{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008325354868251259,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016650709736502518,
      "grad_norm": 0.014066397212445736,
      "learning_rate": 1e-05,
      "loss": 10.3787,
      "step": 1
    },
    {
      "epoch": 0.00016650709736502518,
      "eval_loss": 10.377163887023926,
      "eval_runtime": 114.0301,
      "eval_samples_per_second": 88.705,
      "eval_steps_per_second": 44.357,
      "step": 1
    },
    {
      "epoch": 0.00033301419473005036,
      "grad_norm": 0.013571134768426418,
      "learning_rate": 2e-05,
      "loss": 10.3779,
      "step": 2
    },
    {
      "epoch": 0.00033301419473005036,
      "eval_loss": 10.377161026000977,
      "eval_runtime": 73.7608,
      "eval_samples_per_second": 137.133,
      "eval_steps_per_second": 68.573,
      "step": 2
    },
    {
      "epoch": 0.0004995212920950755,
      "grad_norm": 0.012663794681429863,
      "learning_rate": 3e-05,
      "loss": 10.3784,
      "step": 3
    },
    {
      "epoch": 0.0006660283894601007,
      "grad_norm": 0.014929154887795448,
      "learning_rate": 4e-05,
      "loss": 10.3793,
      "step": 4
    },
    {
      "epoch": 0.0006660283894601007,
      "eval_loss": 10.377142906188965,
      "eval_runtime": 59.0618,
      "eval_samples_per_second": 171.261,
      "eval_steps_per_second": 85.639,
      "step": 4
    },
    {
      "epoch": 0.0008325354868251259,
      "grad_norm": 0.01790194772183895,
      "learning_rate": 5e-05,
      "loss": 10.3777,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 517236326400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}