{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.921962992759453,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0,
      "loss": 0.5933,
      "step": 1
    },
    {
      "epoch": 0.1,
      "learning_rate": 0,
      "loss": 0.6073,
      "step": 2
    },
    {
      "epoch": 0.16,
      "learning_rate": 0,
      "loss": 0.6047,
      "step": 3
    },
    {
      "epoch": 0.21,
      "learning_rate": 0,
      "loss": 0.5982,
      "step": 4
    },
    {
      "epoch": 0.26,
      "learning_rate": 0,
      "loss": 0.5986,
      "step": 5
    },
    {
      "epoch": 0.31,
      "learning_rate": 0,
      "loss": 0.593,
      "step": 6
    },
    {
      "epoch": 0.37,
      "learning_rate": 0,
      "loss": 0.5914,
      "step": 7
    },
    {
      "epoch": 0.42,
      "learning_rate": 0,
      "loss": 0.6023,
      "step": 8
    },
    {
      "epoch": 0.47,
      "learning_rate": 0,
      "loss": 0.6148,
      "step": 9
    },
    {
      "epoch": 0.52,
      "learning_rate": 0,
      "loss": 0.5973,
      "step": 10
    },
    {
      "epoch": 0.58,
      "learning_rate": 0,
      "loss": 0.5975,
      "step": 11
    },
    {
      "epoch": 0.63,
      "learning_rate": 0,
      "loss": 0.5867,
      "step": 12
    },
    {
      "epoch": 0.68,
      "learning_rate": 0,
      "loss": 0.5975,
      "step": 13
    },
    {
      "epoch": 0.73,
      "learning_rate": 0,
      "loss": 0.6077,
      "step": 14
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0,
      "loss": 0.6097,
      "step": 15
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0,
      "loss": 0.6477,
      "step": 16
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.020599913279623e-06,
      "loss": 0.649,
      "step": 17
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.542425094393249e-06,
      "loss": 0.647,
      "step": 18
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.2041199826559246e-05,
      "loss": 0.6232,
      "step": 19
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.3979400086720374e-05,
      "loss": 0.5682,
      "step": 20
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.5563025007672873e-05,
      "loss": 0.5723,
      "step": 21
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.6901960800285137e-05,
      "loss": 0.5791,
      "step": 22
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.806179973983887e-05,
      "loss": 0.575,
      "step": 23
    },
    {
      "epoch": 1.26,
      "learning_rate": 1.9084850188786497e-05,
      "loss": 0.5563,
      "step": 24
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.569,
      "step": 25
    },
    {
      "epoch": 1.36,
      "learning_rate": 2e-05,
      "loss": 0.5692,
      "step": 26
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.96969696969697e-05,
      "loss": 0.5626,
      "step": 27
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.9393939393939395e-05,
      "loss": 0.545,
      "step": 28
    },
    {
      "epoch": 1.52,
      "learning_rate": 1.9090909090909094e-05,
      "loss": 0.5551,
      "step": 29
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.8787878787878792e-05,
      "loss": 0.5515,
      "step": 30
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.8484848484848487e-05,
      "loss": 0.5383,
      "step": 31
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.5502,
      "step": 32
    },
    {
      "epoch": 1.73,
      "learning_rate": 1.787878787878788e-05,
      "loss": 0.5573,
      "step": 33
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.7575757575757576e-05,
      "loss": 0.5423,
      "step": 34
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.7272727272727274e-05,
      "loss": 0.5436,
      "step": 35
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.6969696969696972e-05,
      "loss": 0.5366,
      "step": 36
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5452,
      "step": 37
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 0.5332,
      "step": 38
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.606060606060606e-05,
      "loss": 0.494,
      "step": 39
    },
    {
      "epoch": 2.09,
      "learning_rate": 1.575757575757576e-05,
