{
  "best_metric": 1.0850846767425537,
  "best_model_checkpoint": "output/eminem/checkpoint-452",
  "epoch": 1.0,
  "global_step": 452,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0001303175293643722,
      "loss": 1.3814,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012923970346668577,
      "loss": 1.4469,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00012808864972555433,
      "loss": 1.3639,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00012686575814089952,
      "loss": 1.4233,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012557250546324088,
      "loss": 1.4142,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00012421045341038384,
      "loss": 1.5476,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00012278124678150593,
      "loss": 1.5554,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00012128661147092046,
      "loss": 1.3787,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00011972835238390038,
      "loss": 1.504,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00011810835125709465,
      "loss": 1.4927,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00011642856438616613,
      "loss": 1.543,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00011469102026339135,
      "loss": 1.4018,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00011289781712806903,
      "loss": 1.5591,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001110511204327154,
      "loss": 1.2862,
      "step": 70
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00010915316022808772,
      "loss": 1.5977,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00010720622847019248,
      "loss": 1.2878,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00010521267625255193,
      "loss": 1.2948,
      "step": 85
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00010317491096704546,
      "loss": 1.2196,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00010109539339677022,
      "loss": 1.4123,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.897663474442627e-05,
      "loss": 1.3245,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 9.682119359981574e-05,
      "loss": 1.3909,
      "step": 105
    },
    {
      "epoch": 0.24,
      "learning_rate": 9.463167285011763e-05,
      "loss": 1.458,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 9.241071653666979e-05,
      "loss": 1.3268,
      "step": 115
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.016100666205339e-05,
      "loss": 1.3456,
      "step": 120
    },
    {
      "epoch": 0.28,
      "learning_rate": 8.788525995133601e-05,
      "loss": 1.2974,
      "step": 125
    },
    {
      "epoch": 0.29,
      "learning_rate": 8.558622457138398e-05,
      "loss": 1.3235,
      "step": 130
    },
    {
      "epoch": 0.3,
      "learning_rate": 8.326667681220627e-05,
      "loss": 1.416,
      "step": 135
    },
    {
      "epoch": 0.31,
      "learning_rate": 8.092941773433681e-05,
      "loss": 1.5582,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 7.857726978630461e-05,
      "loss": 1.5253,
      "step": 145
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.621307339627555e-05,
      "loss": 1.3431,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 7.383968354198248e-05,
      "loss": 1.4096,
      "step": 155
    },
    {
      "epoch": 0.35,
      "learning_rate": 7.145996630308523e-05,
      "loss": 1.5607,
      "step": 160
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.907679540012421e-05,
      "loss": 1.3956,
      "step": 165
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.669304872424775e-05,
      "loss": 1.4131,
      "step": 170
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.431160486189736e-05,
      "loss": 1.5354,
      "step": 175
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.193533961866798e-05,
      "loss": 1.4403,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.9567122546507705e-05,
      "loss": 1.5146,
      "step": 185
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.7209813478478305e-05,
      "loss": 1.4112,
      "step": 190
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.48662590752607e-05,
      "loss": 1.5145,
      "step": 195
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.2539289387549954e-05,
      "loss": 1.4062,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.023171443851796e-05,
      "loss": 1.2077,
      "step": 205
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.7946320830464014e-05,
      "loss": 1.3632,
      "step": 210
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.568586837974509e-05,
      "loss": 1.3578,
      "step": 215
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.3453086784043506e-05,
      "loss": 1.2558,
      "step": 220
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.1250672326022146e-05,
      "loss": 1.4552,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.908128461732282e-05,
      "loss": 1.4219,
      "step": 230
    },
    {
      "epoch": 0.52,
      "learning_rate": 3.694754338684033e-05,
      "loss": 1.297,
      "step": 235
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.485202531717449e-05,
