{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.108401684770561,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005542008423852805,
      "grad_norm": 0.07243233174085617,
      "learning_rate": 1.2315270935960592e-05,
      "loss": 1.4594,
      "step": 25
    },
    {
      "epoch": 0.01108401684770561,
      "grad_norm": 0.40484485030174255,
      "learning_rate": 2.4630541871921184e-05,
      "loss": 2.2032,
      "step": 50
    },
    {
      "epoch": 0.016626025271558414,
      "grad_norm": 0.06850667297840118,
      "learning_rate": 3.694581280788178e-05,
      "loss": 1.2931,
      "step": 75
    },
    {
      "epoch": 0.02216803369541122,
      "grad_norm": 0.4395073354244232,
      "learning_rate": 4.926108374384237e-05,
      "loss": 1.5698,
      "step": 100
    },
    {
      "epoch": 0.027710042119264023,
      "grad_norm": 0.077068030834198,
      "learning_rate": 6.157635467980296e-05,
      "loss": 1.0537,
      "step": 125
    },
    {
      "epoch": 0.03325205054311683,
      "grad_norm": 0.3282291293144226,
      "learning_rate": 7.389162561576355e-05,
      "loss": 0.9749,
      "step": 150
    },
    {
      "epoch": 0.03879405896696963,
      "grad_norm": 0.0593000203371048,
      "learning_rate": 8.620689655172413e-05,
      "loss": 0.9349,
      "step": 175
    },
    {
      "epoch": 0.04433606739082244,
      "grad_norm": 0.25612473487854004,
      "learning_rate": 9.852216748768474e-05,
      "loss": 0.8974,
      "step": 200
    },
    {
      "epoch": 0.04987807581467524,
      "grad_norm": 0.0757347121834755,
      "learning_rate": 0.00011083743842364534,
      "loss": 0.9081,
      "step": 225
    },
    {
      "epoch": 0.055420084238528046,
      "grad_norm": 0.14145499467849731,
      "learning_rate": 0.00012315270935960593,
      "loss": 0.8607,
      "step": 250
    },
    {
      "epoch": 0.06096209266238085,
      "grad_norm": 0.07710155844688416,
      "learning_rate": 0.00013546798029556652,
      "loss": 0.8973,
      "step": 275
    },
    {
      "epoch": 0.06650410108623366,
      "grad_norm": 0.14791467785835266,
      "learning_rate": 0.0001477832512315271,
      "loss": 0.7924,
      "step": 300
    },
    {
      "epoch": 0.07204610951008646,
      "grad_norm": 0.07742594182491302,
      "learning_rate": 0.00016009852216748767,
      "loss": 0.8698,
      "step": 325
    },
    {
      "epoch": 0.07758811793393926,
      "grad_norm": 0.14303487539291382,
      "learning_rate": 0.00017241379310344826,
      "loss": 0.786,
      "step": 350
    },
    {
      "epoch": 0.08313012635779206,
      "grad_norm": 0.0865108072757721,
      "learning_rate": 0.00018472906403940888,
      "loss": 0.8606,
      "step": 375
    },
    {
      "epoch": 0.08867213478164487,
      "grad_norm": 0.7533164024353027,
      "learning_rate": 0.00019704433497536947,
      "loss": 0.807,
      "step": 400
    },
    {
      "epoch": 0.09421414320549767,
      "grad_norm": 0.08325570821762085,
      "learning_rate": 0.00019999896617927833,
      "loss": 0.8635,
      "step": 425
    },
    {
      "epoch": 0.09975615162935048,
      "grad_norm": 0.1043543666601181,
      "learning_rate": 0.0001999944557842899,
      "loss": 0.7825,
      "step": 450
    },
    {
      "epoch": 0.10529816005320328,
      "grad_norm": 0.07949995994567871,
      "learning_rate": 0.0001999863658806385,
      "loss": 0.8379,
      "step": 475
    },
    {
      "epoch": 0.11084016847705609,
      "grad_norm": 0.12020070850849152,
      "learning_rate": 0.00019997469675791905,
      "loss": 0.768,
      "step": 500
    },
    {
      "epoch": 0.11638217690090889,
      "grad_norm": 0.0803595781326294,
      "learning_rate": 0.00019995944883385196,
      "loss": 0.8487,
      "step": 525
    },
    {
      "epoch": 0.1219241853247617,
      "grad_norm": 0.11509452760219574,
      "learning_rate": 0.0001999406226542682,
      "loss": 0.7787,
      "step": 550
    },
    {
      "epoch": 0.1274661937486145,
      "grad_norm": 0.07928384840488434,
      "learning_rate": 0.00019991821889308987,
      "loss": 0.8357,
      "step": 575
    },
    {
      "epoch": 0.1330082021724673,
      "grad_norm": 0.09423446655273438,
      "learning_rate": 0.00019989223835230606,
      "loss": 0.7564,
      "step": 600
    },
    {
      "epoch": 0.1385502105963201,
      "grad_norm": 0.0835939422249794,
      "learning_rate": 0.000199862681961944,
