{
  "best_metric": 1.3277837038040161,
  "best_model_checkpoint": "outputs/checkpoint-800",
  "epoch": 0.2737850787132101,
  "global_step": 800,
  "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
    }
  ],
  "max_steps": 5844,
  "num_train_epochs": 2,
  "total_flos": 4.76478839980032e+16,
  "trial_name": null,
  "trial_params": null
}