{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 300,
  "global_step": 2241,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013391362571141614,
      "grad_norm": 1.1251516342163086,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.1230167388916015,
      "step": 10
    },
    {
      "epoch": 0.026782725142283227,
      "grad_norm": 1.4087316989898682,
      "learning_rate": 4.222222222222223e-06,
      "loss": 2.060458946228027,
      "step": 20
    },
    {
      "epoch": 0.040174087713424844,
      "grad_norm": 1.6200941801071167,
      "learning_rate": 6.4444444444444445e-06,
      "loss": 2.076141929626465,
      "step": 30
    },
    {
      "epoch": 0.053565450284566454,
      "grad_norm": 1.388713002204895,
      "learning_rate": 8.666666666666668e-06,
      "loss": 2.0496809005737306,
      "step": 40
    },
    {
      "epoch": 0.06695681285570806,
      "grad_norm": 1.3109877109527588,
      "learning_rate": 1.088888888888889e-05,
      "loss": 2.1139976501464846,
      "step": 50
    },
    {
      "epoch": 0.08034817542684969,
      "grad_norm": 0.8334707617759705,
      "learning_rate": 1.3111111111111113e-05,
      "loss": 1.8950347900390625,
      "step": 60
    },
    {
      "epoch": 0.0937395379979913,
      "grad_norm": 0.8505852222442627,
      "learning_rate": 1.5333333333333334e-05,
      "loss": 1.795738410949707,
      "step": 70
    },
    {
      "epoch": 0.10713090056913291,
      "grad_norm": 0.9232431650161743,
      "learning_rate": 1.7555555555555556e-05,
      "loss": 1.710242462158203,
      "step": 80
    },
    {
      "epoch": 0.12052226314027452,
      "grad_norm": 0.8113048076629639,
      "learning_rate": 1.9777777777777778e-05,
      "loss": 1.7132640838623048,
      "step": 90
    },
    {
      "epoch": 0.13391362571141613,
      "grad_norm": 0.8083556294441223,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.690536880493164,
      "step": 100
    },
    {
      "epoch": 0.14730498828255775,
      "grad_norm": 0.673184335231781,
      "learning_rate": 2.4222222222222224e-05,
      "loss": 1.5726326942443847,
      "step": 110
    },
    {
      "epoch": 0.16069635085369938,
      "grad_norm": 0.963398814201355,
      "learning_rate": 2.6444444444444443e-05,
      "loss": 1.3888358116149901,
      "step": 120
    },
    {
      "epoch": 0.17408771342484097,
      "grad_norm": 0.6759088635444641,
      "learning_rate": 2.8666666666666668e-05,
      "loss": 1.3290005683898927,
      "step": 130
    },
    {
      "epoch": 0.1874790759959826,
      "grad_norm": 0.844614565372467,
      "learning_rate": 3.088888888888889e-05,
      "loss": 1.2599190711975097,
      "step": 140
    },
    {
      "epoch": 0.2008704385671242,
      "grad_norm": 0.6923516988754272,
      "learning_rate": 3.311111111111112e-05,
      "loss": 1.2773826599121094,
      "step": 150
    },
    {
      "epoch": 0.21426180113826582,
      "grad_norm": 0.7745124101638794,
      "learning_rate": 3.5333333333333336e-05,
      "loss": 1.2277652740478515,
      "step": 160
    },
    {
      "epoch": 0.22765316370940744,
      "grad_norm": 1.0810950994491577,
      "learning_rate": 3.7555555555555554e-05,
      "loss": 1.2010490417480468,
      "step": 170
    },
    {
      "epoch": 0.24104452628054904,
      "grad_norm": 0.7222780585289001,
      "learning_rate": 3.977777777777778e-05,
      "loss": 1.1438576698303222,
      "step": 180
    },
    {
      "epoch": 0.25443588885169066,
      "grad_norm": 0.9007810950279236,
      "learning_rate": 4.2e-05,
      "loss": 1.1083187103271483,
      "step": 190
    },
    {
      "epoch": 0.26782725142283226,
      "grad_norm": 0.7866023182868958,
      "learning_rate": 4.422222222222222e-05,
      "loss": 1.0768976211547852,
      "step": 200
    },
    {
      "epoch": 0.2812186139939739,
      "grad_norm": 0.8120918273925781,
      "learning_rate": 4.644444444444445e-05,
      "loss": 1.1097023963928223,
      "step": 210
    },
    {
      "epoch": 0.2946099765651155,
      "grad_norm": 0.9135192036628723,
      "learning_rate": 4.866666666666667e-05,
      "loss": 1.119042205810547,
      "step": 220
    },
    {
      "epoch": 0.3080013391362571,
      "grad_norm": 0.8874865770339966,
      "learning_rate": 4.9999514323288454e-05,
      "loss": 0.980173397064209,
      "step": 230
    },
    {
      "epoch": 0.32139270170739875,
      "grad_norm": 0.8983038067817688,
      "learning_rate": 4.999405067699773e-05,
      "loss": 0.970307731628418,
      "step": 240
    },
    {
      "epoch": 0.33478406427854035,
      "grad_norm": 0.9653483033180237,
      "learning_rate": 4.998251761970997e-05,
      "loss": 1.032784652709961,
      "step": 250
    },
    {
      "epoch": 0.34817542684968195,
      "grad_norm": 1.141289472579956,
      "learning_rate": 4.996491795204623e-05,
      "loss": 0.9785713195800781,
      "step": 260
    },
    {
      "epoch": 0.36156678942082354,
      "grad_norm": 1.0336418151855469,
      "learning_rate": 4.9941255947808224e-05,
      "loss": 0.9411398887634277,
      "step": 270
    },
    {
      "epoch": 0.3749581519919652,
      "grad_norm": 0.9689179062843323,
      "learning_rate": 4.991153735294049e-05,
      "loss": 1.0034279823303223,
      "step": 280
    },
    {
      "epoch": 0.3883495145631068,
      "grad_norm": 0.8199458718299866,
      "learning_rate": 4.987576938413504e-05,
      "loss": 0.9443310737609864,
      "step": 290
    },
    {
