{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.999745123027154,
  "global_step": 9561,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 2.3693,
      "step": 500
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 2.3495,
      "step": 1000
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001,
      "loss": 2.342,
      "step": 1500
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001,
      "loss": 2.3221,
      "step": 2000
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 2.3242,
      "step": 2500
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001,
      "loss": 2.3137,
      "step": 3000
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001,
      "loss": 2.3027,
      "step": 3500
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001,
      "loss": 2.2815,
      "step": 4000
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0001,
      "loss": 2.2797,
      "step": 4500
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0001,
      "loss": 2.2757,
      "step": 5000
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001,
      "loss": 2.2765,
      "step": 5500
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0001,
      "loss": 2.2684,
      "step": 6000
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0001,
      "loss": 2.261,
      "step": 6500
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0001,
      "loss": 2.2373,
      "step": 7000
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0001,
      "loss": 2.2413,
      "step": 7500
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0001,
      "loss": 2.2277,
      "step": 8000
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0001,
      "loss": 2.2338,
      "step": 8500
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0001,
      "loss": 2.2395,
      "step": 9000
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0001,
      "loss": 2.2297,
      "step": 9500
    },
    {
      "epoch": 3.0,
      "step": 9561,
      "total_flos": 1.655576989296722e+17,
      "train_loss": 2.2826747393560716,
      "train_runtime": 17657.3625,
      "train_samples_per_second": 34.663,
      "train_steps_per_second": 0.541
    }
  ],
  "max_steps": 9561,
  "num_train_epochs": 3,
  "total_flos": 1.655576989296722e+17,
  "trial_name": null,
  "trial_params": null
}