{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 660,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 0.000984848484848485,
      "loss": 1.0952,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0009696969696969698,
      "loss": 1.0962,
      "step": 20
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0009545454545454546,
      "loss": 1.0441,
      "step": 30
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0009393939393939394,
      "loss": 1.0023,
      "step": 40
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0009242424242424242,
      "loss": 1.0408,
      "step": 50
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009090909090909091,
      "loss": 0.9821,
      "step": 60
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000893939393939394,
      "loss": 0.9633,
      "step": 70
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0008787878787878789,
      "loss": 0.9761,
      "step": 80
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0008636363636363636,
      "loss": 0.9594,
      "step": 90
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0008484848484848485,
      "loss": 0.9244,
      "step": 100
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0008333333333333334,
      "loss": 0.8843,
      "step": 110
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0008181818181818183,
      "loss": 0.9871,
      "step": 120
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000803030303030303,
      "loss": 0.8856,
      "step": 130
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0007878787878787878,
      "loss": 0.9153,
      "step": 140
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0007727272727272727,
      "loss": 0.8418,
      "step": 150
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0007575757575757576,
      "loss": 0.9174,
      "step": 160
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0007424242424242425,
      "loss": 0.843,
      "step": 170
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0007272727272727273,
      "loss": 0.8595,
      "step": 180
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0007121212121212122,
      "loss": 0.8605,
      "step": 190
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.000696969696969697,
      "loss": 0.8475,
      "step": 200
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0006818181818181818,
      "loss": 0.7622,
      "step": 210
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0006666666666666666,
      "loss": 0.8596,
      "step": 220
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0006515151515151515,
      "loss": 0.8955,
      "step": 230
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0006363636363636364,
      "loss": 0.8299,
      "step": 240
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0006212121212121212,
      "loss": 0.7741,
      "step": 250
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0006060606060606061,
      "loss": 0.8159,
      "step": 260
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0005909090909090909,
      "loss": 0.7613,
      "step": 270
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0005757575757575758,
      "loss": 0.8293,
      "step": 280
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0005606060606060606,
      "loss": 0.7065,
      "step": 290
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0005454545454545455,
      "loss": 0.6833,
      "step": 300
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0005303030303030302,
      "loss": 0.7731,
      "step": 310
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0005151515151515151,
      "loss": 0.7636,
      "step": 320
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0005,
      "loss": 0.7438,
      "step": 330
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0004848484848484849,
      "loss": 0.7412,
      "step": 340
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0004696969696969697,
      "loss": 0.6841,
      "step": 350
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.00045454545454545455,
      "loss": 0.7718,
      "step": 360
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0004393939393939394,
      "loss": 0.7617,
      "step": 370
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.00042424242424242425,
      "loss": 0.7614,
      "step": 380
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.00040909090909090913,
      "loss": 0.6873,
      "step": 390
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.0003939393939393939,
      "loss": 0.6847,
      "step": 400
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0003787878787878788,
      "loss": 0.6395,
      "step": 410
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.00036363636363636367,
      "loss": 0.5941,
      "step": 420
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.0003484848484848485,
      "loss": 0.6728,
      "step": 430
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0003333333333333333,
      "loss": 0.6522,
      "step": 440
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.0003181818181818182,
      "loss": 0.6334,
      "step": 450
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.00030303030303030303,
      "loss": 0.5879,
      "step": 460
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.0002878787878787879,
      "loss": 0.6708,
      "step": 470
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.00027272727272727274,
      "loss": 0.6268,
      "step": 480
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.00025757575757575756,
      "loss": 0.5994,
      "step": 490
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.00024242424242424245,
      "loss": 0.5764,
      "step": 500
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.00022727272727272727,
      "loss": 0.5851,
      "step": 510
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.00021212121212121213,
      "loss": 0.57,
      "step": 520
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.00019696969696969695,
      "loss": 0.6229,
      "step": 530
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.4952,
      "step": 540
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.00016666666666666666,
      "loss": 0.4905,
      "step": 550
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.00015151515151515152,
      "loss": 0.4768,
      "step": 560
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.00013636363636363637,
      "loss": 0.5296,
      "step": 570
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.00012121212121212122,
      "loss": 0.4509,
      "step": 580
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.00010606060606060606,
      "loss": 0.4345,
      "step": 590
    },
    {
      "epoch": 4.55,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.4995,
      "step": 600
    },
    {
      "epoch": 4.62,
      "learning_rate": 7.575757575757576e-05,
      "loss": 0.5118,
      "step": 610
    },
    {
      "epoch": 4.7,
      "learning_rate": 6.060606060606061e-05,
      "loss": 0.5233,
      "step": 620
    },
    {
      "epoch": 4.77,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.502,
      "step": 630
    },
    {
      "epoch": 4.85,
      "learning_rate": 3.0303030303030306e-05,
      "loss": 0.4967,
      "step": 640
    },
    {
      "epoch": 4.92,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 0.4572,
      "step": 650
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.4601,
      "step": 660
    },
    {
      "epoch": 5.0,
      "step": 660,
      "total_flos": 24828499691520.0,
      "train_loss": 0.7359953800837199,
      "train_runtime": 22.7458,
      "train_samples_per_second": 924.784,
      "train_steps_per_second": 29.016
    }
  ],
  "max_steps": 660,
  "num_train_epochs": 5,
  "total_flos": 24828499691520.0,
  "trial_name": null,
  "trial_params": null
}