{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1970831690973591,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.999997870262096e-05,
      "loss": 2.714,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.999991481057455e-05,
      "loss": 2.7679,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.9999808324132915e-05,
      "loss": 2.6887,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.999965924374964e-05,
      "loss": 2.6986,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.999946757005972e-05,
      "loss": 2.7536,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.9999233303879592e-05,
      "loss": 2.7516,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.99989564462071e-05,
      "loss": 2.6283,
      "step": 35
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.999863699822152e-05,
      "loss": 2.708,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9998274961283523e-05,
      "loss": 2.6932,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9997870336935207e-05,
      "loss": 2.6321,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9997423126900056e-05,
      "loss": 2.7129,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9996933333082945e-05,
      "loss": 2.6179,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9996400957570148e-05,
      "loss": 2.6052,
      "step": 65
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.99958260026293e-05,
      "loss": 2.7054,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9995208470709405e-05,
      "loss": 2.6568,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9994548364440836e-05,
      "loss": 2.6436,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.999384568663529e-05,
      "loss": 2.7091,
      "step": 85
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9993100440285805e-05,
      "loss": 2.5557,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.999231262856675e-05,
      "loss": 2.5945,
      "step": 95
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.999148225483378e-05,
      "loss": 2.4729,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9990609322623854e-05,
      "loss": 2.6724,
      "step": 105
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9989693835655205e-05,
      "loss": 2.5272,
      "step": 110
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9988735797827336e-05,
      "loss": 2.6145,
      "step": 115
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9987735213220975e-05,
      "loss": 2.6772,
      "step": 120
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9986692086098095e-05,
      "loss": 2.6388,
      "step": 125
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.998560642090187e-05,
      "loss": 2.4973,
      "step": 130
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.998447822225666e-05,
      "loss": 2.5338,
      "step": 135
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9983307494968e-05,
      "loss": 2.6469,
      "step": 140
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9982094244022582e-05,
      "loss": 2.6008,
      "step": 145
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9980838474588214e-05,
      "loss": 2.5936,
      "step": 150
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9979540192013814e-05,
      "loss": 2.5862,
      "step": 155
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.997819940182939e-05,
      "loss": 2.568,
      "step": 160
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9976816109746e-05,
      "loss": 2.5343,
      "step": 165
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9975390321655745e-05,
      "loss": 2.5575,
      "step": 170
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9973922043631737e-05,
      "loss": 2.5399,
      "step": 175
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9972411281928068e-05,
      "loss": 2.6394,
      "step": 180
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9970858042979794e-05,
      "loss": 2.5378,
      "step": 185
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9969262333402893e-05,
      "loss": 2.5373,
      "step": 190
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9967624159994262e-05,
      "loss": 2.5414,
      "step": 195
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9965943529731646e-05,
      "loss": 2.5606,
      "step": 200
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9964220449773664e-05,
      "loss": 2.5154,
      "step": 205
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9962454927459723e-05,
      "loss": 2.5468,
      "step": 210
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9960646970310027e-05,
      "loss": 2.5137,
      "step": 215
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9958796586025527e-05,
      "loss": 2.5453,
      "step": 220
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9956903782487885e-05,
      "loss": 2.5325,
      "step": 225
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9954968567759456e-05,
      "loss": 2.5054,
      "step": 230
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9952990950083236e-05,
      "loss": 2.5139,
      "step": 235
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.995097093788285e-05,
      "loss": 2.5097,
      "step": 240
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.994890853976248e-05,
      "loss": 2.5546,
      "step": 245
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.994680376450686e-05,
      "loss": 2.4609,
      "step": 250
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.994465662108124e-05,
      "loss": 2.5063,
      "step": 255
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9942467118631322e-05,
      "loss": 2.5162,
      "step": 260
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.994023526648323e-05,
      "loss": 2.5317,
      "step": 265
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9937961074143492e-05,
      "loss": 2.4621,
      "step": 270
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9935644551298976e-05,
      "loss": 2.5879,
      "step": 275
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.993328570781685e-05,
      "loss": 2.4742,
      "step": 280
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.993088455374456e-05,
      "loss": 2.4661,
      "step": 285
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.992844109930975e-05,
      "loss": 2.4943,
      "step": 290
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9925955354920265e-05,
      "loss": 2.4322,
      "step": 295
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9923427331164072e-05,
      "loss": 2.484,
      "step": 300
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9920857038809223e-05,
      "loss": 2.5334,
      "step": 305
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.991824448880382e-05,
      "loss": 2.6554,
      "step": 310
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9915589692275955e-05,
      "loss": 2.4749,
      "step": 315
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.991289266053367e-05,
      "loss": 2.5076,
      "step": 320
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9910153405064904e-05,
      "loss": 2.4635,
      "step": 325
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.990737193753745e-05,
      "loss": 2.5443,
      "step": 330
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9904548269798906e-05,
      "loss": 2.6012,
      "step": 335
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.990168241387662e-05,
      "loss": 2.4818,
      "step": 340
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9898774381977618e-05,
      "loss": 2.4717,
      "step": 345
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.989582418648861e-05,
      "loss": 2.4756,
      "step": 350
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9892831839975874e-05,
      "loss": 2.4868,
      "step": 355
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9889797355185237e-05,
      "loss": 2.5652,
      "step": 360
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9886720745042017e-05,
      "loss": 2.3907,
      "step": 365
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.988360202265096e-05,
      "loss": 2.4984,
      "step": 370
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9880441201296186e-05,
      "loss": 2.5654,
      "step": 375
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.987723829444114e-05,
      "loss": 2.581,
      "step": 380
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9873993315728523e-05,
      "loss": 2.5189,
      "step": 385
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.987070627898025e-05,
      "loss": 2.491,
      "step": 390
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9867377198197367e-05,
      "loss": 2.4875,
      "step": 395
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9864006087560016e-05,
      "loss": 2.4828,
      "step": 400
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9860592961427358e-05,
      "loss": 2.5298,
      "step": 405
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9857137834337527e-05,
      "loss": 2.4873,
      "step": 410
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.985364072100755e-05,
      "loss": 2.5371,
      "step": 415
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.98501016363333e-05,
      "loss": 2.4167,
      "step": 420
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9846520595389415e-05,
      "loss": 2.4312,
      "step": 425
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.984289761342926e-05,
      "loss": 2.4471,
      "step": 430
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9839232705884836e-05,
      "loss": 2.4971,
      "step": 435
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9835525888366727e-05,
      "loss": 2.5206,
      "step": 440
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9831777176664035e-05,
      "loss": 2.5067,
      "step": 445
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9827986586744302e-05,
      "loss": 2.4903,
      "step": 450
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.982415413475346e-05,
      "loss": 2.4391,
      "step": 455
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9820279837015742e-05,
      "loss": 2.4358,
      "step": 460
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.981636371003363e-05,
      "loss": 2.4809,
      "step": 465
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.9812405770487763e-05,
      "loss": 2.516,
      "step": 470
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.9808406035236897e-05,
      "loss": 2.4091,
      "step": 475
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.9804364521317806e-05,
      "loss": 2.5363,
      "step": 480
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.9800281245945217e-05,
      "loss": 2.51,
      "step": 485
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.9796156226511747e-05,
      "loss": 2.5049,
      "step": 490
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9791989480587815e-05,
      "loss": 2.4722,
      "step": 495
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.978778102592157e-05,
      "loss": 2.4111,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 7611,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 6744791407656960.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}