      "loss": 0.8568,
      "step": 625
    },
    {
      "epoch": 0.1440922190201729,
      "grad_norm": 0.09292898327112198,
      "learning_rate": 0.0001998295507800359,
      "loss": 0.7612,
      "step": 650
    },
    {
      "epoch": 0.1496342274440257,
      "grad_norm": 0.07704215496778488,
      "learning_rate": 0.00019979284599258107,
      "loss": 0.8263,
      "step": 675
    },
    {
      "epoch": 0.15517623586787851,
      "grad_norm": 0.10980474948883057,
      "learning_rate": 0.0001997525689135034,
      "loss": 0.7677,
      "step": 700
    },
    {
      "epoch": 0.16071824429173132,
      "grad_norm": 0.08016064018011093,
      "learning_rate": 0.0001997087209846043,
      "loss": 0.8344,
      "step": 725
    },
    {
      "epoch": 0.16626025271558412,
      "grad_norm": 0.0950881615281105,
      "learning_rate": 0.0001996613037755113,
      "loss": 0.769,
      "step": 750
    },
    {
      "epoch": 0.17180226113943692,
      "grad_norm": 0.07932984828948975,
      "learning_rate": 0.00019961031898362152,
      "loss": 0.8156,
      "step": 775
    },
    {
      "epoch": 0.17734426956328975,
      "grad_norm": 0.09336528927087784,
      "learning_rate": 0.00019955576843404128,
      "loss": 0.7767,
      "step": 800
    },
    {
      "epoch": 0.18288627798714255,
      "grad_norm": 0.08560346812009811,
      "learning_rate": 0.00019949765407952042,
      "loss": 0.8228,
      "step": 825
    },
    {
      "epoch": 0.18842828641099535,
      "grad_norm": 0.08475169539451599,
      "learning_rate": 0.00019943597800038267,
      "loss": 0.7669,
      "step": 850
    },
    {
      "epoch": 0.19397029483484815,
      "grad_norm": 0.09038034081459045,
      "learning_rate": 0.00019937074240445105,
      "loss": 0.8182,
      "step": 875
    },
    {
      "epoch": 0.19951230325870095,
      "grad_norm": 0.09195873886346817,
      "learning_rate": 0.0001993019496269688,
      "loss": 0.7598,
      "step": 900
    },
    {
      "epoch": 0.20505431168255375,
      "grad_norm": 0.08655796200037003,
      "learning_rate": 0.0001992296021305159,
      "loss": 0.8167,
      "step": 925
    },
    {
      "epoch": 0.21059632010640655,
      "grad_norm": 0.08353498578071594,
      "learning_rate": 0.00019915370250492084,
      "loss": 0.7486,
      "step": 950
    },
    {
      "epoch": 0.21613832853025935,
      "grad_norm": 0.09225723147392273,
      "learning_rate": 0.0001990742534671679,
      "loss": 0.8138,
      "step": 975
    },
    {
      "epoch": 0.22168033695411218,
      "grad_norm": 0.12104763090610504,
      "learning_rate": 0.00019899125786129997,
      "loss": 0.7153,
      "step": 1000
    },
    {
      "epoch": 0.22722234537796498,
      "grad_norm": 0.0815986767411232,
      "learning_rate": 0.00019890471865831669,
      "loss": 0.7983,
      "step": 1025
    },
    {
      "epoch": 0.23276435380181779,
      "grad_norm": 0.08845670521259308,
      "learning_rate": 0.00019881463895606805,
      "loss": 0.7187,
      "step": 1050
    },
    {
      "epoch": 0.2383063622256706,
      "grad_norm": 0.0821809321641922,
      "learning_rate": 0.00019872102197914359,
      "loss": 0.804,
      "step": 1075
    },
    {
      "epoch": 0.2438483706495234,
      "grad_norm": 0.08711609989404678,
      "learning_rate": 0.00019862387107875688,
      "loss": 0.7795,
      "step": 1100
    },
    {
      "epoch": 0.2493903790733762,
      "grad_norm": 0.08517508953809738,
      "learning_rate": 0.00019852318973262567,
      "loss": 0.7937,
      "step": 1125
    },
    {
      "epoch": 0.254932387497229,
      "grad_norm": 0.10830071568489075,
      "learning_rate": 0.00019841898154484726,
      "loss": 0.7458,
      "step": 1150
    },
    {
      "epoch": 0.2604743959210818,
      "grad_norm": 0.08541836589574814,
      "learning_rate": 0.0001983112502457696,
      "loss": 0.8131,
      "step": 1175
    },
    {
      "epoch": 0.2660164043449346,
      "grad_norm": 0.08794037252664566,
      "learning_rate": 0.00019819999969185762,
      "loss": 0.7577,
      "step": 1200
    },
    {
      "epoch": 0.2715584127687874,
      "grad_norm": 0.08078176528215408,
      "learning_rate": 0.00019808523386555542,
      "loss": 0.812,
      "step": 1225
    },
    {
      "epoch": 0.2771004211926402,
      "grad_norm": 0.09263130277395248,
      "learning_rate": 0.0001979669568751434,
      "loss": 0.7582,
