{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02768166089965398,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005536332179930796,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.005536332179930796,
      "eval_loss": NaN,
      "eval_runtime": 33.078,
      "eval_samples_per_second": 9.221,
      "eval_steps_per_second": 4.625,
      "step": 1
    },
    {
      "epoch": 0.011072664359861591,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.011072664359861591,
      "eval_loss": NaN,
      "eval_runtime": 1.4855,
      "eval_samples_per_second": 205.318,
      "eval_steps_per_second": 102.996,
      "step": 2
    },
    {
      "epoch": 0.01660899653979239,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.022145328719723183,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.022145328719723183,
      "eval_loss": NaN,
      "eval_runtime": 1.5635,
      "eval_samples_per_second": 195.077,
      "eval_steps_per_second": 97.858,
      "step": 4
    },
    {
      "epoch": 0.02768166089965398,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "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": 42995055329280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}