0425531914893615,
      "grad_norm": 0.28837406635284424,
      "learning_rate": 0.00019098842577186314,
      "loss": 0.0137,
      "step": 480
    },
    {
      "epoch": 2.0851063829787235,
      "grad_norm": 0.08533861488103867,
      "learning_rate": 0.00019061507866756347,
      "loss": 0.0182,
      "step": 490
    },
    {
      "epoch": 2.127659574468085,
      "grad_norm": 0.3499375581741333,
      "learning_rate": 0.00019023453410591635,
      "loss": 0.0221,
      "step": 500
    },
    {
      "epoch": 2.1702127659574466,
      "grad_norm": 0.07716694474220276,
      "learning_rate": 0.00018984682231316333,
      "loss": 0.0075,
      "step": 510
    },
    {
      "epoch": 2.2127659574468086,
      "grad_norm": 0.3093757927417755,
      "learning_rate": 0.00018945197408483123,
      "loss": 0.0133,
      "step": 520
    },
    {
      "epoch": 2.25531914893617,
      "grad_norm": 0.13492655754089355,
      "learning_rate": 0.00018905002078328632,
      "loss": 0.0184,
      "step": 530
    },
    {
      "epoch": 2.297872340425532,
      "grad_norm": 0.07833054661750793,
      "learning_rate": 0.000188640994335243,
      "loss": 0.0109,
      "step": 540
    },
    {
      "epoch": 2.3404255319148937,
      "grad_norm": 0.08865915983915329,
      "learning_rate": 0.0001882249272292282,
      "loss": 0.0121,
      "step": 550
    },
    {
      "epoch": 2.382978723404255,
      "grad_norm": 0.31314581632614136,
      "learning_rate": 0.00018780185251300046,
      "loss": 0.0242,
      "step": 560
    },
    {
      "epoch": 2.425531914893617,
      "grad_norm": 0.10387410968542099,
      "learning_rate": 0.00018737180379092537,
      "loss": 0.0285,
      "step": 570
    },
    {
      "epoch": 2.4680851063829787,
      "grad_norm": 0.11755700409412384,
      "learning_rate": 0.0001869348152213061,
      "loss": 0.0281,
      "step": 580
    },
    {
      "epoch": 2.5106382978723403,
      "grad_norm": 0.1438552439212799,
      "learning_rate": 0.0001864909215136705,
      "loss": 0.0216,
      "step": 590
    },
    {
      "epoch": 2.5531914893617023,
      "grad_norm": 0.08940370380878448,
      "learning_rate": 0.00018604015792601396,
      "loss": 0.0226,
      "step": 600
    },
    {
      "epoch": 2.595744680851064,
      "grad_norm": 0.19193390011787415,
      "learning_rate": 0.00018558256026199896,
      "loss": 0.0184,
      "step": 610
    },
    {
      "epoch": 2.6382978723404253,
      "grad_norm": 0.4586654603481293,
      "learning_rate": 0.00018511816486811134,
      "loss": 0.0154,
      "step": 620
    },
    {
      "epoch": 2.6808510638297873,
      "grad_norm": 0.05811255797743797,
      "learning_rate": 0.00018464700863077312,
      "loss": 0.0238,
      "step": 630
    },
    {
      "epoch": 2.723404255319149,
      "grad_norm": 0.16280680894851685,
      "learning_rate": 0.00018416912897341295,
      "loss": 0.0253,
      "step": 640
    },
    {
      "epoch": 2.7659574468085104,
      "grad_norm": 0.07031189650297165,
      "learning_rate": 0.00018368456385349334,
      "loss": 0.0146,
      "step": 650
    },
    {
      "epoch": 2.8085106382978724,
      "grad_norm": 0.07851342856884003,
      "learning_rate": 0.0001831933517594957,
      "loss": 0.0301,
      "step": 660
    },
    {
      "epoch": 2.851063829787234,
      "grad_norm": 0.11461298912763596,
      "learning_rate": 0.0001826955317078636,
      "loss": 0.0155,
      "step": 670
    },
    {
      "epoch": 2.8936170212765955,
      "grad_norm": 0.1839868575334549,
      "learning_rate": 0.00018219114323990345,
      "loss": 0.0099,
      "step": 680
    },
    {
      "epoch": 2.9361702127659575,
      "grad_norm": 0.04199373722076416,
      "learning_rate": 0.00018168022641864377,
      "loss": 0.0192,
      "step": 690
    },
    {
      "epoch": 2.978723404255319,
      "grad_norm": 0.3203773498535156,
      "learning_rate": 0.00018116282182565311,
      "loss": 0.0272,
      "step": 700
    },
    {
      "epoch": 3.021276595744681,
      "grad_norm": 0.327921599149704,
      "learning_rate": 0.0001806389705578168,