      "epoch": 0.4017408771342484,
      "grad_norm": 1.082461953163147,
      "learning_rate": 4.9833960727078975e-05,
      "loss": 0.9262508392333985,
      "step": 300
    },
    {
      "epoch": 0.4017408771342484,
      "eval_loss": 1.022187352180481,
      "eval_runtime": 54.3223,
      "eval_samples_per_second": 12.223,
      "eval_steps_per_second": 12.223,
      "step": 300
    },
    {
      "epoch": 0.41513223970539004,
      "grad_norm": 1.213780164718628,
      "learning_rate": 4.9786121534345265e-05,
      "loss": 0.9448966979980469,
      "step": 310
    },
    {
      "epoch": 0.42852360227653163,
      "grad_norm": 1.0836976766586304,
      "learning_rate": 4.9732263422927315e-05,
      "loss": 1.0215834617614745,
      "step": 320
    },
    {
      "epoch": 0.44191496484767323,
      "grad_norm": 0.8629345893859863,
      "learning_rate": 4.967239947141803e-05,
      "loss": 0.9825343132019043,
      "step": 330
    },
    {
      "epoch": 0.4553063274188149,
      "grad_norm": 1.254758596420288,
      "learning_rate": 4.960654421683386e-05,
      "loss": 0.8087763786315918,
      "step": 340
    },
    {
      "epoch": 0.4686976899899565,
      "grad_norm": 1.1041864156723022,
      "learning_rate": 4.9534713651084696e-05,
      "loss": 0.8968398094177246,
      "step": 350
    },
    {
      "epoch": 0.4820890525610981,
      "grad_norm": 1.221664309501648,
      "learning_rate": 4.94569252170905e-05,
      "loss": 0.9529605865478515,
      "step": 360
    },
    {
      "epoch": 0.4954804151322397,
      "grad_norm": 1.0954457521438599,
      "learning_rate": 4.937319780454559e-05,
      "loss": 0.9047369003295899,
      "step": 370
    },
    {
      "epoch": 0.5088717777033813,
      "grad_norm": 1.3573025465011597,
      "learning_rate": 4.9283551745331534e-05,
      "loss": 0.9805423736572265,
      "step": 380
    },
    {
      "epoch": 0.5222631402745229,
      "grad_norm": 1.2266513109207153,
      "learning_rate": 4.9188008808579914e-05,
      "loss": 0.9189679145812988,
      "step": 390
    },
    {
      "epoch": 0.5356545028456645,
      "grad_norm": 1.1925843954086304,
      "learning_rate": 4.9086592195385974e-05,
      "loss": 0.8736061096191406,
      "step": 400
    },
    {
      "epoch": 0.5490458654168061,
      "grad_norm": 0.9948152899742126,
      "learning_rate": 4.89793265331747e-05,
      "loss": 0.8509424209594727,
      "step": 410
    },
    {
      "epoch": 0.5624372279879478,
      "grad_norm": 1.0283681154251099,
      "learning_rate": 4.886623786972033e-05,
      "loss": 0.8601439476013184,
      "step": 420
    },
    {
      "epoch": 0.5758285905590894,
      "grad_norm": 0.9124083518981934,
      "learning_rate": 4.874735366682115e-05,
      "loss": 0.8764433860778809,
      "step": 430
    },
    {
      "epoch": 0.589219953130231,
      "grad_norm": 1.104988932609558,
      "learning_rate": 4.8622702793630756e-05,
      "loss": 0.8691943168640137,
      "step": 440
    },
    {
      "epoch": 0.6026113157013726,
      "grad_norm": 1.0378754138946533,
      "learning_rate": 4.849231551964771e-05,
      "loss": 0.8470947265625,
      "step": 450
    },
    {
      "epoch": 0.6160026782725142,
      "grad_norm": 0.9452361464500427,
      "learning_rate": 4.8356223507364996e-05,
      "loss": 0.872993278503418,
      "step": 460
    },
    {
      "epoch": 0.6293940408436558,
      "grad_norm": 1.0585964918136597,
      "learning_rate": 4.821445980458134e-05,
      "loss": 0.8613449096679687,
      "step": 470
    },
    {
      "epoch": 0.6427854034147975,
      "grad_norm": 0.962693989276886,
      "learning_rate": 4.8067058836376044e-05,
      "loss": 0.8473030090332031,
      "step": 480
    },
    {
      "epoch": 0.6561767659859391,
      "grad_norm": 1.213151216506958,
      "learning_rate": 4.791405639674941e-05,
      "loss": 0.8945110321044922,
      "step": 490
    },
    {
      "epoch": 0.6695681285570807,
      "grad_norm": 1.098382592201233,
      "learning_rate": 4.775548963993072e-05,
      "loss": 0.8379823684692382,
      "step": 500
    },
    {
      "epoch": 0.6829594911282223,
      "grad_norm": 1.2232801914215088,
      "learning_rate": 4.759139707135592e-05,
      "loss": 0.8914398193359375,
      "step": 510
    },
    {
      "epoch": 0.6963508536993639,
      "grad_norm": 1.1614588499069214,
      "learning_rate": 4.742181853831721e-05,
      "loss": 0.7714352130889892,
      "step": 520
    },
    {
      "epoch": 0.7097422162705055,
      "grad_norm": 1.0375906229019165,
      "learning_rate": 4.724679522028672e-05,
      "loss": 0.8399144172668457,
      "step": 530
    },
    {
      "epoch": 0.7231335788416471,
      "grad_norm": 1.6367172002792358,
      "learning_rate": 4.706636961891673e-05,
      "loss": 0.8434115409851074,
      "step": 540
    },
    {
      "epoch": 0.7365249414127888,
      "grad_norm": 1.4899160861968994,
      "learning_rate": 4.6880585547718845e-05,
      "loss": 0.8600223541259766,
      "step": 550
    },
    {
      "epoch": 0.7499163039839304,
      "grad_norm": 1.3136088848114014,
      "learning_rate": 4.668948812142453e-05,
      "loss": 0.8417681694030762,
      "step": 560
    },
    {
      "epoch": 0.763307666555072,
      "grad_norm": 1.5014512538909912,
      "learning_rate": 4.649312374502976e-05,
      "loss": 0.8598422050476074,
      "step": 570
    },
    {
      "epoch": 0.7766990291262136,
      "grad_norm": 1.1034916639328003,
