{
  "best_metric": 1.306809425354004,
  "best_model_checkpoint": "outputs/checkpoint-1800",
  "epoch": 0.6160164271047228,
  "global_step": 1800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1e-05,
      "loss": 1.8606,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 1.8806,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 3e-05,
      "loss": 1.8434,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 1.7431,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 1.7721,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-05,
      "loss": 1.6826,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 7e-05,
      "loss": 1.5892,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 1.6333,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 9e-05,
      "loss": 1.5955,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.5504,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.5621,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012,
      "loss": 1.5142,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.4386,
      "step": 65
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014,
      "loss": 1.5017,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.4666,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00016,
      "loss": 1.4295,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00017,
      "loss": 1.4402,
      "step": 85
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018,
      "loss": 1.4795,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019,
      "loss": 1.4138,
      "step": 95
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.4493,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001998259052924791,
      "loss": 1.4918,
      "step": 105
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019965181058495822,
      "loss": 1.4659,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019947771587743734,
      "loss": 1.4573,
      "step": 115
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019930362116991646,
      "loss": 1.4274,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019912952646239555,
      "loss": 1.4064,
      "step": 125
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019895543175487465,
      "loss": 1.4048,
      "step": 130
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019878133704735376,
      "loss": 1.4493,
      "step": 135
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019860724233983288,
      "loss": 1.3317,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019843314763231198,
      "loss": 1.4041,
      "step": 145
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001982590529247911,
      "loss": 1.4311,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001980849582172702,
      "loss": 1.3626,
      "step": 155
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019791086350974934,
      "loss": 1.4296,
      "step": 160
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019773676880222843,
      "loss": 1.3888,
      "step": 165
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019756267409470752,
      "loss": 1.3389,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019738857938718664,
      "loss": 1.4544,
      "step": 175
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019721448467966573,
      "loss": 1.4382,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019704038997214485,
      "loss": 1.4953,
      "step": 185
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019686629526462397,
      "loss": 1.4026,
      "step": 190
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019669220055710306,
      "loss": 1.3757,
      "step": 195
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019651810584958218,
      "loss": 1.3247,
      "step": 200
    },
    {
      "epoch": 0.07,
      "eval_loss": 1.3710952997207642,
      "eval_runtime": 738.1164,
      "eval_samples_per_second": 7.038,
      "eval_steps_per_second": 0.881,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001963440111420613,
      "loss": 1.4409,
      "step": 205
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001961699164345404,
      "loss": 1.4023,
      "step": 210
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019599582172701951,
      "loss": 1.3736,
      "step": 215
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001958217270194986,
      "loss": 1.4321,
      "step": 220
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019564763231197773,
      "loss": 1.4344,
      "step": 225
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019547353760445685,
      "loss": 1.3539,
      "step": 230
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019529944289693594,
      "loss": 1.438,
      "step": 235
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019512534818941506,
      "loss": 1.457,
      "step": 240
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019495125348189415,
      "loss": 1.429,
      "step": 245
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019477715877437327,
      "loss": 1.4465,
      "step": 250
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001946030640668524,
      "loss": 1.4202,
      "step": 255
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019442896935933148,
      "loss": 1.343,
      "step": 260
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001942548746518106,
      "loss": 1.4127,
      "step": 265
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001940807799442897,
      "loss": 1.3171,
      "step": 270
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001939066852367688,
      "loss": 1.4012,
      "step": 275
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019373259052924793,
      "loss": 1.2933,
      "step": 280
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019355849582172702,
      "loss": 1.326,
      "step": 285
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019338440111420614,
      "loss": 1.3951,
      "step": 290
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019321030640668524,
