{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9961549837326236,
  "eval_steps": 500,
  "global_step": 1266,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023661638568470866,
      "grad_norm": 5.716220186648855,
      "learning_rate": 5e-06,
      "loss": 0.8897,
      "step": 10
    },
    {
      "epoch": 0.04732327713694173,
      "grad_norm": 0.8490804690852378,
      "learning_rate": 5e-06,
      "loss": 0.7877,
      "step": 20
    },
    {
      "epoch": 0.0709849157054126,
      "grad_norm": 0.8359497191663584,
      "learning_rate": 5e-06,
      "loss": 0.7533,
      "step": 30
    },
    {
      "epoch": 0.09464655427388347,
      "grad_norm": 2.872573622069312,
      "learning_rate": 5e-06,
      "loss": 0.7354,
      "step": 40
    },
    {
      "epoch": 0.11830819284235433,
      "grad_norm": 1.2235372630281218,
      "learning_rate": 5e-06,
      "loss": 0.726,
      "step": 50
    },
    {
      "epoch": 0.1419698314108252,
      "grad_norm": 0.7914495021160732,
      "learning_rate": 5e-06,
      "loss": 0.7152,
      "step": 60
    },
    {
      "epoch": 0.16563146997929606,
      "grad_norm": 0.6440056541571992,
      "learning_rate": 5e-06,
      "loss": 0.7101,
      "step": 70
    },
    {
      "epoch": 0.18929310854776693,
      "grad_norm": 1.2255311186058144,
      "learning_rate": 5e-06,
      "loss": 0.7007,
      "step": 80
    },
    {
      "epoch": 0.2129547471162378,
      "grad_norm": 0.5863287056241707,
      "learning_rate": 5e-06,
      "loss": 0.6856,
      "step": 90
    },
    {
      "epoch": 0.23661638568470866,
      "grad_norm": 0.6673942726540693,
      "learning_rate": 5e-06,
      "loss": 0.685,
      "step": 100
    },
    {
      "epoch": 0.26027802425317953,
      "grad_norm": 0.6052355221282993,
      "learning_rate": 5e-06,
      "loss": 0.6898,
      "step": 110
    },
    {
      "epoch": 0.2839396628216504,
      "grad_norm": 0.6230907972132269,
      "learning_rate": 5e-06,
      "loss": 0.6772,
      "step": 120
    },
    {
      "epoch": 0.30760130139012126,
      "grad_norm": 0.5418727176057381,
      "learning_rate": 5e-06,
      "loss": 0.6733,
      "step": 130
    },
    {
      "epoch": 0.33126293995859213,
      "grad_norm": 0.6020619371732497,
      "learning_rate": 5e-06,
      "loss": 0.6819,
      "step": 140
    },
    {
      "epoch": 0.354924578527063,
      "grad_norm": 0.8518067973190109,
      "learning_rate": 5e-06,
      "loss": 0.6648,
      "step": 150
    },
    {
      "epoch": 0.37858621709553386,
      "grad_norm": 0.5115922350127938,
      "learning_rate": 5e-06,
      "loss": 0.6691,
      "step": 160
    },
    {
      "epoch": 0.4022478556640047,
      "grad_norm": 0.7022530591693269,
      "learning_rate": 5e-06,
      "loss": 0.667,
      "step": 170
    },
    {
      "epoch": 0.4259094942324756,
      "grad_norm": 0.5834704070363212,
      "learning_rate": 5e-06,
      "loss": 0.6739,
      "step": 180
    },
    {
      "epoch": 0.44957113280094646,
      "grad_norm": 0.4653603355749383,
      "learning_rate": 5e-06,
      "loss": 0.6698,
      "step": 190
    },
    {
      "epoch": 0.4732327713694173,
      "grad_norm": 0.568232089382732,
      "learning_rate": 5e-06,
      "loss": 0.6688,
      "step": 200
    },
    {
      "epoch": 0.4968944099378882,
      "grad_norm": 1.0573970656294764,
      "learning_rate": 5e-06,
      "loss": 0.6697,
      "step": 210
    },
    {
      "epoch": 0.5205560485063591,
      "grad_norm": 0.7158198022991291,
