{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9974160206718347,
  "eval_steps": 500,
  "global_step": 193,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.8521,
      "step": 10
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.4306,
      "step": 20
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.3037,
      "step": 30
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.2252,
      "step": 40
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.2007,
      "step": 50
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.1315,
      "step": 60
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.1229,
      "step": 70
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.0858,
      "step": 80
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.0459,
      "step": 90
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.0339,
      "step": 100
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.0291,
      "step": 110
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.9882,
      "step": 120
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.9745,
      "step": 130
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.964,
      "step": 140
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.9044,
      "step": 150
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.853,
      "step": 160
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.8678,
      "step": 170
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.8541,
      "step": 180
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.819,
      "step": 190
    }
  ],
  "logging_steps": 10,
  "max_steps": 579,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.2632199387099955e+17,
  "trial_name": null,
  "trial_params": null
}