{
  "best_metric": 0.3279295265674591,
  "best_model_checkpoint": "output/eminem/checkpoint-1365",
  "epoch": 3.0,
  "global_step": 1365,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.0194653534426477e-06,
      "loss": 0.6762,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.530415424531046e-07,
      "loss": 0.6579,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.675914059099763e-07,
      "loss": 0.7016,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.6345512013444254e-07,
      "loss": 0.6176,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.087595819659287e-08,
      "loss": 0.563,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0,
      "loss": 0.689,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.0875958196577634e-08,
      "loss": 0.6532,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.634551201344197e-07,
      "loss": 0.5922,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 3.6759140590974026e-07,
      "loss": 0.6565,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 6.530415424530588e-07,
      "loss": 0.7043,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.0194653534425943e-06,
      "loss": 0.597,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.4664261646975495e-06,
      "loss": 0.7246,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.993391324572832e-06,
      "loss": 0.639,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.5997328387288936e-06,
      "loss": 0.6834,
      "step": 70
    },
    {
      "epoch": 0.16,
      "learning_rate": 3.2847281185253694e-06,
      "loss": 0.6745,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.0475608421405796e-06,
      "loss": 0.5851,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.887321927404397e-06,
      "loss": 0.6805,
      "step": 85
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.803010615159864e-06,
      "loss": 0.6536,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 6.793535661893871e-06,
      "loss": 0.6119,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.857716640189427e-06,
      "loss": 0.6954,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.994285345464919e-06,
      "loss": 0.7077,
      "step": 105
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.0201887307313696e-05,
      "loss": 0.6852,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.147908340365762e-05,
      "loss": 0.6743,
      "step": 115
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.2824351575772418e-05,
      "loss": 0.7093,
      "step": 120
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.4236088642155879e-05,
      "loss": 0.696,
      "step": 125
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.5712612209063624e-05,
      "loss": 0.6607,
      "step": 130
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.7252162675462687e-05,
      "loss": 0.5847,
      "step": 135
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.8852905329964338e-05,
      "loss": 0.6638,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.051293253729783e-05,
      "loss": 0.6221,
      "step": 145
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.2230266011669234e-05,
      "loss": 0.5733,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 2.4002859174324688e-05,
      "loss": 0.6478,
      "step": 155
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.5828599592491126e-05,
      "loss": 0.5237,
      "step": 160
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.770531149681108e-05,
      "loss": 0.6559,
      "step": 165
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.9630758374242324e-05,
      "loss": 0.6755,
      "step": 170
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.1602645633354207e-05,
      "loss": 0.6611,
      "step": 175
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.3618623338835595e-05,
      "loss": 0.651,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.5676289011958925e-05,
      "loss": 0.7284,
      "step": 185
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.7773190493652644e-05,
      "loss": 0.6301,
      "step": 190
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.990682886679578e-05,
      "loss": 0.6188,
      "step": 195
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.2074661434217846e-05,
      "loss": 0.586,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.427410474888269e-05,
      "loss": 0.6809,
      "step": 205
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.650253769262196e-05,
      "loss": 0.6343,
      "step": 210
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.875730459979135e-05,
