{
  "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": 1.96969696969697e-05,
      "loss": 1.1658,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9393939393939395e-05,
      "loss": 1.1076,
      "step": 20
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.9090909090909094e-05,
      "loss": 1.0267,
      "step": 30
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.8787878787878792e-05,
      "loss": 0.9707,
      "step": 40
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.8484848484848487e-05,
      "loss": 1.0231,
      "step": 50
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.9652,
      "step": 60
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.787878787878788e-05,
      "loss": 0.9454,
      "step": 70
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.7575757575757576e-05,
      "loss": 0.9635,
      "step": 80
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.7272727272727274e-05,
      "loss": 0.9535,
      "step": 90
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.6969696969696972e-05,
      "loss": 0.9017,
      "step": 100
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.8334,
      "step": 110
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 0.8924,
      "step": 120
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.606060606060606e-05,
      "loss": 0.8255,
      "step": 130
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.575757575757576e-05,
      "loss": 0.7972,
      "step": 140
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.5454545454545454e-05,
      "loss": 0.8028,
      "step": 150
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 0.7566,
      "step": 160
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.484848484848485e-05,
      "loss": 0.7345,
      "step": 170
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.4545454545454546e-05,
      "loss": 0.7123,
      "step": 180
    },
    {
      "epoch": 1.44,
      "learning_rate": 1.4242424242424245e-05,
      "loss": 0.7344,
      "step": 190
    },
    {
      "epoch": 1.52,
      "learning_rate": 1.3939393939393942e-05,
      "loss": 0.6757,
      "step": 200
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 0.665,
      "step": 210
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.7071,
      "step": 220
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.3030303030303032e-05,
      "loss": 0.6266,
      "step": 230
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.2727272727272728e-05,
      "loss": 0.5948,
      "step": 240
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.2424242424242425e-05,
      "loss": 0.6127,
      "step": 250
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 0.5923,
      "step": 260
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.181818181818182e-05,
      "loss": 0.5744,
      "step": 270
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.1515151515151517e-05,
      "loss": 0.6321,
      "step": 280
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.1212121212121212e-05,
      "loss": 0.4866,
      "step": 290
    },
    {
      "epoch": 2.27,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 0.4829,
      "step": 300
    },
    {
      "epoch": 2.35,
      "learning_rate": 1.0606060606060606e-05,
      "loss": 0.5416,
      "step": 310
    },
    {
      "epoch": 2.42,
      "learning_rate": 1.0303030303030304e-05,
      "loss": 0.5801,
      "step": 320
    },
    {
      "epoch": 2.5,
      "learning_rate": 1e-05,
      "loss": 0.536,
      "step": 330
    },
    {
      "epoch": 2.58,
      "learning_rate": 9.696969696969698e-06,
      "loss": 0.4988,
      "step": 340
    },
    {
      "epoch": 2.65,
      "learning_rate": 9.393939393939396e-06,
      "loss": 0.5227,
      "step": 350
    },
    {
      "epoch": 2.73,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.5278,
      "step": 360
    },
    {
      "epoch": 2.8,
      "learning_rate": 8.787878787878788e-06,
      "loss": 0.5426,
      "step": 370
    },
    {
      "epoch": 2.88,
      "learning_rate": 8.484848484848486e-06,
      "loss": 0.5464,
      "step": 380
    },
    {
      "epoch": 2.95,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.415,
      "step": 390
    },
    {
      "epoch": 3.03,
      "learning_rate": 7.87878787878788e-06,
      "loss": 0.4644,
      "step": 400
    },
    {
      "epoch": 3.11,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 0.4674,
      "step": 410
    },
    {
      "epoch": 3.18,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.441,
      "step": 420
    },
    {
      "epoch": 3.26,
      "learning_rate": 6.969696969696971e-06,
      "loss": 0.5166,
      "step": 430
    },
    {
      "epoch": 3.33,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.4607,
      "step": 440
    },
    {
      "epoch": 3.41,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.428,
      "step": 450
    },
    {
      "epoch": 3.48,
      "learning_rate": 6.060606060606061e-06,
      "loss": 0.4172,
      "step": 460
    },
    {
      "epoch": 3.56,
      "learning_rate": 5.7575757575757586e-06,
      "loss": 0.4494,
      "step": 470
    },
    {
      "epoch": 3.64,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.4084,
      "step": 480
    },
    {
      "epoch": 3.71,
      "learning_rate": 5.151515151515152e-06,
      "loss": 0.4428,
      "step": 490
    },
    {
      "epoch": 3.79,
      "learning_rate": 4.848484848484849e-06,
      "loss": 0.4007,
      "step": 500
    },
    {
      "epoch": 3.86,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.4297,
      "step": 510
    },
    {
      "epoch": 3.94,
      "learning_rate": 4.242424242424243e-06,
      "loss": 0.4108,
      "step": 520
    },
    {
      "epoch": 4.02,
      "learning_rate": 3.93939393939394e-06,
      "loss": 0.4433,
      "step": 530
    },
    {
      "epoch": 4.09,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.4151,
      "step": 540
    },
    {
      "epoch": 4.17,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.3749,
      "step": 550
    },
    {
      "epoch": 4.24,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 0.3343,
      "step": 560
    },
    {
      "epoch": 4.32,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.3746,
      "step": 570
    },
    {
      "epoch": 4.39,
      "learning_rate": 2.4242424242424244e-06,
      "loss": 0.4396,
      "step": 580
    },
    {
      "epoch": 4.47,
      "learning_rate": 2.1212121212121216e-06,
      "loss": 0.3793,
      "step": 590
    },
    {
      "epoch": 4.55,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.4193,
      "step": 600
    },
    {
      "epoch": 4.62,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 0.4185,
      "step": 610
    },
    {
      "epoch": 4.7,
      "learning_rate": 1.2121212121212122e-06,
      "loss": 0.3987,
      "step": 620
    },
    {
      "epoch": 4.77,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.3946,
      "step": 630
    },
    {
      "epoch": 4.85,
      "learning_rate": 6.060606060606061e-07,
      "loss": 0.3512,
      "step": 640
    },
    {
      "epoch": 4.92,
      "learning_rate": 3.0303030303030305e-07,
      "loss": 0.3771,
      "step": 650
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.4206,
      "step": 660
    },
    {
      "epoch": 5.0,
      "step": 660,
      "total_flos": 1383647685477120.0,
      "train_loss": 0.6022974249088403,
      "train_runtime": 176.6939,
      "train_samples_per_second": 119.048,
      "train_steps_per_second": 3.735
    }
  ],
  "max_steps": 660,
  "num_train_epochs": 5,
  "total_flos": 1383647685477120.0,
  "trial_name": null,
  "trial_params": null
}