{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 0,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034482758620689655,
      "grad_norm": 0.6793215870857239,
      "learning_rate": 9.655172413793105e-06,
      "loss": 1.6232,
      "step": 1
    },
    {
      "epoch": 0.06896551724137931,
      "grad_norm": 0.6347041130065918,
      "learning_rate": 9.310344827586207e-06,
      "loss": 1.575,
      "step": 2
    },
    {
      "epoch": 0.10344827586206896,
      "grad_norm": 0.5805194973945618,
      "learning_rate": 8.965517241379312e-06,
      "loss": 1.6011,
      "step": 3
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 0.5291101932525635,
      "learning_rate": 8.620689655172414e-06,
      "loss": 1.4978,
      "step": 4
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 0.5476824641227722,
      "learning_rate": 8.275862068965518e-06,
      "loss": 1.5871,
      "step": 5
    },
    {
      "epoch": 0.20689655172413793,
      "grad_norm": 0.5213686227798462,
      "learning_rate": 7.93103448275862e-06,
      "loss": 1.5345,
      "step": 6
    },
    {
      "epoch": 0.2413793103448276,
      "grad_norm": 0.48467984795570374,
      "learning_rate": 7.586206896551724e-06,
      "loss": 1.5334,
      "step": 7
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 0.5327280759811401,
      "learning_rate": 7.241379310344828e-06,
      "loss": 1.5781,
      "step": 8
    },
    {
      "epoch": 0.3103448275862069,
      "grad_norm": 0.45802709460258484,
      "learning_rate": 6.896551724137932e-06,
      "loss": 1.527,
      "step": 9
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.41651248931884766,
      "learning_rate": 6.551724137931035e-06,
      "loss": 1.4651,
      "step": 10
    },
    {
      "epoch": 0.3793103448275862,
      "grad_norm": 0.43467557430267334,
      "learning_rate": 6.206896551724138e-06,
      "loss": 1.5037,
      "step": 11
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 0.4417734146118164,
      "learning_rate": 5.862068965517242e-06,
      "loss": 1.5014,
      "step": 12
    },
    {
      "epoch": 0.4482758620689655,
      "grad_norm": 0.4484947919845581,
      "learning_rate": 5.517241379310345e-06,
      "loss": 1.531,
      "step": 13
    },
    {
      "epoch": 0.4827586206896552,
      "grad_norm": 0.4251164495944977,
      "learning_rate": 5.172413793103449e-06,
      "loss": 1.5195,
      "step": 14
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 0.4342622458934784,
      "learning_rate": 4.8275862068965525e-06,
      "loss": 1.4873,
      "step": 15
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 0.39838141202926636,
      "learning_rate": 4.482758620689656e-06,
      "loss": 1.505,
      "step": 16
    },
    {
      "epoch": 0.5862068965517241,
      "grad_norm": 0.39071160554885864,
      "learning_rate": 4.137931034482759e-06,
      "loss": 1.4806,
      "step": 17
    },
    {
      "epoch": 0.6206896551724138,
      "grad_norm": 0.39296573400497437,
      "learning_rate": 3.793103448275862e-06,
      "loss": 1.4711,
      "step": 18
    },
    {
      "epoch": 0.6551724137931034,
      "grad_norm": 0.4163892865180969,
      "learning_rate": 3.448275862068966e-06,
      "loss": 1.5433,
      "step": 19
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.39345088601112366,
      "learning_rate": 3.103448275862069e-06,
      "loss": 1.492,
      "step": 20
    },
    {
      "epoch": 0.7241379310344828,
      "grad_norm": 0.3705739974975586,
      "learning_rate": 2.7586206896551725e-06,
      "loss": 1.4745,
      "step": 21
    },
    {
      "epoch": 0.7586206896551724,
      "grad_norm": 0.36647993326187134,
      "learning_rate": 2.4137931034482762e-06,
      "loss": 1.4574,
      "step": 22
    },
    {
      "epoch": 0.7931034482758621,
      "grad_norm": 0.3478335440158844,
      "learning_rate": 2.0689655172413796e-06,
      "loss": 1.4456,
      "step": 23
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 0.39132043719291687,
      "learning_rate": 1.724137931034483e-06,
      "loss": 1.5449,
      "step": 24
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.33611077070236206,
      "learning_rate": 1.3793103448275862e-06,
      "loss": 1.4818,
      "step": 25
    },
    {
      "epoch": 0.896551724137931,
      "grad_norm": 0.34352853894233704,
      "learning_rate": 1.0344827586206898e-06,
      "loss": 1.4655,
      "step": 26
    },
    {
      "epoch": 0.9310344827586207,
      "grad_norm": 0.3807932138442993,
      "learning_rate": 6.896551724137931e-07,
      "loss": 1.4891,
      "step": 27
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 0.33738523721694946,
      "learning_rate": 3.4482758620689656e-07,
      "loss": 1.4687,
      "step": 28
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.32474052906036377,
      "learning_rate": 0.0,
      "loss": 1.3985,
      "step": 29
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 29,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0927152748822528e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}