{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.8846153846153846,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 2.0952,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000298793242156074,
      "loss": 2.2593,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000297586484312148,
      "loss": 2.1623,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000296379726468222,
      "loss": 1.9038,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000295172968624296,
      "loss": 1.8576,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00029396621078037004,
      "loss": 1.8397,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00029275945293644407,
      "loss": 1.8032,
      "step": 35
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00029155269509251804,
      "loss": 1.7281,
      "step": 40
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00029034593724859206,
      "loss": 1.7097,
      "step": 45
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00028913917940466614,
      "loss": 1.7421,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002879324215607401,
      "loss": 1.6861,
      "step": 55
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00028672566371681414,
      "loss": 1.6848,
      "step": 60
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00028551890587288816,
      "loss": 1.5163,
      "step": 65
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002843121480289622,
      "loss": 1.7266,
      "step": 70
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002831053901850362,
      "loss": 1.5888,
      "step": 75
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002818986323411102,
      "loss": 1.5463,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002806918744971842,
      "loss": 1.4611,
      "step": 85
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00027948511665325823,
      "loss": 1.5554,
      "step": 90
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00027827835880933226,
      "loss": 1.5481,
      "step": 95
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002770716009654062,
      "loss": 1.4464,
      "step": 100
    },
    {
      "epoch": 0.25,
      "eval_loss": 1.6602041721343994,
      "eval_runtime": 25.516,
      "eval_samples_per_second": 8.191,
      "eval_steps_per_second": 1.058,
      "step": 104
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00027586484312148025,
      "loss": 1.6648,
      "step": 105
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002746580852775543,
      "loss": 1.6464,
      "step": 110
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002734513274336283,
      "loss": 1.524,
      "step": 115
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002722445695897023,
      "loss": 1.4791,
      "step": 120
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002710378117457763,
      "loss": 1.5162,
      "step": 125
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002698310539018503,
      "loss": 1.6636,
      "step": 130
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00026862429605792435,
      "loss": 1.7803,
      "step": 135
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00026741753821399837,
      "loss": 1.7384,
      "step": 140
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002662107803700724,
      "loss": 1.5462,
      "step": 145
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002650040225261464,
      "loss": 1.5802,
      "step": 150
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00026379726468222045,
      "loss": 1.4942,
      "step": 155
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002625905068382944,
      "loss": 1.601,
      "step": 160
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00026138374899436844,
      "loss": 1.5822,
      "step": 165
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00026017699115044247,
      "loss": 1.5071,
      "step": 170
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002589702333065165,
      "loss": 1.5926,
      "step": 175
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00025776347546259046,
      "loss": 1.4206,
      "step": 180
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002565567176186645,
      "loss": 1.5317,
      "step": 185
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002553499597747385,
      "loss": 1.4862,
      "step": 190
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00025414320193081253,
      "loss": 1.4387,
      "step": 195
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00025293644408688656,
      "loss": 1.5276,
      "step": 200
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00025172968624296053,
      "loss": 1.55,
      "step": 205
    },
    {
      "epoch": 0.5,
      "eval_loss": 1.6166218519210815,
      "eval_runtime": 13.3266,
      "eval_samples_per_second": 15.683,
      "eval_steps_per_second": 2.026,
      "step": 208
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00025052292839903455,