      "step": 1250
    },
    {
      "epoch": 0.282642429616493,
      "grad_norm": 0.08198932558298111,
      "learning_rate": 0.00019784517295459147,
      "loss": 0.7958,
      "step": 1275
    },
    {
      "epoch": 0.2881844380403458,
      "grad_norm": 0.07858102023601532,
      "learning_rate": 0.00019771988646340725,
      "loss": 0.7744,
      "step": 1300
    },
    {
      "epoch": 0.2937264464641986,
      "grad_norm": 0.0851408839225769,
      "learning_rate": 0.00019759110188648026,
      "loss": 0.7913,
      "step": 1325
    },
    {
      "epoch": 0.2992684548880514,
      "grad_norm": 0.09252189099788666,
      "learning_rate": 0.00019745882383392116,
      "loss": 0.7675,
      "step": 1350
    },
    {
      "epoch": 0.30481046331190426,
      "grad_norm": 0.08306555449962616,
      "learning_rate": 0.0001973230570408968,
      "loss": 0.8059,
      "step": 1375
    },
    {
      "epoch": 0.31035247173575703,
      "grad_norm": 0.0797729641199112,
      "learning_rate": 0.0001971838063674608,
      "loss": 0.7424,
      "step": 1400
    },
    {
      "epoch": 0.31589448015960986,
      "grad_norm": 0.08266165107488632,
      "learning_rate": 0.0001970410767983794,
      "loss": 0.7847,
      "step": 1425
    },
    {
      "epoch": 0.32143648858346263,
      "grad_norm": 0.09364205598831177,
      "learning_rate": 0.00019689487344295322,
      "loss": 0.6924,
      "step": 1450
    },
    {
      "epoch": 0.32697849700731546,
      "grad_norm": 0.08461842685937881,
      "learning_rate": 0.00019674520153483414,
      "loss": 0.8007,
      "step": 1475
    },
    {
      "epoch": 0.33252050543116823,
      "grad_norm": 0.0840207040309906,
      "learning_rate": 0.00019659206643183813,
      "loss": 0.7139,
      "step": 1500
    },
    {
      "epoch": 0.33806251385502106,
      "grad_norm": 0.08344192802906036,
      "learning_rate": 0.00019643547361575343,
      "loss": 0.7982,
      "step": 1525
    },
    {
      "epoch": 0.34360452227887384,
      "grad_norm": 0.07934779673814774,
      "learning_rate": 0.0001962754286921442,
      "loss": 0.7164,
      "step": 1550
    },
    {
      "epoch": 0.34914653070272667,
      "grad_norm": 0.08716201782226562,
      "learning_rate": 0.00019611193739015,
      "loss": 0.7846,
      "step": 1575
    },
    {
      "epoch": 0.3546885391265795,
      "grad_norm": 0.08384064584970474,
      "learning_rate": 0.0001959450055622806,
      "loss": 0.7416,
      "step": 1600
    },
    {
      "epoch": 0.36023054755043227,
      "grad_norm": 0.08661937713623047,
      "learning_rate": 0.0001957746391842066,
      "loss": 0.8075,
      "step": 1625
    },
    {
      "epoch": 0.3657725559742851,
      "grad_norm": 0.09327207505702972,
      "learning_rate": 0.00019560084435454536,
      "loss": 0.7596,
      "step": 1650
    },
    {
      "epoch": 0.37131456439813787,
      "grad_norm": 0.08391096442937851,
      "learning_rate": 0.00019542362729464273,
      "loss": 0.7794,
      "step": 1675
    },
    {
      "epoch": 0.3768565728219907,
      "grad_norm": 0.07694080471992493,
      "learning_rate": 0.00019524299434835052,
      "loss": 0.7424,
      "step": 1700
    },
    {
      "epoch": 0.38239858124584347,
      "grad_norm": 0.08567491173744202,
      "learning_rate": 0.00019505895198179912,
      "loss": 0.7996,
      "step": 1725
    },
    {
      "epoch": 0.3879405896696963,
      "grad_norm": 0.08828684687614441,
      "learning_rate": 0.0001948715067831663,
      "loss": 0.7394,
      "step": 1750
    },
    {
      "epoch": 0.39348259809354913,
      "grad_norm": 0.08347714692354202,
      "learning_rate": 0.00019468066546244117,
      "loss": 0.7734,
      "step": 1775
    },
    {
      "epoch": 0.3990246065174019,
      "grad_norm": 0.07736373692750931,
      "learning_rate": 0.00019448643485118412,
      "loss": 0.7134,
      "step": 1800
    },
    {
      "epoch": 0.40456661494125473,
      "grad_norm": 0.0840897262096405,
      "learning_rate": 0.00019428882190228216,
      "loss": 0.787,
      "step": 1825
    },
    {
      "epoch": 0.4101086233651075,
      "grad_norm": 0.08665871620178223,
      "learning_rate": 0.0001940878336897001,
      "loss": 0.7151,
      "step": 1850
    },
    {
      "epoch": 0.41565063178896033,
      "grad_norm": 0.08358912914991379,
      "learning_rate": 0.0001938834774082274,
      "loss": 0.7982,
      "step": 1875
    },
