{
  "best_metric": 1.3240652084350586,
  "best_model_checkpoint": "output/taylor-swift/checkpoint-1413",
  "epoch": 9.0,
  "global_step": 1413,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.00013686126352583852,
      "loss": 3.3494,
      "step": 5
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00013584839936279803,
      "loss": 3.1755,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00013417141025243517,
      "loss": 3.1276,
      "step": 15
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00013184685763435497,
      "loss": 3.1339,
      "step": 20
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00012889769809041896,
      "loss": 3.1666,
      "step": 25
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00012535305663245375,
      "loss": 2.8811,
      "step": 30
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00012124793907240209,
      "loss": 2.9824,
      "step": 35
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00011662288631546257,
      "loss": 2.9442,
      "step": 40
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00011152357399031441,
      "loss": 2.961,
      "step": 45
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000106000361370359,
      "loss": 2.7762,
      "step": 50
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00010010779404069628,
      "loss": 2.8665,
      "step": 55
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.390406522234693e-05,
      "loss": 2.9223,
      "step": 60
    },
    {
      "epoch": 0.41,
      "learning_rate": 8.745044107352033e-05,
      "loss": 2.8602,
      "step": 65
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.081065564347997e-05,
      "loss": 2.8085,
      "step": 70
    },
    {
      "epoch": 0.47,
      "learning_rate": 7.405028145425961e-05,
      "loss": 2.7651,
      "step": 75
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.723608192617619e-05,
      "loss": 2.7224,
      "step": 80
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.043535204238934e-05,
      "loss": 2.6702,
      "step": 85
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.371525376390658e-05,
      "loss": 2.8382,
      "step": 90
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.714215275827523e-05,
      "loss": 2.5947,
      "step": 95
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.078096299222862e-05,
      "loss": 2.7596,
      "step": 100
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.4694505660892814e-05,
      "loss": 2.8001,
      "step": 105
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.894288878457539e-05,
      "loss": 2.7797,
      "step": 110
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.358291360005225e-05,
      "loss": 2.6613,
      "step": 115
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.8667513608652705e-05,
      "loss": 2.6169,
      "step": 120
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.424523182093601e-05,
      "loss": 2.5101,
      "step": 125
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.0359741360532426e-05,
      "loss": 2.6278,
      "step": 130
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.049414161522035e-06,
      "loss": 2.8319,
      "step": 135
    },
    {
      "epoch": 0.89,
      "learning_rate": 4.346942018765275e-06,
      "loss": 2.7047,
      "step": 140
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.2790137335786513e-06,
      "loss": 2.7375,
      "step": 145
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.660515431675314e-07,
      "loss": 2.9128,
      "step": 150
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.2200943675939755e-07,
      "loss": 2.6662,
      "step": 155
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.5653560161590576,
      "eval_runtime": 2.784,
      "eval_samples_per_second": 76.868,
      "eval_steps_per_second": 9.698,
      "step": 158
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.4235350207093555e-08,
      "loss": 2.594,
      "step": 160
    },
    {
      "epoch": 1.04,
      "learning_rate": 6.633985999863723e-07,
      "loss": 2.722,
      "step": 165
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.94348327322787e-06,
      "loss": 2.6618,
      "step": 170
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.881847639061565e-06,
      "loss": 2.5415,
      "step": 175
    },
    {
      "epoch": 1.14,
      "learning_rate": 6.459348994545111e-06,
      "loss": 2.5807,
