{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017095843573031308,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034191687146062615,
      "grad_norm": 0.23697754740715027,
      "learning_rate": 1e-05,
      "loss": 0.8763,
      "step": 1
    },
    {
      "epoch": 0.00034191687146062615,
      "eval_loss": 0.8716678023338318,
      "eval_runtime": 364.1248,
      "eval_samples_per_second": 13.528,
      "eval_steps_per_second": 6.764,
      "step": 1
    },
    {
      "epoch": 0.0006838337429212523,
      "grad_norm": 0.250388503074646,
      "learning_rate": 2e-05,
      "loss": 0.8897,
      "step": 2
    },
    {
      "epoch": 0.0006838337429212523,
      "eval_loss": 0.8679426312446594,
      "eval_runtime": 205.2095,
      "eval_samples_per_second": 24.005,
      "eval_steps_per_second": 12.002,
      "step": 2
    },
    {
      "epoch": 0.0010257506143818785,
      "grad_norm": 0.23880982398986816,
      "learning_rate": 3e-05,
      "loss": 0.892,
      "step": 3
    },
    {
      "epoch": 0.0013676674858425046,
      "grad_norm": 0.22471384704113007,
      "learning_rate": 4e-05,
      "loss": 0.7974,
      "step": 4
    },
    {
      "epoch": 0.0013676674858425046,
      "eval_loss": 0.8633438944816589,
      "eval_runtime": 329.7648,
      "eval_samples_per_second": 14.938,
      "eval_steps_per_second": 7.469,
      "step": 4
    },
    {
      "epoch": 0.0017095843573031308,
      "grad_norm": 0.24357256293296814,
      "learning_rate": 5e-05,
      "loss": 0.8763,
      "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": 6519713974714368.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}