{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 6.549214839935303,
      "learning_rate": 0.0,
      "loss": 3.4994,
      "step": 1
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 6.105001449584961,
      "learning_rate": 2e-05,
      "loss": 3.2632,
      "step": 2
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 5.976911544799805,
      "learning_rate": 4e-05,
      "loss": 3.4378,
      "step": 3
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 3.958751916885376,
      "learning_rate": 6e-05,
      "loss": 3.1395,
      "step": 4
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 2.1597373485565186,
      "learning_rate": 8e-05,
      "loss": 2.835,
      "step": 5
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 1.4170883893966675,
      "learning_rate": 0.0001,
      "loss": 2.8319,
      "step": 6
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.4487881660461426,
      "learning_rate": 9.705882352941177e-05,
      "loss": 2.7282,
      "step": 7
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 1.3781570196151733,
      "learning_rate": 9.411764705882353e-05,
      "loss": 2.5667,
      "step": 8
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 1.3253191709518433,
      "learning_rate": 9.11764705882353e-05,
      "loss": 2.4651,
      "step": 9
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.2783066034317017,
      "learning_rate": 8.823529411764706e-05,
      "loss": 2.2565,
      "step": 10
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 1.1675422191619873,
      "learning_rate": 8.529411764705883e-05,
      "loss": 2.2769,
      "step": 11
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 1.0909103155136108,
      "learning_rate": 8.23529411764706e-05,
      "loss": 2.2644,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.3002947568893433,
      "learning_rate": 7.941176470588235e-05,
      "loss": 2.1082,
      "step": 13
    },
    {
      "epoch": 1.0792079207920793,
      "grad_norm": 0.9523069858551025,
      "learning_rate": 7.647058823529411e-05,
      "loss": 2.003,
      "step": 14
    },
    {
      "epoch": 1.1584158415841583,
      "grad_norm": 1.067624807357788,
      "learning_rate": 7.352941176470589e-05,
      "loss": 2.0389,
      "step": 15
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 0.9104287624359131,
      "learning_rate": 7.058823529411765e-05,
      "loss": 1.9365,
      "step": 16
    },
    {
      "epoch": 1.316831683168317,
      "grad_norm": 1.080199122428894,
      "learning_rate": 6.764705882352942e-05,
      "loss": 1.969,
      "step": 17
    },
    {
      "epoch": 1.396039603960396,
      "grad_norm": 0.9602163434028625,
      "learning_rate": 6.470588235294118e-05,
      "loss": 1.8985,
      "step": 18
    },
    {
      "epoch": 1.4752475247524752,
      "grad_norm": 1.0336861610412598,
      "learning_rate": 6.176470588235295e-05,
      "loss": 1.9017,
      "step": 19
    },
    {
      "epoch": 1.5544554455445545,
      "grad_norm": 1.0135937929153442,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.818,
      "step": 20
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 0.992509663105011,
      "learning_rate": 5.588235294117647e-05,
      "loss": 1.9192,
      "step": 21
    },
    {
      "epoch": 1.7128712871287128,
      "grad_norm": 1.026796579360962,
      "learning_rate": 5.294117647058824e-05,
      "loss": 1.8481,
      "step": 22
    },
    {
      "epoch": 1.7920792079207921,
      "grad_norm": 1.0603959560394287,
      "learning_rate": 5e-05,
      "loss": 1.8775,
      "step": 23
    },
    {
      "epoch": 1.8712871287128712,
      "grad_norm": 0.9811307787895203,
      "learning_rate": 4.705882352941177e-05,
      "loss": 1.8,
      "step": 24
    },
    {
      "epoch": 1.9504950495049505,
      "grad_norm": 0.9634355306625366,
      "learning_rate": 4.411764705882353e-05,
      "loss": 1.8717,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2133365869522095,
      "learning_rate": 4.11764705882353e-05,
      "loss": 1.7917,
      "step": 26
    },
    {
      "epoch": 2.0792079207920793,
      "grad_norm": 0.9011691212654114,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 1.7983,
      "step": 27
    },
    {
      "epoch": 2.1584158415841586,
      "grad_norm": 0.9259710311889648,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.7291,
      "step": 28
    },
    {
      "epoch": 2.237623762376238,
      "grad_norm": 1.024478554725647,
      "learning_rate": 3.235294117647059e-05,
      "loss": 1.6769,
      "step": 29
    },
    {
      "epoch": 2.3168316831683167,
      "grad_norm": 1.0245115756988525,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.6442,
      "step": 30
    },
    {
      "epoch": 2.396039603960396,
      "grad_norm": 0.9633392095565796,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.6068,
      "step": 31
    },
    {
      "epoch": 2.4752475247524752,
      "grad_norm": 1.0113288164138794,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.6279,
      "step": 32
    },
    {
      "epoch": 2.5544554455445545,
      "grad_norm": 0.9936370253562927,
      "learning_rate": 2.058823529411765e-05,
      "loss": 1.5992,
      "step": 33
    },
    {
      "epoch": 2.633663366336634,
      "grad_norm": 0.9961249232292175,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.5965,
      "step": 34
    },
    {
      "epoch": 2.7128712871287126,
      "grad_norm": 1.025579571723938,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.7482,
      "step": 35
    },
    {
      "epoch": 2.792079207920792,
      "grad_norm": 1.0427050590515137,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.6692,
      "step": 36
    },
    {
      "epoch": 2.871287128712871,
      "grad_norm": 1.0147291421890259,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.6683,
      "step": 37
    },
    {
      "epoch": 2.9504950495049505,
      "grad_norm": 0.9655409455299377,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.6321,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.2957016229629517,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.6597,
      "step": 39
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4251074854576128.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}