      "learning_rate": 4.6291540102526235e-05,
      "loss": 0.82028169631958,
      "step": 580
    },
    {
      "epoch": 0.7900903916973552,
      "grad_norm": 1.0077992677688599,
      "learning_rate": 4.608478614532215e-05,
      "loss": 0.8477327346801757,
      "step": 590
    },
    {
      "epoch": 0.8034817542684968,
      "grad_norm": 1.4599281549453735,
      "learning_rate": 4.587291208035503e-05,
      "loss": 0.7847702503204346,
      "step": 600
    },
    {
      "epoch": 0.8034817542684968,
      "eval_loss": 0.8773947954177856,
      "eval_runtime": 54.0516,
      "eval_samples_per_second": 12.285,
      "eval_steps_per_second": 12.285,
      "step": 600
    },
    {
      "epoch": 0.8168731168396385,
      "grad_norm": 1.3578146696090698,
      "learning_rate": 4.5655969357899874e-05,
      "loss": 0.8327409744262695,
      "step": 610
    },
    {
      "epoch": 0.8302644794107801,
      "grad_norm": 1.1919622421264648,
      "learning_rate": 4.543401065907516e-05,
      "loss": 0.8041424751281738,
      "step": 620
    },
    {
      "epoch": 0.8436558419819217,
      "grad_norm": 1.1500847339630127,
      "learning_rate": 4.5207089883050136e-05,
      "loss": 0.7486717224121093,
      "step": 630
    },
    {
      "epoch": 0.8570472045530633,
      "grad_norm": 1.1832966804504395,
      "learning_rate": 4.497526213395623e-05,
      "loss": 0.8147689819335937,
      "step": 640
    },
    {
      "epoch": 0.8704385671242049,
      "grad_norm": 1.350236415863037,
      "learning_rate": 4.4738583707505885e-05,
      "loss": 0.7860679626464844,
      "step": 650
    },
    {
      "epoch": 0.8838299296953465,
      "grad_norm": 1.2207894325256348,
      "learning_rate": 4.4497112077322044e-05,
      "loss": 0.8117258071899414,
      "step": 660
    },
    {
      "epoch": 0.8972212922664882,
      "grad_norm": 1.0513477325439453,
      "learning_rate": 4.4250905880981574e-05,
      "loss": 0.7919021129608155,
      "step": 670
    },
    {
      "epoch": 0.9106126548376298,
      "grad_norm": 1.3217025995254517,
      "learning_rate": 4.400002490577604e-05,
      "loss": 0.8166803359985352,
      "step": 680
    },
    {
      "epoch": 0.9240040174087714,
      "grad_norm": 1.1715842485427856,
      "learning_rate": 4.374453007419336e-05,
      "loss": 0.7445796012878418,
      "step": 690
    },
    {
      "epoch": 0.937395379979913,
      "grad_norm": 1.4749701023101807,
      "learning_rate": 4.3484483429123656e-05,
      "loss": 0.866641616821289,
      "step": 700
    },
    {
      "epoch": 0.9507867425510546,
      "grad_norm": 1.17747962474823,
      "learning_rate": 4.3219948118793214e-05,
      "loss": 0.7444936275482178,
      "step": 710
    },
    {
      "epoch": 0.9641781051221961,
      "grad_norm": 1.2830913066864014,
      "learning_rate": 4.295098838142985e-05,
      "loss": 0.8117733955383301,
      "step": 720
    },
    {
      "epoch": 0.9775694676933377,
      "grad_norm": 1.336511492729187,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.7992856979370118,
      "step": 730
    },
    {
      "epoch": 0.9909608302644795,
      "grad_norm": 1.4292641878128052,
      "learning_rate": 4.240005793466709e-05,
      "loss": 0.7759786605834961,
      "step": 740
    },
    {
      "epoch": 1.0040174087713425,
      "grad_norm": 1.2945338487625122,
      "learning_rate": 4.211822101003734e-05,
      "loss": 0.8514230728149415,
      "step": 750
    },
    {
      "epoch": 1.0174087713424842,
      "grad_norm": 1.1430498361587524,
      "learning_rate": 4.183222719542643e-05,
      "loss": 0.7180036544799805,
      "step": 760
    },
    {
      "epoch": 1.0308001339136257,
      "grad_norm": 1.380825400352478,
      "learning_rate": 4.154214593992149e-05,
      "loss": 0.7814423084259033,
      "step": 770
    },
    {
      "epoch": 1.0441914964847674,
      "grad_norm": 1.2941365242004395,
      "learning_rate": 4.1248047685180215e-05,
      "loss": 0.7181880950927735,
      "step": 780
    },
    {
      "epoch": 1.0575828590559089,
      "grad_norm": 1.4261479377746582,
      "learning_rate": 4.095000384832522e-05,
      "loss": 0.7421597480773926,
      "step": 790
    },
    {
      "epoch": 1.0709742216270506,
      "grad_norm": 1.4144198894500732,
      "learning_rate": 4.064808680460148e-05,
      "loss": 0.7506948947906494,
      "step": 800
    },
    {
      "epoch": 1.084365584198192,
      "grad_norm": 1.3969988822937012,
      "learning_rate": 4.034236986980119e-05,
      "loss": 0.7060422897338867,
      "step": 810
    },
    {
      "epoch": 1.0977569467693338,
      "grad_norm": 1.485485315322876,
      "learning_rate": 4.0032927282460146e-05,
      "loss": 0.7774518966674805,
      "step": 820
    },
    {
      "epoch": 1.1111483093404755,
      "grad_norm": 1.787782073020935,
      "learning_rate": 3.9719834185830116e-05,
      "loss": 0.8183602333068848,
      "step": 830
    },
    {
      "epoch": 1.124539671911617,
      "grad_norm": 1.1777045726776123,
      "learning_rate": 3.940316660963147e-05,
      "loss": 0.740683126449585,
      "step": 840
    },
    {
      "epoch": 1.1379310344827587,
      "grad_norm": 1.3298629522323608,
      "learning_rate": 3.908300145159055e-05,
      "loss": 0.7469647884368896,
      "step": 850
    },
    {
      "epoch": 1.1513223970539002,
      "grad_norm": 1.3478955030441284,
      "learning_rate": 3.875941645876631e-05,
      "loss": 0.7432316780090332,
