{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0004993997599039616,
      "loss": 9.442,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004987995198079231,
      "loss": 6.4069,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004981992797118848,
      "loss": 5.2241,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004975990396158463,
      "loss": 4.6629,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004969987995198079,
      "loss": 4.4599,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004963985594237695,
      "loss": 4.4699,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004957983193277311,
      "loss": 4.328,
      "step": 35
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004951980792316927,
      "loss": 4.2845,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004945978391356542,
      "loss": 4.2205,
      "step": 45
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004939975990396158,
      "loss": 4.1616,
      "step": 50
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004933973589435775,
      "loss": 4.1001,
      "step": 55
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000492797118847539,
      "loss": 4.051,
      "step": 60
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004921968787515006,
      "loss": 3.9317,
      "step": 65
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004915966386554621,
      "loss": 3.9395,
      "step": 70
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004909963985594238,
      "loss": 3.892,
      "step": 75
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004903961584633854,
      "loss": 3.7325,
      "step": 80
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004897959183673469,
      "loss": 3.735,
      "step": 85
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004891956782713085,
      "loss": 3.6928,
      "step": 90
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004885954381752701,
      "loss": 3.7048,
      "step": 95
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004879951980792317,
      "loss": 3.5304,
      "step": 100
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00048739495798319325,
      "loss": 3.565,
      "step": 105
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00048679471788715486,
      "loss": 3.6801,
      "step": 110
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00048619447779111647,
      "loss": 3.5079,
      "step": 115
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00048559423769507803,
      "loss": 3.5053,
      "step": 120
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00048499399759903964,
      "loss": 3.35,
      "step": 125
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0004843937575030012,
      "loss": 3.4045,
      "step": 130
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0004837935174069628,
      "loss": 3.3187,
      "step": 135
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00048319327731092437,
      "loss": 3.3906,
      "step": 140
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000482593037214886,
      "loss": 3.3228,
      "step": 145
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00048199279711884753,
      "loss": 3.297,
      "step": 150
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00048139255702280915,
      "loss": 3.3078,
      "step": 155
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0004807923169267707,
      "loss": 3.312,
      "step": 160
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0004801920768307323,
      "loss": 3.3131,
      "step": 165
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00047959183673469387,
      "loss": 3.2012,
      "step": 170
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0004789915966386555,
      "loss": 3.2605,
      "step": 175
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00047839135654261704,
      "loss": 3.1821,
      "step": 180
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00047779111644657865,
      "loss": 3.1836,
      "step": 185
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0004771908763505402,
      "loss": 3.1439,
      "step": 190
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0004765906362545018,
      "loss": 3.1493,
      "step": 195
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0004759903961584634,
      "loss": 3.0728,
      "step": 200
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000475390156062425,
      "loss": 3.1574,
      "step": 205
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00047478991596638654,
      "loss": 3.1272,
      "step": 210
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00047418967587034816,
      "loss": 3.0083,
      "step": 215
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00047358943577430977,
      "loss": 3.0536,
      "step": 220
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0004729891956782713,
      "loss": 3.0536,
      "step": 225
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0004723889555822329,
      "loss": 3.0091,
      "step": 230
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0004717887154861945,
      "loss": 3.0709,
      "step": 235
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0004711884753901561,
      "loss": 2.9084,
      "step": 240
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00047058823529411766,
      "loss": 2.9807,
      "step": 245
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0004699879951980792,
      "loss": 2.9563,
      "step": 250
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00046938775510204083,
      "loss": 2.9508,
      "step": 255
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00046878751500600244,
      "loss": 2.9896,
      "step": 260
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000468187274909964,
      "loss": 2.8946,
      "step": 265
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00046758703481392555,
      "loss": 2.9081,
      "step": 270
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00046698679471788716,
      "loss": 2.8824,
      "step": 275
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0004663865546218488,
      "loss": 2.9004,
      "step": 280
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00046578631452581033,
      "loss": 2.8155,
      "step": 285
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0004651860744297719,
      "loss": 2.8921,
      "step": 290
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0004645858343337335,
      "loss": 2.8942,
      "step": 295
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0004639855942376951,
      "loss": 2.8331,
      "step": 300
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00046338535414165667,
      "loss": 2.9032,
      "step": 305
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0004627851140456182,
      "loss": 2.8443,
      "step": 310
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00046218487394957984,
      "loss": 2.9231,
      "step": 315
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00046158463385354145,
      "loss": 2.8204,
      "step": 320
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000460984393757503,
      "loss": 2.8024,
      "step": 325
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00046038415366146456,
      "loss": 2.8511,
      "step": 330
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00045978391356542623,
      "loss": 2.7767,
      "step": 335
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0004591836734693878,
      "loss": 2.7563,
      "step": 340