      "step": 180
    },
    {
      "epoch": 1.17,
      "learning_rate": 9.650532712235251e-06,
      "loss": 2.6543,
      "step": 185
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.3423883622425528e-05,
      "loss": 2.5415,
      "step": 190
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.7742137247474782e-05,
      "loss": 2.435,
      "step": 195
    },
    {
      "epoch": 1.27,
      "learning_rate": 2.256264781457008e-05,
      "loss": 2.629,
      "step": 200
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.783780941254068e-05,
      "loss": 2.4759,
      "step": 205
    },
    {
      "epoch": 1.33,
      "learning_rate": 3.3515526133505226e-05,
      "loss": 2.5917,
      "step": 210
    },
    {
      "epoch": 1.36,
      "learning_rate": 3.953972655637492e-05,
      "loss": 2.6353,
      "step": 215
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.585091749132818e-05,
      "loss": 2.6671,
      "step": 220
    },
    {
      "epoch": 1.42,
      "learning_rate": 5.238677151664272e-05,
      "loss": 2.4302,
      "step": 225
    },
    {
      "epoch": 1.46,
      "learning_rate": 5.908274250554988e-05,
      "loss": 2.65,
      "step": 230
    },
    {
      "epoch": 1.49,
      "learning_rate": 6.587270306435089e-05,
      "loss": 2.6803,
      "step": 235
    },
    {
      "epoch": 1.52,
      "learning_rate": 7.268959758664963e-05,
      "loss": 2.7479,
      "step": 240
    },
    {
      "epoch": 1.55,
      "learning_rate": 7.946610447433497e-05,
      "loss": 2.5183,
      "step": 245
    },
    {
      "epoch": 1.58,
      "learning_rate": 8.613530098541655e-05,
      "loss": 2.4577,
      "step": 250
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.263132414287828e-05,
      "loss": 2.6144,
      "step": 255
    },
    {
      "epoch": 1.65,
      "learning_rate": 9.889002117761157e-05,
      "loss": 2.3613,
      "step": 260
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0001048495830818497,
      "loss": 2.3438,
      "step": 265
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.000110451155016322,
      "loss": 2.5456,
      "step": 270
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00011563941754292792,
      "loss": 2.4388,
      "step": 275
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00012036313294285455,
      "loss": 2.337,
      "step": 280
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00012457565122486245,
      "loss": 2.4888,
      "step": 285
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00012823537082655537,
      "loss": 2.5507,
      "step": 290
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00013130614945888676,
      "loss": 2.4084,
      "step": 295
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001337576610365259,
      "loss": 2.5188,
      "step": 300
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001355656951691469,
      "loss": 2.4279,
      "step": 305
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013671239625595536,
      "loss": 2.4089,
      "step": 310
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0001371864398222265,
      "loss": 2.3992,
      "step": 315
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.427677631378174,
      "eval_runtime": 2.7859,
      "eval_samples_per_second": 76.814,
      "eval_steps_per_second": 9.691,
      "step": 316
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00013698314435640815,
      "loss": 2.4731,
      "step": 320
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013610451754331968,
      "loss": 2.5107,
      "step": 325
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013455923643686105,
      "loss": 2.2137,
      "step": 330
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00013236256176804074,
      "loss": 2.433,
      "step": 335
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00012953618723459046,
      "loss": 2.2366,
      "step": 340
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00012610802526053698,
      "loss": 2.2305,
      "step": 345
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0001221119313415056,
      "loss": 2.0334,
      "step": 350
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00011758736969803705,
      "loss": 2.2182,
      "step": 355
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00011257902353882629,
      "loss": 2.4565,
      "step": 360
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00010713635378280492,