    {
      "epoch": 0.4211926402128131,
      "grad_norm": 0.07928963005542755,
      "learning_rate": 0.0001936757603732203,
      "loss": 0.7195,
      "step": 1900
    },
    {
      "epoch": 0.42673464863666594,
      "grad_norm": 0.08886470645666122,
      "learning_rate": 0.00019346469002034042,
      "loss": 0.7762,
      "step": 1925
    },
    {
      "epoch": 0.4322766570605187,
      "grad_norm": 0.1071886494755745,
      "learning_rate": 0.00019325027390528822,
      "loss": 0.7453,
      "step": 1950
    },
    {
      "epoch": 0.43781866548437154,
      "grad_norm": 0.08474262803792953,
      "learning_rate": 0.00019303251970353261,
      "loss": 0.7839,
      "step": 1975
    },
    {
      "epoch": 0.44336067390822437,
      "grad_norm": 0.08803894370794296,
      "learning_rate": 0.0001928114352100363,
      "loss": 0.7171,
      "step": 2000
    },
    {
      "epoch": 0.44890268233207714,
      "grad_norm": 0.08429575711488724,
      "learning_rate": 0.00019258702833897665,
      "loss": 0.7781,
      "step": 2025
    },
    {
      "epoch": 0.45444469075592997,
      "grad_norm": 0.08510231226682663,
      "learning_rate": 0.00019235930712346248,
      "loss": 0.6949,
      "step": 2050
    },
    {
      "epoch": 0.45998669917978274,
      "grad_norm": 0.08167176693677902,
      "learning_rate": 0.00019212827971524634,
      "loss": 0.7722,
      "step": 2075
    },
    {
      "epoch": 0.46552870760363557,
      "grad_norm": 0.06542418897151947,
      "learning_rate": 0.00019189395438443278,
      "loss": 0.7203,
      "step": 2100
    },
    {
      "epoch": 0.47107071602748835,
      "grad_norm": 0.08293402194976807,
      "learning_rate": 0.00019165633951918247,
      "loss": 0.7735,
      "step": 2125
    },
    {
      "epoch": 0.4766127244513412,
      "grad_norm": 0.0809284895658493,
      "learning_rate": 0.00019141544362541162,
      "loss": 0.7412,
      "step": 2150
    },
    {
      "epoch": 0.48215473287519395,
      "grad_norm": 0.08212891221046448,
      "learning_rate": 0.00019117127532648773,
      "loss": 0.7629,
      "step": 2175
    },
    {
      "epoch": 0.4876967412990468,
      "grad_norm": 0.08602219074964523,
      "learning_rate": 0.0001909238433629208,
      "loss": 0.6935,
      "step": 2200
    },
    {
      "epoch": 0.4932387497228996,
      "grad_norm": 0.08529417216777802,
      "learning_rate": 0.0001906731565920505,
      "loss": 0.7915,
      "step": 2225
    },
    {
      "epoch": 0.4987807581467524,
      "grad_norm": 0.08774964511394501,
      "learning_rate": 0.00019041922398772897,
      "loss": 0.7359,
      "step": 2250
    },
    {
      "epoch": 0.5043227665706052,
      "grad_norm": 0.08649475872516632,
      "learning_rate": 0.00019016205463999984,
      "loss": 0.7696,
      "step": 2275
    },
    {
      "epoch": 0.509864774994458,
      "grad_norm": 0.0878506749868393,
      "learning_rate": 0.00018990165775477252,
      "loss": 0.7365,
      "step": 2300
    },
    {
      "epoch": 0.5154067834183108,
      "grad_norm": 0.09131711721420288,
      "learning_rate": 0.0001896380426534929,
      "loss": 0.7809,
      "step": 2325
    },
    {
      "epoch": 0.5209487918421636,
      "grad_norm": 0.07379825413227081,
      "learning_rate": 0.00018937121877280957,
      "loss": 0.7029,
      "step": 2350
    },
    {
      "epoch": 0.5264908002660164,
      "grad_norm": 0.08535836637020111,
      "learning_rate": 0.00018910119566423598,
      "loss": 0.7679,
      "step": 2375
    },
    {
      "epoch": 0.5320328086898692,
      "grad_norm": 0.06719771772623062,
      "learning_rate": 0.00018882798299380864,
      "loss": 0.7121,
      "step": 2400
    },
    {
      "epoch": 0.537574817113722,
      "grad_norm": 0.09019796550273895,
      "learning_rate": 0.00018855159054174093,
      "loss": 0.7754,
      "step": 2425
    },
    {
      "epoch": 0.5431168255375748,
      "grad_norm": 0.08144286274909973,
      "learning_rate": 0.0001882720282020732,
      "loss": 0.7255,
      "step": 2450
    },
    {
      "epoch": 0.5486588339614277,
      "grad_norm": 0.08412271738052368,
      "learning_rate": 0.0001879893059823185,
      "loss": 0.7722,
      "step": 2475
    },
    {
      "epoch": 0.5542008423852804,
      "grad_norm": 0.09016039222478867,
      "learning_rate": 0.0001877034340031042,
      "loss": 0.7275,
      "step": 2500
    },
    {