      "loss": 1.5525,
      "step": 210
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002493161705551086,
      "loss": 1.5591,
      "step": 215
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002481094127111826,
      "loss": 1.529,
      "step": 220
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002469026548672566,
      "loss": 1.7152,
      "step": 225
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00024569589702333065,
      "loss": 1.7493,
      "step": 230
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002444891391794047,
      "loss": 1.5288,
      "step": 235
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00024328238133547868,
      "loss": 1.5651,
      "step": 240
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00024207562349155267,
      "loss": 1.5144,
      "step": 245
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002408688656476267,
      "loss": 1.5334,
      "step": 250
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002396621078037007,
      "loss": 1.5988,
      "step": 255
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00023845534995977472,
      "loss": 1.6401,
      "step": 260
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00023724859211584875,
      "loss": 1.5929,
      "step": 265
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00023604183427192274,
      "loss": 1.3948,
      "step": 270
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00023483507642799677,
      "loss": 1.221,
      "step": 275
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00023362831858407077,
      "loss": 1.5604,
      "step": 280
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002324215607401448,
      "loss": 1.505,
      "step": 285
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002312148028962188,
      "loss": 1.5008,
      "step": 290
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002300080450522928,
      "loss": 1.5176,
      "step": 295
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002288012872083668,
      "loss": 1.4227,
      "step": 300
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00022759452936444084,
      "loss": 1.1778,
      "step": 305
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00022638777152051486,
      "loss": 1.5052,
      "step": 310
    },
    {
      "epoch": 0.75,
      "eval_loss": 1.5979019403457642,
      "eval_runtime": 13.342,
      "eval_samples_per_second": 15.665,
      "eval_steps_per_second": 2.024,
      "step": 312
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00022518101367658886,
      "loss": 1.5228,
      "step": 315
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002239742558326629,
      "loss": 1.5385,
      "step": 320
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002227674979887369,
      "loss": 1.5072,
      "step": 325
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022156074014481093,
      "loss": 1.5032,
      "step": 330
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00022035398230088496,
      "loss": 1.5981,
      "step": 335
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00021914722445695895,
      "loss": 1.422,
      "step": 340
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00021794046661303298,
      "loss": 1.4948,
      "step": 345
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00021673370876910698,
      "loss": 1.4421,
      "step": 350
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000215526950925181,
      "loss": 1.6086,
      "step": 355
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000214320193081255,
      "loss": 1.3874,
      "step": 360
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00021311343523732902,
      "loss": 1.2493,
      "step": 365
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00021190667739340302,
      "loss": 1.5565,
      "step": 370
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00021069991954947705,
      "loss": 1.4739,
      "step": 375
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00020949316170555107,
      "loss": 1.5288,
      "step": 380
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00020828640386162507,
      "loss": 1.4837,
      "step": 385
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002070796460176991,
      "loss": 1.5009,
      "step": 390
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002058728881737731,
      "loss": 1.3469,
      "step": 395
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00020466613032984712,
      "loss": 1.3949,
      "step": 400
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00020345937248592117,
      "loss": 1.3688,
      "step": 405
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00020225261464199517,
      "loss": 1.6629,
      "step": 410
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002010458567980692,
      "loss": 1.5395,
      "step": 415
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.589026927947998,
      "eval_runtime": 13.34,
