{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9994079336885732,
  "eval_steps": 500,
  "global_step": 844,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.0,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.0,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.0,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.0,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.0,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.0,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.0,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.0,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.0,
      "learning_rate": 9.411764705882353e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.0,
      "learning_rate": 0.00010588235294117647,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.0,
      "learning_rate": 0.00011764705882352942,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.0,
      "learning_rate": 0.00012941176470588237,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.0,
      "learning_rate": 0.0001411764705882353,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.0,
      "learning_rate": 0.00015294117647058822,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.0,
      "learning_rate": 0.0001647058823529412,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.0,
      "learning_rate": 0.00017647058823529413,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.0,
      "learning_rate": 0.00018823529411764707,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.0,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.0,
      "learning_rate": 0.00019997858536356672,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.0,
      "learning_rate": 0.00019991435062599998,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.0,
      "learning_rate": 0.00019980732329857076,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.0,
      "learning_rate": 0.00019965754922030517,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.0,
      "learning_rate": 0.00019946509253835192,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.0,
      "learning_rate": 0.00019923003568050844,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.0,
      "learning_rate": 0.00019895247931991776,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.0,
      "learning_rate": 0.00019863254233195093,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.0,
      "learning_rate": 0.00019827036174329353,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.0,
      "learning_rate": 0.00019786609267325814,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.0,
      "learning_rate": 0.00019741990826734794,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.0,
      "learning_rate": 0.0001969319996230995,
      "loss": 0.0,
      "step": 145
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.0,
      "learning_rate": 0.0001964025757082375,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.0,
      "learning_rate": 0.000195831863271175,
      "loss": 0.0,
      "step": 155
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.0,
      "learning_rate": 0.000195220106743899,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.0,
      "learning_rate": 0.00019456756813728186,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.0,
      "learning_rate": 0.0001938745269288639,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.0,
      "learning_rate": 0.0001931412799431554,
      "loss": 0.0,
      "step": 175
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.0,
      "learning_rate": 0.00019236814122450865,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.0,
      "learning_rate": 0.00019155544190261508,
      "loss": 0.0,
      "step": 185
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.0,
      "learning_rate": 0.00019070353005068484,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.0,
      "learning_rate": 0.0001898127705363696,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.0,
      "learning_rate": 0.00018888354486549237,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.0,
      "learning_rate": 0.00018791625101865117,
      "loss": 0.0,
      "step": 205
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.0,
      "learning_rate": 0.00018691130328076717,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.0,
      "learning_rate": 0.00018586913206364918,
      "loss": 0.0,
      "step": 215
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.0,
      "learning_rate": 0.0001847901837216515,
      "loss": 0.0,
      "step": 220
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.0,
      "learning_rate": 0.00018367492036050362,
      "loss": 0.0,
      "step": 225
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.0,
      "learning_rate": 0.00018252381963939366,
      "loss": 0.0,
      "step": 230
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.0,
      "learning_rate": 0.00018133737456639044,
      "loss": 0.0,
      "step": 235
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.0,
      "learning_rate": 0.00018011609328729168,
      "loss": 0.0,
      "step": 240
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.0,
      "learning_rate": 0.0001788604988679889,
      "loss": 0.0,
      "step": 245
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.0,
      "learning_rate": 0.000177571129070442,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.0,
      "learning_rate": 0.00017624853612235986,
      "loss": 0.0,
      "step": 255
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.0,
      "learning_rate": 0.00017489328648068512,