      "epoch": 0.5597428508091332,
      "grad_norm": 0.08850298821926117,
      "learning_rate": 0.00018741442249781,
      "loss": 0.7828,
      "step": 2525
    },
    {
      "epoch": 0.565284859232986,
      "grad_norm": 0.06989564746618271,
      "learning_rate": 0.00018712228181220128,
      "loss": 0.7111,
      "step": 2550
    },
    {
      "epoch": 0.5708268676568389,
      "grad_norm": 0.09214618802070618,
      "learning_rate": 0.00018682702240405906,
      "loss": 0.7752,
      "step": 2575
    },
    {
      "epoch": 0.5763688760806917,
      "grad_norm": 0.07766986638307571,
      "learning_rate": 0.0001865286548428054,
      "loss": 0.7108,
      "step": 2600
    },
    {
      "epoch": 0.5819108845045444,
      "grad_norm": 0.07919591665267944,
      "learning_rate": 0.00018622718980912514,
      "loss": 0.775,
      "step": 2625
    },
    {
      "epoch": 0.5874528929283972,
      "grad_norm": 0.07524783164262772,
      "learning_rate": 0.00018592263809458361,
      "loss": 0.6941,
      "step": 2650
    },
    {
      "epoch": 0.5929949013522501,
      "grad_norm": 0.08549198508262634,
      "learning_rate": 0.00018561501060124024,
      "loss": 0.7718,
      "step": 2675
    },
    {
      "epoch": 0.5985369097761029,
      "grad_norm": 0.08182788640260696,
      "learning_rate": 0.0001853043183412584,
      "loss": 0.7072,
      "step": 2700
    },
    {
      "epoch": 0.6040789181999556,
      "grad_norm": 0.084741972386837,
      "learning_rate": 0.00018499057243651096,
      "loss": 0.7478,
      "step": 2725
    },
    {
      "epoch": 0.6096209266238085,
      "grad_norm": 0.06824459880590439,
      "learning_rate": 0.0001846737841181825,
      "loss": 0.7238,
      "step": 2750
    },
    {
      "epoch": 0.6151629350476613,
      "grad_norm": 0.08315033465623856,
      "learning_rate": 0.00018435396472636704,
      "loss": 0.7597,
      "step": 2775
    },
    {
      "epoch": 0.6207049434715141,
      "grad_norm": 0.07116558402776718,
      "learning_rate": 0.00018403112570966216,
      "loss": 0.7096,
      "step": 2800
    },
    {
      "epoch": 0.6262469518953668,
      "grad_norm": 0.08500215411186218,
      "learning_rate": 0.00018370527862475916,
      "loss": 0.756,
      "step": 2825
    },
    {
      "epoch": 0.6317889603192197,
      "grad_norm": 0.07979004830121994,
      "learning_rate": 0.00018337643513602933,
      "loss": 0.6886,
      "step": 2850
    },
    {
      "epoch": 0.6373309687430725,
      "grad_norm": 0.08140358328819275,
      "learning_rate": 0.00018304460701510652,
      "loss": 0.7648,
      "step": 2875
    },
    {
      "epoch": 0.6428729771669253,
      "grad_norm": 0.07779423147439957,
      "learning_rate": 0.0001827098061404656,
      "loss": 0.7222,
      "step": 2900
    },
    {
      "epoch": 0.6484149855907781,
      "grad_norm": 0.08853591978549957,
      "learning_rate": 0.0001823720444969974,
      "loss": 0.7736,
      "step": 2925
    },
    {
      "epoch": 0.6539569940146309,
      "grad_norm": 0.07350102066993713,
      "learning_rate": 0.0001820313341755795,
      "loss": 0.7256,
      "step": 2950
    },
    {
      "epoch": 0.6594990024384837,
      "grad_norm": 0.08152145147323608,
      "learning_rate": 0.0001816876873726436,
      "loss": 0.7598,
      "step": 2975
    },
    {
      "epoch": 0.6650410108623365,
      "grad_norm": 0.08045897632837296,
      "learning_rate": 0.00018134111638973876,
      "loss": 0.7275,
      "step": 3000
    },
    {
      "epoch": 0.6705830192861894,
      "grad_norm": 0.08514434099197388,
      "learning_rate": 0.00018099163363309123,
      "loss": 0.7688,
      "step": 3025
    },
    {
      "epoch": 0.6761250277100421,
      "grad_norm": 0.060850344598293304,
      "learning_rate": 0.00018063925161316012,
      "loss": 0.7019,
      "step": 3050
    },
    {
      "epoch": 0.6816670361338949,
      "grad_norm": 0.08471492677927017,
      "learning_rate": 0.00018028398294418977,
      "loss": 0.7573,
      "step": 3075
    },
    {
      "epoch": 0.6872090445577477,
      "grad_norm": 0.0642291009426117,
      "learning_rate": 0.00017992584034375798,
      "loss": 0.7108,
      "step": 3100
    },
    {
      "epoch": 0.6927510529816006,
      "grad_norm": 0.09357668459415436,
      "learning_rate": 0.000179564836632321,
      "loss": 0.7478,
      "step": 3125
    },
    {
      "epoch": 0.6982930614054533,
