{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00270947639368692,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000541895278737384,
      "grad_norm": 0.017115788534283638,
      "learning_rate": 1e-05,
      "loss": 11.7633,
      "step": 1
    },
    {
      "epoch": 0.000541895278737384,
      "eval_loss": 11.762702941894531,
      "eval_runtime": 28.372,
      "eval_samples_per_second": 109.545,
      "eval_steps_per_second": 54.772,
      "step": 1
    },
    {
      "epoch": 0.001083790557474768,
      "grad_norm": 0.026317128911614418,
      "learning_rate": 2e-05,
      "loss": 11.7575,
      "step": 2
    },
    {
      "epoch": 0.001083790557474768,
      "eval_loss": 11.762699127197266,
      "eval_runtime": 14.8648,
      "eval_samples_per_second": 209.085,
      "eval_steps_per_second": 104.542,
      "step": 2
    },
    {
      "epoch": 0.001625685836212152,
      "grad_norm": 0.024394601583480835,
      "learning_rate": 3e-05,
      "loss": 11.7645,
      "step": 3
    },
    {
      "epoch": 0.002167581114949536,
      "grad_norm": 0.02581326849758625,
      "learning_rate": 4e-05,
      "loss": 11.7582,
      "step": 4
    },
    {
      "epoch": 0.002167581114949536,
      "eval_loss": 11.762683868408203,
      "eval_runtime": 14.9414,
      "eval_samples_per_second": 208.012,
      "eval_steps_per_second": 104.006,
      "step": 4
    },
    {
      "epoch": 0.00270947639368692,
      "grad_norm": 0.023471258580684662,
      "learning_rate": 5e-05,
      "loss": 11.7628,
      "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": 1079081533440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}