      "loss": 0.0,
      "step": 260
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.0,
      "learning_rate": 0.00017350596058898483,
      "loss": 0.0,
      "step": 265
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.0,
      "learning_rate": 0.0001720871526288507,
      "loss": 0.0,
      "step": 270
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.0,
      "learning_rate": 0.00017063747026541543,
      "loss": 0.0,
      "step": 275
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.0,
      "learning_rate": 0.00016915753438709417,
      "loss": 0.0,
      "step": 280
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.0,
      "learning_rate": 0.00016764797883966244,
      "loss": 0.0,
      "step": 285
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.0,
      "learning_rate": 0.00016610945015478482,
      "loss": 0.0,
      "step": 290
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.0,
      "learning_rate": 0.00016454260727310978,
      "loss": 0.0,
      "step": 295
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.0,
      "learning_rate": 0.00016294812126205056,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.0,
      "learning_rate": 0.00016132667502837165,
      "loss": 0.0,
      "step": 305
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.0,
      "learning_rate": 0.00015967896302570485,
      "loss": 0.0,
      "step": 310
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.0,
      "learning_rate": 0.00015800569095711982,
      "loss": 0.0,
      "step": 315
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.0,
      "learning_rate": 0.00015630757547287666,
      "loss": 0.0,
      "step": 320
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.0,
      "learning_rate": 0.00015458534386348966,
      "loss": 0.0,
      "step": 325
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.0,
      "learning_rate": 0.00015283973374823423,
      "loss": 0.0,
      "step": 330
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.0,
      "learning_rate": 0.0001510714927592298,
      "loss": 0.0,
      "step": 335
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.0,
      "learning_rate": 0.00014928137822123452,
      "loss": 0.0,
      "step": 340
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.0,
      "learning_rate": 0.00014747015682728843,
      "loss": 0.0,
      "step": 345
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.0,
      "learning_rate": 0.00014563860431034465,
      "loss": 0.0,
      "step": 350
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.0,
      "learning_rate": 0.00014378750511102826,
      "loss": 0.0,
      "step": 355
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.0,
      "learning_rate": 0.00014191765204166643,
      "loss": 0.0,
      "step": 360
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.0,
      "learning_rate": 0.0001400298459467324,
      "loss": 0.0,
      "step": 365
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.0,
      "learning_rate": 0.00013812489535984981,
      "loss": 0.0,
      "step": 370
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.0,
      "learning_rate": 0.00013620361615750343,
      "loss": 0.0,
      "step": 375
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.0,
      "learning_rate": 0.00013426683120960542,
      "loss": 0.0,
      "step": 380
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.0,
      "learning_rate": 0.00013231537002706594,
      "loss": 0.0,
      "step": 385
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.0,
      "learning_rate": 0.00013035006840651968,
      "loss": 0.0,
      "step": 390
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.0,
      "learning_rate": 0.00012837176807236041,
      "loss": 0.0,
      "step": 395
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.0,
      "learning_rate": 0.0001263813163162364,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.0,
      "learning_rate": 0.00012437956563416148,
      "loss": 0.0,
      "step": 405
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.0,
      "learning_rate": 0.00012236737336139748,
      "loss": 0.0,
      "step": 410
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.0,
      "learning_rate": 0.0001203456013052634,
      "loss": 0.0,
      "step": 415
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.0,
      "learning_rate": 0.00011831511537602995,
      "loss": 0.0,
      "step": 420
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.0,
      "learning_rate": 0.00011627678521605629,
      "loss": 0.0,
      "step": 425
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.0,
      "learning_rate": 0.00011423148382732853,
      "loss": 0.0,
      "step": 430
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.0,
      "learning_rate": 0.0001121800871975594,
      "loss": 0.0,
      "step": 435
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.0,
      "learning_rate": 0.00011012347392500906,
      "loss": 0.0,
      "step": 440
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.0,
      "learning_rate": 0.0001080625248421878,
      "loss": 0.0,
      "step": 445
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.0,
      "learning_rate": 0.00010599812263860193,
      "loss": 0.0,
      "step": 450
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.0,
      "learning_rate": 0.00010393115148270431,
      "loss": 0.0,
      "step": 455
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.0,
      "learning_rate": 0.00010186249664321139,
      "loss": 0.0,
      "step": 460
