{
  "best_metric": 0.16962459683418274,
  "best_model_checkpoint": "output/eminem/checkpoint-459",
  "epoch": 1.0,
  "global_step": 459,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0001295937875943477,
      "loss": 0.4175,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001306389012238537,
      "loss": 0.4452,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013161040580202325,
      "loss": 0.4523,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00013250714864031736,
      "loss": 0.4272,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00013332806575487712,
      "loss": 0.4701,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013407218312893365,
      "loss": 0.4872,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00013473861786848294,
      "loss": 0.4231,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00013532657924983333,
      "loss": 0.4708,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001358353696578007,
      "loss": 0.5047,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00013626438541342652,
      "loss": 0.4957,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00013661311749024328,
      "loss": 0.4333,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001368811521182315,
      "loss": 0.4417,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00013706817127475857,
      "loss": 0.4644,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00013717395306191163,
      "loss": 0.5235,
      "step": 70
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00013719837196977938,
      "loss": 0.4143,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00013714139902536895,
      "loss": 0.4418,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00013700310182698214,
      "loss": 0.4862,
      "step": 85
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001367836444640114,
      "loss": 0.5152,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00013648328732224639,
      "loss": 0.4401,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00013610238677492728,
      "loss": 0.4883,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00013564139475990883,
      "loss": 0.475,
      "step": 105
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001351008582434381,
      "loss": 0.4708,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00013448141857117668,
      "loss": 0.5114,
      "step": 115
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000133783810707247,
      "loss": 0.4598,
      "step": 120
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00013300886236219912,
      "loss": 0.5016,
      "step": 125
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00013215749301093531,
      "loss": 0.5246,
      "step": 130
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001312307128017492,
      "loss": 0.4599,
      "step": 135
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00013022962135779,
      "loss": 0.5193,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001291554064723639,
      "loss": 0.4855,
      "step": 145
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00012800934269961218,
      "loss": 0.4923,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00012679278984226595,
      "loss": 0.5141,
      "step": 155
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00012550719133822919,
      "loss": 0.4847,
      "step": 160
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001241540725479539,
      "loss": 0.4419,
      "step": 165
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00012273503894459195,
      "loss": 0.5324,
      "step": 170
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00012125177420911749,
      "loss": 0.4099,
      "step": 175
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00011970603823262598,
      "loss": 0.4894,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00011809966502824082,
      "loss": 0.5617,
      "step": 185
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011643456055504982,
      "loss": 0.5006,
      "step": 190
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011471270045669035,
      "loss": 0.4947,
      "step": 195
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00011293612771726151,
      "loss": 0.5112,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011110695023730843,
      "loss": 0.4745,
      "step": 205
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00010922733833281926,
      "loss": 0.4961,
      "step": 210
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001072995221601338,
      "loss": 0.5159,
      "step": 215
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010532578906988555,
      "loss": 0.4521,
      "step": 220
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010330848089304184,
      "loss": 0.4683,
      "step": 225
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010124999116234466,
      "loss": 0.4694,
      "step": 230
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.915276227237154e-05,
      "loss": 0.4838,
      "step": 235
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.701928258165896e-05,
      "loss": 0.4934,
      "step": 240
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.485208346024501e-05,
      "loss": 0.4964,
      "step": 245
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.265373628622407e-05,
      "loss": 0.478,
      "step": 250
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.04268493947969e-05,
      "loss": 0.4836,
      "step": 255
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.817406498348864e-05,
      "loss": 0.4783,
      "step": 260
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.589805597719735e-05,
      "loss": 0.5033,
      "step": 265
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.360152285675815e-05,
      "loss": 0.4933,
      "step": 270
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.128719045483102e-05,
      "loss": 0.4802,
      "step": 275
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.895780472289125e-05,
      "loss": 0.4608,
      "step": 280
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.661612947317637e-05,
      "loss": 0.451,
      "step": 285
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.426494309940237e-05,
      "loss": 0.452,
      "step": 290
    },
    {
      "epoch": 0.65,
      "learning_rate": 7.190703528022759e-05,
      "loss": 0.4496,
      "step": 295
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.95452036692842e-05,
      "loss": 0.4758,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.718225057579034e-05,
      "loss": 0.4928,
      "step": 305
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.48209796395876e-05,
      "loss": 0.5023,
      "step": 310
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.246419250465058e-05,
      "loss": 0.426,
      "step": 315
    },
    {
      "epoch": 0.7,
      "learning_rate": 6.011468549492541e-05,
      "loss": 0.4651,
      "step": 320
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.777524629650007e-05,
      "loss": 0.5082,
      "step": 325
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.544865065003111e-05,
      "loss": 0.4546,
      "step": 330
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.313765905731657e-05,
      "loss": 0.4512,
      "step": 335
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.084501350596927e-05,
      "loss": 0.4794,
      "step": 340
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.857343421605311e-05,
      "loss": 0.4781,
      "step": 345
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.63256164125579e-05,
      "loss": 0.5233,
      "step": 350
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.410422712750424e-05,
      "loss": 0.4695,
      "step": 355
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.191190203551854e-05,
      "loss": 0.4788,
      "step": 360
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.975124232661141e-05,
      "loss": 0.4318,
      "step": 365
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.762481161987185e-05,
      "loss": 0.4609,
      "step": 370
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.553513292174085e-05,
      "loss": 0.4854,
      "step": 375
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.348468563245461e-05,
      "loss": 0.4337,
      "step": 380
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.1475902604251e-05,
      "loss": 0.4707,
      "step": 385
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.951116725479596e-05,
      "loss": 0.4394,
      "step": 390
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.7592810739257415e-05,
      "loss": 0.5088,
      "step": 395
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.572310918439686e-05,
      "loss": 0.4753,
      "step": 400
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.3904280987944108e-05,
      "loss": 0.4626,
      "step": 405
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.2138484186474054e-05,
      "loss": 0.4473,
      "step": 410
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.0427813894908452e-05,
      "loss": 0.4662,
      "step": 415
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.877429982065378e-05,
      "loss": 0.4383,
      "step": 420
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.7179903855360063e-05,
      "loss": 0.4584,
      "step": 425
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.564651774714127e-05,
      "loss": 0.4932,
      "step": 430
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4175960856020567e-05,
      "loss": 0.4168,
      "step": 435
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.2769977995264743e-05,
      "loss": 0.5093,
      "step": 440
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.1430237361156786e-05,
      "loss": 0.486,
      "step": 445
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0158328553691274e-05,
      "loss": 0.4456,
      "step": 450
    },
    {
      "epoch": 1.0,
      "learning_rate": 8.95576069051646e-06,
      "loss": 0.4546,
      "step": 455
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.200975701212883,
      "eval_runtime": 14.7931,
      "eval_samples_per_second": 42.993,
      "eval_steps_per_second": 5.408,
      "step": 456
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.16962459683418274,
      "eval_runtime": 12.708,
      "eval_samples_per_second": 47.687,
      "eval_steps_per_second": 5.98,
      "step": 459
    }
  ],
  "max_steps": 918,
  "num_train_epochs": 2,
  "total_flos": 478817648640000.0,
  "trial_name": null,
  "trial_params": null
}