      "loss": 1.3149,
      "step": 295
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019303621169916436,
      "loss": 1.4046,
      "step": 300
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019286211699164348,
      "loss": 1.343,
      "step": 305
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019268802228412257,
      "loss": 1.3676,
      "step": 310
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019251392757660166,
      "loss": 1.3593,
      "step": 315
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001923398328690808,
      "loss": 1.3869,
      "step": 320
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001921657381615599,
      "loss": 1.3841,
      "step": 325
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019199164345403902,
      "loss": 1.3806,
      "step": 330
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001918175487465181,
      "loss": 1.4527,
      "step": 335
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001916434540389972,
      "loss": 1.4161,
      "step": 340
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019146935933147635,
      "loss": 1.3019,
      "step": 345
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019129526462395544,
      "loss": 1.4082,
      "step": 350
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019112116991643454,
      "loss": 1.4261,
      "step": 355
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019094707520891365,
      "loss": 1.4152,
      "step": 360
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019077298050139277,
      "loss": 1.4289,
      "step": 365
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001905988857938719,
      "loss": 1.3951,
      "step": 370
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019042479108635099,
      "loss": 1.3578,
      "step": 375
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019025069637883008,
      "loss": 1.3342,
      "step": 380
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001900766016713092,
      "loss": 1.3959,
      "step": 385
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00018990250696378832,
      "loss": 1.4336,
      "step": 390
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018972841225626744,
      "loss": 1.464,
      "step": 395
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018955431754874653,
      "loss": 1.4053,
      "step": 400
    },
    {
      "epoch": 0.14,
      "eval_loss": 1.3470327854156494,
      "eval_runtime": 738.9389,
      "eval_samples_per_second": 7.03,
      "eval_steps_per_second": 0.88,
      "step": 400
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018938022284122562,
      "loss": 1.3582,
      "step": 405
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018920612813370474,
      "loss": 1.375,
      "step": 410
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018903203342618386,
      "loss": 1.4229,
      "step": 415
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018885793871866295,
      "loss": 1.3843,
      "step": 420
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00018868384401114207,
      "loss": 1.39,
      "step": 425
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00018850974930362116,
      "loss": 1.3863,
      "step": 430
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00018833565459610028,
      "loss": 1.3597,
      "step": 435
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001881615598885794,
      "loss": 1.4114,
      "step": 440
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001879874651810585,
      "loss": 1.2929,
      "step": 445
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00018781337047353762,
      "loss": 1.3087,
      "step": 450
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001876392757660167,
      "loss": 1.3748,
      "step": 455
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018746518105849583,
      "loss": 1.3716,
      "step": 460
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018729108635097495,
      "loss": 1.404,
      "step": 465
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018711699164345404,
      "loss": 1.2931,
      "step": 470
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018694289693593316,
      "loss": 1.3345,
      "step": 475
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018676880222841225,
      "loss": 1.3836,
      "step": 480
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018659470752089137,
      "loss": 1.3923,
      "step": 485
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001864206128133705,
      "loss": 1.3166,
      "step": 490
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018624651810584958,
      "loss": 1.3697,
      "step": 495
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001860724233983287,
      "loss": 1.437,
      "step": 500
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018589832869080782,
      "loss": 1.3579,
      "step": 505
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018572423398328691,
      "loss": 1.3769,
      "step": 510
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018555013927576603,
      "loss": 1.3989,
      "step": 515
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018537604456824513,
      "loss": 1.331,
      "step": 520
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018520194986072425,
      "loss": 1.3678,
      "step": 525
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018502785515320337,
      "loss": 1.3475,
      "step": 530
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018485376044568246,
      "loss": 1.4465,
      "step": 535
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018467966573816158,
      "loss": 1.3304,
      "step": 540
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018450557103064067,
      "loss": 1.4006,
      "step": 545
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001843314763231198,
      "loss": 1.3645,
      "step": 550
