{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005732301519059902,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011464603038119805,
      "grad_norm": 0.016806595027446747,
      "learning_rate": 1e-05,
      "loss": 11.9434,
      "step": 1
    },
    {
      "epoch": 0.0011464603038119805,
      "eval_loss": 11.943551063537598,
      "eval_runtime": 8.2169,
      "eval_samples_per_second": 178.899,
      "eval_steps_per_second": 89.45,
      "step": 1
    },
    {
      "epoch": 0.002292920607623961,
      "grad_norm": 0.014706296846270561,
      "learning_rate": 2e-05,
      "loss": 11.942,
      "step": 2
    },
    {
      "epoch": 0.002292920607623961,
      "eval_loss": 11.943548202514648,
      "eval_runtime": 2.0668,
      "eval_samples_per_second": 711.26,
      "eval_steps_per_second": 355.63,
      "step": 2
    },
    {
      "epoch": 0.0034393809114359416,
      "grad_norm": 0.017973467707633972,
      "learning_rate": 3e-05,
      "loss": 11.9459,
      "step": 3
    },
    {
      "epoch": 0.004585841215247922,
      "grad_norm": 0.018925825133919716,
      "learning_rate": 4e-05,
      "loss": 11.9411,
      "step": 4
    },
    {
      "epoch": 0.004585841215247922,
      "eval_loss": 11.943533897399902,
      "eval_runtime": 2.1156,
      "eval_samples_per_second": 694.843,
      "eval_steps_per_second": 347.421,
      "step": 4
    },
    {
      "epoch": 0.005732301519059902,
      "grad_norm": 0.015836453065276146,
      "learning_rate": 5e-05,
      "loss": 11.9431,
      "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": 2363228160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}