      "grad_norm": 0.07198700308799744,
      "learning_rate": 0.00017920098473275445,
      "loss": 0.6973,
      "step": 3150
    },
    {
      "epoch": 0.7038350698293061,
      "grad_norm": 0.08420095592737198,
      "learning_rate": 0.00017883429766989064,
      "loss": 0.7487,
      "step": 3175
    },
    {
      "epoch": 0.709377078253159,
      "grad_norm": 0.06639819592237473,
      "learning_rate": 0.00017846478857005255,
      "loss": 0.6741,
      "step": 3200
    },
    {
      "epoch": 0.7149190866770118,
      "grad_norm": 0.08200914412736893,
      "learning_rate": 0.00017809247066058378,
      "loss": 0.7526,
      "step": 3225
    },
    {
      "epoch": 0.7204610951008645,
      "grad_norm": 0.07311141490936279,
      "learning_rate": 0.0001777173572693751,
      "loss": 0.677,
      "step": 3250
    },
    {
      "epoch": 0.7260031035247173,
      "grad_norm": 0.08722089231014252,
      "learning_rate": 0.00017733946182438726,
      "loss": 0.7585,
      "step": 3275
    },
    {
      "epoch": 0.7315451119485702,
      "grad_norm": 0.06589449942111969,
      "learning_rate": 0.00017695879785317048,
      "loss": 0.708,
      "step": 3300
    },
    {
      "epoch": 0.737087120372423,
      "grad_norm": 0.08262074738740921,
      "learning_rate": 0.0001765753789823801,
      "loss": 0.749,
      "step": 3325
    },
    {
      "epoch": 0.7426291287962757,
      "grad_norm": 0.07514823973178864,
      "learning_rate": 0.00017618921893728867,
      "loss": 0.6918,
      "step": 3350
    },
    {
      "epoch": 0.7481711372201286,
      "grad_norm": 0.08757175505161285,
      "learning_rate": 0.00017580033154129503,
      "loss": 0.7445,
      "step": 3375
    },
    {
      "epoch": 0.7537131456439814,
      "grad_norm": 0.0716458335518837,
      "learning_rate": 0.0001754087307154289,
      "loss": 0.7122,
      "step": 3400
    },
    {
      "epoch": 0.7592551540678342,
      "grad_norm": 0.08453212678432465,
      "learning_rate": 0.00017501443047785296,
      "loss": 0.7656,
      "step": 3425
    },
    {
      "epoch": 0.7647971624916869,
      "grad_norm": 0.06761575490236282,
      "learning_rate": 0.00017461744494336098,
      "loss": 0.6673,
      "step": 3450
    },
    {
      "epoch": 0.7703391709155398,
      "grad_norm": 0.08577297627925873,
      "learning_rate": 0.0001742177883228724,
      "loss": 0.7494,
      "step": 3475
    },
    {
      "epoch": 0.7758811793393926,
      "grad_norm": 0.05691730976104736,
      "learning_rate": 0.00017381547492292376,
      "loss": 0.6972,
      "step": 3500
    },
    {
      "epoch": 0.7814231877632454,
      "grad_norm": 0.09115194529294968,
      "learning_rate": 0.00017341051914515656,
      "loss": 0.7706,
      "step": 3525
    },
    {
      "epoch": 0.7869651961870983,
      "grad_norm": 0.07214304804801941,
      "learning_rate": 0.00017300293548580162,
      "loss": 0.6807,
      "step": 3550
    },
    {
      "epoch": 0.792507204610951,
      "grad_norm": 0.08448139578104019,
      "learning_rate": 0.00017259273853516028,
      "loss": 0.7661,
      "step": 3575
    },
    {
      "epoch": 0.7980492130348038,
      "grad_norm": 0.08282499015331268,
      "learning_rate": 0.00017217994297708195,
      "loss": 0.7391,
      "step": 3600
    },
    {
      "epoch": 0.8035912214586566,
      "grad_norm": 0.0804004818201065,
      "learning_rate": 0.00017176456358843875,
      "loss": 0.7402,
      "step": 3625
    },
    {
      "epoch": 0.8091332298825095,
      "grad_norm": 0.07265755534172058,
      "learning_rate": 0.00017134661523859622,
      "loss": 0.7019,
      "step": 3650
    },
    {
      "epoch": 0.8146752383063622,
      "grad_norm": 0.08803457766771317,
      "learning_rate": 0.00017092611288888125,
      "loss": 0.7572,
      "step": 3675
    },
    {
      "epoch": 0.820217246730215,
      "grad_norm": 0.0652441680431366,
      "learning_rate": 0.0001705030715920464,
      "loss": 0.706,
      "step": 3700
    },
    {
      "epoch": 0.8257592551540678,
      "grad_norm": 0.08185753971338272,
      "learning_rate": 0.0001700775064917312,
      "loss": 0.764,
      "step": 3725
    },
    {
      "epoch": 0.8313012635779207,
      "grad_norm": 0.0859500914812088,
      "learning_rate": 0.00016964943282191984,
      "loss": 0.6927,
      "step": 3750
    },
    {
      "epoch": 0.8368432720017734,
      "grad_norm": 0.09176376461982727,
