{
  "best_metric": 3.2645678520202637,
  "best_model_checkpoint": "output/eminem/checkpoint-458",
  "epoch": 1.0,
  "global_step": 458,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.00013715965772858815,
      "loss": 3.1417,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000137038678363299,
      "loss": 2.9863,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013683720419516428,
      "loss": 3.1237,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00013655547218994425,
      "loss": 3.0636,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00013619381370941783,
      "loss": 3.1631,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001357526541216486,
      "loss": 3.017,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000135232512300684,
      "loss": 3.1919,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00013463400001627657,
      "loss": 3.404,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001339578212143452,
      "loss": 3.2587,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00013320477118902276,
      "loss": 3.2812,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00013237573564726276,
      "loss": 2.9708,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000131471689667107,
      "loss": 3.2539,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00013049369655083827,
      "loss": 3.3207,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00012944290657436735,
      "loss": 3.1984,
      "step": 70
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00012832055563432473,
      "loss": 3.2094,
      "step": 75
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001271279637944492,
      "loss": 3.2116,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00012586653373298248,
      "loss": 3.2721,
      "step": 85
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00012453774909289557,
      "loss": 3.2313,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00012314317273688812,
      "loss": 3.3427,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00012168444490921243,
      "loss": 3.3434,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00012016328130648513,
      "loss": 3.0684,
      "step": 105
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00011858147105975337,
      "loss": 2.9787,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001169408746301919,
      "loss": 3.0232,
      "step": 115
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00011524342162090394,
      "loss": 3.097,
      "step": 120
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00011349110850740006,
      "loss": 2.9875,
      "step": 125
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00011168599628942434,
      "loss": 3.069,
      "step": 130
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00010983020806688995,
      "loss": 3.2752,
      "step": 135
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00010792592654277545,
      "loss": 3.0414,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00010597539145591715,
      "loss": 3.2296,
      "step": 145
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001039808969467193,
      "loss": 3.2247,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00010194478885887969,
      "loss": 3.0732,
      "step": 155
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.986946198030201e-05,
      "loss": 3.0828,
      "step": 160
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.775735722644407e-05,
      "loss": 3.0514,
      "step": 165
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.561095876941162e-05,
      "loss": 2.9164,
      "step": 170
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.343279111617608e-05,
      "loss": 3.0357,
      "step": 175
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.122541613935095e-05,
      "loss": 3.2488,
      "step": 180
    },
    {
      "epoch": 0.4,
      "learning_rate": 8.89914300640212e-05,
      "loss": 3.017,
      "step": 185
    },
    {
      "epoch": 0.41,
      "learning_rate": 8.673346041416928e-05,
      "loss": 3.1126,
      "step": 190
    },
    {
      "epoch": 0.43,
      "learning_rate": 8.445416292228631e-05,
      "loss": 3.2453,
      "step": 195
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.215621840580805e-05,
      "loss": 3.0444,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 7.984232961404542e-05,
      "loss": 3.1687,
      "step": 205
    },
    {
      "epoch": 0.46,
      "learning_rate": 7.75152180493212e-05,
      "loss": 3.225,
      "step": 210
    },
    {
      "epoch": 0.47,
      "learning_rate": 7.517762076604763e-05,
      "loss": 3.0953,
      "step": 215
    },
    {
      "epoch": 0.48,
      "learning_rate": 7.283228715151494e-05,
      "loss": 3.25,
      "step": 220
    },
    {
      "epoch": 0.49,
      "learning_rate": 7.048197569217281e-05,
      "loss": 3.1282,
      "step": 225
    },
    {
      "epoch": 0.5,
      "learning_rate": 6.812945072921086e-05,
      "loss": 2.9809,
      "step": 230
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.577747920725168e-05,
      "loss": 3.0873,
      "step": 235
    },
    {
      "epoch": 0.52,
      "learning_rate": 6.342882741998283e-05,
      "loss": 3.0845,
      "step": 240
    },