      "step": 860
    },
    {
      "epoch": 1.1647137596250419,
      "grad_norm": 1.2774122953414917,
      "learning_rate": 3.84324902086706e-05,
      "loss": 0.7554194927215576,
      "step": 870
    },
    {
      "epoch": 1.1781051221961834,
      "grad_norm": 1.4324496984481812,
      "learning_rate": 3.810230209018694e-05,
      "loss": 0.7671016216278076,
      "step": 880
    },
    {
      "epoch": 1.191496484767325,
      "grad_norm": 1.7440871000289917,
      "learning_rate": 3.7768932284292146e-05,
      "loss": 0.7613705158233642,
      "step": 890
    },
    {
      "epoch": 1.2048878473384668,
      "grad_norm": 1.281699538230896,
      "learning_rate": 3.74324617445856e-05,
      "loss": 0.6879847049713135,
      "step": 900
    },
    {
      "epoch": 1.2048878473384668,
      "eval_loss": 0.8266693353652954,
      "eval_runtime": 53.6628,
      "eval_samples_per_second": 12.374,
      "eval_steps_per_second": 12.374,
      "step": 900
    },
    {
      "epoch": 1.2182792099096083,
      "grad_norm": 1.360567569732666,
      "learning_rate": 3.7092972177631e-05,
      "loss": 0.693269157409668,
      "step": 910
    },
    {
      "epoch": 1.23167057248075,
      "grad_norm": 1.8303319215774536,
      "learning_rate": 3.6750546023115216e-05,
      "loss": 0.7522525310516357,
      "step": 920
    },
    {
      "epoch": 1.2450619350518914,
      "grad_norm": 1.4251999855041504,
      "learning_rate": 3.6405266433829075e-05,
      "loss": 0.6977858066558837,
      "step": 930
    },
    {
      "epoch": 1.2584532976230332,
      "grad_norm": 1.5451791286468506,
      "learning_rate": 3.6057217255475034e-05,
      "loss": 0.7128232479095459,
      "step": 940
    },
    {
      "epoch": 1.2718446601941746,
      "grad_norm": 1.4011023044586182,
      "learning_rate": 3.570648300630657e-05,
      "loss": 0.7067931175231934,
      "step": 950
    },
    {
      "epoch": 1.2852360227653163,
      "grad_norm": 1.397749662399292,
      "learning_rate": 3.535314885660426e-05,
      "loss": 0.7212980270385743,
      "step": 960
    },
    {
      "epoch": 1.298627385336458,
      "grad_norm": 1.23228919506073,
      "learning_rate": 3.499730060799352e-05,
      "loss": 0.6783730506896972,
      "step": 970
    },
    {
      "epoch": 1.3120187479075995,
      "grad_norm": 1.3948746919631958,
      "learning_rate": 3.463902467260905e-05,
      "loss": 0.7117942333221435,
      "step": 980
    },
    {
      "epoch": 1.3254101104787412,
      "grad_norm": 1.3566443920135498,
      "learning_rate": 3.4278408052110946e-05,
      "loss": 0.7409574508666992,
      "step": 990
    },
    {
      "epoch": 1.338801473049883,
      "grad_norm": 1.3537638187408447,
      "learning_rate": 3.391553831655782e-05,
      "loss": 0.7592925548553466,
      "step": 1000
    },
    {
      "epoch": 1.3521928356210244,
      "grad_norm": 1.3646985292434692,
      "learning_rate": 3.355050358314172e-05,
      "loss": 0.7301356315612793,
      "step": 1010
    },
    {
      "epoch": 1.365584198192166,
      "grad_norm": 1.3367135524749756,
      "learning_rate": 3.318339249479026e-05,
      "loss": 0.7809906482696534,
      "step": 1020
    },
    {
      "epoch": 1.3789755607633076,
      "grad_norm": 1.567679524421692,
      "learning_rate": 3.281429419864112e-05,
      "loss": 0.6707557201385498,
      "step": 1030
    },
    {
      "epoch": 1.3923669233344493,
      "grad_norm": 1.8063384294509888,
      "learning_rate": 3.244329832439404e-05,
      "loss": 0.7046602725982666,
      "step": 1040
    },
    {
      "epoch": 1.4057582859055908,
      "grad_norm": 1.3105945587158203,
      "learning_rate": 3.207049496254569e-05,
      "loss": 0.758818244934082,
      "step": 1050
    },
    {
      "epoch": 1.4191496484767325,
      "grad_norm": 1.470205545425415,
      "learning_rate": 3.1695974642512585e-05,
      "loss": 0.7399599075317382,
      "step": 1060
    },
    {
      "epoch": 1.4325410110478742,
      "grad_norm": 1.3003753423690796,
      "learning_rate": 3.131982831064744e-05,
      "loss": 0.7131163120269776,
      "step": 1070
    },
    {
      "epoch": 1.4459323736190157,
      "grad_norm": 1.6275579929351807,
      "learning_rate": 3.094214730815433e-05,
      "loss": 0.6929296493530274,
      "step": 1080
    },
    {
      "epoch": 1.4593237361901574,
      "grad_norm": 1.5746970176696777,
      "learning_rate": 3.056302334890786e-05,
      "loss": 0.7268266677856445,
      "step": 1090
    },
    {
      "epoch": 1.472715098761299,
      "grad_norm": 2.2328906059265137,
      "learning_rate": 3.0182548497181946e-05,
      "loss": 0.6977500438690185,
      "step": 1100
    },
    {
      "epoch": 1.4861064613324406,
      "grad_norm": 1.3399721384048462,
      "learning_rate": 2.980081514529341e-05,
      "loss": 0.7302239894866943,
      "step": 1110
    },
    {
      "epoch": 1.499497823903582,
      "grad_norm": 1.4288753271102905,
      "learning_rate": 2.9417915991166008e-05,
      "loss": 0.7567366600036621,
      "step": 1120
    },
    {
      "epoch": 1.5128891864747238,
      "grad_norm": 1.75603449344635,
      "learning_rate": 2.903394401582017e-05,
      "loss": 0.7654183387756348,
      "step": 1130
    },
    {
      "epoch": 1.5262805490458655,
      "grad_norm": 1.3314752578735352,
      "learning_rate": 2.8648992460794056e-05,
      "loss": 0.7135534763336182,
      "step": 1140
    },
    {
      "epoch": 1.539671911617007,