      "loss": 0.7333,
      "step": 215
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.103571842205178e-05,
      "loss": 0.6158,
      "step": 220
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.3335063930595955e-05,
      "loss": 0.6216,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.565260095192864e-05,
      "loss": 0.7031,
      "step": 230
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.7985567633386964e-05,
      "loss": 0.7186,
      "step": 235
    },
    {
      "epoch": 0.53,
      "learning_rate": 6.033118373448471e-05,
      "loss": 0.6841,
      "step": 240
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.268665394018899e-05,
      "loss": 0.6929,
      "step": 245
    },
    {
      "epoch": 0.55,
      "learning_rate": 6.504917119214232e-05,
      "loss": 0.8001,
      "step": 250
    },
    {
      "epoch": 0.56,
      "learning_rate": 6.741592003389098e-05,
      "loss": 0.6497,
      "step": 255
    },
    {
      "epoch": 0.57,
      "learning_rate": 6.978407996610794e-05,
      "loss": 0.6001,
      "step": 260
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.21508288078566e-05,
      "loss": 0.7792,
      "step": 265
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.451334605980994e-05,
      "loss": 0.6229,
      "step": 270
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.686881626551423e-05,
      "loss": 0.6103,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.921443236661197e-05,
      "loss": 0.6509,
      "step": 280
    },
    {
      "epoch": 0.63,
      "learning_rate": 8.15473990480703e-05,
      "loss": 0.7008,
      "step": 285
    },
    {
      "epoch": 0.64,
      "learning_rate": 8.3864936069403e-05,
      "loss": 0.6919,
      "step": 290
    },
    {
      "epoch": 0.65,
      "learning_rate": 8.616428157794718e-05,
      "loss": 0.7347,
      "step": 295
    },
    {
      "epoch": 0.66,
      "learning_rate": 8.844269540020762e-05,
      "loss": 0.7356,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 9.069746230737702e-05,
      "loss": 0.7,
      "step": 305
    },
    {
      "epoch": 0.68,
      "learning_rate": 9.29258952511163e-05,
      "loss": 0.6359,
      "step": 310
    },
    {
      "epoch": 0.69,
      "learning_rate": 9.512533856578116e-05,
      "loss": 0.7165,
      "step": 315
    },
    {
      "epoch": 0.7,
      "learning_rate": 9.729317113320324e-05,
      "loss": 0.7637,
      "step": 320
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.942680950634639e-05,
      "loss": 0.6223,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00010152371098804014,
      "loss": 0.5555,
      "step": 330
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00010358137666116348,
      "loss": 0.7219,
      "step": 335
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00010559735436664489,
      "loss": 0.7501,
      "step": 340
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001075692416257568,
      "loss": 0.7454,
      "step": 345
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00010949468850318805,
      "loss": 0.6956,
      "step": 350
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00011137140040750957,
      "loss": 0.7294,
      "step": 355
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00011319714082567451,
      "loss": 0.7416,
      "step": 360
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00011496973398832998,
      "loss": 0.6926,
      "step": 365
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00011668706746270142,
      "loss": 0.7841,
      "step": 370
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00011834709467003491,
      "loss": 0.7603,
      "step": 375
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00011994783732453659,
      "loss": 0.7249,
      "step": 380
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001214873877909357,
      "loss": 0.7231,
      "step": 385
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00012296391135784465,
      "loss": 0.7101,
      "step": 390
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012437564842422694,
      "loss": 0.7521,
      "step": 395
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00012572091659634178,
      "loss": 0.6694,
      "step": 400
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00012699811269268675,
      "loss": 0.6763,
      "step": 405
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00012820571465453455,
      "loss": 0.7881,
      "step": 410
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00012934228335981007,
      "loss": 0.7906,
      "step": 415