      "learning_rate": 0.00016921886590639602,
      "loss": 0.7567,
      "step": 3775
    },
    {
      "epoch": 0.8423852804256262,
      "grad_norm": 0.0646485984325409,
      "learning_rate": 0.0001687858211581943,
      "loss": 0.6848,
      "step": 3800
    },
    {
      "epoch": 0.8479272888494791,
      "grad_norm": 0.08545655012130737,
      "learning_rate": 0.00016835031407904839,
      "loss": 0.7546,
      "step": 3825
    },
    {
      "epoch": 0.8534692972733319,
      "grad_norm": 0.06338818371295929,
      "learning_rate": 0.00016791236025883626,
      "loss": 0.6655,
      "step": 3850
    },
    {
      "epoch": 0.8590113056971846,
      "grad_norm": 0.08781229704618454,
      "learning_rate": 0.00016747197537502205,
      "loss": 0.7441,
      "step": 3875
    },
    {
      "epoch": 0.8645533141210374,
      "grad_norm": 0.06220358610153198,
      "learning_rate": 0.00016702917519209487,
      "loss": 0.6795,
      "step": 3900
    },
    {
      "epoch": 0.8700953225448903,
      "grad_norm": 0.08917712420225143,
      "learning_rate": 0.0001665839755610044,
      "loss": 0.7552,
      "step": 3925
    },
    {
      "epoch": 0.8756373309687431,
      "grad_norm": 0.06624036282300949,
      "learning_rate": 0.00016613639241859355,
      "loss": 0.6632,
      "step": 3950
    },
    {
      "epoch": 0.8811793393925959,
      "grad_norm": 0.08898719400167465,
      "learning_rate": 0.00016568644178702803,
      "loss": 0.757,
      "step": 3975
    },
    {
      "epoch": 0.8867213478164487,
      "grad_norm": 0.05095354840159416,
      "learning_rate": 0.0001652341397732227,
      "loss": 0.6992,
      "step": 4000
    },
    {
      "epoch": 0.8922633562403015,
      "grad_norm": 0.08842916786670685,
      "learning_rate": 0.0001647795025682649,
      "loss": 0.7504,
      "step": 4025
    },
    {
      "epoch": 0.8978053646641543,
      "grad_norm": 0.0758206844329834,
      "learning_rate": 0.00016432254644683516,
      "loss": 0.7081,
      "step": 4050
    },
    {
      "epoch": 0.903347373088007,
      "grad_norm": 0.0940496176481247,
      "learning_rate": 0.0001638632877666243,
      "loss": 0.746,
      "step": 4075
    },
    {
      "epoch": 0.9088893815118599,
      "grad_norm": 0.06626766920089722,
      "learning_rate": 0.00016340174296774804,
      "loss": 0.6647,
      "step": 4100
    },
    {
      "epoch": 0.9144313899357127,
      "grad_norm": 0.08919317275285721,
      "learning_rate": 0.00016293792857215844,
      "loss": 0.7516,
      "step": 4125
    },
    {
      "epoch": 0.9199733983595655,
      "grad_norm": 0.06990760564804077,
      "learning_rate": 0.00016247186118305252,
      "loss": 0.7011,
      "step": 4150
    },
    {
      "epoch": 0.9255154067834183,
      "grad_norm": 0.0870794802904129,
      "learning_rate": 0.00016200355748427782,
      "loss": 0.7529,
      "step": 4175
    },
    {
      "epoch": 0.9310574152072711,
      "grad_norm": 0.06882854551076889,
      "learning_rate": 0.00016153303423973526,
      "loss": 0.7005,
      "step": 4200
    },
    {
      "epoch": 0.9365994236311239,
      "grad_norm": 0.084992416203022,
      "learning_rate": 0.0001610603082927789,
      "loss": 0.7519,
      "step": 4225
    },
    {
      "epoch": 0.9421414320549767,
      "grad_norm": 0.0638299211859703,
      "learning_rate": 0.00016058539656561323,
      "loss": 0.716,
      "step": 4250
    },
    {
      "epoch": 0.9476834404788296,
      "grad_norm": 0.08899606764316559,
      "learning_rate": 0.00016010831605868715,
      "loss": 0.7257,
      "step": 4275
    },
    {
      "epoch": 0.9532254489026823,
      "grad_norm": 0.06550378352403641,
      "learning_rate": 0.00015962908385008565,
      "loss": 0.7174,
      "step": 4300
    },
    {
      "epoch": 0.9587674573265351,
      "grad_norm": 0.09001540392637253,
      "learning_rate": 0.00015914771709491828,
      "loss": 0.7271,
      "step": 4325
    },
    {
      "epoch": 0.9643094657503879,
      "grad_norm": 0.06641615182161331,
      "learning_rate": 0.000158664233024705,
      "loss": 0.69,
      "step": 4350
    },
    {
      "epoch": 0.9698514741742408,
      "grad_norm": 0.08917039632797241,
      "learning_rate": 0.0001581786489467596,
      "loss": 0.7483,
      "step": 4375
    },
    {
      "epoch": 0.9753934825980936,
      "grad_norm": 0.05995697155594826,
      "learning_rate": 0.00015769098224356992,