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.0,
      "learning_rate": 9.979304410994895e-05,
      "loss": 0.0,
      "step": 465
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.0,
      "learning_rate": 9.772368021438943e-05,
      "loss": 0.0,
      "step": 470
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.0,
      "learning_rate": 9.56552912500422e-05,
      "loss": 0.0,
      "step": 475
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.0,
      "learning_rate": 9.358876309286075e-05,
      "loss": 0.0,
      "step": 480
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.0,
      "learning_rate": 9.152498082182835e-05,
      "loss": 0.0,
      "step": 485
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.0,
      "learning_rate": 8.94648283398853e-05,
      "loss": 0.0,
      "step": 490
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.0,
      "learning_rate": 8.74091879953595e-05,
      "loss": 0.0,
      "step": 495
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.0,
      "learning_rate": 8.535894020406328e-05,
      "loss": 0.0,
      "step": 500
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.0,
      "learning_rate": 8.331496307221762e-05,
      "loss": 0.0,
      "step": 505
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.0,
      "learning_rate": 8.127813202036566e-05,
      "loss": 0.0,
      "step": 510
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.0,
      "learning_rate": 7.924931940843639e-05,
      "loss": 0.0,
      "step": 515
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.0,
      "learning_rate": 7.722939416211937e-05,
      "loss": 0.0,
      "step": 520
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.0,
      "learning_rate": 7.521922140071002e-05,
      "loss": 0.0,
      "step": 525
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.0,
      "learning_rate": 7.32196620665854e-05,
      "loss": 0.0,
      "step": 530
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.0,
      "learning_rate": 7.123157255646888e-05,
      "loss": 0.0,
      "step": 535
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.0,
      "learning_rate": 6.925580435464158e-05,
      "loss": 0.0,
      "step": 540
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.0,
      "learning_rate": 6.729320366825784e-05,
      "loss": 0.0,
      "step": 545
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.0,
      "learning_rate": 6.534461106492093e-05,
      "loss": 0.0,
      "step": 550
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.0,
      "learning_rate": 6.341086111267402e-05,
      "loss": 0.0,
      "step": 555
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.0,
      "learning_rate": 6.149278202256064e-05,
      "loss": 0.0,
      "step": 560
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.0,
      "learning_rate": 5.9591195293908174e-05,
      "loss": 0.0,
      "step": 565
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.0,
      "learning_rate": 5.770691536248538e-05,
      "loss": 0.0,
      "step": 570
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.0,
      "learning_rate": 5.584074925168568e-05,
      "loss": 0.0,
      "step": 575
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.0,
      "learning_rate": 5.399349622688479e-05,
      "loss": 0.0,
      "step": 580
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.0,
      "learning_rate": 5.216594745312127e-05,
      "loss": 0.0,
      "step": 585
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.0,
      "learning_rate": 5.035888565624618e-05,
      "loss": 0.0,
      "step": 590
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.0,
      "learning_rate": 4.8573084787687326e-05,
      "loss": 0.0,
      "step": 595
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.0,
      "learning_rate": 4.680930969297166e-05,
      "loss": 0.0,
      "step": 600
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.0,
      "learning_rate": 4.5068315784147186e-05,
      "loss": 0.0,
      "step": 605
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.0,
      "learning_rate": 4.335084871624572e-05,
      "loss": 0.0,
      "step": 610
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.0,
      "learning_rate": 4.165764406792416e-05,
      "loss": 0.0,
      "step": 615
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.0,
      "learning_rate": 3.998942702642152e-05,
      "loss": 0.0,
      "step": 620
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.0,
      "learning_rate": 3.834691207696649e-05,
      "loss": 0.0,
      "step": 625
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.0,
      "learning_rate": 3.673080269676871e-05,
      "loss": 0.0,
      "step": 630
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.0,
      "learning_rate": 3.5141791053724405e-05,
      "loss": 0.0,
      "step": 635
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.0,
      "learning_rate": 3.3580557709966066e-05,
      "loss": 0.0,
      "step": 640
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.0,
      "learning_rate": 3.204777133038257e-05,
      "loss": 0.0,
      "step": 645
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.0,
      "learning_rate": 3.0544088396234896e-05,
      "loss": 0.0,
      "step": 650
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.0,
      "learning_rate": 2.9070152923989946e-05,
      "loss": 0.0,
      "step": 655
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.0,
      "learning_rate": 2.7626596189492983e-05,
      "loss": 0.0,
      "step": 660
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.0,