      "loss": 2.3876,
      "step": 365
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00010131311059799552,
      "loss": 2.3244,
      "step": 370
    },
    {
      "epoch": 2.37,
      "learning_rate": 9.516680258103397e-05,
      "loss": 2.1224,
      "step": 375
    },
    {
      "epoch": 2.41,
      "learning_rate": 8.875812881958139e-05,
      "loss": 2.1287,
      "step": 380
    },
    {
      "epoch": 2.44,
      "learning_rate": 8.215037944640755e-05,
      "loss": 2.3755,
      "step": 385
    },
    {
      "epoch": 2.47,
      "learning_rate": 7.540881060509307e-05,
      "loss": 2.1973,
      "step": 390
    },
    {
      "epoch": 2.5,
      "learning_rate": 6.860000000000001e-05,
      "loss": 2.3247,
      "step": 395
    },
    {
      "epoch": 2.53,
      "learning_rate": 6.179118939490698e-05,
      "loss": 2.0219,
      "step": 400
    },
    {
      "epoch": 2.56,
      "learning_rate": 5.504962055359254e-05,
      "loss": 2.2227,
      "step": 405
    },
    {
      "epoch": 2.59,
      "learning_rate": 4.844187118041858e-05,
      "loss": 2.0213,
      "step": 410
    },
    {
      "epoch": 2.63,
      "learning_rate": 4.203319741896607e-05,
      "loss": 2.4335,
      "step": 415
    },
    {
      "epoch": 2.66,
      "learning_rate": 3.5886889402004514e-05,
      "loss": 2.1705,
      "step": 420
    },
    {
      "epoch": 2.69,
      "learning_rate": 3.006364621719512e-05,
      "loss": 2.0096,
      "step": 425
    },
    {
      "epoch": 2.72,
      "learning_rate": 2.462097646117378e-05,
      "loss": 2.233,
      "step": 430
    },
    {
      "epoch": 2.75,
      "learning_rate": 1.9612630301962937e-05,
      "loss": 2.2407,
      "step": 435
    },
    {
      "epoch": 2.78,
      "learning_rate": 1.508806865849441e-05,
      "loss": 2.1925,
      "step": 440
    },
    {
      "epoch": 2.82,
      "learning_rate": 1.1091974739463048e-05,
      "loss": 2.0939,
      "step": 445
    },
    {
      "epoch": 2.85,
      "learning_rate": 7.66381276540956e-06,
      "loss": 2.1105,
      "step": 450
    },
    {
      "epoch": 2.88,
      "learning_rate": 4.8374382319592885e-06,
      "loss": 2.1558,
      "step": 455
    },
    {
      "epoch": 2.91,
      "learning_rate": 2.6407635631389823e-06,
      "loss": 2.3444,
      "step": 460
    },
    {
      "epoch": 2.94,
      "learning_rate": 1.0954824566803356e-06,
      "loss": 2.0945,
      "step": 465
    },
    {
      "epoch": 2.97,
      "learning_rate": 2.168556435918659e-07,
      "loss": 1.9806,
      "step": 470
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.2620296478271484,
      "eval_runtime": 2.784,
      "eval_samples_per_second": 76.867,
      "eval_steps_per_second": 9.698,
      "step": 474
    },
    {
      "epoch": 3.01,
      "learning_rate": 1.3560177773502823e-08,
      "loss": 1.9753,
      "step": 475
    },
    {
      "epoch": 3.04,
      "learning_rate": 4.87603744044624e-07,
      "loss": 2.0561,
      "step": 480
    },
    {
      "epoch": 3.07,
      "learning_rate": 1.6343048308530896e-06,
      "loss": 2.0054,
      "step": 485
    },
    {
      "epoch": 3.1,
      "learning_rate": 3.4423389634741234e-06,
      "loss": 2.0684,
      "step": 490
    },
    {
      "epoch": 3.13,
      "learning_rate": 5.893850541113203e-06,
      "loss": 1.8837,
      "step": 495
    },
    {
      "epoch": 3.16,
      "learning_rate": 8.964629173444626e-06,
      "loss": 1.9202,
      "step": 500
    },
    {
      "epoch": 3.2,
      "learning_rate": 1.2624348775137553e-05,
      "loss": 1.9576,
      "step": 505
    },
    {
      "epoch": 3.23,
      "learning_rate": 1.6836867057145347e-05,
      "loss": 2.1642,
      "step": 510
    },
    {
      "epoch": 3.26,
      "learning_rate": 2.156058245707209e-05,
      "loss": 2.2199,
      "step": 515
    },
    {
      "epoch": 3.29,
      "learning_rate": 2.6748844983678075e-05,
      "loss": 2.24,
      "step": 520
    },
    {
      "epoch": 3.32,
      "learning_rate": 3.235041691815028e-05,
      "loss": 2.2476,
      "step": 525
    },
    {
      "epoch": 3.35,
      "learning_rate": 3.830997882238844e-05,
      "loss": 1.9431,
      "step": 530
    },
    {
      "epoch": 3.39,
      "learning_rate": 4.456867585712155e-05,
      "loss": 1.9221,
      "step": 535
    },
    {
      "epoch": 3.42,
      "learning_rate": 5.1064699014583464e-05,
      "loss": 1.8139,
      "step": 540
    },
    {