      "grad_norm": 1.4941315650939941,
      "learning_rate": 2.8263154805501297e-05,
      "loss": 0.7175502300262451,
      "step": 1150
    },
    {
      "epoch": 1.5530632741881485,
      "grad_norm": 1.3964297771453857,
      "learning_rate": 2.787652474453097e-05,
      "loss": 0.6766695976257324,
      "step": 1160
    },
    {
      "epoch": 1.5664546367592904,
      "grad_norm": 1.5959055423736572,
      "learning_rate": 2.748919616489542e-05,
      "loss": 0.7289943218231201,
      "step": 1170
    },
    {
      "epoch": 1.579845999330432,
      "grad_norm": 1.670637607574463,
      "learning_rate": 2.710126312323119e-05,
      "loss": 0.7110982418060303,
      "step": 1180
    },
    {
      "epoch": 1.5932373619015734,
      "grad_norm": 1.6263046264648438,
      "learning_rate": 2.6712819822958917e-05,
      "loss": 0.6757009029388428,
      "step": 1190
    },
    {
      "epoch": 1.606628724472715,
      "grad_norm": 1.5645346641540527,
      "learning_rate": 2.632396059140749e-05,
      "loss": 0.6717938899993896,
      "step": 1200
    },
    {
      "epoch": 1.606628724472715,
      "eval_loss": 0.7993327975273132,
      "eval_runtime": 53.7389,
      "eval_samples_per_second": 12.356,
      "eval_steps_per_second": 12.356,
      "step": 1200
    },
    {
      "epoch": 1.6200200870438568,
      "grad_norm": 1.5552890300750732,
      "learning_rate": 2.593477985690815e-05,
      "loss": 0.7486276626586914,
      "step": 1210
    },
    {
      "epoch": 1.6334114496149983,
      "grad_norm": 1.6185609102249146,
      "learning_rate": 2.5545372125864032e-05,
      "loss": 0.6816000938415527,
      "step": 1220
    },
    {
      "epoch": 1.6468028121861398,
      "grad_norm": 1.3382222652435303,
      "learning_rate": 2.515583195980084e-05,
      "loss": 0.6346513271331787,
      "step": 1230
    },
    {
      "epoch": 1.6601941747572817,
      "grad_norm": 1.7194113731384277,
      "learning_rate": 2.4766253952404024e-05,
      "loss": 0.7409485340118408,
      "step": 1240
    },
    {
      "epoch": 1.6735855373284232,
      "grad_norm": 1.340211272239685,
      "learning_rate": 2.4376732706548183e-05,
      "loss": 0.7009283542633057,
      "step": 1250
    },
    {
      "epoch": 1.6869768998995647,
      "grad_norm": 1.3874890804290771,
      "learning_rate": 2.3987362811324298e-05,
      "loss": 0.6419552803039551,
      "step": 1260
    },
    {
      "epoch": 1.7003682624707064,
      "grad_norm": 1.1811823844909668,
      "learning_rate": 2.3598238819070202e-05,
      "loss": 0.7221670150756836,
      "step": 1270
    },
    {
      "epoch": 1.713759625041848,
      "grad_norm": 1.9249383211135864,
      "learning_rate": 2.3209455222410122e-05,
      "loss": 0.6979920864105225,
      "step": 1280
    },
    {
      "epoch": 1.7271509876129896,
      "grad_norm": 1.743878960609436,
      "learning_rate": 2.2821106431308544e-05,
      "loss": 0.7516108512878418,
      "step": 1290
    },
    {
      "epoch": 1.7405423501841313,
      "grad_norm": 1.7867244482040405,
      "learning_rate": 2.2433286750144293e-05,
      "loss": 0.6997213363647461,
      "step": 1300
    },
    {
      "epoch": 1.753933712755273,
      "grad_norm": 1.5474790334701538,
      "learning_rate": 2.204609035481018e-05,
      "loss": 0.7326123714447021,
      "step": 1310
    },
    {
      "epoch": 1.7673250753264145,
      "grad_norm": 1.6504864692687988,
      "learning_rate": 2.1659611269843906e-05,
      "loss": 0.7474339008331299,
      "step": 1320
    },
    {
      "epoch": 1.780716437897556,
      "grad_norm": 1.4319754838943481,
      "learning_rate": 2.1273943345595637e-05,
      "loss": 0.7082053661346436,
      "step": 1330
    },
    {
      "epoch": 1.7941078004686977,
      "grad_norm": 1.4845492839813232,
      "learning_rate": 2.0889180235437976e-05,
      "loss": 0.7185158252716064,
      "step": 1340
    },
    {
      "epoch": 1.8074991630398394,
      "grad_norm": 1.6886359453201294,
      "learning_rate": 2.0505415373023684e-05,
      "loss": 0.7255223274230957,
      "step": 1350
    },
    {
      "epoch": 1.8208905256109809,
      "grad_norm": 1.462658166885376,
      "learning_rate": 2.0122741949596797e-05,
      "loss": 0.678316307067871,
      "step": 1360
    },
    {
      "epoch": 1.8342818881821226,
      "grad_norm": 1.6203972101211548,
      "learning_rate": 1.9741252891362612e-05,
      "loss": 0.7009586334228516,
      "step": 1370
    },
    {
      "epoch": 1.8476732507532643,
      "grad_norm": 1.6375197172164917,
      "learning_rate": 1.936104083692202e-05,
      "loss": 0.711057710647583,
      "step": 1380
    },
    {
      "epoch": 1.8610646133244058,
      "grad_norm": 1.4735863208770752,
      "learning_rate": 1.8982198114775682e-05,
      "loss": 0.753815746307373,
      "step": 1390
    },
    {
      "epoch": 1.8744559758955472,
      "grad_norm": 1.4079184532165527,
      "learning_rate": 1.86048167209035e-05,
      "loss": 0.7394311428070068,
      "step": 1400
    },
    {
      "epoch": 1.887847338466689,
      "grad_norm": 1.1998661756515503,
      "learning_rate": 1.8228988296424877e-05,
      "loss": 0.6970119953155518,
      "step": 1410
    },
    {
      "epoch": 1.9012387010378307,
      "grad_norm": 1.4150874614715576,
      "learning_rate": 1.7854804105345062e-05,
      "loss": 0.7221133708953857,
      "step": 1420
    },
    {
      "epoch": 1.9146300636089721,
      "grad_norm": 1.9703272581100464,