      "learning_rate": 5e-06,
      "loss": 0.6681,
      "step": 220
    },
    {
      "epoch": 0.54421768707483,
      "grad_norm": 0.43788884341448125,
      "learning_rate": 5e-06,
      "loss": 0.6603,
      "step": 230
    },
    {
      "epoch": 0.5678793256433008,
      "grad_norm": 0.4725698050393869,
      "learning_rate": 5e-06,
      "loss": 0.6645,
      "step": 240
    },
    {
      "epoch": 0.5915409642117717,
      "grad_norm": 0.6197309721248793,
      "learning_rate": 5e-06,
      "loss": 0.6616,
      "step": 250
    },
    {
      "epoch": 0.6152026027802425,
      "grad_norm": 0.5419735846310992,
      "learning_rate": 5e-06,
      "loss": 0.652,
      "step": 260
    },
    {
      "epoch": 0.6388642413487134,
      "grad_norm": 0.7492458117282386,
      "learning_rate": 5e-06,
      "loss": 0.6641,
      "step": 270
    },
    {
      "epoch": 0.6625258799171843,
      "grad_norm": 0.6330397603875498,
      "learning_rate": 5e-06,
      "loss": 0.6652,
      "step": 280
    },
    {
      "epoch": 0.6861875184856552,
      "grad_norm": 0.5065865148226276,
      "learning_rate": 5e-06,
      "loss": 0.6597,
      "step": 290
    },
    {
      "epoch": 0.709849157054126,
      "grad_norm": 0.6357867453691719,
      "learning_rate": 5e-06,
      "loss": 0.6535,
      "step": 300
    },
    {
      "epoch": 0.7335107956225969,
      "grad_norm": 0.5149227689012754,
      "learning_rate": 5e-06,
      "loss": 0.6619,
      "step": 310
    },
    {
      "epoch": 0.7571724341910677,
      "grad_norm": 0.44037598215405893,
      "learning_rate": 5e-06,
      "loss": 0.6556,
      "step": 320
    },
    {
      "epoch": 0.7808340727595386,
      "grad_norm": 0.5181894268105267,
      "learning_rate": 5e-06,
      "loss": 0.6541,
      "step": 330
    },
    {
      "epoch": 0.8044957113280095,
      "grad_norm": 0.6098945421576618,
      "learning_rate": 5e-06,
      "loss": 0.6538,
      "step": 340
    },
    {
      "epoch": 0.8281573498964804,
      "grad_norm": 0.5384169075272255,
      "learning_rate": 5e-06,
      "loss": 0.6602,
      "step": 350
    },
    {
      "epoch": 0.8518189884649512,
      "grad_norm": 0.47214684121487954,
      "learning_rate": 5e-06,
      "loss": 0.6538,
      "step": 360
    },
    {
      "epoch": 0.8754806270334221,
      "grad_norm": 0.4904597024034496,
      "learning_rate": 5e-06,
      "loss": 0.6567,
      "step": 370
    },
    {
      "epoch": 0.8991422656018929,
      "grad_norm": 0.4775889282770322,
      "learning_rate": 5e-06,
      "loss": 0.6478,
      "step": 380
    },
    {
      "epoch": 0.9228039041703638,
      "grad_norm": 0.6785347844213175,
      "learning_rate": 5e-06,
      "loss": 0.6553,
      "step": 390
    },
    {
      "epoch": 0.9464655427388347,
      "grad_norm": 0.48131943447081366,
      "learning_rate": 5e-06,
      "loss": 0.6466,
      "step": 400
    },
    {
      "epoch": 0.9701271813073056,
      "grad_norm": 0.4819882000845211,
      "learning_rate": 5e-06,
      "loss": 0.6491,
      "step": 410
    },
    {
      "epoch": 0.9937888198757764,
      "grad_norm": 0.48326887732044893,
      "learning_rate": 5e-06,
      "loss": 0.648,
      "step": 420
    },
    {
      "epoch": 0.9985211475894705,
      "eval_loss": 0.6503860950469971,
      "eval_runtime": 295.5868,
      "eval_samples_per_second": 38.53,
      "eval_steps_per_second": 0.602,
      "step": 422
    },
    {
      "epoch": 1.0177462289263532,