      "epoch": 3.45,
      "learning_rate": 5.773389552566511e-05,
      "loss": 2.0033,
      "step": 545
    },
    {
      "epoch": 3.48,
      "learning_rate": 6.451040241335031e-05,
      "loss": 2.0651,
      "step": 550
    },
    {
      "epoch": 3.51,
      "learning_rate": 7.132729693564907e-05,
      "loss": 2.034,
      "step": 555
    },
    {
      "epoch": 3.54,
      "learning_rate": 7.811725749444997e-05,
      "loss": 1.8939,
      "step": 560
    },
    {
      "epoch": 3.58,
      "learning_rate": 8.481322848335718e-05,
      "loss": 2.2029,
      "step": 565
    },
    {
      "epoch": 3.61,
      "learning_rate": 9.134908250867189e-05,
      "loss": 1.9256,
      "step": 570
    },
    {
      "epoch": 3.64,
      "learning_rate": 9.766027344362499e-05,
      "loss": 1.9943,
      "step": 575
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.00010368447386649474,
      "loss": 1.9552,
      "step": 580
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.00010936219058745934,
      "loss": 1.9243,
      "step": 585
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.00011463735218542983,
      "loss": 1.8552,
      "step": 590
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.00011945786275252523,
      "loss": 2.067,
      "step": 595
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.00012377611637757444,
      "loss": 2.0837,
      "step": 600
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0001275494672877647,
      "loss": 2.0373,
      "step": 605
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.0001307406510054549,
      "loss": 1.8866,
      "step": 610
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.0001333181523609384,
      "loss": 2.045,
      "step": 615
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.00013525651672677215,
      "loss": 2.0499,
      "step": 620
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.00013653660140001365,
      "loss": 1.9574,
      "step": 625
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.0001371457646497929,
      "loss": 2.1066,
      "step": 630
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.209007978439331,
      "eval_runtime": 2.7857,
      "eval_samples_per_second": 76.822,
      "eval_steps_per_second": 9.692,
      "step": 632
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.0001370779905632406,
      "loss": 1.8936,
      "step": 635
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.00013633394845683248,
      "loss": 1.9616,
      "step": 640
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00013492098626642133,
      "loss": 1.7865,
      "step": 645
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.00013285305798123475,
      "loss": 1.8786,
      "step": 650
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.00013015058583847798,
      "loss": 1.9233,
      "step": 655
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.00012684025863946756,
      "loss": 1.8903,
      "step": 660
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.000122954768179064,
      "loss": 1.895,
      "step": 665
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.00011853248639134728,
      "loss": 1.8842,
      "step": 670
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.00011361708639994783,
      "loss": 1.7602,
      "step": 675
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.00010825711121542465,
      "loss": 1.7436,
      "step": 680
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.00010250549433910721,
      "loss": 1.8129,
      "step": 685
    },
    {
      "epoch": 4.37,
      "learning_rate": 9.64190370077714e-05,
      "loss": 1.7891,
      "step": 690
    },
    {
      "epoch": 4.4,
      "learning_rate": 9.005784724172477e-05,
      "loss": 1.8476,
      "step": 695
    },
    {
      "epoch": 4.43,
      "learning_rate": 8.348474623609351e-05,
      "loss": 2.0649,
      "step": 700
    },
    {
      "epoch": 4.46,
      "learning_rate": 7.676464795761073e-05,
      "loss": 1.9673,
      "step": 705
    },
    {
      "epoch": 4.49,
      "learning_rate": 6.996391807382385e-05,
      "loss": 2.0106,
      "step": 710
    },
    {
      "epoch": 4.53,
      "learning_rate": 6.314971854574042e-05,
      "loss": 1.8144,
      "step": 715
    },
    {
      "epoch": 4.56,
      "learning_rate": 5.638934435652005e-05,
      "loss": 1.8997,
      "step": 720
    },
    {
      "epoch": 4.59,
