{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00825082508250825,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008250825082508251,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 2.7478,
      "step": 1
    },
    {
      "epoch": 0.0008250825082508251,
      "eval_loss": NaN,
      "eval_runtime": 28.8115,
      "eval_samples_per_second": 17.736,
      "eval_steps_per_second": 8.885,
      "step": 1
    },
    {
      "epoch": 0.0016501650165016502,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 1.7026,
      "step": 2
    },
    {
      "epoch": 0.0024752475247524753,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 4.3595,
      "step": 3
    },
    {
      "epoch": 0.0024752475247524753,
      "eval_loss": NaN,
      "eval_runtime": 27.4562,
      "eval_samples_per_second": 18.611,
      "eval_steps_per_second": 9.324,
      "step": 3
    },
    {
      "epoch": 0.0033003300330033004,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 1.8586,
      "step": 4
    },
    {
      "epoch": 0.004125412541254125,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 7.1714,
      "step": 5
    },
    {
      "epoch": 0.0049504950495049506,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 7.9769,
      "step": 6
    },
    {
      "epoch": 0.0049504950495049506,
      "eval_loss": NaN,
      "eval_runtime": 27.504,
      "eval_samples_per_second": 18.579,
      "eval_steps_per_second": 9.308,
      "step": 6
    },
    {
      "epoch": 0.005775577557755775,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 7.0561,
      "step": 7
    },
    {
      "epoch": 0.006600660066006601,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 7.3968,
      "step": 8
    },
    {
      "epoch": 0.007425742574257425,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 3.491,
      "step": 9
    },
    {
      "epoch": 0.007425742574257425,
      "eval_loss": NaN,
      "eval_runtime": 27.4746,
      "eval_samples_per_second": 18.599,
      "eval_steps_per_second": 9.318,
      "step": 9
    },
    {
      "epoch": 0.00825082508250825,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 3.6194,
      "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": 3505343598428160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}