      "learning_rate": 1.7482355012393177e-05,
      "loss": 0.6811443328857422,
      "step": 1430
    },
    {
      "epoch": 1.9280214261801139,
      "grad_norm": 1.3968387842178345,
      "learning_rate": 1.711173146095712e-05,
      "loss": 0.6836700439453125,
      "step": 1440
    },
    {
      "epoch": 1.9414127887512556,
      "grad_norm": 1.778705358505249,
      "learning_rate": 1.6743023451120832e-05,
      "loss": 0.729839277267456,
      "step": 1450
    },
    {
      "epoch": 1.954804151322397,
      "grad_norm": 1.753574252128601,
      "learning_rate": 1.637632051780917e-05,
      "loss": 0.7108103275299072,
      "step": 1460
    },
    {
      "epoch": 1.9681955138935385,
      "grad_norm": 1.5915656089782715,
      "learning_rate": 1.6011711709045813e-05,
      "loss": 0.6830355167388916,
      "step": 1470
    },
    {
      "epoch": 1.9815868764646802,
      "grad_norm": 1.4856032133102417,
      "learning_rate": 1.5649285564329296e-05,
      "loss": 0.6683127880096436,
      "step": 1480
    },
    {
      "epoch": 1.994978239035822,
      "grad_norm": 1.5113037824630737,
      "learning_rate": 1.5289130093132632e-05,
      "loss": 0.6894254684448242,
      "step": 1490
    },
    {
      "epoch": 2.008034817542685,
      "grad_norm": 1.2598875761032104,
      "learning_rate": 1.4931332753531574e-05,
      "loss": 0.7270267486572266,
      "step": 1500
    },
    {
      "epoch": 2.008034817542685,
      "eval_loss": 0.7799016833305359,
      "eval_runtime": 53.8556,
      "eval_samples_per_second": 12.329,
      "eval_steps_per_second": 12.329,
      "step": 1500
    },
    {
      "epoch": 2.0214261801138265,
      "grad_norm": 1.647517204284668,
      "learning_rate": 1.4575980430966807e-05,
      "loss": 0.6441567897796631,
      "step": 1510
    },
    {
      "epoch": 2.0348175426849684,
      "grad_norm": 1.5853488445281982,
      "learning_rate": 1.4223159417145179e-05,
      "loss": 0.6234518527984619,
      "step": 1520
    },
    {
      "epoch": 2.04820890525611,
      "grad_norm": 1.6781729459762573,
      "learning_rate": 1.387295538908519e-05,
      "loss": 0.6324089527130127,
      "step": 1530
    },
    {
      "epoch": 2.0616002678272514,
      "grad_norm": 1.4559346437454224,
      "learning_rate": 1.3525453388311554e-05,
      "loss": 0.7007440090179443,
      "step": 1540
    },
    {
      "epoch": 2.074991630398393,
      "grad_norm": 1.4268717765808105,
      "learning_rate": 1.318073780020433e-05,
      "loss": 0.6957920074462891,
      "step": 1550
    },
    {
      "epoch": 2.088382992969535,
      "grad_norm": 1.7965197563171387,
      "learning_rate": 1.2838892333507154e-05,
      "loss": 0.6843597888946533,
      "step": 1560
    },
    {
      "epoch": 2.1017743555406763,
      "grad_norm": 1.6434122323989868,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.641016960144043,
      "step": 1570
    },
    {
      "epoch": 2.1151657181118177,
      "grad_norm": 1.5839534997940063,
      "learning_rate": 1.2164143094340993e-05,
      "loss": 0.5900714874267579,
      "step": 1580
    },
    {
      "epoch": 2.1285570806829597,
      "grad_norm": 1.3161916732788086,
      "learning_rate": 1.183140317408248e-05,
      "loss": 0.6945799350738525,
      "step": 1590
    },
    {
      "epoch": 2.141948443254101,
      "grad_norm": 1.5822694301605225,
      "learning_rate": 1.1501861039866094e-05,
      "loss": 0.6906570434570313,
      "step": 1600
    },
    {
      "epoch": 2.1553398058252426,
      "grad_norm": 1.6532809734344482,
      "learning_rate": 1.1175596715801515e-05,
      "loss": 0.7173725128173828,
      "step": 1610
    },
    {
      "epoch": 2.168731168396384,
      "grad_norm": 1.806372046470642,
      "learning_rate": 1.0852689430033972e-05,
      "loss": 0.6307380676269532,
      "step": 1620
    },
    {
      "epoch": 2.182122530967526,
      "grad_norm": 1.7923976182937622,
      "learning_rate": 1.0533217595504858e-05,
      "loss": 0.65055832862854,
      "step": 1630
    },
    {
      "epoch": 2.1955138935386675,
      "grad_norm": 1.5243982076644897,
      "learning_rate": 1.0217258790910448e-05,
      "loss": 0.635548210144043,
      "step": 1640
    },
    {
      "epoch": 2.208905256109809,
      "grad_norm": 1.9043457508087158,
      "learning_rate": 9.90488974186306e-06,
      "loss": 0.6788571357727051,
      "step": 1650
    },
    {
      "epoch": 2.222296618680951,
      "grad_norm": 1.3352289199829102,
      "learning_rate": 9.596186302259563e-06,
      "loss": 0.6936195373535157,
      "step": 1660
    },
    {
      "epoch": 2.2356879812520924,
      "grad_norm": 1.5376029014587402,
      "learning_rate": 9.291223435861318e-06,
      "loss": 0.6575944900512696,
      "step": 1670
    },
    {
      "epoch": 2.249079343823234,
      "grad_norm": 1.5691180229187012,
      "learning_rate": 8.99007519809053e-06,
      "loss": 0.6259189128875733,
      "step": 1680
    },
    {
      "epoch": 2.2624707063943754,
      "grad_norm": 1.382432460784912,
      "learning_rate": 8.69281471804698e-06,
      "loss": 0.6597430229187011,
      "step": 1690
    },
    {
      "epoch": 2.2758620689655173,
      "grad_norm": 1.8340421915054321,
      "learning_rate": 8.399514180749795e-06,
      "loss": 0.6881356716156006,
      "step": 1700
    },
    {
      "epoch": 2.289253431536659,
      "grad_norm": 1.7811270952224731,
      "learning_rate": 8.110244809608495e-06,