      "eval_samples_per_second": 15.667,
      "eval_steps_per_second": 2.024,
      "step": 416
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001998390989541432,
      "loss": 1.5794,
      "step": 420
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001986323411102172,
      "loss": 1.4746,
      "step": 425
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001974255832662912,
      "loss": 1.3205,
      "step": 430
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00019621882542236523,
      "loss": 1.491,
      "step": 435
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00019501206757843926,
      "loss": 1.4803,
      "step": 440
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00019380530973451326,
      "loss": 1.3436,
      "step": 445
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00019259855189058728,
      "loss": 1.3893,
      "step": 450
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00019139179404666128,
      "loss": 1.0474,
      "step": 455
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001901850362027353,
      "loss": 1.3388,
      "step": 460
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001889782783588093,
      "loss": 1.4201,
      "step": 465
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00018777152051488333,
      "loss": 1.4805,
      "step": 470
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00018656476267095732,
      "loss": 1.2253,
      "step": 475
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00018535800482703135,
      "loss": 1.5064,
      "step": 480
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00018415124698310537,
      "loss": 1.3565,
      "step": 485
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00018294448913917937,
      "loss": 1.3976,
      "step": 490
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00018173773129525342,
      "loss": 1.5882,
      "step": 495
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00018053097345132742,
      "loss": 1.4698,
      "step": 500
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017932421560740145,
      "loss": 1.5326,
      "step": 505
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017811745776347547,
      "loss": 1.5659,
      "step": 510
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00017691069991954947,
      "loss": 1.4489,
      "step": 515
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001757039420756235,
      "loss": 1.5312,
      "step": 520
    },
    {
      "epoch": 1.25,
      "eval_loss": 1.5857353210449219,
      "eval_runtime": 13.3247,
      "eval_samples_per_second": 15.685,
      "eval_steps_per_second": 2.026,
      "step": 520
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001744971842316975,
      "loss": 1.3595,
      "step": 525
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00017329042638777152,
      "loss": 1.1543,
      "step": 530
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001720836685438455,
      "loss": 1.4568,
      "step": 535
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00017087691069991954,
      "loss": 1.3682,
      "step": 540
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00016967015285599354,
      "loss": 1.5323,
      "step": 545
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00016846339501206756,
      "loss": 1.6644,
      "step": 550
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00016725663716814158,
      "loss": 1.5735,
      "step": 555
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00016604987932421558,
      "loss": 1.4759,
      "step": 560
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001648431214802896,
      "loss": 1.3774,
      "step": 565
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001636363636363636,
      "loss": 1.3321,
      "step": 570
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00016242960579243763,
      "loss": 1.2843,
      "step": 575
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016122284794851163,
      "loss": 1.4636,
      "step": 580
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016001609010458568,
      "loss": 1.4082,
      "step": 585
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001588093322606597,
      "loss": 1.3848,
      "step": 590
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001576025744167337,
      "loss": 1.5396,
      "step": 595
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00015639581657280773,
      "loss": 1.4889,
      "step": 600
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00015518905872888172,
      "loss": 1.4019,
      "step": 605
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00015398230088495575,
      "loss": 1.3788,
      "step": 610
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00015277554304102975,
      "loss": 1.409,
      "step": 615
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00015156878519710377,
      "loss": 1.5675,
      "step": 620
    },
    {
