{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9996477632969355,
  "eval_steps": 500,
  "global_step": 1419,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.4084507042253521e-06,
      "loss": 1.9425,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.042253521126762e-06,
      "loss": 2.0234,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4084507042253523e-05,
      "loss": 1.9715,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.112676056338028e-05,
      "loss": 1.9477,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8169014084507046e-05,
      "loss": 1.8815,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.5211267605633805e-05,
      "loss": 1.8108,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.225352112676056e-05,
      "loss": 1.7765,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.929577464788733e-05,
      "loss": 1.7328,
      "step": 35
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.633802816901409e-05,
      "loss": 1.7477,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.338028169014085e-05,
      "loss": 1.6816,
      "step": 45
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.042253521126761e-05,
      "loss": 1.6714,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.746478873239437e-05,
      "loss": 1.642,
      "step": 55
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.450704225352113e-05,
      "loss": 1.612,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.15492957746479e-05,
      "loss": 1.592,
      "step": 65
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.859154929577466e-05,
      "loss": 1.6068,
      "step": 70
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001056338028169014,
      "loss": 1.5911,
      "step": 75
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011267605633802819,
      "loss": 1.5727,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011971830985915493,
      "loss": 1.5929,
      "step": 85
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001267605633802817,
      "loss": 1.5441,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013380281690140845,
      "loss": 1.5659,
      "step": 95
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014084507042253522,
      "loss": 1.5422,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000147887323943662,
      "loss": 1.5782,
      "step": 105
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00015492957746478874,
      "loss": 1.5553,
      "step": 110
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001619718309859155,
      "loss": 1.5324,
      "step": 115
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00016901408450704225,
      "loss": 1.4999,
      "step": 120
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00017605633802816902,
      "loss": 1.5137,
      "step": 125
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001830985915492958,
      "loss": 1.5549,
      "step": 130
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019014084507042254,
      "loss": 1.5369,
      "step": 135
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001971830985915493,
      "loss": 1.5427,
      "step": 140
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999727649301603,
      "loss": 1.5195,
      "step": 145
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019998063337645585,
      "loss": 1.5184,
      "step": 150
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001999488627179007,
      "loss": 1.5382,
      "step": 155
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019990196932440123,
      "loss": 1.5211,
      "step": 160
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019983996029114938,
      "loss": 1.5237,
      "step": 165
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019976284500040467,
      "loss": 1.5225,
      "step": 170
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019967063512007482,
      "loss": 1.5393,
      "step": 175
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019956334460195015,
      "loss": 1.4915,
      "step": 180
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019944098967959278,
      "loss": 1.492,
      "step": 185
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019930358886588025,
      "loss": 1.5237,
      "step": 190
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019915116295020458,
      "loss": 1.5198,
      "step": 195
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019898373499532666,
      "loss": 1.5046,
      "step": 200
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001988013303338867,
      "loss": 1.4883,
      "step": 205
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019860397656457147,
      "loss": 1.4738,
      "step": 210
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019839170354793827,
      "loss": 1.5288,
      "step": 215
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019816454340189693,
      "loss": 1.5271,
      "step": 220
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001979225304968504,
      "loss": 1.4791,
      "step": 225
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019766570145049407,
      "loss": 1.4587,
      "step": 230
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001973940951222756,
      "loss": 1.4508,
      "step": 235
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001971077526075151,
      "loss": 1.5056,
      "step": 240
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019680671723118734,
      "loss": 1.4492,
      "step": 245
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001964910345413664,
      "loss": 1.5118,
      "step": 250
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019616075230233408,
      "loss": 1.4772,
      "step": 255
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019581592048735296,
      "loss": 1.4862,
      "step": 260
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019545659127110507,
      "loss": 1.4979,
      "step": 265
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019508281902179782,
      "loss": 1.4564,
      "step": 270
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019469466029293776,
      "loss": 1.4446,
      "step": 275
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019429217381477357,
      "loss": 1.4828,
      "step": 280
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019387542048541023,
      "loss": 1.4632,
      "step": 285
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001934444633615946,
      "loss": 1.4543,
      "step": 290