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00045858343337334934,
      "loss": 2.8491,
      "step": 345
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0004579831932773109,
      "loss": 2.8621,
      "step": 350
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00045738295318127257,
      "loss": 2.7985,
      "step": 355
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0004567827130852341,
      "loss": 2.8162,
      "step": 360
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0004561824729891957,
      "loss": 2.7087,
      "step": 365
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00045558223289315724,
      "loss": 2.7947,
      "step": 370
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0004549819927971189,
      "loss": 2.7413,
      "step": 375
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00045438175270108046,
      "loss": 2.7319,
      "step": 380
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000453781512605042,
      "loss": 2.8137,
      "step": 385
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00045318127250900357,
      "loss": 2.7292,
      "step": 390
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00045258103241296524,
      "loss": 2.8123,
      "step": 395
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0004519807923169268,
      "loss": 2.7721,
      "step": 400
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00045138055222088835,
      "loss": 2.7073,
      "step": 405
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0004507803121248499,
      "loss": 2.6707,
      "step": 410
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0004501800720288116,
      "loss": 2.6422,
      "step": 415
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00044957983193277313,
      "loss": 2.7066,
      "step": 420
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0004489795918367347,
      "loss": 2.6398,
      "step": 425
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0004483793517406963,
      "loss": 2.7323,
      "step": 430
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0004477791116446579,
      "loss": 2.695,
      "step": 435
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00044717887154861947,
      "loss": 2.6634,
      "step": 440
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000446578631452581,
      "loss": 2.6284,
      "step": 445
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00044597839135654264,
      "loss": 2.7046,
      "step": 450
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00044537815126050425,
      "loss": 2.7038,
      "step": 455
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0004447779111644658,
      "loss": 2.6489,
      "step": 460
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00044417767106842736,
      "loss": 2.6162,
      "step": 465
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000443577430972389,
      "loss": 2.6625,
      "step": 470
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00044297719087635053,
      "loss": 2.6046,
      "step": 475
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00044237695078031214,
      "loss": 2.6556,
      "step": 480
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0004417767106842737,
      "loss": 2.5762,
      "step": 485
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0004411764705882353,
      "loss": 2.6441,
      "step": 490
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00044057623049219687,
      "loss": 2.6731,
      "step": 495
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0004399759903961585,
      "loss": 2.5839,
      "step": 500
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00043937575030012003,
      "loss": 2.5429,
      "step": 505
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00043877551020408165,
      "loss": 2.5735,
      "step": 510
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004381752701080432,
      "loss": 2.561,
      "step": 515
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004375750300120048,
      "loss": 2.5553,
      "step": 520
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00043697478991596637,
      "loss": 2.5196,
      "step": 525
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000436374549819928,
      "loss": 2.5371,
      "step": 530
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00043577430972388954,
      "loss": 2.4678,
      "step": 535
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00043517406962785115,
      "loss": 2.5223,
      "step": 540
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00043457382953181276,
      "loss": 2.5111,
      "step": 545
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004339735894357743,
      "loss": 2.5562,
      "step": 550
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004333733493397359,
      "loss": 2.5992,
      "step": 555
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004327731092436975,
      "loss": 2.5308,
      "step": 560
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004321728691476591,
      "loss": 2.5141,
      "step": 565
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00043157262905162066,
      "loss": 2.5755,
      "step": 570
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004309723889555822,
      "loss": 2.5723,
      "step": 575
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004303721488595438,
      "loss": 2.4098,
      "step": 580
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00042977190876350544,
      "loss": 2.5296,
      "step": 585
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000429171668667467,
      "loss": 2.547,
      "step": 590
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00042857142857142855,
      "loss": 2.4059,
      "step": 595
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00042797118847539016,
      "loss": 2.4101,
      "step": 600
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00042737094837935177,
      "loss": 2.5301,
      "step": 605
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00042677070828331333,
      "loss": 2.4837,
      "step": 610
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004261704681872749,
      "loss": 2.5095,
      "step": 615
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004255702280912365,
      "loss": 2.4423,
      "step": 620
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0004249699879951981,
      "loss": 2.4299,
      "step": 625
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00042436974789915967,
      "loss": 2.487,
      "step": 630
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004237695078031212,
      "loss": 2.4534,
      "step": 635
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004231692677070829,
      "loss": 2.4706,
      "step": 640
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00042256902761104444,
      "loss": 2.4558,
      "step": 645
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.000421968787515006,
      "loss": 2.4226,
      "step": 650
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00042136854741896756,
      "loss": 2.4443,
      "step": 655
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004207683073229292,
      "loss": 2.4487,
      "step": 660
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0004201680672268908,
      "loss": 2.4283,
      "step": 665
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00041956782713085234,
      "loss": 2.4918,
      "step": 670
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004189675870348139,
      "loss": 2.4895,