      "learning_rate": 4.974955892647975e-05,
      "loss": 1.6943,
      "step": 725
    },
    {
      "epoch": 4.62,
      "learning_rate": 4.329593477765313e-05,
      "loss": 1.784,
      "step": 730
    },
    {
      "epoch": 4.65,
      "learning_rate": 3.709220595930377e-05,
      "loss": 1.7719,
      "step": 735
    },
    {
      "epoch": 4.68,
      "learning_rate": 3.119963862964102e-05,
      "loss": 1.6203,
      "step": 740
    },
    {
      "epoch": 4.72,
      "learning_rate": 2.5676426009685593e-05,
      "loss": 1.7432,
      "step": 745
    },
    {
      "epoch": 4.75,
      "learning_rate": 2.0577113684537407e-05,
      "loss": 1.6835,
      "step": 750
    },
    {
      "epoch": 4.78,
      "learning_rate": 1.5952060927597964e-05,
      "loss": 1.8013,
      "step": 755
    },
    {
      "epoch": 4.81,
      "learning_rate": 1.1846943367546308e-05,
      "loss": 1.6429,
      "step": 760
    },
    {
      "epoch": 4.84,
      "learning_rate": 8.302301909581063e-06,
      "loss": 1.8303,
      "step": 765
    },
    {
      "epoch": 4.87,
      "learning_rate": 5.353142365645029e-06,
      "loss": 1.6484,
      "step": 770
    },
    {
      "epoch": 4.91,
      "learning_rate": 3.0285897475648074e-06,
      "loss": 1.7701,
      "step": 775
    },
    {
      "epoch": 4.94,
      "learning_rate": 1.3516006372019799e-06,
      "loss": 1.7971,
      "step": 780
    },
    {
      "epoch": 4.97,
      "learning_rate": 3.3873647416147947e-07,
      "loss": 1.8325,
      "step": 785
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 1.7255,
      "step": 790
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.1195662021636963,
      "eval_runtime": 2.7825,
      "eval_samples_per_second": 76.91,
      "eval_steps_per_second": 9.704,
      "step": 790
    },
    {
      "epoch": 4.97,
      "learning_rate": 3.303277502872983e-07,
      "loss": 1.9264,
      "step": 795
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 1.9314,
      "step": 800
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.466734766960144,
      "eval_runtime": 9.3674,
      "eval_samples_per_second": 21.351,
      "eval_steps_per_second": 2.669,
      "step": 800
    },
    {
      "epoch": 5.03,
      "learning_rate": 3.303277502872907e-07,
      "loss": 1.908,
      "step": 805
    },
    {
      "epoch": 5.06,
      "learning_rate": 1.3181297643383773e-06,
      "loss": 1.8545,
      "step": 810
    },
    {
      "epoch": 5.09,
      "learning_rate": 2.9538929687704367e-06,
      "loss": 2.0338,
      "step": 815
    },
    {
      "epoch": 5.12,
      "learning_rate": 5.221864069725677e-06,
      "loss": 1.7718,
      "step": 820
    },
    {
      "epoch": 5.16,
      "learning_rate": 8.100201265702767e-06,
      "loss": 1.8307,
      "step": 825
    },
    {
      "epoch": 5.19,
      "learning_rate": 1.1561184596045435e-05,
      "loss": 1.8088,
      "step": 830
    },
    {
      "epoch": 5.22,
      "learning_rate": 1.5571482899316272e-05,
      "loss": 1.6236,
      "step": 835
    },
    {
      "epoch": 5.25,
      "learning_rate": 2.0092474810602853e-05,
      "loss": 2.1289,
      "step": 840
    },
    {
      "epoch": 5.28,
      "learning_rate": 2.5080620706373914e-05,
      "loss": 1.4544,
      "step": 845
    },
    {
      "epoch": 5.31,
      "learning_rate": 3.048788201485526e-05,
      "loss": 2.0407,
      "step": 850
    },
    {
      "epoch": 5.34,
      "learning_rate": 3.6262183853736515e-05,
      "loss": 1.8147,
      "step": 855
    },
    {
      "epoch": 5.38,
      "learning_rate": 4.2347916539754777e-05,
      "loss": 1.8843,
      "step": 860
    },
    {
      "epoch": 5.41,
      "learning_rate": 4.868647114034379e-05,
      "loss": 1.8188,
      "step": 865
    },
    {
      "epoch": 5.44,
      "learning_rate": 5.521680390969348e-05,
      "loss": 1.8368,
      "step": 870
    },
    {
      "epoch": 5.47,
      "learning_rate": 6.1876024173392e-05,
      "loss": 1.8814,
      "step": 875
    },
    {
      "epoch": 5.5,
      "learning_rate": 6.859999999999984e-05,
      "loss": 1.9456,
      "step": 880
    },
    {
      "epoch": 5.53,
      "learning_rate": 7.532397582660791e-05,
      "loss": 1.6534,
      "step": 885
    },
    {
      "epoch": 5.56,
      "learning_rate": 8.198319609030643e-05,
      "loss": 1.8587,
      "step": 890
    },
    {
      "epoch": 5.59,
      "learning_rate": 8.851352885965613e-05,
      "loss": 2.0249,