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013040646433810568,
      "loss": 0.7662,
      "step": 420
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013139698938483972,
      "loss": 0.7165,
      "step": 425
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013231267807259521,
      "loss": 0.7159,
      "step": 430
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013315243915785907,
      "loss": 0.7796,
      "step": 435
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001339152718814749,
      "loss": 0.8222,
      "step": 440
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001346002671612708,
      "loss": 0.7428,
      "step": 445
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00013520660867542692,
      "loss": 0.7597,
      "step": 450
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00013573357383530262,
      "loss": 0.8769,
      "step": 455
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.36263224482536316,
      "eval_runtime": 29.2619,
      "eval_samples_per_second": 22.008,
      "eval_steps_per_second": 2.768,
      "step": 455
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001361805346465572,
      "loss": 0.6009,
      "step": 460
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00013654695845754679,
      "loss": 0.6886,
      "step": 465
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00013683240859409016,
      "loss": 0.648,
      "step": 470
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001370365448798655,
      "loss": 0.6639,
      "step": 475
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013715912404180336,
      "loss": 0.6411,
      "step": 480
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001372,
      "loss": 0.5669,
      "step": 485
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00013715912404180345,
      "loss": 0.7041,
      "step": 490
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00013703654487986564,
      "loss": 0.7196,
      "step": 495
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00013683240859409013,
      "loss": 0.6656,
      "step": 500
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00013654695845754679,
      "loss": 0.7371,
      "step": 505
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00013618053464655754,
      "loss": 0.6728,
      "step": 510
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001357335738353026,
      "loss": 0.663,
      "step": 515
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00013520660867542687,
      "loss": 0.5962,
      "step": 520
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001346002671612713,
      "loss": 0.6391,
      "step": 525
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013391527188147485,
      "loss": 0.7195,
      "step": 530
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013315243915785902,
      "loss": 0.7751,
      "step": 535
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001323126780725959,
      "loss": 0.6413,
      "step": 540
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00013139698938484045,
      "loss": 0.7913,
      "step": 545
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001304064643381056,
      "loss": 0.7761,
      "step": 550
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00012934228335981002,
      "loss": 0.6472,
      "step": 555
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00012820571465453544,
      "loss": 0.6222,
      "step": 560
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001269981126926867,
      "loss": 0.6736,
      "step": 565
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00012572091659634172,
      "loss": 0.73,
      "step": 570
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.000124375648424228,
      "loss": 0.6426,
      "step": 575
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012296391135784457,
      "loss": 0.7043,
      "step": 580
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00012148738779093562,
      "loss": 0.7227,
      "step": 585
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011994783732453781,
      "loss": 0.7366,
      "step": 590
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011834709467003617,
      "loss": 0.7144,
      "step": 595
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011668706746270132,
      "loss": 0.6817,
      "step": 600
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011496973398833133,
      "loss": 0.6274,
      "step": 605
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011319714082567588,
      "loss": 0.6754,