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001929993676491747,
      "loss": 1.4742,
      "step": 295
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019254020069323386,
      "loss": 1.4811,
      "step": 300
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019206703196790096,
      "loss": 1.4505,
      "step": 305
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019157993306583867,
      "loss": 1.4237,
      "step": 310
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019107897768741127,
      "loss": 1.4285,
      "step": 315
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001905642416295333,
      "loss": 1.4454,
      "step": 320
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001900358027742012,
      "loss": 1.42,
      "step": 325
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018949374107670935,
      "loss": 1.4507,
      "step": 330
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001889381385535525,
      "loss": 1.4222,
      "step": 335
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018836907927001628,
      "loss": 1.4502,
      "step": 340
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018778664932745772,
      "loss": 1.4255,
      "step": 345
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001871909368502777,
      "loss": 1.4597,
      "step": 350
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018658203197258728,
      "loss": 1.432,
      "step": 355
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001859600268245701,
      "loss": 1.4676,
      "step": 360
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018532501551854242,
      "loss": 1.4267,
      "step": 365
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018467709413471378,
      "loss": 1.4392,
      "step": 370
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018401636070664945,
      "loss": 1.4067,
      "step": 375
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001833429152064374,
      "loss": 1.4427,
      "step": 380
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018265685952956222,
      "loss": 1.4519,
      "step": 385
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018195829747948773,
      "loss": 1.4449,
      "step": 390
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018124733475195117,
      "loss": 1.424,
      "step": 395
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018052407891897075,
      "loss": 1.447,
      "step": 400
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001797886394125696,
      "loss": 1.4363,
      "step": 405
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017904112750821824,
      "loss": 1.4152,
      "step": 410
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017828165630799796,
      "loss": 1.41,
      "step": 415
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000177510340723488,
      "loss": 1.446,
      "step": 420
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001767272974583789,
      "loss": 1.4449,
      "step": 425
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017593264499081465,
      "loss": 1.4519,
      "step": 430
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017512650355546634,
      "loss": 1.4323,
      "step": 435
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017430899512534026,
      "loss": 1.424,
      "step": 440
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017348024339332259,
      "loss": 1.3989,
      "step": 445
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001726403737534642,
      "loss": 1.4005,
      "step": 450
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017178951328200798,
      "loss": 1.4457,
      "step": 455
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001709277907181615,
      "loss": 1.4335,
      "step": 460
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001700553364446182,
      "loss": 1.4705,
      "step": 465
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016917228246782987,
      "loss": 1.4012,
      "step": 470
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016827876239803352,
      "loss": 1.4038,
      "step": 475
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001673749114290354,
      "loss": 1.4353,
      "step": 480
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016646086631775563,
      "loss": 1.4034,
      "step": 485
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016553676536353612,
      "loss": 1.4265,
      "step": 490
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016460274838721545,
      "loss": 1.4354,
      "step": 495
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016365895670997305,
      "loss": 1.4099,
      "step": 500
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016270553313194684,
      "loss": 1.4237,
      "step": 505
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016174262191062674,
      "loss": 1.4616,
      "step": 510
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016077036873902797,
      "loss": 1.4041,
      "step": 515
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015978892072364694,
      "loss": 1.4019,
      "step": 520
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015879842636220328,
      "loss": 1.3983,
      "step": 525
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015779903552117153,
      "loss": 1.4043,
      "step": 530
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015679089941310575,
      "loss": 1.373,
      "step": 535
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015577417057376,
      "loss": 1.4002,
      "step": 540
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015474900283900923,
      "loss": 1.3802,
      "step": 545
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015371555132157318,
      "loss": 1.3933,
      "step": 550
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015267397238754693,
      "loss": 1.4463,
      "step": 555
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015162442363274214,
      "loss": 1.3943,
      "step": 560
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00015056706385884196,
      "loss": 1.4336,
      "step": 565
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014950205304937368,
      "loss": 1.3881,
      "step": 570
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014842955234550231,
      "loss": 1.3875,
      "step": 575
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014734972402164932,
      "loss": 1.4053,
      "step": 580
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014626273146093967,
      "loss": 1.404,