      "step": 895
    },
    {
      "epoch": 5.62,
      "learning_rate": 9.485208346024515e-05,
      "loss": 1.9597,
      "step": 900
    },
    {
      "epoch": 5.66,
      "learning_rate": 0.00010093781614626339,
      "loss": 1.499,
      "step": 905
    },
    {
      "epoch": 5.69,
      "learning_rate": 0.00010671211798514466,
      "loss": 1.6634,
      "step": 910
    },
    {
      "epoch": 5.72,
      "learning_rate": 0.00011211937929362601,
      "loss": 1.789,
      "step": 915
    },
    {
      "epoch": 5.75,
      "learning_rate": 0.00011710752518939709,
      "loss": 1.6422,
      "step": 920
    },
    {
      "epoch": 5.78,
      "learning_rate": 0.00012162851710068368,
      "loss": 1.83,
      "step": 925
    },
    {
      "epoch": 5.81,
      "learning_rate": 0.00012563881540395453,
      "loss": 1.8398,
      "step": 930
    },
    {
      "epoch": 5.84,
      "learning_rate": 0.0001290997987342972,
      "loss": 1.8865,
      "step": 935
    },
    {
      "epoch": 5.88,
      "learning_rate": 0.0001319781359302743,
      "loss": 2.0384,
      "step": 940
    },
    {
      "epoch": 5.91,
      "learning_rate": 0.00013424610703122953,
      "loss": 1.8054,
      "step": 945
    },
    {
      "epoch": 5.94,
      "learning_rate": 0.0001358818702356616,
      "loss": 1.6484,
      "step": 950
    },
    {
      "epoch": 5.97,
      "learning_rate": 0.0001368696722497127,
      "loss": 2.0007,
      "step": 955
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.0001372,
      "loss": 1.8572,
      "step": 960
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.5031535625457764,
      "eval_runtime": 9.4961,
      "eval_samples_per_second": 21.061,
      "eval_steps_per_second": 2.633,
      "step": 960
    },
    {
      "epoch": 6.03,
      "learning_rate": 0.00013686967224971273,
      "loss": 1.4942,
      "step": 965
    },
    {
      "epoch": 6.06,
      "learning_rate": 0.00013588187023566163,
      "loss": 1.782,
      "step": 970
    },
    {
      "epoch": 6.09,
      "learning_rate": 0.00013424610703122958,
      "loss": 1.8084,
      "step": 975
    },
    {
      "epoch": 6.12,
      "learning_rate": 0.00013197813593027432,
      "loss": 1.7091,
      "step": 980
    },
    {
      "epoch": 6.16,
      "learning_rate": 0.00012909979873429724,
      "loss": 1.8472,
      "step": 985
    },
    {
      "epoch": 6.19,
      "learning_rate": 0.00012563881540395458,
      "loss": 1.7417,
      "step": 990
    },
    {
      "epoch": 6.22,
      "learning_rate": 0.00012162851710068373,
      "loss": 1.6717,
      "step": 995
    },
    {
      "epoch": 6.25,
      "learning_rate": 0.00011710752518939715,
      "loss": 1.6891,
      "step": 1000
    },
    {
      "epoch": 6.28,
      "learning_rate": 0.00011211937929362609,
      "loss": 1.8756,
      "step": 1005
    },
    {
      "epoch": 6.31,
      "learning_rate": 0.00010671211798514474,
      "loss": 1.6079,
      "step": 1010
    },
    {
      "epoch": 6.34,
      "learning_rate": 0.00010093781614626349,
      "loss": 1.7571,
      "step": 1015
    },
    {
      "epoch": 6.38,
      "learning_rate": 9.485208346024524e-05,
      "loss": 1.3666,
      "step": 1020
    },
    {
      "epoch": 6.41,
      "learning_rate": 8.851352885965622e-05,
      "loss": 1.7333,
      "step": 1025
    },
    {
      "epoch": 6.44,
      "learning_rate": 8.198319609030653e-05,
      "loss": 1.4846,
      "step": 1030
    },
    {
      "epoch": 6.47,
      "learning_rate": 7.532397582660802e-05,
      "loss": 1.4929,
      "step": 1035
    },
    {
      "epoch": 6.5,
      "learning_rate": 6.859999999999993e-05,
      "loss": 1.7269,
      "step": 1040
    },
    {
      "epoch": 6.53,
      "learning_rate": 6.18760241733921e-05,
      "loss": 1.5586,
      "step": 1045
    },
    {
      "epoch": 6.56,
      "learning_rate": 5.5216803909693576e-05,
      "loss": 1.7124,
      "step": 1050
    },
    {
      "epoch": 6.59,
      "learning_rate": 4.868647114034389e-05,
      "loss": 1.7847,
      "step": 1055
    },
    {
      "epoch": 6.62,
      "learning_rate": 4.2347916539754865e-05,
      "loss": 1.5791,
      "step": 1060
    },
    {
      "epoch": 6.66,
      "learning_rate": 3.62621838537366e-05,
      "loss": 1.71,
      "step": 1065
    },
    {
      "epoch": 6.69,
      "learning_rate": 3.0487882014855342e-05,
      "loss": 1.6788,
      "step": 1070
    },
    {
      "epoch": 6.72,