      "step": 610
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011137140040750945,
      "loss": 0.6134,
      "step": 615
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00010949468850318951,
      "loss": 0.698,
      "step": 620
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00010756924162575829,
      "loss": 0.8638,
      "step": 625
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010559735436664478,
      "loss": 0.7123,
      "step": 630
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00010358137666116336,
      "loss": 0.666,
      "step": 635
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010152371098804174,
      "loss": 0.6977,
      "step": 640
    },
    {
      "epoch": 1.42,
      "learning_rate": 9.942680950634801e-05,
      "loss": 0.5854,
      "step": 645
    },
    {
      "epoch": 1.43,
      "learning_rate": 9.729317113320311e-05,
      "loss": 0.6888,
      "step": 650
    },
    {
      "epoch": 1.44,
      "learning_rate": 9.512533856578284e-05,
      "loss": 0.6905,
      "step": 655
    },
    {
      "epoch": 1.45,
      "learning_rate": 9.2925895251118e-05,
      "loss": 0.664,
      "step": 660
    },
    {
      "epoch": 1.46,
      "learning_rate": 9.069746230737689e-05,
      "loss": 0.7013,
      "step": 665
    },
    {
      "epoch": 1.47,
      "learning_rate": 8.844269540020936e-05,
      "loss": 0.6946,
      "step": 670
    },
    {
      "epoch": 1.48,
      "learning_rate": 8.616428157794893e-05,
      "loss": 0.7819,
      "step": 675
    },
    {
      "epoch": 1.49,
      "learning_rate": 8.386493606940288e-05,
      "loss": 0.6662,
      "step": 680
    },
    {
      "epoch": 1.51,
      "learning_rate": 8.154739904807017e-05,
      "loss": 0.5889,
      "step": 685
    },
    {
      "epoch": 1.52,
      "learning_rate": 7.921443236661376e-05,
      "loss": 0.7833,
      "step": 690
    },
    {
      "epoch": 1.53,
      "learning_rate": 7.686881626551602e-05,
      "loss": 0.7548,
      "step": 695
    },
    {
      "epoch": 1.54,
      "learning_rate": 7.45133460598098e-05,
      "loss": 0.6886,
      "step": 700
    },
    {
      "epoch": 1.55,
      "learning_rate": 7.215082880785842e-05,
      "loss": 0.7179,
      "step": 705
    },
    {
      "epoch": 1.56,
      "learning_rate": 6.978407996610975e-05,
      "loss": 0.745,
      "step": 710
    },
    {
      "epoch": 1.57,
      "learning_rate": 6.741592003389085e-05,
      "loss": 0.5811,
      "step": 715
    },
    {
      "epoch": 1.58,
      "learning_rate": 6.504917119214413e-05,
      "loss": 0.6962,
      "step": 720
    },
    {
      "epoch": 1.59,
      "learning_rate": 6.268665394019079e-05,
      "loss": 0.6763,
      "step": 725
    },
    {
      "epoch": 1.6,
      "learning_rate": 6.033118373448457e-05,
      "loss": 0.6247,
      "step": 730
    },
    {
      "epoch": 1.62,
      "learning_rate": 5.7985567633386836e-05,
      "loss": 0.7763,
      "step": 735
    },
    {
      "epoch": 1.63,
      "learning_rate": 5.5652600951930425e-05,
      "loss": 0.6239,
      "step": 740
    },
    {
      "epoch": 1.64,
      "learning_rate": 5.333506393059772e-05,
      "loss": 0.7218,
      "step": 745
    },
    {
      "epoch": 1.65,
      "learning_rate": 5.103571842205165e-05,
      "loss": 0.695,
      "step": 750
    },
    {
      "epoch": 1.66,
      "learning_rate": 4.8757304599793096e-05,
      "loss": 0.7938,
      "step": 755
    },
    {
      "epoch": 1.67,
      "learning_rate": 4.650253769262368e-05,
      "loss": 0.7333,
      "step": 760
    },
    {
      "epoch": 1.68,
      "learning_rate": 4.4274104748882565e-05,
      "loss": 0.7092,
      "step": 765
    },
    {
      "epoch": 1.69,
      "learning_rate": 4.2074661434219527e-05,
      "loss": 0.764,
      "step": 770
    },
    {
      "epoch": 1.7,
      "learning_rate": 3.9906828866797437e-05,
      "loss": 0.7929,
      "step": 775
    },
    {
      "epoch": 1.71,
      "learning_rate": 3.777319049365253e-05,
      "loss": 0.6747,
      "step": 780
    },
    {
      "epoch": 1.73,
      "learning_rate": 3.56762890119588e-05,
      "loss": 0.6921,
      "step": 785
    },
    {
      "epoch": 1.74,
      "learning_rate": 3.361862333883716e-05,
      "loss": 0.7049,
      "step": 790
    },
    {
      "epoch": 1.75,
      "learning_rate": 3.160264563335574e-05,
      "loss": 0.778,
      "step": 795
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.9630758374242215e-05,
      "loss": 0.6684,
      "step": 800
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.7705311496812532e-05,