      "grad_norm": 0.5034024020075702,
      "learning_rate": 5e-06,
      "loss": 0.6519,
      "step": 430
    },
    {
      "epoch": 1.041407867494824,
      "grad_norm": 0.5181852823487637,
      "learning_rate": 5e-06,
      "loss": 0.6054,
      "step": 440
    },
    {
      "epoch": 1.0650695060632949,
      "grad_norm": 0.8086692425168592,
      "learning_rate": 5e-06,
      "loss": 0.6036,
      "step": 450
    },
    {
      "epoch": 1.0887311446317658,
      "grad_norm": 0.7087824451639375,
      "learning_rate": 5e-06,
      "loss": 0.6138,
      "step": 460
    },
    {
      "epoch": 1.1123927832002367,
      "grad_norm": 0.6293561803711789,
      "learning_rate": 5e-06,
      "loss": 0.611,
      "step": 470
    },
    {
      "epoch": 1.1360544217687074,
      "grad_norm": 0.8003707364488958,
      "learning_rate": 5e-06,
      "loss": 0.6114,
      "step": 480
    },
    {
      "epoch": 1.1597160603371783,
      "grad_norm": 0.5556436203083284,
      "learning_rate": 5e-06,
      "loss": 0.6083,
      "step": 490
    },
    {
      "epoch": 1.1833776989056493,
      "grad_norm": 0.5222890058260059,
      "learning_rate": 5e-06,
      "loss": 0.6038,
      "step": 500
    },
    {
      "epoch": 1.2070393374741202,
      "grad_norm": 0.5834395725334883,
      "learning_rate": 5e-06,
      "loss": 0.6038,
      "step": 510
    },
    {
      "epoch": 1.2307009760425909,
      "grad_norm": 0.6523486232667094,
      "learning_rate": 5e-06,
      "loss": 0.6103,
      "step": 520
    },
    {
      "epoch": 1.2543626146110618,
      "grad_norm": 0.509097134236641,
      "learning_rate": 5e-06,
      "loss": 0.6129,
      "step": 530
    },
    {
      "epoch": 1.2780242531795327,
      "grad_norm": 0.6109585275321274,
      "learning_rate": 5e-06,
      "loss": 0.6125,
      "step": 540
    },
    {
      "epoch": 1.3016858917480034,
      "grad_norm": 0.4671830560905703,
      "learning_rate": 5e-06,
      "loss": 0.6094,
      "step": 550
    },
    {
      "epoch": 1.3253475303164743,
      "grad_norm": 0.43619649641699987,
      "learning_rate": 5e-06,
      "loss": 0.6076,
      "step": 560
    },
    {
      "epoch": 1.3490091688849453,
      "grad_norm": 0.9334517894855655,
      "learning_rate": 5e-06,
      "loss": 0.6086,
      "step": 570
    },
    {
      "epoch": 1.3726708074534162,
      "grad_norm": 0.6158441071105143,
      "learning_rate": 5e-06,
      "loss": 0.6114,
      "step": 580
    },
    {
      "epoch": 1.396332446021887,
      "grad_norm": 0.4177935072924951,
      "learning_rate": 5e-06,
      "loss": 0.6118,
      "step": 590
    },
    {
      "epoch": 1.4199940845903578,
      "grad_norm": 0.5261498840709943,
      "learning_rate": 5e-06,
      "loss": 0.6012,
      "step": 600
    },
    {
      "epoch": 1.4436557231588287,
      "grad_norm": 0.4118403315344034,
      "learning_rate": 5e-06,
      "loss": 0.6006,
      "step": 610
    },
    {
      "epoch": 1.4673173617272997,
      "grad_norm": 0.4500509679639768,
      "learning_rate": 5e-06,
      "loss": 0.6041,
      "step": 620
    },
    {
      "epoch": 1.4909790002957704,
      "grad_norm": 0.47480411557819086,
      "learning_rate": 5e-06,
      "loss": 0.6161,
      "step": 630
    },
    {
      "epoch": 1.5146406388642415,
      "grad_norm": 0.44192140481751196,
      "learning_rate": 5e-06,
      "loss": 0.6104,
      "step": 640
    },
    {
      "epoch": 1.5383022774327122,
      "grad_norm": 0.43019141037435493,
      "learning_rate": 5e-06,