      "loss": 0.6642444610595704,
      "step": 1710
    },
    {
      "epoch": 2.3026447941078003,
      "grad_norm": 1.4019266366958618,
      "learning_rate": 7.825076849127458e-06,
      "loss": 0.6552130222320557,
      "step": 1720
    },
    {
      "epoch": 2.3160361566789422,
      "grad_norm": 1.4278745651245117,
      "learning_rate": 7.5440795478481815e-06,
      "loss": 0.6528130054473877,
      "step": 1730
    },
    {
      "epoch": 2.3294275192500837,
      "grad_norm": 1.4227335453033447,
      "learning_rate": 7.26732114153334e-06,
      "loss": 0.6589642524719238,
      "step": 1740
    },
    {
      "epoch": 2.342818881821225,
      "grad_norm": 1.4000329971313477,
      "learning_rate": 6.99486883659684e-06,
      "loss": 0.677797269821167,
      "step": 1750
    },
    {
      "epoch": 2.3562102443923667,
      "grad_norm": 1.4296038150787354,
      "learning_rate": 6.72678879378377e-06,
      "loss": 0.6286413192749023,
      "step": 1760
    },
    {
      "epoch": 2.3696016069635086,
      "grad_norm": 1.8827868700027466,
      "learning_rate": 6.463146112104332e-06,
      "loss": 0.6587582111358643,
      "step": 1770
    },
    {
      "epoch": 2.38299296953465,
      "grad_norm": 1.996030569076538,
      "learning_rate": 6.204004813025568e-06,
      "loss": 0.6844182014465332,
      "step": 1780
    },
    {
      "epoch": 2.3963843321057916,
      "grad_norm": 1.7106478214263916,
      "learning_rate": 5.949427824924731e-06,
      "loss": 0.680266284942627,
      "step": 1790
    },
    {
      "epoch": 2.4097756946769335,
      "grad_norm": 1.4984078407287598,
      "learning_rate": 5.699476967808168e-06,
      "loss": 0.6131497859954834,
      "step": 1800
    },
    {
      "epoch": 2.4097756946769335,
      "eval_loss": 0.7755688428878784,
      "eval_runtime": 53.8672,
      "eval_samples_per_second": 12.327,
      "eval_steps_per_second": 12.327,
      "step": 1800
    },
    {
      "epoch": 2.423167057248075,
      "grad_norm": 1.5627659559249878,
      "learning_rate": 5.454212938299255e-06,
      "loss": 0.6224833488464355,
      "step": 1810
    },
    {
      "epoch": 2.4365584198192165,
      "grad_norm": 1.5051418542861938,
      "learning_rate": 5.2136952948992346e-06,
      "loss": 0.6476008892059326,
      "step": 1820
    },
    {
      "epoch": 2.449949782390358,
      "grad_norm": 1.4398276805877686,
      "learning_rate": 4.977982443524304e-06,
      "loss": 0.6809599876403809,
      "step": 1830
    },
    {
      "epoch": 2.4633411449615,
      "grad_norm": 1.5645432472229004,
      "learning_rate": 4.747131623322737e-06,
      "loss": 0.6530858993530273,
      "step": 1840
    },
    {
      "epoch": 2.4767325075326414,
      "grad_norm": 1.5863847732543945,
      "learning_rate": 4.521198892775203e-06,
      "loss": 0.683343505859375,
      "step": 1850
    },
    {
      "epoch": 2.490123870103783,
      "grad_norm": 1.8528956174850464,
      "learning_rate": 4.3002391160818775e-06,
      "loss": 0.6594698905944825,
      "step": 1860
    },
    {
      "epoch": 2.503515232674925,
      "grad_norm": 1.7349070310592651,
      "learning_rate": 4.0843059498395065e-06,
      "loss": 0.6450272083282471,
      "step": 1870
    },
    {
      "epoch": 2.5169065952460663,
      "grad_norm": 1.7238874435424805,
      "learning_rate": 3.873451830011795e-06,
      "loss": 0.6686948776245117,
      "step": 1880
    },
    {
      "epoch": 2.530297957817208,
      "grad_norm": 1.7201752662658691,
      "learning_rate": 3.66772795919611e-06,
      "loss": 0.6779526710510254,
      "step": 1890
    },
    {
      "epoch": 2.5436893203883493,
      "grad_norm": 1.8537648916244507,
      "learning_rate": 3.4671842941897765e-06,
      "loss": 0.6612625598907471,
      "step": 1900
    },
    {
      "epoch": 2.557080682959491,
      "grad_norm": 1.8143243789672852,
      "learning_rate": 3.27186953385884e-06,
      "loss": 0.688960599899292,
      "step": 1910
    },
    {
      "epoch": 2.5704720455306327,
      "grad_norm": 1.7363539934158325,
      "learning_rate": 3.081831107312308e-06,
      "loss": 0.6001778602600097,
      "step": 1920
    },
    {
      "epoch": 2.5838634081017746,
      "grad_norm": 1.6225067377090454,
      "learning_rate": 2.8971151623847587e-06,
      "loss": 0.6114172458648681,
      "step": 1930
    },
    {
      "epoch": 2.597254770672916,
      "grad_norm": 1.894216775894165,
      "learning_rate": 2.717766554430043e-06,
      "loss": 0.6248059749603272,
      "step": 1940
    },
    {
      "epoch": 2.6106461332440576,
      "grad_norm": 1.4052571058273315,
      "learning_rate": 2.543828835428899e-06,
      "loss": 0.6594170570373535,
      "step": 1950
    },
    {
      "epoch": 2.624037495815199,
      "grad_norm": 1.518526554107666,
      "learning_rate": 2.3753442434129997e-06,
      "loss": 0.6457861423492431,
      "step": 1960
    },
    {
      "epoch": 2.6374288583863406,
      "grad_norm": 1.4106321334838867,
      "learning_rate": 2.212353692208172e-06,
      "loss": 0.6338630676269531,
      "step": 1970
    },
    {
      "epoch": 2.6508202209574825,
      "grad_norm": 1.7220522165298462,
      "learning_rate": 2.0548967614990507e-06,
      "loss": 0.6565276145935058,
      "step": 1980
    },
    {
      "epoch": 2.664211583528624,
      "grad_norm": 1.791856050491333,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.6439648628234863,
      "step": 1990
    },
    {