      "epoch": 1.5,
      "eval_loss": 1.584699273109436,
      "eval_runtime": 13.3509,
      "eval_samples_per_second": 15.654,
      "eval_steps_per_second": 2.022,
      "step": 624
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001503620273531778,
      "loss": 1.3176,
      "step": 625
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001491552695092518,
      "loss": 1.3114,
      "step": 630
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00014794851166532582,
      "loss": 1.4261,
      "step": 635
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00014674175382139982,
      "loss": 1.5156,
      "step": 640
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00014553499597747384,
      "loss": 1.3231,
      "step": 645
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00014432823813354787,
      "loss": 1.4353,
      "step": 650
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00014312148028962186,
      "loss": 1.4423,
      "step": 655
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001419147224456959,
      "loss": 1.1512,
      "step": 660
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001407079646017699,
      "loss": 1.3562,
      "step": 665
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0001395012067578439,
      "loss": 1.4033,
      "step": 670
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00013829444891391793,
      "loss": 1.5435,
      "step": 675
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00013708769106999193,
      "loss": 1.4543,
      "step": 680
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00013588093322606596,
      "loss": 1.3509,
      "step": 685
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00013467417538213995,
      "loss": 1.4268,
      "step": 690
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.000133467417538214,
      "loss": 1.4231,
      "step": 695
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.000132260659694288,
      "loss": 1.4727,
      "step": 700
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00013105390185036203,
      "loss": 1.2846,
      "step": 705
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00012984714400643603,
      "loss": 1.3458,
      "step": 710
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00012864038616251005,
      "loss": 1.6349,
      "step": 715
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00012743362831858405,
      "loss": 1.4798,
      "step": 720
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00012622687047465807,
      "loss": 1.6157,
      "step": 725
    },
    {
      "epoch": 1.75,
      "eval_loss": 1.5761181116104126,
      "eval_runtime": 13.3218,
      "eval_samples_per_second": 15.689,
      "eval_steps_per_second": 2.027,
      "step": 728
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00012502011263073207,
      "loss": 1.4723,
      "step": 730
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001238133547868061,
      "loss": 1.4487,
      "step": 735
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00012260659694288012,
      "loss": 1.3613,
      "step": 740
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00012139983909895413,
      "loss": 1.1906,
      "step": 745
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00012019308125502816,
      "loss": 1.4962,
      "step": 750
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00011898632341110217,
      "loss": 1.5629,
      "step": 755
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00011777956556717618,
      "loss": 1.3566,
      "step": 760
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00011657280772325019,
      "loss": 1.3442,
      "step": 765
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001153660498793242,
      "loss": 1.4071,
      "step": 770
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00011415929203539821,
      "loss": 1.4331,
      "step": 775
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00011295253419147222,
      "loss": 1.3572,
      "step": 780
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00011174577634754626,
      "loss": 1.4009,
      "step": 785
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00011053901850362027,
      "loss": 1.47,
      "step": 790
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00010933226065969428,
      "loss": 1.233,
      "step": 795
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001081255028157683,
      "loss": 1.4593,
      "step": 800
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00010691874497184231,
      "loss": 1.4147,
      "step": 805
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00010571198712791632,
      "loss": 1.2775,
      "step": 810
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00010450522928399033,
      "loss": 1.5372,
      "step": 815
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00010329847144006434,
      "loss": 1.2994,
      "step": 820
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00010209171359613835,