      "loss": 0.6044,
      "step": 650
    },
    {
      "epoch": 1.5619639160011831,
      "grad_norm": 0.5928638480003088,
      "learning_rate": 5e-06,
      "loss": 0.6093,
      "step": 660
    },
    {
      "epoch": 1.585625554569654,
      "grad_norm": 0.680185794067505,
      "learning_rate": 5e-06,
      "loss": 0.6018,
      "step": 670
    },
    {
      "epoch": 1.6092871931381247,
      "grad_norm": 0.4446498601791125,
      "learning_rate": 5e-06,
      "loss": 0.6103,
      "step": 680
    },
    {
      "epoch": 1.6329488317065957,
      "grad_norm": 0.5328567150499224,
      "learning_rate": 5e-06,
      "loss": 0.6013,
      "step": 690
    },
    {
      "epoch": 1.6566104702750666,
      "grad_norm": 0.5840475503667699,
      "learning_rate": 5e-06,
      "loss": 0.6109,
      "step": 700
    },
    {
      "epoch": 1.6802721088435373,
      "grad_norm": 0.5235562677113405,
      "learning_rate": 5e-06,
      "loss": 0.6094,
      "step": 710
    },
    {
      "epoch": 1.7039337474120084,
      "grad_norm": 0.6484686160336842,
      "learning_rate": 5e-06,
      "loss": 0.6122,
      "step": 720
    },
    {
      "epoch": 1.7275953859804791,
      "grad_norm": 0.5923644814057659,
      "learning_rate": 5e-06,
      "loss": 0.612,
      "step": 730
    },
    {
      "epoch": 1.75125702454895,
      "grad_norm": 0.4896255525659027,
      "learning_rate": 5e-06,
      "loss": 0.6042,
      "step": 740
    },
    {
      "epoch": 1.774918663117421,
      "grad_norm": 0.47313474988505516,
      "learning_rate": 5e-06,
      "loss": 0.6105,
      "step": 750
    },
    {
      "epoch": 1.7985803016858917,
      "grad_norm": 0.4971344193994014,
      "learning_rate": 5e-06,
      "loss": 0.6146,
      "step": 760
    },
    {
      "epoch": 1.8222419402543626,
      "grad_norm": 0.42650481882946567,
      "learning_rate": 5e-06,
      "loss": 0.6161,
      "step": 770
    },
    {
      "epoch": 1.8459035788228335,
      "grad_norm": 0.45409425789151847,
      "learning_rate": 5e-06,
      "loss": 0.607,
      "step": 780
    },
    {
      "epoch": 1.8695652173913042,
      "grad_norm": 0.47548804917566284,
      "learning_rate": 5e-06,
      "loss": 0.6057,
      "step": 790
    },
    {
      "epoch": 1.8932268559597754,
      "grad_norm": 0.49936009431407224,
      "learning_rate": 5e-06,
      "loss": 0.614,
      "step": 800
    },
    {
      "epoch": 1.916888494528246,
      "grad_norm": 0.42095008482708873,
      "learning_rate": 5e-06,
      "loss": 0.6118,
      "step": 810
    },
    {
      "epoch": 1.940550133096717,
      "grad_norm": 0.469345021146904,
      "learning_rate": 5e-06,
      "loss": 0.6,
      "step": 820
    },
    {
      "epoch": 1.964211771665188,
      "grad_norm": 0.4821117072104332,
      "learning_rate": 5e-06,
      "loss": 0.6112,
      "step": 830
    },
    {
      "epoch": 1.9878734102336586,
      "grad_norm": 0.42444873739826294,
      "learning_rate": 5e-06,
      "loss": 0.5984,
      "step": 840
    },
    {
      "epoch": 1.999704229517894,
      "eval_loss": 0.640017032623291,
      "eval_runtime": 291.0784,
      "eval_samples_per_second": 39.127,
      "eval_steps_per_second": 0.612,
      "step": 845
    },
    {
      "epoch": 2.0118308192842353,
      "grad_norm": 0.743615658405185,
      "learning_rate": 5e-06,
      "loss": 0.612,
      "step": 850
    },
    {
      "epoch": 2.0354924578527065,
      "grad_norm": 0.6307060227030052,
      "learning_rate": 5e-06,