      "step": 585
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014516873913048117,
      "loss": 1.4101,
      "step": 590
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001440679125564799,
      "loss": 1.3958,
      "step": 595
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014296041829919522,
      "loss": 1.3972,
      "step": 600
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00014184642392773845,
      "loss": 1.4385,
      "step": 605
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00014072609799471896,
      "loss": 1.4154,
      "step": 610
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00013959961001074113,
      "loss": 1.392,
      "step": 615
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013846713041875693,
      "loss": 1.3893,
      "step": 620
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013732883056827684,
      "loss": 1.3978,
      "step": 625
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001361848826894439,
      "loss": 1.414,
      "step": 630
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013503545986697456,
      "loss": 1.3606,
      "step": 635
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013388073601397008,
      "loss": 1.4059,
      "step": 640
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001327208858456027,
      "loss": 1.3912,
      "step": 645
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013155608485268031,
      "loss": 1.4211,
      "step": 650
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013038650927509404,
      "loss": 1.384,
      "step": 655
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00012921233607515216,
      "loss": 1.3631,
      "step": 660
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001280337429108049,
      "loss": 1.3803,
      "step": 665
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012685090810876407,
      "loss": 1.3631,
      "step": 670
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001256640106375212,
      "loss": 1.4074,
      "step": 675
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001244732300802689,
      "loss": 1.386,
      "step": 680
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012327874660772898,
      "loss": 1.4198,
      "step": 685
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012208074095089192,
      "loss": 1.3607,
      "step": 690
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012087939437367126,
      "loss": 1.3762,
      "step": 695
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001196748886454775,
      "loss": 1.389,
      "step": 700
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011846740601371576,
      "loss": 1.4058,
      "step": 705
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011725712917621059,
      "loss": 1.3868,
      "step": 710
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011604424125356312,
      "loss": 1.3644,
      "step": 715
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011482892576144405,
      "loss": 1.3894,
      "step": 720
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011361136658282663,
      "loss": 1.363,
      "step": 725
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011239174794016469,
      "loss": 1.3882,
      "step": 730
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00011117025436751855,
      "loss": 1.409,
      "step": 735
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010994707068263434,
      "loss": 1.3615,
      "step": 740
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010872238195898019,
      "loss": 1.3623,
      "step": 745
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010749637349774357,
      "loss": 1.3658,
      "step": 750
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010626923079979465,
      "loss": 1.3687,
      "step": 755
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010504113953761885,
      "loss": 1.3753,
      "step": 760
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010381228552722392,
      "loss": 1.3861,
      "step": 765
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010258285470002494,
      "loss": 1.3645,
      "step": 770
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00010135303307471213,
      "loss": 1.3761,
      "step": 775
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00010012300672910535,
      "loss": 1.3553,
      "step": 780
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.889296177199954e-05,
      "loss": 1.3739,
      "step": 785
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.766308431500566e-05,
      "loss": 1.3452,
      "step": 790
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.64335604443912e-05,
      "loss": 1.3559,
      "step": 795
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.520457619292423e-05,
      "loss": 1.3802,
      "step": 800
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.397631751172601e-05,
      "loss": 1.3469,
      "step": 805
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.274897024213544e-05,
      "loss": 1.3818,
      "step": 810
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.152272008759076e-05,
      "loss": 1.3351,
      "step": 815
    },
    {
      "epoch": 0.58,
      "learning_rate": 9.029775258553128e-05,
      "loss": 1.3855,
      "step": 820
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.907425307932514e-05,
      "loss": 1.3522,
      "step": 825
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.785240669022568e-05,
      "loss": 1.344,
      "step": 830
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.663239828936174e-05,
      "loss": 1.3704,
      "step": 835
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.541441246976607e-05,
      "loss": 1.3571,
      "step": 840
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.419863351844508e-05,
      "loss": 1.3621,
      "step": 845
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.298524538849576e-05,
      "loss": 1.3889,
      "step": 850
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.177443167127244e-05,
      "loss": 1.3597,
      "step": 855
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.056637556860872e-05,
      "loss": 1.3719,
      "step": 860
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.936125986509803e-05,
      "loss": 1.3565,
      "step": 865
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.815926690043756e-05,
      "loss": 1.3909,
      "step": 870
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.696057854183935e-05,
