{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09762050030506407,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004881025015253203,
      "grad_norm": 5.221165657043457,
      "learning_rate": 1e-05,
      "loss": 31.5558,
      "step": 1
    },
    {
      "epoch": 0.004881025015253203,
      "eval_loss": NaN,
      "eval_runtime": 41.1622,
      "eval_samples_per_second": 8.381,
      "eval_steps_per_second": 4.203,
      "step": 1
    },
    {
      "epoch": 0.009762050030506406,
      "grad_norm": 6.555931091308594,
      "learning_rate": 2e-05,
      "loss": 33.1187,
      "step": 2
    },
    {
      "epoch": 0.01464307504575961,
      "grad_norm": 5.362478256225586,
      "learning_rate": 3e-05,
      "loss": 33.9645,
      "step": 3
    },
    {
      "epoch": 0.019524100061012812,
      "grad_norm": 5.424245357513428,
      "learning_rate": 4e-05,
      "loss": 31.1053,
      "step": 4
    },
    {
      "epoch": 0.024405125076266018,
      "grad_norm": 5.1612162590026855,
      "learning_rate": 5e-05,
      "loss": 27.9206,
      "step": 5
    },
    {
      "epoch": 0.024405125076266018,
      "eval_loss": NaN,
      "eval_runtime": 20.8876,
      "eval_samples_per_second": 16.517,
      "eval_steps_per_second": 8.282,
      "step": 5
    },
    {
      "epoch": 0.02928615009151922,
      "grad_norm": 7.646149635314941,
      "learning_rate": 6e-05,
      "loss": 36.6748,
      "step": 6
    },
    {
      "epoch": 0.034167175106772425,
      "grad_norm": 7.209367275238037,
      "learning_rate": 7e-05,
      "loss": 32.7558,
      "step": 7
    },
    {
      "epoch": 0.039048200122025624,
      "grad_norm": 8.468503952026367,
      "learning_rate": 8e-05,
      "loss": 33.3483,
      "step": 8
    },
    {
      "epoch": 0.04392922513727883,
      "grad_norm": 9.408645629882812,
      "learning_rate": 9e-05,
      "loss": 27.8902,
      "step": 9
    },
    {
      "epoch": 0.048810250152532035,
      "grad_norm": 18.291357040405273,
      "learning_rate": 0.0001,
      "loss": 38.1456,
      "step": 10
    },
    {
      "epoch": 0.048810250152532035,
      "eval_loss": NaN,
      "eval_runtime": 12.8586,
      "eval_samples_per_second": 26.83,
      "eval_steps_per_second": 13.454,
      "step": 10
    },
    {
      "epoch": 0.053691275167785234,
      "grad_norm": 15.582109451293945,
      "learning_rate": 9.755282581475769e-05,
      "loss": 29.7319,
      "step": 11
    },
    {
      "epoch": 0.05857230018303844,
      "grad_norm": 15.503959655761719,
      "learning_rate": 9.045084971874738e-05,
      "loss": 23.9208,
      "step": 12
    },
    {
      "epoch": 0.06345332519829164,
      "grad_norm": 15.541723251342773,
      "learning_rate": 7.938926261462366e-05,
      "loss": 20.7569,
      "step": 13
    },
    {
      "epoch": 0.06833435021354485,
      "grad_norm": 13.2829008102417,
      "learning_rate": 6.545084971874738e-05,
      "loss": 15.8231,
      "step": 14
    },
    {
      "epoch": 0.07321537522879805,
      "grad_norm": 15.085909843444824,
      "learning_rate": 5e-05,
      "loss": 15.9119,
      "step": 15
    },
    {
      "epoch": 0.07321537522879805,
      "eval_loss": NaN,
      "eval_runtime": 12.8553,
      "eval_samples_per_second": 26.837,
      "eval_steps_per_second": 13.458,
      "step": 15
    },
    {
      "epoch": 0.07809640024405125,
      "grad_norm": 17.47039031982422,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 15.2074,
      "step": 16
    },
    {
      "epoch": 0.08297742525930446,
      "grad_norm": 18.992610931396484,
      "learning_rate": 2.061073738537635e-05,
      "loss": 16.7687,
      "step": 17
    },
    {
      "epoch": 0.08785845027455766,
      "grad_norm": 16.991191864013672,
      "learning_rate": 9.549150281252633e-06,
      "loss": 14.9071,
      "step": 18
    },
    {
      "epoch": 0.09273947528981086,
      "grad_norm": 18.0512752532959,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 16.9377,
      "step": 19
    },
    {
      "epoch": 0.09762050030506407,
      "grad_norm": 11.317153930664062,
      "learning_rate": 0.0,
      "loss": 11.7923,
      "step": 20
    },
    {
      "epoch": 0.09762050030506407,
      "eval_loss": NaN,
      "eval_runtime": 22.3144,
      "eval_samples_per_second": 15.461,
      "eval_steps_per_second": 7.753,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.7178938925056e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}