      "loss": 0.6652,
      "step": 805
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.582859959249102e-05,
      "loss": 0.7384,
      "step": 810
    },
    {
      "epoch": 1.79,
      "learning_rate": 2.400285917432458e-05,
      "loss": 0.6104,
      "step": 815
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.2230266011670566e-05,
      "loss": 0.7144,
      "step": 820
    },
    {
      "epoch": 1.81,
      "learning_rate": 2.0512932537299123e-05,
      "loss": 0.5937,
      "step": 825
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.885290532996424e-05,
      "loss": 0.7779,
      "step": 830
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.7252162675462595e-05,
      "loss": 0.7421,
      "step": 835
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.571261220906478e-05,
      "loss": 0.7221,
      "step": 840
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.4236088642155802e-05,
      "loss": 0.757,
      "step": 845
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.2824351575772341e-05,
      "loss": 0.752,
      "step": 850
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.1479083403658627e-05,
      "loss": 0.743,
      "step": 855
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.0201887307313627e-05,
      "loss": 0.5773,
      "step": 860
    },
    {
      "epoch": 1.9,
      "learning_rate": 8.994285345464858e-06,
      "loss": 0.7125,
      "step": 865
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.857716640190273e-06,
      "loss": 0.6377,
      "step": 870
    },
    {
      "epoch": 1.92,
      "learning_rate": 6.793535661894656e-06,
      "loss": 0.7089,
      "step": 875
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.803010615159811e-06,
      "loss": 0.61,
      "step": 880
    },
    {
      "epoch": 1.95,
      "learning_rate": 4.887321927404351e-06,
      "loss": 0.696,
      "step": 885
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.047560842141189e-06,
      "loss": 0.6485,
      "step": 890
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.2847281185253237e-06,
      "loss": 0.6823,
      "step": 895
    },
    {
      "epoch": 1.98,
      "learning_rate": 2.599732838728863e-06,
      "loss": 0.7038,
      "step": 900
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.993391324573266e-06,
      "loss": 0.6816,
      "step": 905
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.4664261646975266e-06,
      "loss": 0.6658,
      "step": 910
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.3614741861820221,
      "eval_runtime": 29.3257,
      "eval_samples_per_second": 21.96,
      "eval_steps_per_second": 2.762,
      "step": 910
    },
    {
      "epoch": 2.01,
      "learning_rate": 1.0194653534425715e-06,
      "loss": 0.6519,
      "step": 915
    },
    {
      "epoch": 2.02,
      "learning_rate": 6.530415424533102e-07,
      "loss": 0.5683,
      "step": 920
    },
    {
      "epoch": 2.03,
      "learning_rate": 3.6759140590993064e-07,
      "loss": 0.6592,
      "step": 925
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.6345512013440448e-07,
      "loss": 0.5654,
      "step": 930
    },
    {
      "epoch": 2.05,
      "learning_rate": 4.0875958196577634e-08,
      "loss": 0.6149,
      "step": 935
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0,
      "loss": 0.6412,
      "step": 940
    },
    {
      "epoch": 2.08,
      "learning_rate": 4.0875958196600484e-08,
      "loss": 0.6781,
      "step": 945
    },
    {
      "epoch": 2.09,
      "learning_rate": 1.6345512013445016e-07,
      "loss": 0.6225,
      "step": 950
    },
    {
      "epoch": 2.1,
      "learning_rate": 3.675914059097936e-07,
      "loss": 0.5624,
      "step": 955
    },
    {
      "epoch": 2.11,
      "learning_rate": 6.530415424531273e-07,
      "loss": 0.6362,
      "step": 960
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.0194653534426706e-06,
      "loss": 0.598,
      "step": 965
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.4664261646972448e-06,
      "loss": 0.623,
      "step": 970
    },
    {
      "epoch": 2.14,
      "learning_rate": 1.9933913245729463e-06,
      "loss": 0.6036,
      "step": 975
    },
    {
      "epoch": 2.15,
      "learning_rate": 2.599732838729023e-06,
      "loss": 0.6551,
      "step": 980
    },
    {
      "epoch": 2.16,
      "learning_rate": 3.2847281185249125e-06,
      "loss": 0.674,
      "step": 985
    },
    {
      "epoch": 2.18,
      "learning_rate": 4.047560842140732e-06,
      "loss": 0.6451,
      "step": 990
    },
    {
      "epoch": 2.19,
