{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.026455026455026454,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026455026455026454,
      "grad_norm": 0.3250984251499176,
      "learning_rate": 2e-05,
      "loss": 10.8434,
      "step": 1
    },
    {
      "epoch": 0.0026455026455026454,
      "eval_loss": 10.844588279724121,
      "eval_runtime": 1.3642,
      "eval_samples_per_second": 117.282,
      "eval_steps_per_second": 58.641,
      "step": 1
    },
    {
      "epoch": 0.005291005291005291,
      "grad_norm": 0.4192297160625458,
      "learning_rate": 4e-05,
      "loss": 10.8485,
      "step": 2
    },
    {
      "epoch": 0.007936507936507936,
      "grad_norm": 0.42748063802719116,
      "learning_rate": 6e-05,
      "loss": 10.833,
      "step": 3
    },
    {
      "epoch": 0.007936507936507936,
      "eval_loss": 10.844182968139648,
      "eval_runtime": 0.4867,
      "eval_samples_per_second": 328.764,
      "eval_steps_per_second": 164.382,
      "step": 3
    },
    {
      "epoch": 0.010582010582010581,
      "grad_norm": 0.36031121015548706,
      "learning_rate": 8e-05,
      "loss": 10.8367,
      "step": 4
    },
    {
      "epoch": 0.013227513227513227,
      "grad_norm": 0.25945383310317993,
      "learning_rate": 0.0001,
      "loss": 10.8487,
      "step": 5
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 0.3726327121257782,
      "learning_rate": 0.00012,
      "loss": 10.8405,
      "step": 6
    },
    {
      "epoch": 0.015873015873015872,
      "eval_loss": 10.841897964477539,
      "eval_runtime": 0.4974,
      "eval_samples_per_second": 321.683,
      "eval_steps_per_second": 160.841,
      "step": 6
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 0.30775487422943115,
      "learning_rate": 0.00014,
      "loss": 10.8418,
      "step": 7
    },
    {
      "epoch": 0.021164021164021163,
      "grad_norm": 0.3520079255104065,
      "learning_rate": 0.00016,
      "loss": 10.843,
      "step": 8
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 0.31247809529304504,
      "learning_rate": 0.00018,
      "loss": 10.8267,
      "step": 9
    },
    {
      "epoch": 0.023809523809523808,
      "eval_loss": 10.838133811950684,
      "eval_runtime": 0.4872,
      "eval_samples_per_second": 328.439,
      "eval_steps_per_second": 164.219,
      "step": 9
    },
    {
      "epoch": 0.026455026455026454,
      "grad_norm": 0.27570220828056335,
      "learning_rate": 0.0002,
      "loss": 10.8264,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1291965825024.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}