{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9171270718232045,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.6057,
      "step": 1
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.6492,
      "step": 2
    },
    {
      "epoch": 0.13,
      "learning_rate": 2e-05,
      "loss": 1.5781,
      "step": 3
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9987569212189224e-05,
      "loss": 1.365,
      "step": 4
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9950307753654016e-05,
      "loss": 1.5415,
      "step": 5
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.9888308262251286e-05,
      "loss": 1.2678,
      "step": 6
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.9801724878485438e-05,
      "loss": 1.2053,
      "step": 7
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.969077286229078e-05,
      "loss": 1.2021,
      "step": 8
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.955572805786141e-05,
      "loss": 1.1851,
      "step": 9
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 1.1589,
      "step": 10
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.921476211870408e-05,
      "loss": 1.1465,
      "step": 11
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.900968867902419e-05,
      "loss": 1.1318,
      "step": 12
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.8782215733702286e-05,
      "loss": 1.1279,
      "step": 13
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.8532908816321557e-05,
      "loss": 1.1071,
      "step": 14
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.826238774315995e-05,
      "loss": 1.0994,
      "step": 15
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.7971325072229227e-05,
      "loss": 1.0902,
      "step": 16
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.766044443118978e-05,
      "loss": 1.0745,
      "step": 17
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.7330518718298263e-05,
      "loss": 1.0742,
      "step": 18
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.698236818086073e-05,
      "loss": 1.0671,
      "step": 19
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.6616858375968596e-05,
      "loss": 1.0704,
      "step": 20
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.6234898018587336e-05,
      "loss": 1.0553,
      "step": 21
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.5837436722347902e-05,
      "loss": 1.0565,
      "step": 22
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.5425462638657597e-05,
      "loss": 1.0477,
      "step": 23
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.0238,
      "step": 24
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.4562106573531632e-05,
      "loss": 1.0179,
      "step": 25
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.4112871031306118e-05,
      "loss": 1.0312,
      "step": 26
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.3653410243663953e-05,
      "loss": 1.0149,
      "step": 27
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.3184866502516846e-05,
      "loss": 1.0096,
      "step": 28
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.2708404681430054e-05,
      "loss": 0.9969,
      "step": 29
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.2225209339563144e-05,
      "loss": 1.0026,
      "step": 30
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.9957,
      "step": 31
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.1243437046474854e-05,
      "loss": 1.0106,
      "step": 32
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.0747300935864245e-05,
      "loss": 0.9747,
      "step": 33
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.0249306917380731e-05,
      "loss": 0.9871,
      "step": 34
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.750693082619274e-06,
      "loss": 0.9625,
      "step": 35
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.252699064135759e-06,
      "loss": 0.9851,
      "step": 36
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.756562953525151e-06,
      "loss": 0.969,
      "step": 37
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.9961,
      "step": 38
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.774790660436857e-06,
      "loss": 0.9688,
      "step": 39
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.291595318569951e-06,
      "loss": 0.9729,
      "step": 40
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.815133497483157e-06,
      "loss": 0.9558,
      "step": 41
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.34658975633605e-06,
      "loss": 0.9746,
      "step": 42
    },
    {
      "epoch": 1.9,
      "learning_rate": 5.887128968693887e-06,
      "loss": 0.9725,
      "step": 43
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.43789342646837e-06,
      "loss": 0.9567,
      "step": 44
    },
    {
      "epoch": 1.99,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.959,
      "step": 45
    },
    {
      "epoch": 2.03,
      "learning_rate": 4.5745373613424075e-06,
      "loss": 0.9651,
      "step": 46
    },
    {
      "epoch": 2.08,
      "learning_rate": 4.162563277652104e-06,
      "loss": 0.9515,
      "step": 47
    },
    {
      "epoch": 2.12,
      "learning_rate": 3.7651019814126656e-06,
      "loss": 0.9565,
      "step": 48
    },
    {
      "epoch": 2.17,
      "learning_rate": 3.3831416240314085e-06,
      "loss": 0.9751,
      "step": 49
    },
    {
      "epoch": 2.21,
      "learning_rate": 3.017631819139273e-06,
      "loss": 0.9456,
      "step": 50
    },
    {
      "epoch": 2.25,
      "learning_rate": 2.669481281701739e-06,
      "loss": 0.9551,
      "step": 51
    },
    {
      "epoch": 2.3,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.9397,
      "step": 52
    },
    {
      "epoch": 2.34,
      "learning_rate": 2.0286749277707783e-06,
      "loss": 0.9437,
      "step": 53
    },
    {
      "epoch": 2.39,
      "learning_rate": 1.7376122568400533e-06,
      "loss": 0.938,
      "step": 54
    },
    {
      "epoch": 2.43,
      "learning_rate": 1.467091183678444e-06,
      "loss": 0.9395,
      "step": 55
    },
    {
      "epoch": 2.48,
      "learning_rate": 1.2177842662977136e-06,
      "loss": 0.944,
      "step": 56
    },
    {
      "epoch": 2.52,
      "learning_rate": 9.903113209758098e-07,
      "loss": 0.9169,
      "step": 57
    },
    {
      "epoch": 2.56,
      "learning_rate": 7.852378812959227e-07,
      "loss": 0.9301,
      "step": 58
    },
    {
      "epoch": 2.61,
      "learning_rate": 6.030737921409169e-07,
      "loss": 0.946,
      "step": 59
    },
    {
      "epoch": 2.65,
      "learning_rate": 4.4427194213859216e-07,
      "loss": 0.943,
      "step": 60
    },
    {
      "epoch": 2.7,
      "learning_rate": 3.0922713770922155e-07,
      "loss": 0.9523,
      "step": 61
    },
    {
      "epoch": 2.74,
      "learning_rate": 1.9827512151456175e-07,
      "loss": 0.916,
      "step": 62
    },
    {
      "epoch": 2.78,
      "learning_rate": 1.1169173774871478e-07,
      "loss": 0.9382,
      "step": 63
    },
    {
      "epoch": 2.83,
      "learning_rate": 4.9692246345985905e-08,
      "loss": 0.9543,
      "step": 64
    },
    {
      "epoch": 2.87,
      "learning_rate": 1.2430787810776556e-08,
      "loss": 0.9474,
      "step": 65
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0,
      "loss": 0.9358,
      "step": 66
    }
  ],
  "max_steps": 66,
  "num_train_epochs": 3,
  "total_flos": 85858745057280.0,
  "trial_name": null,
  "trial_params": null
}