      "learning_rate": 2.5080620706373995e-05,
      "loss": 1.6755,
      "step": 1075
    },
    {
      "epoch": 6.75,
      "learning_rate": 2.009247481060292e-05,
      "loss": 1.4464,
      "step": 1080
    },
    {
      "epoch": 6.78,
      "learning_rate": 1.5571482899316333e-05,
      "loss": 1.7238,
      "step": 1085
    },
    {
      "epoch": 6.81,
      "learning_rate": 1.1561184596045489e-05,
      "loss": 1.4748,
      "step": 1090
    },
    {
      "epoch": 6.84,
      "learning_rate": 8.100201265702821e-06,
      "loss": 1.488,
      "step": 1095
    },
    {
      "epoch": 6.88,
      "learning_rate": 5.221864069725715e-06,
      "loss": 1.545,
      "step": 1100
    },
    {
      "epoch": 6.91,
      "learning_rate": 2.9538929687704672e-06,
      "loss": 1.5979,
      "step": 1105
    },
    {
      "epoch": 6.94,
      "learning_rate": 1.3181297643383925e-06,
      "loss": 1.7046,
      "step": 1110
    },
    {
      "epoch": 6.97,
      "learning_rate": 3.303277502872983e-07,
      "loss": 1.5848,
      "step": 1115
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.0,
      "loss": 1.6901,
      "step": 1120
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.4377235174179077,
      "eval_runtime": 9.5035,
      "eval_samples_per_second": 21.045,
      "eval_steps_per_second": 2.631,
      "step": 1120
    },
    {
      "epoch": 7.17,
      "learning_rate": 9.076596574074994e-06,
      "loss": 1.4269,
      "step": 1125
    },
    {
      "epoch": 7.2,
      "learning_rate": 1.2780475216607764e-05,
      "loss": 1.559,
      "step": 1130
    },
    {
      "epoch": 7.23,
      "learning_rate": 1.7042649548372873e-05,
      "loss": 1.529,
      "step": 1135
    },
    {
      "epoch": 7.26,
      "learning_rate": 2.182049015671568e-05,
      "loss": 1.6687,
      "step": 1140
    },
    {
      "epoch": 7.29,
      "learning_rate": 2.7066210038327817e-05,
      "loss": 1.5638,
      "step": 1145
    },
    {
      "epoch": 7.32,
      "learning_rate": 3.2727342555268683e-05,
      "loss": 1.5554,
      "step": 1150
    },
    {
      "epoch": 7.36,
      "learning_rate": 3.874726619575346e-05,
      "loss": 1.317,
      "step": 1155
    },
    {
      "epoch": 7.39,
      "learning_rate": 4.5065770891153554e-05,
      "loss": 1.679,
      "step": 1160
    },
    {
      "epoch": 7.42,
      "learning_rate": 5.161966022502662e-05,
      "loss": 1.6683,
      "step": 1165
    },
    {
      "epoch": 7.45,
      "learning_rate": 5.834338351099537e-05,
      "loss": 1.4034,
      "step": 1170
    },
    {
      "epoch": 7.48,
      "learning_rate": 6.516969141756308e-05,
      "loss": 1.6013,
      "step": 1175
    },
    {
      "epoch": 7.52,
      "learning_rate": 7.20303085824368e-05,
      "loss": 1.5516,
      "step": 1180
    },
    {
      "epoch": 7.55,
      "learning_rate": 7.885661648900452e-05,
      "loss": 1.5248,
      "step": 1185
    },
    {
      "epoch": 7.58,
      "learning_rate": 8.558033977497326e-05,
      "loss": 1.3379,
      "step": 1190
    },
    {
      "epoch": 7.61,
      "learning_rate": 9.213422910884634e-05,
      "loss": 1.3994,
      "step": 1195
    },
    {
      "epoch": 7.64,
      "learning_rate": 9.845273380424641e-05,
      "loss": 1.4434,
      "step": 1200
    },
    {
      "epoch": 7.68,
      "learning_rate": 0.00010447265744473122,
      "loss": 1.6187,
      "step": 1205
    },
    {
      "epoch": 7.71,
      "learning_rate": 0.00011013378996167208,
      "loss": 1.5693,
      "step": 1210
    },
    {
      "epoch": 7.74,
      "learning_rate": 0.00011537950984328424,
      "loss": 1.4006,
      "step": 1215
    },
    {
      "epoch": 7.77,
      "learning_rate": 0.00012015735045162704,
      "loss": 1.7153,
      "step": 1220
    },
    {
      "epoch": 7.8,
      "learning_rate": 0.0001244195247833922,
      "loss": 1.5277,
      "step": 1225
    },
    {
      "epoch": 7.83,
      "learning_rate": 0.00012812340342592494,
      "loss": 1.5052,
      "step": 1230
    },
    {
      "epoch": 7.87,
      "learning_rate": 0.0001312319409280581,
      "loss": 1.548,
      "step": 1235
    },
    {
      "epoch": 7.9,
      "learning_rate": 0.00013371404632128166,
      "loss": 1.4896,
      "step": 1240
    },
    {
      "epoch": 7.93,
      "learning_rate": 0.0001355448940853745,
      "loss": 1.5506,
      "step": 1245
    },
    {
      "epoch": 7.96,
      "learning_rate": 0.00013670617244827653,