      "loss": 0.5665,
      "step": 860
    },
    {
      "epoch": 2.059154096421177,
      "grad_norm": 0.4909469687109977,
      "learning_rate": 5e-06,
      "loss": 0.5669,
      "step": 870
    },
    {
      "epoch": 2.082815734989648,
      "grad_norm": 0.4982651206960173,
      "learning_rate": 5e-06,
      "loss": 0.5576,
      "step": 880
    },
    {
      "epoch": 2.106477373558119,
      "grad_norm": 0.5189496162921208,
      "learning_rate": 5e-06,
      "loss": 0.5632,
      "step": 890
    },
    {
      "epoch": 2.1301390121265897,
      "grad_norm": 0.5290452662480181,
      "learning_rate": 5e-06,
      "loss": 0.5673,
      "step": 900
    },
    {
      "epoch": 2.1538006506950604,
      "grad_norm": 0.4298930748962063,
      "learning_rate": 5e-06,
      "loss": 0.5608,
      "step": 910
    },
    {
      "epoch": 2.1774622892635316,
      "grad_norm": 0.46653862184558975,
      "learning_rate": 5e-06,
      "loss": 0.5622,
      "step": 920
    },
    {
      "epoch": 2.2011239278320023,
      "grad_norm": 0.47565404277144174,
      "learning_rate": 5e-06,
      "loss": 0.5634,
      "step": 930
    },
    {
      "epoch": 2.2247855664004734,
      "grad_norm": 0.45977306537518353,
      "learning_rate": 5e-06,
      "loss": 0.5642,
      "step": 940
    },
    {
      "epoch": 2.248447204968944,
      "grad_norm": 0.6195624778560548,
      "learning_rate": 5e-06,
      "loss": 0.5701,
      "step": 950
    },
    {
      "epoch": 2.272108843537415,
      "grad_norm": 0.5625286018926492,
      "learning_rate": 5e-06,
      "loss": 0.5624,
      "step": 960
    },
    {
      "epoch": 2.295770482105886,
      "grad_norm": 0.5516894450156284,
      "learning_rate": 5e-06,
      "loss": 0.5688,
      "step": 970
    },
    {
      "epoch": 2.3194321206743567,
      "grad_norm": 0.46703213745702465,
      "learning_rate": 5e-06,
      "loss": 0.5687,
      "step": 980
    },
    {
      "epoch": 2.3430937592428274,
      "grad_norm": 0.4529577298482224,
      "learning_rate": 5e-06,
      "loss": 0.5664,
      "step": 990
    },
    {
      "epoch": 2.3667553978112985,
      "grad_norm": 0.5294804903105876,
      "learning_rate": 5e-06,
      "loss": 0.5679,
      "step": 1000
    },
    {
      "epoch": 2.390417036379769,
      "grad_norm": 0.476104510415757,
      "learning_rate": 5e-06,
      "loss": 0.5661,
      "step": 1010
    },
    {
      "epoch": 2.4140786749482404,
      "grad_norm": 0.50214160643677,
      "learning_rate": 5e-06,
      "loss": 0.5632,
      "step": 1020
    },
    {
      "epoch": 2.437740313516711,
      "grad_norm": 0.4770392958453329,
      "learning_rate": 5e-06,
      "loss": 0.5646,
      "step": 1030
    },
    {
      "epoch": 2.4614019520851818,
      "grad_norm": 0.4746961197857643,
      "learning_rate": 5e-06,
      "loss": 0.5663,
      "step": 1040
    },
    {
      "epoch": 2.485063590653653,
      "grad_norm": 0.5075465690483602,
      "learning_rate": 5e-06,
      "loss": 0.5705,
      "step": 1050
    },
    {
      "epoch": 2.5087252292221236,
      "grad_norm": 0.5735236324477879,
      "learning_rate": 5e-06,
      "loss": 0.5692,
      "step": 1060
    },
    {
      "epoch": 2.5323868677905947,
      "grad_norm": 0.7357338280472365,
      "learning_rate": 5e-06,
      "loss": 0.5693,
      "step": 1070
    },
    {
      "epoch": 2.5560485063590654,
      "grad_norm": 0.6312728091303266,
      "learning_rate": 5e-06,
      "loss": 0.5721,
      "step": 1080