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001841573816155989,
      "loss": 1.3217,
      "step": 555
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000183983286908078,
      "loss": 1.3421,
      "step": 560
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001838091922005571,
      "loss": 1.3283,
      "step": 565
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001836350974930362,
      "loss": 1.4101,
      "step": 570
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018346100278551533,
      "loss": 1.3333,
      "step": 575
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018328690807799445,
      "loss": 1.4574,
      "step": 580
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018311281337047354,
      "loss": 1.3755,
      "step": 585
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018293871866295264,
      "loss": 1.3537,
      "step": 590
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018276462395543176,
      "loss": 1.3734,
      "step": 595
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018259052924791088,
      "loss": 1.3431,
      "step": 600
    },
    {
      "epoch": 0.21,
      "eval_loss": 1.3354507684707642,
      "eval_runtime": 738.7441,
      "eval_samples_per_second": 7.032,
      "eval_steps_per_second": 0.88,
      "step": 600
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018241643454039,
      "loss": 1.3685,
      "step": 605
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001822423398328691,
      "loss": 1.377,
      "step": 610
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018206824512534818,
      "loss": 1.4289,
      "step": 615
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018189415041782733,
      "loss": 1.398,
      "step": 620
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018172005571030642,
      "loss": 1.3915,
      "step": 625
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001815459610027855,
      "loss": 1.4608,
      "step": 630
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018137186629526463,
      "loss": 1.4408,
      "step": 635
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018119777158774372,
      "loss": 1.3443,
      "step": 640
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018102367688022287,
      "loss": 1.4033,
      "step": 645
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018084958217270196,
      "loss": 1.3086,
      "step": 650
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018067548746518105,
      "loss": 1.3581,
      "step": 655
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018050139275766017,
      "loss": 1.3457,
      "step": 660
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001803272980501393,
      "loss": 1.4488,
      "step": 665
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001801532033426184,
      "loss": 1.3765,
      "step": 670
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001799791086350975,
      "loss": 1.4061,
      "step": 675
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001798050139275766,
      "loss": 1.3556,
      "step": 680
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017963091922005572,
      "loss": 1.3359,
      "step": 685
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017945682451253484,
      "loss": 1.2965,
      "step": 690
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017928272980501393,
      "loss": 1.3211,
      "step": 695
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017910863509749305,
      "loss": 1.4063,
      "step": 700
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017893454038997214,
      "loss": 1.3837,
      "step": 705
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017876044568245126,
      "loss": 1.397,
      "step": 710
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017858635097493038,
      "loss": 1.3671,
      "step": 715
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017841225626740947,
      "loss": 1.3666,
      "step": 720
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001782381615598886,
      "loss": 1.3875,
      "step": 725
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017806406685236768,
      "loss": 1.3613,
      "step": 730
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001778899721448468,
      "loss": 1.3611,
      "step": 735
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017771587743732592,
      "loss": 1.357,
      "step": 740
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017754178272980502,
      "loss": 1.3561,
      "step": 745
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017736768802228414,
      "loss": 1.4103,
      "step": 750
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017719359331476323,
      "loss": 1.4355,
      "step": 755
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017701949860724235,
      "loss": 1.3901,
      "step": 760
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017684540389972147,
      "loss": 1.4161,
      "step": 765
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017667130919220056,
      "loss": 1.4353,
      "step": 770
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017649721448467968,
      "loss": 1.3647,
      "step": 775
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001763231197771588,
      "loss": 1.3503,
      "step": 780
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001761490250696379,
      "loss": 1.3034,
      "step": 785
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000175974930362117,
      "loss": 1.3908,
      "step": 790
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001758008356545961,
      "loss": 1.3361,
      "step": 795
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001756267409470752,
      "loss": 1.4012,
      "step": 800
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.3277837038040161,
      "eval_runtime": 737.1439,
      "eval_samples_per_second": 7.047,
      "eval_steps_per_second": 0.882,