      "loss": 0.0081,
      "step": 710
    },
    {
      "epoch": 3.0638297872340425,
      "grad_norm": 0.29155433177948,
      "learning_rate": 0.00018010871422407236,
      "loss": 0.0128,
      "step": 720
    },
    {
      "epoch": 3.106382978723404,
      "grad_norm": 0.06926452368497849,
      "learning_rate": 0.00017957209494210493,
      "loss": 0.0171,
      "step": 730
    },
    {
      "epoch": 3.148936170212766,
      "grad_norm": 0.08231089264154434,
      "learning_rate": 0.0001790291553350016,
      "loss": 0.0098,
      "step": 740
    },
    {
      "epoch": 3.1914893617021276,
      "grad_norm": 0.14707215130329132,
      "learning_rate": 0.0001784799385278661,
      "loss": 0.0092,
      "step": 750
    },
    {
      "epoch": 3.2340425531914896,
      "grad_norm": 0.2735896706581116,
      "learning_rate": 0.00017792448814439333,
      "loss": 0.0115,
      "step": 760
    },
    {
      "epoch": 3.276595744680851,
      "grad_norm": 0.44960370659828186,
      "learning_rate": 0.00017736284830340436,
      "loss": 0.0195,
      "step": 770
    },
    {
      "epoch": 3.3191489361702127,
      "grad_norm": 0.13413724303245544,
      "learning_rate": 0.00017679506361534215,
      "loss": 0.0187,
      "step": 780
    },
    {
      "epoch": 3.3617021276595747,
      "grad_norm": 0.24698686599731445,
      "learning_rate": 0.00017622117917872823,
      "loss": 0.0125,
      "step": 790
    },
    {
      "epoch": 3.404255319148936,
      "grad_norm": 0.48694342374801636,
      "learning_rate": 0.00017564124057658056,
      "loss": 0.0234,
      "step": 800
    },
    {
      "epoch": 3.4468085106382977,
      "grad_norm": 0.6931429505348206,
      "learning_rate": 0.00017505529387279277,
      "loss": 0.0234,
      "step": 810
    },
    {
      "epoch": 3.4893617021276597,
      "grad_norm": 0.13700473308563232,
      "learning_rate": 0.00017446338560847568,
      "loss": 0.0145,
      "step": 820
    },
    {
      "epoch": 3.5319148936170213,
      "grad_norm": 0.3254775404930115,
      "learning_rate": 0.00017386556279826021,
      "loss": 0.0179,
      "step": 830
    },
    {
      "epoch": 3.574468085106383,
      "grad_norm": 0.368379682302475,
      "learning_rate": 0.00017326187292656333,
      "loss": 0.013,
      "step": 840
    },
    {
      "epoch": 3.617021276595745,
      "grad_norm": 0.2745888829231262,
      "learning_rate": 0.00017265236394381633,
      "loss": 0.0136,
      "step": 850
    },
    {
      "epoch": 3.6595744680851063,
      "grad_norm": 0.0781714916229248,
      "learning_rate": 0.00017203708426265614,
      "loss": 0.0126,
      "step": 860
    },
    {
      "epoch": 3.702127659574468,
      "grad_norm": 0.7518234848976135,
      "learning_rate": 0.00017141608275408006,
      "loss": 0.0134,
      "step": 870
    },
    {
      "epoch": 3.74468085106383,
      "grad_norm": 0.4271518886089325,
      "learning_rate": 0.00017078940874356392,
      "loss": 0.0127,
      "step": 880
    },
    {
      "epoch": 3.7872340425531914,
      "grad_norm": 0.34387120604515076,
      "learning_rate": 0.00017015711200714414,
      "loss": 0.0161,
      "step": 890
    },
    {
      "epoch": 3.829787234042553,
      "grad_norm": 0.09641717374324799,
      "learning_rate": 0.00016951924276746425,
      "loss": 0.0185,
      "step": 900
    },
    {
      "epoch": 3.872340425531915,
      "grad_norm": 0.44215765595436096,
      "learning_rate": 0.00016887585168978562,
      "loss": 0.0115,
      "step": 910
    },
    {
      "epoch": 3.9148936170212765,
      "grad_norm": 0.06954783201217651,
      "learning_rate": 0.0001682269898779632,
      "loss": 0.0121,
      "step": 920
    },
    {
      "epoch": 3.9574468085106385,
      "grad_norm": 0.21080243587493896,
      "learning_rate": 0.00016757270887038654,
      "loss": 0.0125,
      "step": 930
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3382236063480377,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0109,
      "step": 940
    },
    {
      "epoch": 4.042553191489362,
      "grad_norm": 0.36123183369636536,