      "learning_rate": 4.887321927404572e-06,
      "loss": 0.5867,
      "step": 995
    },
    {
      "epoch": 2.2,
      "learning_rate": 5.803010615159263e-06,
      "loss": 0.5721,
      "step": 1000
    },
    {
      "epoch": 2.21,
      "learning_rate": 6.7935356618940695e-06,
      "loss": 0.7243,
      "step": 1005
    },
    {
      "epoch": 2.22,
      "learning_rate": 7.857716640189648e-06,
      "loss": 0.6183,
      "step": 1010
    },
    {
      "epoch": 2.23,
      "learning_rate": 8.994285345464189e-06,
      "loss": 0.6326,
      "step": 1015
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.0201887307312919e-05,
      "loss": 0.6777,
      "step": 1020
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.147908340365788e-05,
      "loss": 0.5987,
      "step": 1025
    },
    {
      "epoch": 2.26,
      "learning_rate": 1.2824351575772692e-05,
      "loss": 0.6252,
      "step": 1030
    },
    {
      "epoch": 2.27,
      "learning_rate": 1.423608864215498e-05,
      "loss": 0.5721,
      "step": 1035
    },
    {
      "epoch": 2.29,
      "learning_rate": 1.571261220906393e-05,
      "loss": 0.5737,
      "step": 1040
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.7252162675463e-05,
      "loss": 0.7001,
      "step": 1045
    },
    {
      "epoch": 2.31,
      "learning_rate": 1.885290532996332e-05,
      "loss": 0.5738,
      "step": 1050
    },
    {
      "epoch": 2.32,
      "learning_rate": 2.0512932537298164e-05,
      "loss": 0.6935,
      "step": 1055
    },
    {
      "epoch": 2.33,
      "learning_rate": 2.2230266011669576e-05,
      "loss": 0.6562,
      "step": 1060
    },
    {
      "epoch": 2.34,
      "learning_rate": 2.400285917432356e-05,
      "loss": 0.6026,
      "step": 1065
    },
    {
      "epoch": 2.35,
      "learning_rate": 2.5828599592489968e-05,
      "loss": 0.5634,
      "step": 1070
    },
    {
      "epoch": 2.36,
      "learning_rate": 2.7705311496811458e-05,
      "loss": 0.6095,
      "step": 1075
    },
    {
      "epoch": 2.37,
      "learning_rate": 2.9630758374242713e-05,
      "loss": 0.6006,
      "step": 1080
    },
    {
      "epoch": 2.38,
      "learning_rate": 3.16026456333546e-05,
      "loss": 0.675,
      "step": 1085
    },
    {
      "epoch": 2.4,
      "learning_rate": 3.3618623338836e-05,
      "loss": 0.6409,
      "step": 1090
    },
    {
      "epoch": 2.41,
      "learning_rate": 3.567628901195933e-05,
      "loss": 0.5407,
      "step": 1095
    },
    {
      "epoch": 2.42,
      "learning_rate": 3.777319049365133e-05,
      "loss": 0.6891,
      "step": 1100
    },
    {
      "epoch": 2.43,
      "learning_rate": 3.990682886679622e-05,
      "loss": 0.6107,
      "step": 1105
    },
    {
      "epoch": 2.44,
      "learning_rate": 4.207466143421829e-05,
      "loss": 0.7285,
      "step": 1110
    },
    {
      "epoch": 2.45,
      "learning_rate": 4.42741047488813e-05,
      "loss": 0.6553,
      "step": 1115
    },
    {
      "epoch": 2.46,
      "learning_rate": 4.650253769262241e-05,
      "loss": 0.5883,
      "step": 1120
    },
    {
      "epoch": 2.47,
      "learning_rate": 4.87573045997918e-05,
      "loss": 0.6072,
      "step": 1125
    },
    {
      "epoch": 2.48,
      "learning_rate": 5.103571842205223e-05,
      "loss": 0.6408,
      "step": 1130
    },
    {
      "epoch": 2.49,
      "learning_rate": 5.333506393059641e-05,
      "loss": 0.6753,
      "step": 1135
    },
    {
      "epoch": 2.51,
      "learning_rate": 5.565260095192911e-05,
      "loss": 0.6189,
      "step": 1140
    },
    {
      "epoch": 2.52,
      "learning_rate": 5.7985567633387425e-05,
      "loss": 0.5952,
      "step": 1145
    },
    {
      "epoch": 2.53,
      "learning_rate": 6.033118373448324e-05,
      "loss": 0.6261,
      "step": 1150
    },
    {
      "epoch": 2.54,
      "learning_rate": 6.268665394018945e-05,
      "loss": 0.6251,
      "step": 1155
    },
    {
      "epoch": 2.55,
      "learning_rate": 6.504917119214278e-05,
      "loss": 0.6952,
      "step": 1160
    },
    {
      "epoch": 2.56,
      "learning_rate": 6.74159200338895e-05,
      "loss": 0.6817,
      "step": 1165
    },
    {
      "epoch": 2.57,
      "learning_rate": 6.978407996610841e-05,
      "loss": 0.7109,
      "step": 1170
    },
    {
      "epoch": 2.58,
      "learning_rate": 7.215082880785708e-05,
      "loss": 0.6167,
      "step": 1175
    },
    {
      "epoch": 2.59,
      "learning_rate": 7.451334605981042e-05,
      "loss": 0.6916,
      "step": 1180
    },
    {
      "epoch": 2.6,
      "learning_rate": 7.686881626551469e-05,