    },
    {
      "epoch": 2.579710144927536,
      "grad_norm": 0.6063258814160167,
      "learning_rate": 5e-06,
      "loss": 0.5668,
      "step": 1090
    },
    {
      "epoch": 2.603371783496007,
      "grad_norm": 0.512061567286246,
      "learning_rate": 5e-06,
      "loss": 0.5706,
      "step": 1100
    },
    {
      "epoch": 2.627033422064478,
      "grad_norm": 0.4805538505321553,
      "learning_rate": 5e-06,
      "loss": 0.5643,
      "step": 1110
    },
    {
      "epoch": 2.6506950606329487,
      "grad_norm": 0.47434096978031415,
      "learning_rate": 5e-06,
      "loss": 0.5784,
      "step": 1120
    },
    {
      "epoch": 2.67435669920142,
      "grad_norm": 0.48174002692295587,
      "learning_rate": 5e-06,
      "loss": 0.5642,
      "step": 1130
    },
    {
      "epoch": 2.6980183377698905,
      "grad_norm": 0.5206174302871078,
      "learning_rate": 5e-06,
      "loss": 0.5647,
      "step": 1140
    },
    {
      "epoch": 2.7216799763383612,
      "grad_norm": 0.5231066430924299,
      "learning_rate": 5e-06,
      "loss": 0.5717,
      "step": 1150
    },
    {
      "epoch": 2.7453416149068324,
      "grad_norm": 0.5493755325406757,
      "learning_rate": 5e-06,
      "loss": 0.5722,
      "step": 1160
    },
    {
      "epoch": 2.769003253475303,
      "grad_norm": 0.4710457798970187,
      "learning_rate": 5e-06,
      "loss": 0.5673,
      "step": 1170
    },
    {
      "epoch": 2.792664892043774,
      "grad_norm": 0.6017685441197285,
      "learning_rate": 5e-06,
      "loss": 0.5673,
      "step": 1180
    },
    {
      "epoch": 2.816326530612245,
      "grad_norm": 0.48667322523587175,
      "learning_rate": 5e-06,
      "loss": 0.5712,
      "step": 1190
    },
    {
      "epoch": 2.8399881691807156,
      "grad_norm": 0.6136328812041214,
      "learning_rate": 5e-06,
      "loss": 0.5689,
      "step": 1200
    },
    {
      "epoch": 2.8636498077491868,
      "grad_norm": 0.4848336832061156,
      "learning_rate": 5e-06,
      "loss": 0.5683,
      "step": 1210
    },
    {
      "epoch": 2.8873114463176575,
      "grad_norm": 0.6143451558754445,
      "learning_rate": 5e-06,
      "loss": 0.5611,
      "step": 1220
    },
    {
      "epoch": 2.9109730848861286,
      "grad_norm": 0.45186971294615735,
      "learning_rate": 5e-06,
      "loss": 0.5713,
      "step": 1230
    },
    {
      "epoch": 2.9346347234545993,
      "grad_norm": 0.45118967147278705,
      "learning_rate": 5e-06,
      "loss": 0.5703,
      "step": 1240
    },
    {
      "epoch": 2.95829636202307,
      "grad_norm": 0.5082137766462498,
      "learning_rate": 5e-06,
      "loss": 0.5791,
      "step": 1250
    },
    {
      "epoch": 2.9819580005915407,
      "grad_norm": 0.5446211548606755,
      "learning_rate": 5e-06,
      "loss": 0.5714,
      "step": 1260
    },
    {
      "epoch": 2.9961549837326236,
      "eval_loss": 0.6407967805862427,
      "eval_runtime": 281.5097,
      "eval_samples_per_second": 40.457,
      "eval_steps_per_second": 0.632,
      "step": 1266
    },
    {
      "epoch": 2.9961549837326236,
      "step": 1266,
      "total_flos": 2120387773071360.0,
      "train_loss": 0.6192890667425701,
      "train_runtime": 41807.2835,
      "train_samples_per_second": 15.526,
      "train_steps_per_second": 0.03
    }
  ],
  "logging_steps": 10,
  "max_steps": 1266,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2120387773071360.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}