      "loss": 1.3639,
      "step": 825
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00010088495575221239,
      "loss": 1.4629,
      "step": 830
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.5735822916030884,
      "eval_runtime": 13.3179,
      "eval_samples_per_second": 15.693,
      "eval_steps_per_second": 2.027,
      "step": 832
    },
    {
      "epoch": 2.01,
      "learning_rate": 9.96781979082864e-05,
      "loss": 1.3559,
      "step": 835
    },
    {
      "epoch": 2.02,
      "learning_rate": 9.847144006436041e-05,
      "loss": 1.3924,
      "step": 840
    },
    {
      "epoch": 2.03,
      "learning_rate": 9.726468222043442e-05,
      "loss": 1.2349,
      "step": 845
    },
    {
      "epoch": 2.04,
      "learning_rate": 9.605792437650844e-05,
      "loss": 1.1467,
      "step": 850
    },
    {
      "epoch": 2.06,
      "learning_rate": 9.485116653258245e-05,
      "loss": 1.3251,
      "step": 855
    },
    {
      "epoch": 2.07,
      "learning_rate": 9.364440868865646e-05,
      "loss": 1.1517,
      "step": 860
    },
    {
      "epoch": 2.08,
      "learning_rate": 9.243765084473048e-05,
      "loss": 1.4388,
      "step": 865
    },
    {
      "epoch": 2.09,
      "learning_rate": 9.12308930008045e-05,
      "loss": 1.5138,
      "step": 870
    },
    {
      "epoch": 2.1,
      "learning_rate": 9.002413515687852e-05,
      "loss": 1.4948,
      "step": 875
    },
    {
      "epoch": 2.12,
      "learning_rate": 8.881737731295253e-05,
      "loss": 1.2988,
      "step": 880
    },
    {
      "epoch": 2.13,
      "learning_rate": 8.761061946902654e-05,
      "loss": 1.226,
      "step": 885
    },
    {
      "epoch": 2.14,
      "learning_rate": 8.640386162510055e-05,
      "loss": 1.1645,
      "step": 890
    },
    {
      "epoch": 2.15,
      "learning_rate": 8.519710378117456e-05,
      "loss": 1.278,
      "step": 895
    },
    {
      "epoch": 2.16,
      "learning_rate": 8.399034593724859e-05,
      "loss": 1.3873,
      "step": 900
    },
    {
      "epoch": 2.18,
      "learning_rate": 8.27835880933226e-05,
      "loss": 1.231,
      "step": 905
    },
    {
      "epoch": 2.19,
      "learning_rate": 8.157683024939661e-05,
      "loss": 1.401,
      "step": 910
    },
    {
      "epoch": 2.2,
      "learning_rate": 8.037007240547062e-05,
      "loss": 1.4372,
      "step": 915
    },
    {
      "epoch": 2.21,
      "learning_rate": 7.916331456154465e-05,
      "loss": 1.3624,
      "step": 920
    },
    {
      "epoch": 2.22,
      "learning_rate": 7.795655671761866e-05,
      "loss": 1.5242,
      "step": 925
    },
    {
      "epoch": 2.24,
      "learning_rate": 7.674979887369267e-05,
      "loss": 1.3661,
      "step": 930
    },
    {
      "epoch": 2.25,
      "learning_rate": 7.554304102976669e-05,
      "loss": 1.3608,
      "step": 935
    },
    {
      "epoch": 2.25,
      "eval_loss": 1.582654356956482,
      "eval_runtime": 13.332,
      "eval_samples_per_second": 15.677,
      "eval_steps_per_second": 2.025,
      "step": 936
    },
    {
      "epoch": 2.26,
      "learning_rate": 7.43362831858407e-05,
      "loss": 1.476,
      "step": 940
    },
    {
      "epoch": 2.27,
      "learning_rate": 7.312952534191472e-05,
      "loss": 1.3051,
      "step": 945
    },
    {
      "epoch": 2.28,
      "learning_rate": 7.192276749798874e-05,
      "loss": 1.418,
      "step": 950
    },
    {
      "epoch": 2.3,
      "learning_rate": 7.071600965406275e-05,
      "loss": 1.1781,
      "step": 955
    },
    {
      "epoch": 2.31,
      "learning_rate": 6.950925181013676e-05,
      "loss": 1.4319,
      "step": 960
    },
    {
      "epoch": 2.32,
      "learning_rate": 6.830249396621077e-05,
      "loss": 1.3059,
      "step": 965
    },
    {
      "epoch": 2.33,
      "learning_rate": 6.709573612228479e-05,
      "loss": 1.0836,
      "step": 970
    },
    {
      "epoch": 2.34,
      "learning_rate": 6.588897827835881e-05,
      "loss": 1.376,
      "step": 975
    },
    {
      "epoch": 2.36,
      "learning_rate": 6.468222043443282e-05,
      "loss": 1.5022,
      "step": 980
    },
    {
      "epoch": 2.37,
      "learning_rate": 6.347546259050683e-05,
      "loss": 1.2871,
      "step": 985
    },
    {
      "epoch": 2.38,
      "learning_rate": 6.226870474658084e-05,
      "loss": 1.2777,
      "step": 990
    },
    {
      "epoch": 2.39,
      "learning_rate": 6.106194690265487e-05,
      "loss": 1.5625,
      "step": 995
    },
    {
      "epoch": 2.4,
      "learning_rate": 5.985518905872888e-05,
      "loss": 1.087,
      "step": 1000
    },
    {
      "epoch": 2.42,
      "learning_rate": 5.864843121480289e-05,
      "loss": 1.3169,
      "step": 1005
    },
    {
      "epoch": 2.43,
      "learning_rate": 5.74416733708769e-05,
      "loss": 1.3657,
      "step": 1010
    },
    {
      "epoch": 2.44,
      "learning_rate": 5.6234915526950926e-05,
      "loss": 1.3917,
      "step": 1015
    },
