{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.7192285876347135,
  "eval_steps": 500,
  "global_step": 65,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.36,
      "learning_rate": 0.001,
      "loss": 8.1001,
      "step": 5
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.001,
      "loss": 5.9016,
      "step": 10
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.001,
      "loss": 5.0474,
      "step": 15
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.001,
      "loss": 4.644,
      "step": 20
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.001,
      "loss": 4.4853,
      "step": 25
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.001,
      "loss": 4.3012,
      "step": 30
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.001,
      "loss": 4.1877,
      "step": 35
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.001,
      "loss": 4.1647,
      "step": 40
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.001,
      "loss": 4.0409,
      "step": 45
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.001,
      "loss": 4.0197,
      "step": 50
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.001,
      "loss": 4.0058,
      "step": 55
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.001,
      "loss": 3.8439,
      "step": 60
    },
    {
      "epoch": 4.72,
      "learning_rate": 0.001,
      "loss": 3.9436,
      "step": 65
    },
    {
      "epoch": 4.72,
      "step": 65,
      "total_flos": 3818290544640000.0,
      "train_loss": 4.668148568960336,
      "train_runtime": 1730.4041,
      "train_samples_per_second": 5.094,
      "train_steps_per_second": 0.038
    }
  ],
  "logging_steps": 5,
  "max_steps": 65,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "total_flos": 3818290544640000.0,
  "trial_name": null,
  "trial_params": null
}