    {
      "epoch": 0.53,
      "learning_rate": 6.108625775655505e-05,
      "loss": 2.9657,
      "step": 245
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.875252545257054e-05,
      "loss": 3.0202,
      "step": 250
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.6430375349487304e-05,
      "loss": 3.1417,
      "step": 255
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.412253866624731e-05,
      "loss": 3.0013,
      "step": 260
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.183172978692829e-05,
      "loss": 2.8449,
      "step": 265
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.956064306819361e-05,
      "loss": 3.2741,
      "step": 270
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.731194967029994e-05,
      "loss": 3.024,
      "step": 275
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.508829441538685e-05,
      "loss": 3.0632,
      "step": 280
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.289229267674345e-05,
      "loss": 2.8501,
      "step": 285
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.072652730271264e-05,
      "loss": 3.2079,
      "step": 290
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.859354557884909e-05,
      "loss": 3.1717,
      "step": 295
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.649585623190606e-05,
      "loss": 3.1905,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.443592647917112e-05,
      "loss": 3.0304,
      "step": 305
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.2416179126625834e-05,
      "loss": 2.9144,
      "step": 310
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.0438989719340004e-05,
      "loss": 3.2034,
      "step": 315
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.850668374745048e-05,
      "loss": 2.9562,
      "step": 320
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.662153391101465e-05,
      "loss": 2.9282,
      "step": 325
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.4785757446952362e-05,
      "loss": 2.9689,
      "step": 330
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.3001513521221957e-05,
      "loss": 3.1242,
      "step": 335
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.1270900689296127e-05,
      "loss": 3.174,
      "step": 340
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.959595442792614e-05,
      "loss": 3.0034,
      "step": 345
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.797864474109709e-05,
      "loss": 3.1004,
      "step": 350
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.642087384298789e-05,
      "loss": 2.9905,
      "step": 355
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.4924473920664698e-05,
      "loss": 2.984,
      "step": 360
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.3491204979136316e-05,
      "loss": 3.1477,
      "step": 365
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.2122752771308157e-05,
      "loss": 3.3952,
      "step": 370
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.0820726815267017e-05,
      "loss": 3.2005,
      "step": 375
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.586658501231604e-06,
      "loss": 3.1182,
      "step": 380
    },
    {
      "epoch": 0.84,
      "learning_rate": 8.421999290393463e-06,
      "loss": 3.1384,
      "step": 385
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.328119007766703e-06,
      "loss": 3.2064,
      "step": 390
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.306304231055513e-06,
      "loss": 3.1691,
      "step": 395
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.357756777433396e-06,
      "loss": 2.9847,
      "step": 400
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.4835922900148836e-06,
      "loss": 2.919,
      "step": 405
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.6848389256806193e-06,
      "loss": 3.0809,
      "step": 410
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.9624361458012783e-06,
      "loss": 3.1271,
      "step": 415
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.317233611281141e-06,
      "loss": 3.2683,
      "step": 420
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.7499901832211207e-06,
      "loss": 3.0606,
      "step": 425
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.2613730303772807e-06,
      "loss": 3.1985,
      "step": 430
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.519568444637701e-07,
      "loss": 3.0785,
      "step": 435
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.222231642238413e-07,
      "loss": 3.2775,
      "step": 440
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.7255980906336113e-07,
      "loss": 2.8361,
      "step": 445
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.0326042291338553e-07,
      "loss": 2.9579,
      "step": 450
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.4524128858071773e-08,
      "loss": 3.1667,
      "step": 455
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.2645678520202637,
      "eval_runtime": 27.8254,
      "eval_samples_per_second": 22.102,
      "eval_steps_per_second": 2.767,
      "step": 458
    }
  ],
  "max_steps": 1832,
  "num_train_epochs": 4,
  "total_flos": 478425710592000.0,
  "trial_name": null,
  "trial_params": null
}