      "loss": 0.4812,
      "step": 40
    },
    {
      "epoch": 2.14,
      "learning_rate": 1.5454545454545454e-05,
      "loss": 0.4865,
      "step": 41
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 0.4863,
      "step": 42
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.484848484848485e-05,
      "loss": 0.4869,
      "step": 43
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.4545454545454546e-05,
      "loss": 0.4744,
      "step": 44
    },
    {
      "epoch": 2.35,
      "learning_rate": 1.4242424242424245e-05,
      "loss": 0.4769,
      "step": 45
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.3939393939393942e-05,
      "loss": 0.4812,
      "step": 46
    },
    {
      "epoch": 2.46,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 0.4683,
      "step": 47
    },
    {
      "epoch": 2.51,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.4783,
      "step": 48
    },
    {
      "epoch": 2.56,
      "learning_rate": 1.3030303030303032e-05,
      "loss": 0.471,
      "step": 49
    },
    {
      "epoch": 2.61,
      "learning_rate": 1.2727272727272728e-05,
      "loss": 0.4695,
      "step": 50
    },
    {
      "epoch": 2.67,
      "learning_rate": 1.2424242424242425e-05,
      "loss": 0.4616,
      "step": 51
    },
    {
      "epoch": 2.72,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 0.4683,
      "step": 52
    },
    {
      "epoch": 2.77,
      "learning_rate": 1.181818181818182e-05,
      "loss": 0.471,
      "step": 53
    },
    {
      "epoch": 2.82,
      "learning_rate": 1.1515151515151517e-05,
      "loss": 0.457,
      "step": 54
    },
    {
      "epoch": 2.88,
      "learning_rate": 1.1212121212121212e-05,
      "loss": 0.4613,
      "step": 55
    },
    {
      "epoch": 2.93,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 0.4585,
      "step": 56
    },
    {
      "epoch": 2.98,
      "learning_rate": 1.0606060606060606e-05,
      "loss": 0.4623,
      "step": 57
    },
    {
      "epoch": 3.03,
      "learning_rate": 1.0303030303030304e-05,
      "loss": 0.44,
      "step": 58
    },
    {
      "epoch": 3.09,
      "learning_rate": 1e-05,
      "loss": 0.4382,
      "step": 59
    },
    {
      "epoch": 3.14,
      "learning_rate": 9.696969696969698e-06,
      "loss": 0.4222,
      "step": 60
    },
    {
      "epoch": 3.19,
      "learning_rate": 9.393939393939396e-06,
      "loss": 0.4287,
      "step": 61
    },
    {
      "epoch": 3.24,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.4196,
      "step": 62
    },
    {
      "epoch": 3.29,
      "learning_rate": 8.787878787878788e-06,
      "loss": 0.417,
      "step": 63
    },
    {
      "epoch": 3.35,
      "learning_rate": 8.484848484848486e-06,
      "loss": 0.4203,
      "step": 64
    },
    {
      "epoch": 3.4,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.4195,
      "step": 65
    },
    {
      "epoch": 3.45,
      "learning_rate": 7.87878787878788e-06,
      "loss": 0.4221,
      "step": 66
    },
    {
      "epoch": 3.5,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 0.4148,
      "step": 67
    },
    {
      "epoch": 3.56,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.4171,
      "step": 68
    },
    {
      "epoch": 3.61,
      "learning_rate": 6.969696969696971e-06,
      "loss": 0.4204,
      "step": 69
    },
    {
      "epoch": 3.66,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.4176,
      "step": 70
    },
    {
      "epoch": 3.71,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.4136,
      "step": 71
    },
    {
      "epoch": 3.77,
      "learning_rate": 6.060606060606061e-06,
      "loss": 0.4201,
      "step": 72
    },
    {
      "epoch": 3.82,
      "learning_rate": 5.7575757575757586e-06,
      "loss": 0.4065,
      "step": 73
    },
    {
      "epoch": 3.87,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.4163,
      "step": 74
    },
    {
      "epoch": 3.92,
      "learning_rate": 5.151515151515152e-06,
      "loss": 0.415,
      "step": 75
    }
  ],
  "max_steps": 76,
  "num_train_epochs": 4,
  "total_flos": 8.226533079758406e+18,
  "trial_name": null,
  "trial_params": null
}