      "step": 800
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017545264623955434,
      "loss": 1.3631,
      "step": 805
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017527855153203343,
      "loss": 1.3789,
      "step": 810
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017510445682451255,
      "loss": 1.3418,
      "step": 815
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017493036211699165,
      "loss": 1.3556,
      "step": 820
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017475626740947077,
      "loss": 1.339,
      "step": 825
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017458217270194989,
      "loss": 1.3419,
      "step": 830
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017440807799442898,
      "loss": 1.2919,
      "step": 835
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017423398328690807,
      "loss": 1.3757,
      "step": 840
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001740598885793872,
      "loss": 1.3165,
      "step": 845
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001738857938718663,
      "loss": 1.325,
      "step": 850
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017371169916434543,
      "loss": 1.3846,
      "step": 855
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017353760445682452,
      "loss": 1.393,
      "step": 860
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001733635097493036,
      "loss": 1.3176,
      "step": 865
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017318941504178273,
      "loss": 1.3603,
      "step": 870
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017301532033426185,
      "loss": 1.3858,
      "step": 875
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017284122562674097,
      "loss": 1.3801,
      "step": 880
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017266713091922006,
      "loss": 1.3258,
      "step": 885
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017249303621169916,
      "loss": 1.3958,
      "step": 890
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017231894150417828,
      "loss": 1.3352,
      "step": 895
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001721448467966574,
      "loss": 1.3546,
      "step": 900
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001719707520891365,
      "loss": 1.3576,
      "step": 905
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001717966573816156,
      "loss": 1.5061,
      "step": 910
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001716225626740947,
      "loss": 1.3496,
      "step": 915
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017144846796657385,
      "loss": 1.4537,
      "step": 920
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017127437325905294,
      "loss": 1.4241,
      "step": 925
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017110027855153203,
      "loss": 1.4109,
      "step": 930
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017092618384401115,
      "loss": 1.4104,
      "step": 935
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017075208913649024,
      "loss": 1.4555,
      "step": 940
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017057799442896936,
      "loss": 1.2743,
      "step": 945
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017040389972144848,
      "loss": 1.3573,
      "step": 950
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017022980501392757,
      "loss": 1.3463,
      "step": 955
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001700557103064067,
      "loss": 1.3817,
      "step": 960
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001698816155988858,
      "loss": 1.4315,
      "step": 965
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001697075208913649,
      "loss": 1.3112,
      "step": 970
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016953342618384403,
      "loss": 1.3998,
      "step": 975
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016935933147632312,
      "loss": 1.3697,
      "step": 980
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016918523676880224,
      "loss": 1.3726,
      "step": 985
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016901114206128136,
      "loss": 1.4137,
      "step": 990
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016883704735376045,
      "loss": 1.3371,
      "step": 995
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016866295264623957,
      "loss": 1.3189,
      "step": 1000
    },
    {
      "epoch": 0.34,
      "eval_loss": 1.3234615325927734,
      "eval_runtime": 736.9447,
      "eval_samples_per_second": 7.049,
      "eval_steps_per_second": 0.882,
      "step": 1000
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016848885793871866,
      "loss": 1.3207,
      "step": 1005
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016831476323119778,
      "loss": 1.3369,
      "step": 1010
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001681406685236769,
      "loss": 1.3205,
      "step": 1015
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000167966573816156,
      "loss": 1.3124,
      "step": 1020
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001677924791086351,
      "loss": 1.3317,
      "step": 1025
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001676183844011142,
      "loss": 1.3713,
      "step": 1030
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016744428969359332,
      "loss": 1.3276,
      "step": 1035
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016727019498607244,
      "loss": 1.2705,
      "step": 1040
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016709610027855154,
      "loss": 1.4057,
      "step": 1045
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016692200557103066,
      "loss": 1.4044,
      "step": 1050
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016674791086350975,
      "loss": 1.3438,
      "step": 1055
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016657381615598887,