      "learning_rate": 2.621403645759687e-05,
      "loss": 0.0,
      "step": 665
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.0,
      "learning_rate": 2.4833078717363544e-05,
      "loss": 0.0,
      "step": 670
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.0,
      "learning_rate": 2.3484314422951746e-05,
      "loss": 0.0,
      "step": 675
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.0,
      "learning_rate": 2.2168321240301472e-05,
      "loss": 0.0,
      "step": 680
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.0,
      "learning_rate": 2.0885662799723804e-05,
      "loss": 0.0,
      "step": 685
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.0,
      "learning_rate": 1.9636888454502178e-05,
      "loss": 0.0,
      "step": 690
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.0,
      "learning_rate": 1.8422533045608457e-05,
      "loss": 0.0,
      "step": 695
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.0,
      "learning_rate": 1.7243116672634262e-05,
      "loss": 0.0,
      "step": 700
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.0,
      "learning_rate": 1.6099144471036208e-05,
      "loss": 0.0,
      "step": 705
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.0,
      "learning_rate": 1.4991106395790022e-05,
      "loss": 0.0,
      "step": 710
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.0,
      "learning_rate": 1.3919477011546423e-05,
      "loss": 0.0,
      "step": 715
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.0,
      "learning_rate": 1.288471528937848e-05,
      "loss": 0.0,
      "step": 720
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.0,
      "learning_rate": 1.1887264410207755e-05,
      "loss": 0.0,
      "step": 725
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.0,
      "learning_rate": 1.0927551574992967e-05,
      "loss": 0.0,
      "step": 730
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.0,
      "learning_rate": 1.0005987821763052e-05,
      "loss": 0.0,
      "step": 735
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.0,
      "learning_rate": 9.122967849572517e-06,
      "loss": 0.0,
      "step": 740
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.0,
      "learning_rate": 8.278869849454718e-06,
      "loss": 0.0,
      "step": 745
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.0,
      "learning_rate": 7.474055342445363e-06,
      "loss": 0.0,
      "step": 750
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.0,
      "learning_rate": 6.708869024745767e-06,
      "loss": 0.0,
      "step": 755
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.0,
      "learning_rate": 5.983638620091858e-06,
      "loss": 0.0,
      "step": 760
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.0,
      "learning_rate": 5.298674739392561e-06,
      "loss": 0.0,
      "step": 765
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.0,
      "learning_rate": 4.654270747697375e-06,
      "loss": 0.0,
      "step": 770
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.0,
      "learning_rate": 4.050702638550275e-06,
      "loss": 0.0,
      "step": 775
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.0,
      "learning_rate": 3.488228915783631e-06,
      "loss": 0.0,
      "step": 780
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.0,
      "learning_rate": 2.9670904828030033e-06,
      "loss": 0.0,
      "step": 785
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.0,
      "learning_rate": 2.4875105394098654e-06,
      "loss": 0.0,
      "step": 790
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.0,
      "learning_rate": 2.0496944862067656e-06,
      "loss": 0.0,
      "step": 795
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.0,
      "learning_rate": 1.6538298366257976e-06,
      "loss": 0.0,
      "step": 800
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.0,
      "learning_rate": 1.3000861366179062e-06,
      "loss": 0.0,
      "step": 805
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.0,
      "learning_rate": 9.886148920376203e-07,
      "loss": 0.0,
      "step": 810
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.0,
      "learning_rate": 7.1954950375418e-07,
      "loss": 0.0,
      "step": 815
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.0,
      "learning_rate": 4.93005210516928e-07,
      "loss": 0.0,
      "step": 820
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.0,
      "learning_rate": 3.090790395993692e-07,
      "loss": 0.0,
      "step": 825
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.0,
      "learning_rate": 1.6784976524312213e-07,
      "loss": 0.0,
      "step": 830
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.0,
      "learning_rate": 6.9377874919474e-08,
      "loss": 0.0,
      "step": 835
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.0,
      "learning_rate": 1.370554342302599e-08,
      "loss": 0.0,
      "step": 840
    },
    {
      "epoch": 1.0,
      "eval_loss": NaN,
      "eval_runtime": 266.8314,
      "eval_samples_per_second": 8.657,
      "eval_steps_per_second": 0.543,
      "step": 844
    },
    {
      "epoch": 1.0,
      "step": 844,
      "total_flos": 4538058175676416.0,
      "train_loss": 0.0,
      "train_runtime": 9563.5394,
      "train_samples_per_second": 2.825,
      "train_steps_per_second": 0.088
    }
  ],
  "logging_steps": 5,
  "max_steps": 844,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 4538058175676416.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}