      "learning_rate": 0.00016624809756960444,
      "loss": 0.0093,
      "step": 950
    },
    {
      "epoch": 4.085106382978723,
      "grad_norm": 0.45228853821754456,
      "learning_rate": 0.00016557787248883696,
      "loss": 0.0117,
      "step": 960
    },
    {
      "epoch": 4.127659574468085,
      "grad_norm": 0.2724202275276184,
      "learning_rate": 0.00016490243862883413,
      "loss": 0.0126,
      "step": 970
    },
    {
      "epoch": 4.170212765957447,
      "grad_norm": 0.17904357612133026,
      "learning_rate": 0.00016422184963857432,
      "loss": 0.0103,
      "step": 980
    },
    {
      "epoch": 4.212765957446808,
      "grad_norm": 0.4267734885215759,
      "learning_rate": 0.00016353615957650236,
      "loss": 0.0105,
      "step": 990
    },
    {
      "epoch": 4.25531914893617,
      "grad_norm": 0.11816457659006119,
      "learning_rate": 0.00016284542290623567,
      "loss": 0.0097,
      "step": 1000
    },
    {
      "epoch": 4.297872340425532,
      "grad_norm": 0.04166145250201225,
      "learning_rate": 0.00016214969449223824,
      "loss": 0.0116,
      "step": 1010
    },
    {
      "epoch": 4.340425531914893,
      "grad_norm": 0.0687410831451416,
      "learning_rate": 0.00016144902959546286,
      "loss": 0.0088,
      "step": 1020
    },
    {
      "epoch": 4.382978723404255,
      "grad_norm": 0.37416237592697144,
      "learning_rate": 0.00016074348386896177,
      "loss": 0.019,
      "step": 1030
    },
    {
      "epoch": 4.425531914893617,
      "grad_norm": 0.06069188937544823,
      "learning_rate": 0.00016003311335346636,
      "loss": 0.0138,
      "step": 1040
    },
    {
      "epoch": 4.468085106382979,
      "grad_norm": 0.0817495658993721,
      "learning_rate": 0.00015931797447293552,
      "loss": 0.0084,
      "step": 1050
    },
    {
      "epoch": 4.51063829787234,
      "grad_norm": 0.09787007421255112,
      "learning_rate": 0.00015859812403007443,
      "loss": 0.009,
      "step": 1060
    },
    {
      "epoch": 4.553191489361702,
      "grad_norm": 0.06179153174161911,
      "learning_rate": 0.0001578736192018224,
      "loss": 0.008,
      "step": 1070
    },
    {
      "epoch": 4.595744680851064,
      "grad_norm": 0.3092339038848877,
      "learning_rate": 0.00015714451753481168,
      "loss": 0.0131,
      "step": 1080
    },
    {
      "epoch": 4.638297872340425,
      "grad_norm": 0.06405780464410782,
      "learning_rate": 0.0001564108769407962,
      "loss": 0.0122,
      "step": 1090
    },
    {
      "epoch": 4.680851063829787,
      "grad_norm": 0.21473410725593567,
      "learning_rate": 0.00015567275569205218,
      "loss": 0.0117,
      "step": 1100
    },
    {
      "epoch": 4.723404255319149,
      "grad_norm": 0.3080317974090576,
      "learning_rate": 0.00015493021241674918,
      "loss": 0.011,
      "step": 1110
    },
    {
      "epoch": 4.76595744680851,
      "grad_norm": 0.6501839756965637,
      "learning_rate": 0.0001541833060942937,
      "loss": 0.0124,
      "step": 1120
    },
    {
      "epoch": 4.808510638297872,
      "grad_norm": 0.04628886282444,
      "learning_rate": 0.00015343209605064422,
      "loss": 0.0082,
      "step": 1130
    },
    {
      "epoch": 4.851063829787234,
      "grad_norm": 0.059793177992105484,
      "learning_rate": 0.00015267664195359917,
      "loss": 0.0072,
      "step": 1140
    },
    {
      "epoch": 4.8936170212765955,
      "grad_norm": 0.052162788808345795,
      "learning_rate": 0.00015191700380805752,
      "loss": 0.0095,
      "step": 1150
    },
    {
      "epoch": 4.9361702127659575,
      "grad_norm": 0.06147542968392372,
      "learning_rate": 0.00015115324195125274,
      "loss": 0.0098,
      "step": 1160
    },
    {
      "epoch": 4.9787234042553195,
      "grad_norm": 0.6586833000183105,
      "learning_rate": 0.00015038541704796003,
      "loss": 0.0139,
      "step": 1170
    }
  ],
  "logging_steps": 10,
  "max_steps": 3525,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.72337525157888e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}