      "loss": 1.3711,
      "step": 875
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.576537615651295e-05,
      "loss": 1.3712,
      "step": 880
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.457384058422368e-05,
      "loss": 1.3663,
      "step": 885
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.338615210993074e-05,
      "loss": 1.3771,
      "step": 890
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.220249043650918e-05,
      "loss": 1.3454,
      "step": 895
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.102303465756019e-05,
      "loss": 1.3879,
      "step": 900
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.98479632303131e-05,
      "loss": 1.3803,
      "step": 905
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.867745394862422e-05,
      "loss": 1.3628,
      "step": 910
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.751168391607576e-05,
      "loss": 1.4021,
      "step": 915
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.635082951917897e-05,
      "loss": 1.3821,
      "step": 920
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.519506640068638e-05,
      "loss": 1.3592,
      "step": 925
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.404456943301592e-05,
      "loss": 1.3659,
      "step": 930
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.289951269179215e-05,
      "loss": 1.3887,
      "step": 935
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.17600694295076e-05,
      "loss": 1.3603,
      "step": 940
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.0626412049308965e-05,
      "loss": 1.3654,
      "step": 945
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.949871207891162e-05,
      "loss": 1.3842,
      "step": 950
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.837714014464677e-05,
      "loss": 1.3333,
      "step": 955
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.7261865945644664e-05,
      "loss": 1.3426,
      "step": 960
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.6153058228158686e-05,
      "loss": 1.3652,
      "step": 965
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.505088476003284e-05,
      "loss": 1.3833,
      "step": 970
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.395551230531797e-05,
      "loss": 1.387,
      "step": 975
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.286710659903937e-05,
      "loss": 1.3584,
      "step": 980
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.1785832322120574e-05,
      "loss": 1.3588,
      "step": 985
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.0711853076466045e-05,
      "loss": 1.403,
      "step": 990
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.9645331360207505e-05,
      "loss": 1.3297,
      "step": 995
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.8586428543117434e-05,
      "loss": 1.3314,
      "step": 1000
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.753530484219279e-05,
      "loss": 1.3619,
      "step": 1005
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.6492119297413475e-05,
      "loss": 1.3421,
      "step": 1010
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.545702974767891e-05,
      "loss": 1.356,
      "step": 1015
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.443019280692638e-05,
      "loss": 1.3057,
      "step": 1020
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.341176384043416e-05,
      "loss": 1.3334,
      "step": 1025
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.240189694131458e-05,
      "loss": 1.3574,
      "step": 1030
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.140074490719861e-05,
      "loss": 1.3476,
      "step": 1035
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.040845921711702e-05,
      "loss": 1.36,
      "step": 1040
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.9425190008580826e-05,
      "loss": 1.3517,
      "step": 1045
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.8451086054864896e-05,
      "loss": 1.3709,
      "step": 1050
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.748629474249766e-05,
      "loss": 1.3551,
      "step": 1055
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.6530962048960973e-05,
      "loss": 1.3444,
      "step": 1060
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.558523252060295e-05,
      "loss": 1.3683,
      "step": 1065
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.464924925076758e-05,
      "loss": 1.3673,
      "step": 1070
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.3723153858143784e-05,
      "loss": 1.3692,
      "step": 1075
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.280708646533799e-05,
      "loss": 1.3456,
      "step": 1080
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.1901185677672976e-05,
      "loss": 1.3424,
      "step": 1085
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.100558856221606e-05,
      "loss": 1.3521,
      "step": 1090
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.012043062704034e-05,
      "loss": 1.3721,
      "step": 1095
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.9245845800721574e-05,
      "loss": 1.3416,
      "step": 1100
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.838196641207438e-05,
      "loss": 1.3671,
      "step": 1105
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.752892317012985e-05,
      "loss": 1.3855,
      "step": 1110
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.668684514435914e-05,
      "loss": 1.388,
      "step": 1115
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.5855859745144284e-05,
      "loss": 1.3535,
      "step": 1120
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.503609270450058e-05,
      "loss": 1.3519,
      "step": 1125
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.4227668057052634e-05,
      "loss": 1.3591,
      "step": 1130
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.343070812126752e-05,
      "loss": 1.3823,
      "step": 1135
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.2645333480947173e-05,
      "loss": 1.3482,
      "step": 1140
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.1871662966983663e-05,
      "loss": 1.3656,
      "step": 1145
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.1109813639379427e-05,
      "loss": 1.3696,
      "step": 1150
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.035990076953569e-05,
      "loss": 1.3406,
      "step": 1155
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.9622037822811123e-05,