      "step": 675
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00041836734693877556,
      "loss": 2.4296,
      "step": 680
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004177671068427371,
      "loss": 2.4259,
      "step": 685
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0004171668667466987,
      "loss": 2.4956,
      "step": 690
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00041656662665066023,
      "loss": 2.4708,
      "step": 695
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0004159663865546219,
      "loss": 2.4078,
      "step": 700
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00041536614645858345,
      "loss": 2.4024,
      "step": 705
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000414765906362545,
      "loss": 2.3847,
      "step": 710
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00041416566626650657,
      "loss": 2.361,
      "step": 715
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00041356542617046823,
      "loss": 2.4494,
      "step": 720
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004129651860744298,
      "loss": 2.4495,
      "step": 725
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00041236494597839135,
      "loss": 2.431,
      "step": 730
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0004117647058823529,
      "loss": 2.4143,
      "step": 735
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00041116446578631457,
      "loss": 2.3522,
      "step": 740
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00041056422569027613,
      "loss": 2.4095,
      "step": 745
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0004099639855942377,
      "loss": 2.3399,
      "step": 750
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0004093637454981993,
      "loss": 2.3234,
      "step": 755
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0004087635054021609,
      "loss": 2.3904,
      "step": 760
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00040816326530612246,
      "loss": 2.3691,
      "step": 765
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.000407563025210084,
      "loss": 2.3312,
      "step": 770
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00040696278511404563,
      "loss": 2.3323,
      "step": 775
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00040636254501800724,
      "loss": 2.3701,
      "step": 780
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0004057623049219688,
      "loss": 2.433,
      "step": 785
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00040516206482593036,
      "loss": 2.3172,
      "step": 790
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00040456182472989197,
      "loss": 2.3529,
      "step": 795
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0004039615846338536,
      "loss": 2.4238,
      "step": 800
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00040336134453781514,
      "loss": 2.3834,
      "step": 805
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0004027611044417767,
      "loss": 2.2364,
      "step": 810
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0004021608643457383,
      "loss": 2.3618,
      "step": 815
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0004015606242496999,
      "loss": 2.3188,
      "step": 820
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0004009603841536615,
      "loss": 2.3659,
      "step": 825
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00040036014405762303,
      "loss": 2.3043,
      "step": 830
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00039975990396158464,
      "loss": 2.299,
      "step": 835
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00039915966386554625,
      "loss": 2.1782,
      "step": 840
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0003985594237695078,
      "loss": 2.1026,
      "step": 845
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00039795918367346937,
      "loss": 2.1629,
      "step": 850
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.000397358943577431,
      "loss": 2.1208,
      "step": 855
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0003967587034813926,
      "loss": 2.0706,
      "step": 860
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00039615846338535415,
      "loss": 2.0824,
      "step": 865
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00039555822328931576,
      "loss": 2.1032,
      "step": 870
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0003949579831932773,
      "loss": 2.1157,
      "step": 875
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0003943577430972389,
      "loss": 2.072,
      "step": 880
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0003937575030012005,
      "loss": 2.1275,
      "step": 885
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0003931572629051621,
      "loss": 2.0514,
      "step": 890
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00039255702280912365,
      "loss": 2.0643,
      "step": 895
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00039195678271308526,
      "loss": 2.1485,
      "step": 900
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0003913565426170468,
      "loss": 2.0773,
      "step": 905
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00039075630252100843,
      "loss": 2.0944,
      "step": 910
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00039015606242497,
      "loss": 2.1342,
      "step": 915
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003895558223289316,
      "loss": 2.0535,
      "step": 920
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00038895558223289316,
      "loss": 2.0487,
      "step": 925
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00038835534213685477,
      "loss": 2.0567,
      "step": 930
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0003877551020408163,
      "loss": 2.0674,
      "step": 935
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0003871548619447779,
      "loss": 2.103,
      "step": 940
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0003865546218487395,
      "loss": 2.0839,
      "step": 945
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0003859543817527011,
      "loss": 2.1078,
      "step": 950
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00038535414165666266,
      "loss": 2.1217,
      "step": 955
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0003847539015606242,
      "loss": 2.1457,
      "step": 960
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0003841536614645859,
      "loss": 2.0889,
      "step": 965
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00038355342136854744,
      "loss": 2.0706,
      "step": 970
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.000382953181272509,
      "loss": 2.1443,
      "step": 975
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00038235294117647055,
      "loss": 2.1191,
      "step": 980
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003817527010804322,
      "loss": 2.0608,
      "step": 985
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0003811524609843938,
      "loss": 2.0786,
      "step": 990
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00038055222088835533,
      "loss": 2.1455,
      "step": 995
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003799519807923169,
      "loss": 1.9875,
      "step": 1000
    }
  ],
  "logging_steps": 5,
  "max_steps": 4165,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.974401690333184e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}