      "loss": 1.3871,
      "step": 1060
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000166399721448468,
      "loss": 1.3212,
      "step": 1065
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00016622562674094708,
      "loss": 1.4142,
      "step": 1070
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00016605153203342617,
      "loss": 1.3637,
      "step": 1075
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00016587743732590532,
      "loss": 1.2748,
      "step": 1080
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001657033426183844,
      "loss": 1.4044,
      "step": 1085
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00016552924791086353,
      "loss": 1.3374,
      "step": 1090
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00016535515320334262,
      "loss": 1.3647,
      "step": 1095
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00016518105849582171,
      "loss": 1.4259,
      "step": 1100
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00016500696378830086,
      "loss": 1.2926,
      "step": 1105
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00016483286908077995,
      "loss": 1.4621,
      "step": 1110
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00016465877437325905,
      "loss": 1.3746,
      "step": 1115
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00016448467966573817,
      "loss": 1.4036,
      "step": 1120
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00016431058495821729,
      "loss": 1.4062,
      "step": 1125
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001641364902506964,
      "loss": 1.348,
      "step": 1130
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001639623955431755,
      "loss": 1.3271,
      "step": 1135
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001637883008356546,
      "loss": 1.3663,
      "step": 1140
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001636142061281337,
      "loss": 1.3276,
      "step": 1145
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00016344011142061283,
      "loss": 1.2809,
      "step": 1150
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00016326601671309195,
      "loss": 1.3586,
      "step": 1155
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00016309192200557104,
      "loss": 1.3864,
      "step": 1160
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00016291782729805013,
      "loss": 1.3163,
      "step": 1165
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00016274373259052925,
      "loss": 1.3677,
      "step": 1170
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00016256963788300837,
      "loss": 1.2984,
      "step": 1175
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00016239554317548746,
      "loss": 1.4083,
      "step": 1180
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00016222144846796658,
      "loss": 1.445,
      "step": 1185
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00016204735376044568,
      "loss": 1.3306,
      "step": 1190
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001618732590529248,
      "loss": 1.4185,
      "step": 1195
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00016169916434540392,
      "loss": 1.3581,
      "step": 1200
    },
    {
      "epoch": 0.41,
      "eval_loss": 1.318132996559143,
      "eval_runtime": 737.5524,
      "eval_samples_per_second": 7.044,
      "eval_steps_per_second": 0.881,
      "step": 1200
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000161525069637883,
      "loss": 1.383,
      "step": 1205
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00016135097493036213,
      "loss": 1.4161,
      "step": 1210
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00016117688022284122,
      "loss": 1.3449,
      "step": 1215
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00016100278551532034,
      "loss": 1.3172,
      "step": 1220
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00016082869080779946,
      "loss": 1.3987,
      "step": 1225
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00016065459610027855,
      "loss": 1.3752,
      "step": 1230
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00016048050139275767,
      "loss": 1.4369,
      "step": 1235
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00016030640668523676,
      "loss": 1.3258,
      "step": 1240
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00016013231197771588,
      "loss": 1.3256,
      "step": 1245
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000159958217270195,
      "loss": 1.3357,
      "step": 1250
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001597841225626741,
      "loss": 1.3671,
      "step": 1255
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00015961002785515321,
      "loss": 1.3605,
      "step": 1260
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00015943593314763233,
      "loss": 1.3404,
      "step": 1265
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00015926183844011143,
      "loss": 1.3915,
      "step": 1270
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00015908774373259055,
      "loss": 1.3559,
      "step": 1275
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00015891364902506964,
      "loss": 1.3285,
      "step": 1280
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00015873955431754876,
      "loss": 1.3949,
      "step": 1285
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00015856545961002788,
      "loss": 1.3825,
      "step": 1290
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00015839136490250697,
      "loss": 1.3211,
      "step": 1295
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001582172701949861,
      "loss": 1.332,
      "step": 1300
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00015804317548746518,
      "loss": 1.4379,
      "step": 1305
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001578690807799443,
      "loss": 1.3406,