      "loss": 1.3501,
      "step": 1160
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.8896336441354167e-05,
      "loss": 1.3447,
      "step": 1165
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.8182906427211043e-05,
      "loss": 1.3734,
      "step": 1170
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.7481855725712093e-05,
      "loss": 1.3903,
      "step": 1175
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6793290409139207e-05,
      "loss": 1.3574,
      "step": 1180
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.611731466067655e-05,
      "loss": 1.3495,
      "step": 1185
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.54540307586473e-05,
      "loss": 1.342,
      "step": 1190
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4803539061038119e-05,
      "loss": 1.3346,
      "step": 1195
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.4165937990314915e-05,
      "loss": 1.3269,
      "step": 1200
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3541324018530788e-05,
      "loss": 1.37,
      "step": 1205
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2929791652729439e-05,
      "loss": 1.3472,
      "step": 1210
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.233143342064581e-05,
      "loss": 1.3459,
      "step": 1215
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1746339856706234e-05,
      "loss": 1.3591,
      "step": 1220
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1174599488330051e-05,
      "loss": 1.361,
      "step": 1225
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0616298822535087e-05,
      "loss": 1.3585,
      "step": 1230
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.007152233284866e-05,
      "loss": 1.3768,
      "step": 1235
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.540352446526479e-06,
      "loss": 1.3655,
      "step": 1240
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.022869532080735e-06,
      "loss": 1.3734,
      "step": 1245
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.51915188712027e-06,
      "loss": 1.3404,
      "step": 1250
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.029275726503626e-06,
      "loss": 1.3352,
      "step": 1255
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.553315170807373e-06,
      "loss": 1.3394,
      "step": 1260
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.09134223511132e-06,
      "loss": 1.3762,
      "step": 1265
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.643426818102339e-06,
      "loss": 1.373,
      "step": 1270
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.209636691498366e-06,
      "loss": 1.3304,
      "step": 1275
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.790037489794109e-06,
      "loss": 1.3483,
      "step": 1280
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.384692700330407e-06,
      "loss": 1.3342,
      "step": 1285
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.993663653688152e-06,
      "loss": 1.3695,
      "step": 1290
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.617009514408788e-06,
      "loss": 1.3326,
      "step": 1295
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.254787272042315e-06,
      "loss": 1.352,
      "step": 1300
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.907051732524669e-06,
      "loss": 1.3532,
      "step": 1305
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.573855509885171e-06,
      "loss": 1.3466,
      "step": 1310
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.2552490182858443e-06,
      "loss": 1.3799,
      "step": 1315
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.95128046439348e-06,
      "loss": 1.3706,
      "step": 1320
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.6619958400858513e-06,
      "loss": 1.3794,
      "step": 1325
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.3874389154927233e-06,
      "loss": 1.3892,
      "step": 1330
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.127651232373429e-06,
      "loss": 1.3396,
      "step": 1335
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8826720978313062e-06,
      "loss": 1.352,
      "step": 1340
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.6525385783663028e-06,
      "loss": 1.3655,
      "step": 1345
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4372854942667602e-06,
      "loss": 1.3788,
      "step": 1350
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2369454143408289e-06,
      "loss": 1.339,
      "step": 1355
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.051548650988754e-06,
      "loss": 1.3178,
      "step": 1360
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.811232556163451e-07,
      "loss": 1.3495,
      "step": 1365
    },
    {
      "epoch": 0.97,
      "learning_rate": 7.256950143907815e-07,
      "loss": 1.3702,
      "step": 1370
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.852874443389888e-07,
      "loss": 1.3459,
      "step": 1375
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.5992178978938593e-07,
      "loss": 1.3747,
      "step": 1380
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.496170191575554e-07,
      "loss": 1.3402,
      "step": 1385
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.5438982207622866e-07,
      "loss": 1.3601,
      "step": 1390
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.742546068700168e-07,
      "loss": 1.3837,
      "step": 1395
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0922349837545476e-07,
      "loss": 1.4011,
      "step": 1400
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.9306336106346174e-08,
      "loss": 1.3838,
      "step": 1405
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.4510672765087894e-08,
      "loss": 1.3608,
      "step": 1410
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.8417730998728814e-09,
      "loss": 1.3504,
      "step": 1415
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.355061411857605,
      "eval_runtime": 1858.7192,
      "eval_samples_per_second": 0.709,
      "eval_steps_per_second": 0.089,
      "step": 1419
    },
    {
      "epoch": 1.0,
      "step": 1419,
      "total_flos": 9.977407964782264e+17,
      "train_loss": 1.4210990094399267,
      "train_runtime": 56404.0081,
      "train_samples_per_second": 0.201,
      "train_steps_per_second": 0.025
    }
  ],
  "logging_steps": 5,
  "max_steps": 1419,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 9.977407964782264e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}