{
  "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": 2.086310863494873,
      "learning_rate": 0.0,
      "loss": 2.9605,
      "step": 1
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 2.012209415435791,
      "learning_rate": 2e-05,
      "loss": 2.9404,
      "step": 2
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 2.102048397064209,
      "learning_rate": 4e-05,
      "loss": 2.9326,
      "step": 3
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 1.8146204948425293,
      "learning_rate": 6e-05,
      "loss": 2.88,
      "step": 4
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 1.5558823347091675,
      "learning_rate": 8e-05,
      "loss": 2.7746,
      "step": 5
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 1.5457426309585571,
      "learning_rate": 0.0001,
      "loss": 2.7262,
      "step": 6
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.4023412466049194,
      "learning_rate": 9.705882352941177e-05,
      "loss": 2.4787,
      "step": 7
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 1.4058538675308228,
      "learning_rate": 9.411764705882353e-05,
      "loss": 2.4975,
      "step": 8
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 1.3084802627563477,
      "learning_rate": 9.11764705882353e-05,
      "loss": 2.3444,
      "step": 9
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.3247991800308228,
      "learning_rate": 8.823529411764706e-05,
      "loss": 2.3018,
      "step": 10
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 1.3896480798721313,
      "learning_rate": 8.529411764705883e-05,
      "loss": 2.3105,
      "step": 11
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 1.2478227615356445,
      "learning_rate": 8.23529411764706e-05,
      "loss": 2.1546,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.6431697607040405,
      "learning_rate": 7.941176470588235e-05,
      "loss": 2.1785,
      "step": 13
    },
    {
      "epoch": 1.0792079207920793,
      "grad_norm": 1.2522311210632324,
      "learning_rate": 7.647058823529411e-05,
      "loss": 2.0252,
      "step": 14
    },
    {
      "epoch": 1.1584158415841583,
      "grad_norm": 1.1055082082748413,
      "learning_rate": 7.352941176470589e-05,
      "loss": 1.969,
      "step": 15
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 1.122979998588562,
      "learning_rate": 7.058823529411765e-05,
      "loss": 2.0344,
      "step": 16
    },
    {
      "epoch": 1.316831683168317,
      "grad_norm": 1.1301175355911255,
      "learning_rate": 6.764705882352942e-05,
      "loss": 1.9367,
      "step": 17
    },
    {
      "epoch": 1.396039603960396,
      "grad_norm": 1.063119649887085,
      "learning_rate": 6.470588235294118e-05,
      "loss": 1.9193,
      "step": 18
    },
    {
      "epoch": 1.4752475247524752,
      "grad_norm": 1.098830223083496,
      "learning_rate": 6.176470588235295e-05,
      "loss": 1.982,
      "step": 19
    },
    {
      "epoch": 1.5544554455445545,
      "grad_norm": 1.0108693838119507,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.9742,
      "step": 20
    },
    {
      "epoch": 1.6336633663366338,
      "grad_norm": 1.07749342918396,
      "learning_rate": 5.588235294117647e-05,
      "loss": 1.8888,
      "step": 21
    },
    {
      "epoch": 1.7128712871287128,
      "grad_norm": 1.033948540687561,
      "learning_rate": 5.294117647058824e-05,
      "loss": 1.9594,
      "step": 22
    },
    {
      "epoch": 1.7920792079207921,
      "grad_norm": 1.0835351943969727,
      "learning_rate": 5e-05,
      "loss": 1.961,
      "step": 23
    },
    {
      "epoch": 1.8712871287128712,
      "grad_norm": 1.226639747619629,
      "learning_rate": 4.705882352941177e-05,
      "loss": 1.8515,
      "step": 24
    },
    {
      "epoch": 1.9504950495049505,
      "grad_norm": 1.0335575342178345,
      "learning_rate": 4.411764705882353e-05,
      "loss": 1.9053,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.5242691040039062,
      "learning_rate": 4.11764705882353e-05,
      "loss": 2.019,
      "step": 26
    },
    {
      "epoch": 2.0792079207920793,
      "grad_norm": 1.0608174800872803,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 1.792,
      "step": 27
    },
    {
      "epoch": 2.1584158415841586,
      "grad_norm": 1.087868332862854,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.7688,
      "step": 28
    },
    {
      "epoch": 2.237623762376238,
      "grad_norm": 1.0761433839797974,
      "learning_rate": 3.235294117647059e-05,
      "loss": 1.7183,
      "step": 29
    },
    {
      "epoch": 2.3168316831683167,
      "grad_norm": 1.09471595287323,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.8191,
      "step": 30
    },
    {
      "epoch": 2.396039603960396,
      "grad_norm": 1.1302402019500732,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.7561,
      "step": 31
    },
    {
      "epoch": 2.4752475247524752,
      "grad_norm": 1.1050896644592285,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.6831,
      "step": 32
    },
    {
      "epoch": 2.5544554455445545,
      "grad_norm": 1.1644535064697266,
      "learning_rate": 2.058823529411765e-05,
      "loss": 1.6604,
      "step": 33
    },
    {
      "epoch": 2.633663366336634,
      "grad_norm": 1.104153037071228,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.7274,
      "step": 34
    },
    {
      "epoch": 2.7128712871287126,
      "grad_norm": 1.1515814065933228,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.7369,
      "step": 35
    },
    {
      "epoch": 2.792079207920792,
      "grad_norm": 1.1602736711502075,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.6958,
      "step": 36
    },
    {
      "epoch": 2.871287128712871,
      "grad_norm": 1.1150407791137695,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.6371,
      "step": 37
    },
    {
      "epoch": 2.9504950495049505,
      "grad_norm": 1.1714621782302856,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.6682,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.5426967144012451,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.8014,
      "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": 3522656336517120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}