    {
      "epoch": 2.45,
      "learning_rate": 5.502815768302494e-05,
      "loss": 1.3179,
      "step": 1020
    },
    {
      "epoch": 2.46,
      "learning_rate": 5.382139983909895e-05,
      "loss": 1.4162,
      "step": 1025
    },
    {
      "epoch": 2.48,
      "learning_rate": 5.261464199517296e-05,
      "loss": 1.3564,
      "step": 1030
    },
    {
      "epoch": 2.49,
      "learning_rate": 5.140788415124698e-05,
      "loss": 1.276,
      "step": 1035
    },
    {
      "epoch": 2.5,
      "learning_rate": 5.0201126307320996e-05,
      "loss": 1.3666,
      "step": 1040
    },
    {
      "epoch": 2.5,
      "eval_loss": 1.5801613330841064,
      "eval_runtime": 13.3272,
      "eval_samples_per_second": 15.682,
      "eval_steps_per_second": 2.026,
      "step": 1040
    },
    {
      "epoch": 2.51,
      "learning_rate": 4.899436846339501e-05,
      "loss": 1.4251,
      "step": 1045
    },
    {
      "epoch": 2.52,
      "learning_rate": 4.778761061946902e-05,
      "loss": 1.4518,
      "step": 1050
    },
    {
      "epoch": 2.54,
      "learning_rate": 4.6580852775543036e-05,
      "loss": 1.3541,
      "step": 1055
    },
    {
      "epoch": 2.55,
      "learning_rate": 4.5374094931617054e-05,
      "loss": 1.249,
      "step": 1060
    },
    {
      "epoch": 2.56,
      "learning_rate": 4.4167337087691066e-05,
      "loss": 1.3855,
      "step": 1065
    },
    {
      "epoch": 2.57,
      "learning_rate": 4.2960579243765084e-05,
      "loss": 1.2707,
      "step": 1070
    },
    {
      "epoch": 2.58,
      "learning_rate": 4.1753821399839095e-05,
      "loss": 1.2083,
      "step": 1075
    },
    {
      "epoch": 2.6,
      "learning_rate": 4.0547063555913106e-05,
      "loss": 1.4777,
      "step": 1080
    },
    {
      "epoch": 2.61,
      "learning_rate": 3.934030571198713e-05,
      "loss": 1.4348,
      "step": 1085
    },
    {
      "epoch": 2.62,
      "learning_rate": 3.813354786806114e-05,
      "loss": 1.2354,
      "step": 1090
    },
    {
      "epoch": 2.63,
      "learning_rate": 3.692679002413515e-05,
      "loss": 1.294,
      "step": 1095
    },
    {
      "epoch": 2.64,
      "learning_rate": 3.572003218020917e-05,
      "loss": 1.3231,
      "step": 1100
    },
    {
      "epoch": 2.66,
      "learning_rate": 3.451327433628318e-05,
      "loss": 1.2215,
      "step": 1105
    },
    {
      "epoch": 2.67,
      "learning_rate": 3.33065164923572e-05,
      "loss": 1.1217,
      "step": 1110
    },
    {
      "epoch": 2.68,
      "learning_rate": 3.209975864843121e-05,
      "loss": 1.4292,
      "step": 1115
    },
    {
      "epoch": 2.69,
      "learning_rate": 3.089300080450522e-05,
      "loss": 1.195,
      "step": 1120
    },
    {
      "epoch": 2.7,
      "learning_rate": 2.968624296057924e-05,
      "loss": 1.3549,
      "step": 1125
    },
    {
      "epoch": 2.72,
      "learning_rate": 2.8479485116653255e-05,
      "loss": 1.4274,
      "step": 1130
    },
    {
      "epoch": 2.73,
      "learning_rate": 2.727272727272727e-05,
      "loss": 1.4838,
      "step": 1135
    },
    {
      "epoch": 2.74,
      "learning_rate": 2.6065969428801284e-05,
      "loss": 1.2394,
      "step": 1140
    },
    {
      "epoch": 2.75,
      "eval_loss": 1.5814132690429688,
      "eval_runtime": 13.3223,
      "eval_samples_per_second": 15.688,
      "eval_steps_per_second": 2.027,
      "step": 1144
    },
    {
      "epoch": 2.75,
      "learning_rate": 2.4859211584875302e-05,
      "loss": 1.2414,
      "step": 1145
    },
    {
      "epoch": 2.76,
      "learning_rate": 2.3652453740949313e-05,
      "loss": 1.288,
      "step": 1150
    },
    {
      "epoch": 2.78,
      "learning_rate": 2.244569589702333e-05,
      "loss": 1.2,
      "step": 1155
    },
    {
      "epoch": 2.79,
      "learning_rate": 2.1238938053097343e-05,
      "loss": 1.2117,
      "step": 1160
    },
    {
      "epoch": 2.8,
      "learning_rate": 2.003218020917136e-05,
      "loss": 1.3717,
      "step": 1165
    },
    {
      "epoch": 2.81,
      "learning_rate": 1.8825422365245372e-05,
      "loss": 1.438,
      "step": 1170
    },
    {
      "epoch": 2.82,
      "learning_rate": 1.7618664521319386e-05,
      "loss": 1.3346,
      "step": 1175
    },
    {
      "epoch": 2.84,
      "learning_rate": 1.64119066773934e-05,
      "loss": 1.227,
      "step": 1180
    },
    {
      "epoch": 2.85,
      "learning_rate": 1.5205148833467417e-05,
      "loss": 1.3146,
      "step": 1185
    },
    {
      "epoch": 2.86,
      "learning_rate": 1.3998390989541432e-05,
      "loss": 1.4163,
      "step": 1190
    },
    {
      "epoch": 2.87,
      "learning_rate": 1.2791633145615445e-05,
      "loss": 1.1681,
      "step": 1195
    },
    {
      "epoch": 2.88,
      "learning_rate": 1.158487530168946e-05,
      "loss": 1.4127,
      "step": 1200
    }
  ],
  "max_steps": 1248,
  "num_train_epochs": 3,
  "total_flos": 957297581350656.0,
  "trial_name": null,
  "trial_params": null
}