      "loss": 1.6902,
      "step": 1250
    },
    {
      "epoch": 7.99,
      "learning_rate": 0.0001371862665367597,
      "loss": 1.5112,
      "step": 1255
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.352002739906311,
      "eval_runtime": 5.5761,
      "eval_samples_per_second": 40.889,
      "eval_steps_per_second": 5.201,
      "step": 1256
    },
    {
      "epoch": 8.03,
      "learning_rate": 0.00013698037454606005,
      "loss": 1.3097,
      "step": 1260
    },
    {
      "epoch": 8.06,
      "learning_rate": 0.0001360905557665658,
      "loss": 1.5119,
      "step": 1265
    },
    {
      "epoch": 8.09,
      "learning_rate": 0.00013452570998720767,
      "loss": 1.2738,
      "step": 1270
    },
    {
      "epoch": 8.12,
      "learning_rate": 0.00013230148848155559,
      "loss": 1.2764,
      "step": 1275
    },
    {
      "epoch": 8.15,
      "learning_rate": 0.00012944013746692,
      "loss": 1.2347,
      "step": 1280
    },
    {
      "epoch": 8.18,
      "learning_rate": 0.00012597027560214946,
      "loss": 1.4534,
      "step": 1285
    },
    {
      "epoch": 8.22,
      "learning_rate": 0.00012192660774954517,
      "loss": 1.4193,
      "step": 1290
    },
    {
      "epoch": 8.25,
      "learning_rate": 0.00011734957786379066,
      "loss": 1.5185,
      "step": 1295
    },
    {
      "epoch": 8.28,
      "learning_rate": 0.00011228496447963,
      "loss": 1.5225,
      "step": 1300
    },
    {
      "epoch": 8.31,
      "learning_rate": 0.0001067834228441478,
      "loss": 1.8013,
      "step": 1305
    },
    {
      "epoch": 8.34,
      "learning_rate": 0.00010089997827314661,
      "loss": 1.4035,
      "step": 1310
    },
    {
      "epoch": 8.38,
      "learning_rate": 9.469347579898059e-05,
      "loss": 1.4431,
      "step": 1315
    },
    {
      "epoch": 8.41,
      "learning_rate": 8.82259916143434e-05,
      "loss": 1.3074,
      "step": 1320
    },
    {
      "epoch": 8.44,
      "learning_rate": 8.1562212198643e-05,
      "loss": 1.3587,
      "step": 1325
    },
    {
      "epoch": 8.47,
      "learning_rate": 7.476878733681043e-05,
      "loss": 1.5297,
      "step": 1330
    },
    {
      "epoch": 8.5,
      "learning_rate": 6.791366350152217e-05,
      "loss": 1.2815,
      "step": 1335
    },
    {
      "epoch": 8.54,
      "learning_rate": 6.106540426620946e-05,
      "loss": 1.5607,
      "step": 1340
    },
    {
      "epoch": 8.57,
      "learning_rate": 5.4292504545952105e-05,
      "loss": 1.1765,
      "step": 1345
    },
    {
      "epoch": 8.6,
      "learning_rate": 4.766270552507704e-05,
      "loss": 1.5363,
      "step": 1350
    },
    {
      "epoch": 8.63,
      "learning_rate": 4.124231712342338e-05,
      "loss": 1.4107,
      "step": 1355
    },
    {
      "epoch": 8.66,
      "learning_rate": 3.509555477782507e-05,
      "loss": 1.4608,
      "step": 1360
    },
    {
      "epoch": 8.69,
      "learning_rate": 2.928389717219465e-05,
      "loss": 1.3783,
      "step": 1365
    },
    {
      "epoch": 8.73,
      "learning_rate": 2.386547134005838e-05,
      "loss": 1.2348,
      "step": 1370
    },
    {
      "epoch": 8.76,
      "learning_rate": 1.889447128962836e-05,
      "loss": 1.5068,
      "step": 1375
    },
    {
      "epoch": 8.79,
      "learning_rate": 1.4420615966203568e-05,
      "loss": 1.3345,
      "step": 1380
    },
    {
      "epoch": 8.82,
      "learning_rate": 1.0488651973253671e-05,
      "loss": 1.2429,
      "step": 1385
    },
    {
      "epoch": 8.85,
      "learning_rate": 7.13790602586542e-06,
      "loss": 1.3129,
      "step": 1390
    },
    {
      "epoch": 8.89,
      "learning_rate": 4.401891612830206e-06,
      "loss": 1.2724,
      "step": 1395
    },
    {
      "epoch": 8.92,
      "learning_rate": 2.307973801450113e-06,
      "loss": 1.3608,
      "step": 1400
    },
    {
      "epoch": 8.95,
      "learning_rate": 8.770955376250992e-07,
      "loss": 1.4328,
      "step": 1405
    },
    {
      "epoch": 8.98,
      "learning_rate": 1.2356817870921626e-07,
      "loss": 1.3714,
      "step": 1410
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.3240652084350586,
      "eval_runtime": 5.3842,
      "eval_samples_per_second": 42.346,
      "eval_steps_per_second": 5.386,
      "step": 1413
    }
  ],
  "max_steps": 1884,
  "num_train_epochs": 12,
  "total_flos": 1473164476416000.0,
  "trial_name": null,
  "trial_params": null
}