      "loss": 0.717,
      "step": 1185
    },
    {
      "epoch": 2.62,
      "learning_rate": 7.921443236661243e-05,
      "loss": 0.6463,
      "step": 1190
    },
    {
      "epoch": 2.63,
      "learning_rate": 8.154739904807078e-05,
      "loss": 0.6973,
      "step": 1195
    },
    {
      "epoch": 2.64,
      "learning_rate": 8.386493606940157e-05,
      "loss": 0.6248,
      "step": 1200
    },
    {
      "epoch": 2.65,
      "learning_rate": 8.616428157794764e-05,
      "loss": 0.5914,
      "step": 1205
    },
    {
      "epoch": 2.66,
      "learning_rate": 8.844269540020808e-05,
      "loss": 0.7203,
      "step": 1210
    },
    {
      "epoch": 2.67,
      "learning_rate": 9.069746230737563e-05,
      "loss": 0.6267,
      "step": 1215
    },
    {
      "epoch": 2.68,
      "learning_rate": 9.292589525111675e-05,
      "loss": 0.6014,
      "step": 1220
    },
    {
      "epoch": 2.69,
      "learning_rate": 9.512533856578159e-05,
      "loss": 0.648,
      "step": 1225
    },
    {
      "epoch": 2.7,
      "learning_rate": 9.729317113320367e-05,
      "loss": 0.7405,
      "step": 1230
    },
    {
      "epoch": 2.71,
      "learning_rate": 9.942680950634681e-05,
      "loss": 0.6092,
      "step": 1235
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.00010152371098804056,
      "loss": 0.7414,
      "step": 1240
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0001035813766611639,
      "loss": 0.6629,
      "step": 1245
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.00010559735436664364,
      "loss": 0.6391,
      "step": 1250
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.00010756924162575718,
      "loss": 0.6851,
      "step": 1255
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.00010949468850318844,
      "loss": 0.6383,
      "step": 1260
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00011137140040750841,
      "loss": 0.6092,
      "step": 1265
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.00011319714082567486,
      "loss": 0.7265,
      "step": 1270
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00011496973398833032,
      "loss": 0.7022,
      "step": 1275
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.00011668706746270174,
      "loss": 0.6906,
      "step": 1280
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.00011834709467003525,
      "loss": 0.7019,
      "step": 1285
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0001199478373245369,
      "loss": 0.7799,
      "step": 1290
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.00012148738779093598,
      "loss": 0.6424,
      "step": 1295
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.00012296391135784376,
      "loss": 0.6426,
      "step": 1300
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.00012437564842422724,
      "loss": 0.679,
      "step": 1305
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.00012572091659634205,
      "loss": 0.732,
      "step": 1310
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.00012699811269268599,
      "loss": 0.719,
      "step": 1315
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.00012820571465453477,
      "loss": 0.682,
      "step": 1320
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0001293422833598103,
      "loss": 0.715,
      "step": 1325
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.00013040646433810587,
      "loss": 0.59,
      "step": 1330
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00013139698938483988,
      "loss": 0.6825,
      "step": 1335
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.00013231267807259538,
      "loss": 0.7497,
      "step": 1340
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00013315243915785924,
      "loss": 0.7488,
      "step": 1345
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.00013391527188147444,
      "loss": 0.7079,
      "step": 1350
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.00013460026716127094,
      "loss": 0.6717,
      "step": 1355
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00013520660867542703,
      "loss": 0.6389,
      "step": 1360
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00013573357383530232,
      "loss": 0.6948,
      "step": 1365
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.3279295265674591,
      "eval_runtime": 8.375,
      "eval_samples_per_second": 76.179,
      "eval_steps_per_second": 9.552,
      "step": 1365
    }
  ],
  "max_steps": 1365,
  "num_train_epochs": 3,
  "total_flos": 1424956096512000.0,
  "trial_name": null,
  "trial_params": null
}