{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.47945205479452,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 0.0,
      "loss": 1.7614,
      "step": 1
    },
    {
      "epoch": 0.22,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.7635,
      "step": 2
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.8003,
      "step": 3
    },
    {
      "epoch": 0.44,
      "learning_rate": 1e-05,
      "loss": 1.5796,
      "step": 4
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.2226,
      "step": 5
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.0885,
      "step": 6
    },
    {
      "epoch": 0.77,
      "learning_rate": 2e-05,
      "loss": 0.9511,
      "step": 7
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.9998370105646414e-05,
      "loss": 0.8972,
      "step": 8
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.999348095389677e-05,
      "loss": 0.8481,
      "step": 9
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.998533413851124e-05,
      "loss": 0.72,
      "step": 10
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.9973932315179502e-05,
      "loss": 0.6775,
      "step": 11
    },
    {
      "epoch": 1.32,
      "learning_rate": 1.9959279200655044e-05,
      "loss": 0.6507,
      "step": 12
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.9941379571543597e-05,
      "loss": 0.6566,
      "step": 13
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.9920239262746045e-05,
      "loss": 0.6627,
      "step": 14
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.9895865165556375e-05,
      "loss": 0.6135,
      "step": 15
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.9868265225415263e-05,
      "loss": 0.6025,
      "step": 16
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.9837448439320027e-05,
      "loss": 0.6242,
      "step": 17
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.9803424852891803e-05,
      "loss": 0.5891,
      "step": 18
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.976620555710087e-05,
      "loss": 0.4496,
      "step": 19
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.9725802684651235e-05,
      "loss": 0.3549,
      "step": 20
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.9682229406025635e-05,
      "loss": 0.3397,
      "step": 21
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.963549992519223e-05,
      "loss": 0.3178,
      "step": 22
    },
    {
      "epoch": 2.52,
      "learning_rate": 1.9585629474974413e-05,
      "loss": 0.3091,
      "step": 23
    },
    {
      "epoch": 2.63,
      "learning_rate": 1.953263431208523e-05,
      "loss": 0.3234,
      "step": 24
    },
    {
      "epoch": 2.74,
      "learning_rate": 1.9476531711828027e-05,
      "loss": 0.3159,
      "step": 25
    },
    {
      "epoch": 2.85,
      "learning_rate": 1.9417339962465084e-05,
      "loss": 0.3129,
      "step": 26
    },
    {
      "epoch": 2.96,
      "learning_rate": 1.935507835925601e-05,
      "loss": 0.3669,
      "step": 27
    },
    {
      "epoch": 3.07,
      "learning_rate": 1.9289767198167918e-05,
      "loss": 0.2294,
      "step": 28
    },
    {
      "epoch": 3.18,
      "learning_rate": 1.9221427769259333e-05,
      "loss": 0.1704,
      "step": 29
    },
    {
      "epoch": 3.29,
      "learning_rate": 1.9150082349740123e-05,
      "loss": 0.1899,
      "step": 30
    },
    {
      "epoch": 3.4,
      "learning_rate": 1.9075754196709574e-05,
      "loss": 0.1905,
      "step": 31
    },
    {
      "epoch": 3.51,
      "learning_rate": 1.899846753957507e-05,
      "loss": 0.1895,
      "step": 32
    },
    {
      "epoch": 3.62,
      "learning_rate": 1.8918247572153822e-05,
      "loss": 0.1743,
      "step": 33
    },
    {
      "epoch": 3.73,
      "learning_rate": 1.883512044446023e-05,
      "loss": 0.1939,
      "step": 34
    },
    {
      "epoch": 3.84,
      "learning_rate": 1.8749113254181498e-05,
      "loss": 0.1848,
      "step": 35
    },
    {
      "epoch": 3.95,
      "learning_rate": 1.866025403784439e-05,
      "loss": 0.2112,
      "step": 36
    },
    {
      "epoch": 4.05,
      "learning_rate": 1.8568571761675893e-05,
      "loss": 0.15,
      "step": 37
    },
    {
      "epoch": 4.16,
      "learning_rate": 1.8474096312160866e-05,
      "loss": 0.1066,
      "step": 38
    },
    {
      "epoch": 4.27,
      "learning_rate": 1.837685848629965e-05,
      "loss": 0.1108,
      "step": 39
    },
    {
      "epoch": 4.38,
      "learning_rate": 1.827688998156891e-05,
      "loss": 0.1048,
      "step": 40
    },
    {
      "epoch": 4.49,
      "learning_rate": 1.817422338558892e-05,
      "loss": 0.1231,
      "step": 41
    },
    {
      "epoch": 4.6,
      "learning_rate": 1.8068892165500704e-05,
      "loss": 0.1145,
      "step": 42
    },
    {
      "epoch": 4.71,
      "learning_rate": 1.796093065705644e-05,
      "loss": 0.1314,
      "step": 43
    },
    {
      "epoch": 4.82,
      "learning_rate": 1.7850374053426725e-05,
      "loss": 0.1281,
      "step": 44
    },
    {
      "epoch": 4.93,
      "learning_rate": 1.7737258393728363e-05,
      "loss": 0.1389,
      "step": 45
    },
    {
      "epoch": 5.04,
      "learning_rate": 1.7621620551276366e-05,
      "loss": 0.0999,
      "step": 46
    },
    {
      "epoch": 5.15,
      "learning_rate": 1.7503498221564026e-05,
      "loss": 0.0716,
      "step": 47
    },
    {
      "epoch": 5.26,
      "learning_rate": 1.7382929909974988e-05,
      "loss": 0.088,
      "step": 48
    },
    {
      "epoch": 5.37,
      "learning_rate": 1.725995491923131e-05,
      "loss": 0.0809,
      "step": 49
    },
    {
      "epoch": 5.48,
      "learning_rate": 1.7134613336581602e-05,
      "loss": 0.0747,
      "step": 50
    }
  ],
  "max_steps": 180,
  "num_train_epochs": 20,
  "total_flos": 1.32068633739264e+17,
  "trial_name": null,
  "trial_params": null
}