      "step": 1310
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00015769498607242342,
      "loss": 1.3467,
      "step": 1315
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001575208913649025,
      "loss": 1.374,
      "step": 1320
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001573467966573816,
      "loss": 1.3525,
      "step": 1325
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00015717270194986072,
      "loss": 1.3739,
      "step": 1330
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00015699860724233984,
      "loss": 1.3458,
      "step": 1335
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00015682451253481896,
      "loss": 1.3588,
      "step": 1340
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00015665041782729806,
      "loss": 1.3362,
      "step": 1345
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00015647632311977715,
      "loss": 1.3553,
      "step": 1350
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00015630222841225627,
      "loss": 1.4328,
      "step": 1355
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001561281337047354,
      "loss": 1.2763,
      "step": 1360
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001559540389972145,
      "loss": 1.3359,
      "step": 1365
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001557799442896936,
      "loss": 1.3164,
      "step": 1370
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001556058495821727,
      "loss": 1.29,
      "step": 1375
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00015543175487465184,
      "loss": 1.4188,
      "step": 1380
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00015525766016713093,
      "loss": 1.3594,
      "step": 1385
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00015508356545961002,
      "loss": 1.3535,
      "step": 1390
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00015490947075208914,
      "loss": 1.3415,
      "step": 1395
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00015473537604456823,
      "loss": 1.3417,
      "step": 1400
    },
    {
      "epoch": 0.48,
      "eval_loss": 1.313808798789978,
      "eval_runtime": 733.0569,
      "eval_samples_per_second": 7.087,
      "eval_steps_per_second": 0.887,
      "step": 1400
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00015456128133704738,
      "loss": 1.3421,
      "step": 1405
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00015438718662952647,
      "loss": 1.3915,
      "step": 1410
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00015421309192200557,
      "loss": 1.3097,
      "step": 1415
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00015403899721448469,
      "loss": 1.2905,
      "step": 1420
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001538649025069638,
      "loss": 1.3719,
      "step": 1425
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00015369080779944292,
      "loss": 1.2958,
      "step": 1430
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00015351671309192202,
      "loss": 1.2922,
      "step": 1435
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001533426183844011,
      "loss": 1.3139,
      "step": 1440
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00015316852367688023,
      "loss": 1.3396,
      "step": 1445
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00015299442896935935,
      "loss": 1.2605,
      "step": 1450
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00015282033426183844,
      "loss": 1.4605,
      "step": 1455
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00015264623955431756,
      "loss": 1.4972,
      "step": 1460
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00015247214484679665,
      "loss": 1.3068,
      "step": 1465
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00015229805013927577,
      "loss": 1.3249,
      "step": 1470
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001521239554317549,
      "loss": 1.3316,
      "step": 1475
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00015194986072423398,
      "loss": 1.434,
      "step": 1480
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001517757660167131,
      "loss": 1.4266,
      "step": 1485
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001516016713091922,
      "loss": 1.3159,
      "step": 1490
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00015142757660167132,
      "loss": 1.2304,
      "step": 1495
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00015125348189415043,
      "loss": 1.3826,
      "step": 1500
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00015107938718662953,
      "loss": 1.4042,
      "step": 1505
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00015090529247910865,
      "loss": 1.335,
      "step": 1510
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00015073119777158774,
      "loss": 1.3166,
      "step": 1515
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00015055710306406686,
      "loss": 1.284,
      "step": 1520
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00015038300835654598,
      "loss": 1.2927,
      "step": 1525
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00015020891364902507,
      "loss": 1.4464,
      "step": 1530
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001500348189415042,
      "loss": 1.319,
      "step": 1535
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001498607242339833,
      "loss": 1.3213,
      "step": 1540
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001496866295264624,
      "loss": 1.4009,
      "step": 1545
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00014951253481894152,
      "loss": 1.3166,
      "step": 1550
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00014933844011142061,
      "loss": 1.3605,
      "step": 1555
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001491643454038997,
      "loss": 1.401,
      "step": 1560
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00014899025069637885,
