{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01705516920859751,
  "eval_steps": 2500,
  "global_step": 20000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 4.0477,
      "step": 500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 3.362,
      "step": 1000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 3.1288,
      "step": 1500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.9448,
      "step": 2000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.7412,
      "step": 2500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.6923,
      "step": 3000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.626,
      "step": 3500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.573,
      "step": 4000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.5107,
      "step": 4500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.4911,
      "step": 5000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 2.4486,
      "step": 5500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.4078,
      "step": 6000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.4018,
      "step": 6500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.3685,
      "step": 7000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.3276,
      "step": 7500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.2816,
      "step": 8000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.2986,
      "step": 8500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.2612,
      "step": 9000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.2599,
      "step": 9500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.236,
      "step": 10000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.2057,
      "step": 10500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.1507,
      "step": 11000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.1503,
      "step": 11500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.1285,
      "step": 12000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.0999,
      "step": 12500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.0573,
      "step": 13000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.0916,
      "step": 13500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.0308,
      "step": 14000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.9891,
      "step": 14500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.07,
      "step": 15000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.0298,
      "step": 15500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.9939,
      "step": 16000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 2.0202,
      "step": 16500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.9513,
      "step": 17000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.9685,
      "step": 17500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.963,
      "step": 18000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.9376,
      "step": 18500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.9577,
      "step": 19000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.9424,
      "step": 19500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.9609,
      "step": 20000
    }
  ],
  "logging_steps": 500,
  "max_steps": 20000,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "total_flos": 9.652535293088563e+16,
  "trial_name": null,
  "trial_params": null
}