      "loss": 1.4082,
      "step": 240
    },
    {
      "epoch": 0.54,
      "learning_rate": 3.279726093305622e-05,
      "loss": 1.3862,
      "step": 245
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.0785731545505864e-05,
      "loss": 1.3033,
      "step": 250
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.8819866255437648e-05,
      "loss": 1.5164,
      "step": 255
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.6902039020298912e-05,
      "loss": 1.331,
      "step": 260
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.503456578730975e-05,
      "loss": 1.3233,
      "step": 265
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.3219701696742702e-05,
      "loss": 1.3359,
      "step": 270
    },
    {
      "epoch": 0.61,
      "learning_rate": 2.1459638358647056e-05,
      "loss": 1.3935,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.9756501206284136e-05,
      "loss": 1.3479,
      "step": 280
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.8112346929471017e-05,
      "loss": 1.2397,
      "step": 285
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.652916099095146e-05,
      "loss": 1.2953,
      "step": 290
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.5008855228769237e-05,
      "loss": 1.2815,
      "step": 295
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.3553265547554126e-05,
      "loss": 1.4089,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.2164149701503507e-05,
      "loss": 1.4801,
      "step": 305
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.084318517173762e-05,
      "loss": 1.3129,
      "step": 310
    },
    {
      "epoch": 0.7,
      "learning_rate": 9.59196714059168e-06,
      "loss": 1.4936,
      "step": 315
    },
    {
      "epoch": 0.71,
      "learning_rate": 8.412006565291113e-06,
      "loss": 1.5641,
      "step": 320
    },
    {
      "epoch": 0.72,
      "learning_rate": 7.304728353336137e-06,
      "loss": 1.5021,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 6.271469641798991e-06,
      "loss": 1.486,
      "step": 330
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.3134781826118575e-06,
      "loss": 1.4864,
      "step": 335
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.431910835795231e-06,
      "loss": 1.3247,
      "step": 340
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.627832172446406e-06,
      "loss": 1.3021,
      "step": 345
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.9022131891750565e-06,
      "loss": 1.2565,
      "step": 350
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.255930135538328e-06,
      "loss": 1.3403,
      "step": 355
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.6897634558914518e-06,
      "loss": 1.1603,
      "step": 360
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.2043968469316478e-06,
      "loss": 1.3477,
      "step": 365
    },
    {
      "epoch": 0.82,
      "learning_rate": 8.004164320734945e-07,
      "loss": 1.4542,
      "step": 370
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.783100536527857e-07,
      "loss": 1.171,
      "step": 375
    },
    {
      "epoch": 0.84,
      "learning_rate": 2.384666838129012e-07,
      "loss": 1.3221,
      "step": 380
    },
    {
      "epoch": 0.85,
      "learning_rate": 8.117595478741029e-08,
      "loss": 1.4165,
      "step": 385
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.627809142273766e-09,
      "loss": 1.3171,
      "step": 390
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.4912270403714612e-08,
      "loss": 1.278,
      "step": 395
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.0601933434685848e-07,
      "loss": 1.1844,
      "step": 400
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.798389810765e-07,
      "loss": 1.4166,
      "step": 405
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.361613078862704e-07,
      "loss": 1.347,
      "step": 410
    },
    {
      "epoch": 0.92,
      "learning_rate": 8.746767827346377e-07,
      "loss": 1.2687,
      "step": 415
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.294976618031831e-06,
      "loss": 1.2153,
      "step": 420
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7965532642887846e-06,
      "loss": 1.4466,
      "step": 425
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.3788010230270847e-06,
      "loss": 1.4541,
      "step": 430
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.0410167782133005e-06,
      "loss": 1.646,
      "step": 435
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.7824008453366295e-06,
      "loss": 1.478,
      "step": 440
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.60205793709664e-06,
      "loss": 1.523,
      "step": 445
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.498998244543705e-06,
      "loss": 1.3657,
      "step": 450
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0850846767425537,
      "eval_runtime": 31.9582,
      "eval_samples_per_second": 20.683,
      "eval_steps_per_second": 2.597,
      "step": 452
    }
  ],
  "max_steps": 904,
  "num_train_epochs": 2,
  "total_flos": 472415993856000.0,
  "trial_name": null,
  "trial_params": null
}