      "loss": 0.7033,
      "step": 4400
    },
    {
      "epoch": 0.9809354910219463,
      "grad_norm": 0.08998765051364899,
      "learning_rate": 0.00015720125037217572,
      "loss": 0.7462,
      "step": 4425
    },
    {
      "epoch": 0.9864774994457992,
      "grad_norm": 0.05868702754378319,
      "learning_rate": 0.00015670947086354376,
      "loss": 0.6654,
      "step": 4450
    },
    {
      "epoch": 0.992019507869652,
      "grad_norm": 0.0880926102399826,
      "learning_rate": 0.00015621566132194005,
      "loss": 0.752,
      "step": 4475
    },
    {
      "epoch": 0.9975615162935048,
      "grad_norm": 0.08538970351219177,
      "learning_rate": 0.00015571983942430005,
      "loss": 0.7338,
      "step": 4500
    },
    {
      "epoch": 1.0031035247173576,
      "grad_norm": 0.0827050730586052,
      "learning_rate": 0.0001552220229195956,
      "loss": 0.7174,
      "step": 4525
    },
    {
      "epoch": 1.0086455331412103,
      "grad_norm": 0.10867294669151306,
      "learning_rate": 0.00015472222962819955,
      "loss": 0.7637,
      "step": 4550
    },
    {
      "epoch": 1.0141875415650632,
      "grad_norm": 0.08738269656896591,
      "learning_rate": 0.00015422047744124802,
      "loss": 0.6247,
      "step": 4575
    },
    {
      "epoch": 1.019729549988916,
      "grad_norm": 0.12865987420082092,
      "learning_rate": 0.0001537167843199998,
      "loss": 0.7424,
      "step": 4600
    },
    {
      "epoch": 1.0252715584127687,
      "grad_norm": 0.08619695156812668,
      "learning_rate": 0.00015321116829519345,
      "loss": 0.6461,
      "step": 4625
    },
    {
      "epoch": 1.0308135668366216,
      "grad_norm": 0.11726492643356323,
      "learning_rate": 0.0001527036474664019,
      "loss": 0.7433,
      "step": 4650
    },
    {
      "epoch": 1.0363555752604743,
      "grad_norm": 0.08198727667331696,
      "learning_rate": 0.0001521942400013844,
      "loss": 0.6086,
      "step": 4675
    },
    {
      "epoch": 1.0418975836843272,
      "grad_norm": 0.11951526254415512,
      "learning_rate": 0.00015168296413543635,
      "loss": 0.7521,
      "step": 4700
    },
    {
      "epoch": 1.04743959210818,
      "grad_norm": 0.08714735507965088,
      "learning_rate": 0.0001511698381707363,
      "loss": 0.631,
      "step": 4725
    },
    {
      "epoch": 1.0529816005320327,
      "grad_norm": 0.13869455456733704,
      "learning_rate": 0.00015065488047569107,
      "loss": 0.7524,
      "step": 4750
    },
    {
      "epoch": 1.0585236089558856,
      "grad_norm": 0.08524268865585327,
      "learning_rate": 0.00015013810948427794,
      "loss": 0.6617,
      "step": 4775
    },
    {
      "epoch": 1.0640656173797385,
      "grad_norm": 0.11017199605703354,
      "learning_rate": 0.00014961954369538494,
      "loss": 0.7598,
      "step": 4800
    },
    {
      "epoch": 1.0696076258035911,
      "grad_norm": 0.0834374874830246,
      "learning_rate": 0.00014909920167214858,
      "loss": 0.627,
      "step": 4825
    },
    {
      "epoch": 1.075149634227444,
      "grad_norm": 0.1357167363166809,
      "learning_rate": 0.0001485771020412894,
      "loss": 0.7466,
      "step": 4850
    },
    {
      "epoch": 1.080691642651297,
      "grad_norm": 0.08910629153251648,
      "learning_rate": 0.00014805326349244503,
      "loss": 0.6238,
      "step": 4875
    },
    {
      "epoch": 1.0862336510751496,
      "grad_norm": 0.10706546157598495,
      "learning_rate": 0.00014752770477750144,
      "loss": 0.7533,
      "step": 4900
    },
    {
      "epoch": 1.0917756594990025,
      "grad_norm": 0.09201759845018387,
      "learning_rate": 0.00014700044470992136,
      "loss": 0.6521,
      "step": 4925
    },
    {
      "epoch": 1.0973176679228553,
      "grad_norm": 0.14048361778259277,
      "learning_rate": 0.00014647150216407106,
      "loss": 0.7412,
      "step": 4950
    },
    {
      "epoch": 1.102859676346708,
      "grad_norm": 0.08308299630880356,
      "learning_rate": 0.00014594089607454454,
      "loss": 0.6333,
      "step": 4975
    },
    {
      "epoch": 1.108401684770561,
      "grad_norm": 0.12057497352361679,
      "learning_rate": 0.00014540864543548582,
      "loss": 0.7538,
      "step": 5000
    }
  ],
  "logging_steps": 25,
  "max_steps": 13533,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4028324505774285e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}