      "epoch": 2.677602946099766,
      "grad_norm": 1.4954824447631836,
      "learning_rate": 1.7567353522592477e-06,
      "loss": 0.6367751598358155,
      "step": 2000
    },
    {
      "epoch": 2.6909943086709074,
      "grad_norm": 1.70801842212677,
      "learning_rate": 1.6161032775241503e-06,
      "loss": 0.6390559673309326,
      "step": 2010
    },
    {
      "epoch": 2.704385671242049,
      "grad_norm": 1.5347399711608887,
      "learning_rate": 1.4811496132938196e-06,
      "loss": 0.6345593452453613,
      "step": 2020
    },
    {
      "epoch": 2.7177770338131904,
      "grad_norm": 1.6422340869903564,
      "learning_rate": 1.3519071309370996e-06,
      "loss": 0.6990837097167969,
      "step": 2030
    },
    {
      "epoch": 2.731168396384332,
      "grad_norm": 1.6097452640533447,
      "learning_rate": 1.2284072149524094e-06,
      "loss": 0.6425330638885498,
      "step": 2040
    },
    {
      "epoch": 2.7445597589554738,
      "grad_norm": 1.6756435632705688,
      "learning_rate": 1.1106798553464804e-06,
      "loss": 0.6584507465362549,
      "step": 2050
    },
    {
      "epoch": 2.7579511215266153,
      "grad_norm": 1.7100108861923218,
      "learning_rate": 9.98753640351785e-07,
      "loss": 0.6514320850372315,
      "step": 2060
    },
    {
      "epoch": 2.771342484097757,
      "grad_norm": 1.662879228591919,
      "learning_rate": 8.926557494843085e-07,
      "loss": 0.6387072086334229,
      "step": 2070
    },
    {
      "epoch": 2.7847338466688987,
      "grad_norm": 1.6631816625595093,
      "learning_rate": 7.924119469434665e-07,
      "loss": 0.6538697719573975,
      "step": 2080
    },
    {
      "epoch": 2.79812520924004,
      "grad_norm": 1.4830073118209839,
      "learning_rate": 6.980465753556376e-07,
      "loss": 0.6062188625335694,
      "step": 2090
    },
    {
      "epoch": 2.8115165718111816,
      "grad_norm": 1.6122359037399292,
      "learning_rate": 6.095825498629692e-07,
      "loss": 0.6518032550811768,
      "step": 2100
    },
    {
      "epoch": 2.8115165718111816,
      "eval_loss": 0.7737736701965332,
      "eval_runtime": 53.7285,
      "eval_samples_per_second": 12.358,
      "eval_steps_per_second": 12.358,
      "step": 2100
    },
    {
      "epoch": 2.824907934382323,
      "grad_norm": 1.8782823085784912,
      "learning_rate": 5.270413525587909e-07,
      "loss": 0.7114206790924072,
      "step": 2110
    },
    {
      "epoch": 2.838299296953465,
      "grad_norm": 1.9547419548034668,
      "learning_rate": 4.5044302727100806e-07,
      "loss": 0.6745511054992676,
      "step": 2120
    },
    {
      "epoch": 2.8516906595246065,
      "grad_norm": 1.7238478660583496,
      "learning_rate": 3.7980617469479953e-07,
      "loss": 0.6630192279815674,
      "step": 2130
    },
    {
      "epoch": 2.8650820220957485,
      "grad_norm": 1.986541986465454,
      "learning_rate": 3.1514794787571854e-07,
      "loss": 0.677086067199707,
      "step": 2140
    },
    {
      "epoch": 2.87847338466689,
      "grad_norm": 1.5200341939926147,
      "learning_rate": 2.564840480443503e-07,
      "loss": 0.6238405227661132,
      "step": 2150
    },
    {
      "epoch": 2.8918647472380314,
      "grad_norm": 1.6327656507492065,
      "learning_rate": 2.0382872080351166e-07,
      "loss": 0.6561053276062012,
      "step": 2160
    },
    {
      "epoch": 2.905256109809173,
      "grad_norm": 1.5526694059371948,
      "learning_rate": 1.571947526689349e-07,
      "loss": 0.6776777744293213,
      "step": 2170
    },
    {
      "epoch": 2.918647472380315,
      "grad_norm": 1.7482457160949707,
      "learning_rate": 1.1659346796426551e-07,
      "loss": 0.6567188739776612,
      "step": 2180
    },
    {
      "epoch": 2.9320388349514563,
      "grad_norm": 1.7278902530670166,
      "learning_rate": 8.203472607112295e-08,
      "loss": 0.6143332958221436,
      "step": 2190
    },
    {
      "epoch": 2.945430197522598,
      "grad_norm": 1.835852861404419,
      "learning_rate": 5.352691903491303e-08,
      "loss": 0.6747828960418701,
      "step": 2200
    },
    {
      "epoch": 2.9588215600937398,
      "grad_norm": 1.778841495513916,
      "learning_rate": 3.107696952694139e-08,
      "loss": 0.6927904605865478,
      "step": 2210
    },
    {
      "epoch": 2.9722129226648812,
      "grad_norm": 1.5548834800720215,
      "learning_rate": 1.4690329163363769e-08,
      "loss": 0.629932975769043,
      "step": 2220
    },
    {
      "epoch": 2.9856042852360227,
      "grad_norm": 1.3981481790542603,
      "learning_rate": 4.370977181339386e-09,
      "loss": 0.657701063156128,
      "step": 2230
    },
    {
      "epoch": 2.998995647807164,
      "grad_norm": 1.709903359413147,
      "learning_rate": 1.214194727400253e-10,
      "loss": 0.6368677139282226,
      "step": 2240
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7736465334892273,
      "eval_runtime": 53.8484,
      "eval_samples_per_second": 12.331,
      "eval_steps_per_second": 12.331,
      "step": 2241
    },
    {
      "epoch": 3.0,
      "step": 2241,
      "total_flos": 6.028442138942669e+16,
      "train_loss": 0.8150908792992353,
      "train_runtime": 6217.0342,
      "train_samples_per_second": 2.883,
      "train_steps_per_second": 0.36
    }
  ],
  "logging_steps": 10,
  "max_steps": 2241,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.028442138942669e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}