      "loss": 1.3219,
      "step": 1565
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00014881615598885795,
      "loss": 1.3484,
      "step": 1570
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00014864206128133706,
      "loss": 1.3743,
      "step": 1575
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00014846796657381616,
      "loss": 1.3498,
      "step": 1580
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00014829387186629528,
      "loss": 1.2985,
      "step": 1585
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001481197771587744,
      "loss": 1.3355,
      "step": 1590
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001479456824512535,
      "loss": 1.3278,
      "step": 1595
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00014777158774373258,
      "loss": 1.3111,
      "step": 1600
    },
    {
      "epoch": 0.55,
      "eval_loss": 1.3110042810440063,
      "eval_runtime": 733.0309,
      "eval_samples_per_second": 7.087,
      "eval_steps_per_second": 0.887,
      "step": 1600
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001475974930362117,
      "loss": 1.3197,
      "step": 1605
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00014742339832869082,
      "loss": 1.4121,
      "step": 1610
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00014724930362116994,
      "loss": 1.34,
      "step": 1615
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00014707520891364903,
      "loss": 1.3669,
      "step": 1620
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00014690111420612812,
      "loss": 1.3248,
      "step": 1625
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00014672701949860724,
      "loss": 1.2567,
      "step": 1630
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00014655292479108636,
      "loss": 1.3399,
      "step": 1635
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00014637883008356548,
      "loss": 1.315,
      "step": 1640
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00014620473537604458,
      "loss": 1.2658,
      "step": 1645
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00014603064066852367,
      "loss": 1.3854,
      "step": 1650
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001458565459610028,
      "loss": 1.3889,
      "step": 1655
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001456824512534819,
      "loss": 1.3587,
      "step": 1660
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000145508356545961,
      "loss": 1.3507,
      "step": 1665
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00014533426183844012,
      "loss": 1.3647,
      "step": 1670
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001451601671309192,
      "loss": 1.2777,
      "step": 1675
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00014498607242339836,
      "loss": 1.3376,
      "step": 1680
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00014481197771587745,
      "loss": 1.2869,
      "step": 1685
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00014463788300835654,
      "loss": 1.2855,
      "step": 1690
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00014446378830083566,
      "loss": 1.3387,
      "step": 1695
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00014428969359331475,
      "loss": 1.3416,
      "step": 1700
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00014411559888579387,
      "loss": 1.3574,
      "step": 1705
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000143941504178273,
      "loss": 1.375,
      "step": 1710
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00014376740947075209,
      "loss": 1.3952,
      "step": 1715
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001435933147632312,
      "loss": 1.3429,
      "step": 1720
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00014341922005571032,
      "loss": 1.3726,
      "step": 1725
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00014324512534818942,
      "loss": 1.2442,
      "step": 1730
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00014307103064066854,
      "loss": 1.2478,
      "step": 1735
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00014289693593314763,
      "loss": 1.3317,
      "step": 1740
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00014272284122562675,
      "loss": 1.3172,
      "step": 1745
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00014254874651810587,
      "loss": 1.3594,
      "step": 1750
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00014237465181058496,
      "loss": 1.3597,
      "step": 1755
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00014220055710306408,
      "loss": 1.3468,
      "step": 1760
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00014202646239554317,
      "loss": 1.369,
      "step": 1765
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001418523676880223,
      "loss": 1.2807,
      "step": 1770
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001416782729805014,
      "loss": 1.3454,
      "step": 1775
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001415041782729805,
      "loss": 1.3576,
      "step": 1780
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00014133008356545962,
      "loss": 1.397,
      "step": 1785
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00014115598885793872,
      "loss": 1.2672,
      "step": 1790
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00014098189415041784,
      "loss": 1.3121,
      "step": 1795
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00014080779944289695,
      "loss": 1.3547,
      "step": 1800
    },
    {
      "epoch": 0.62,
      "eval_loss": 1.306809425354004,
      "eval_runtime": 733.2137,
      "eval_samples_per_second": 7.085,
      "eval_steps_per_second": 0.887,
      "step": 1800
    }
  ],
  "max_steps": 5844,
  "num_train_epochs": 2,
  "total_flos": 1.072077389955072e+17,
  "trial_name": null,
  "trial_params": null
}