{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8274776852329147,
  "global_step": 61000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 0.0382,
      "step": 500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 0.0375,
      "step": 1000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 0.0381,
      "step": 1500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0,
      "loss": 0.0369,
      "step": 2000
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0,
      "loss": 0.036,
      "step": 2500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0,
      "loss": 0.0377,
      "step": 3000
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0,
      "loss": 0.0373,
      "step": 3500
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0,
      "loss": 0.0373,
      "step": 4000
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0,
      "loss": 0.0357,
      "step": 4500
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0,
      "loss": 0.0388,
      "step": 5000
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0,
      "loss": 0.0372,
      "step": 5500
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0,
      "loss": 0.0399,
      "step": 6000
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0,
      "loss": 0.0385,
      "step": 6500
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0,
      "loss": 0.0382,
      "step": 7000
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0,
      "loss": 0.0361,
      "step": 7500
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0,
      "loss": 0.0358,
      "step": 8000
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0,
      "loss": 0.04,
      "step": 8500
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0,
      "loss": 0.036,
      "step": 9000
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0,
      "loss": 0.0378,
      "step": 9500
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0,
      "loss": 0.0362,
      "step": 10000
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0,
      "loss": 0.0378,
      "step": 10500
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0,
      "loss": 0.0385,
      "step": 11000
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0,
      "loss": 0.0385,
      "step": 11500
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0,
      "loss": 0.0372,
      "step": 12000
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0,
      "loss": 0.0364,
      "step": 12500
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0,
      "loss": 0.0368,
      "step": 13000
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0,
      "loss": 0.0408,
      "step": 13500
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0,
      "loss": 0.0378,
      "step": 14000
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0,
      "loss": 0.0376,
      "step": 14500
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0,
      "loss": 0.0397,
      "step": 15000
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0,
      "loss": 0.0372,
      "step": 15500
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0,
      "loss": 0.0356,
      "step": 16000
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0,
      "loss": 0.0367,
      "step": 16500
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0,
      "loss": 0.0392,
      "step": 17000
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0,
      "loss": 0.0384,
      "step": 17500
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0,
      "loss": 0.0403,
      "step": 18000
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0,
      "loss": 0.0361,
      "step": 18500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0,
      "loss": 0.04,
      "step": 19000
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0,
      "loss": 0.0361,
      "step": 19500
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0,
      "loss": 0.0371,
      "step": 20000
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0,
      "loss": 0.0369,
      "step": 20500
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0,
      "loss": 0.0397,
      "step": 21000
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0,
      "loss": 0.0374,
      "step": 21500
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0,
      "loss": 0.0407,
      "step": 22000
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0,
      "loss": 0.0399,
      "step": 22500
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0,
      "loss": 0.038,
      "step": 23000
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0,
      "loss": 0.0384,
      "step": 23500
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0,
      "loss": 0.0361,
      "step": 24000
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0,
      "loss": 0.0376,
      "step": 24500
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0,
      "loss": 0.0362,
      "step": 25000
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0,
      "loss": 0.0373,
      "step": 25500
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0,
      "loss": 0.0371,
      "step": 26000
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0,
      "loss": 0.038,
      "step": 26500
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0,
      "loss": 0.0362,
      "step": 27000
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0,
      "loss": 0.0358,
      "step": 27500
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0,
      "loss": 0.037,
      "step": 28000
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0,
      "loss": 0.0374,
      "step": 28500
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0,
      "loss": 0.0362,
      "step": 29000
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0,
      "loss": 0.0361,
      "step": 29500
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0,
      "loss": 0.0385,
      "step": 30000
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0,
      "loss": 0.0403,
      "step": 30500
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0,
      "loss": 0.0356,
      "step": 31000
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0,
      "loss": 0.0398,
      "step": 31500
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0,
      "loss": 0.0363,
      "step": 32000
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0,
      "loss": 0.0375,
      "step": 32500
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0,
      "loss": 0.0376,
      "step": 33000
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0,
      "loss": 0.0388,
      "step": 33500
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0,
      "loss": 0.035,
      "step": 34000
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0,
      "loss": 0.0369,
      "step": 34500
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0,
      "loss": 0.0388,
      "step": 35000
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0,
      "loss": 0.0372,
      "step": 35500
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0,
      "loss": 0.039,
      "step": 36000
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0,
      "loss": 0.0359,
      "step": 36500
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0,
      "loss": 0.0362,
      "step": 37000
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0,
      "loss": 0.039,
      "step": 37500
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0,
      "loss": 0.0397,
      "step": 38000
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0,
      "loss": 0.0381,
      "step": 38500
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0,
      "loss": 0.0362,
      "step": 39000
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0,
      "loss": 0.0358,
      "step": 39500
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0,
      "loss": 0.0383,
      "step": 40000
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0,
      "loss": 0.0402,
      "step": 40500
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0,
      "loss": 0.0368,
      "step": 41000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0,
      "loss": 0.0387,
      "step": 41500
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0,
      "loss": 0.035,
      "step": 42000
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0,
      "loss": 0.0377,
      "step": 42500
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0,
      "loss": 0.0391,
      "step": 43000
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0,
      "loss": 0.0389,
      "step": 43500
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0,
      "loss": 0.039,
      "step": 44000
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0,
      "loss": 0.0375,
      "step": 44500
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0,
      "loss": 0.0381,
      "step": 45000
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0,
      "loss": 0.0374,
      "step": 45500
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0,
      "loss": 0.0376,
      "step": 46000
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0,
      "loss": 0.038,
      "step": 46500
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0,
      "loss": 0.0389,
      "step": 47000
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0,
      "loss": 0.0379,
      "step": 47500
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0,
      "loss": 0.0359,
      "step": 48000
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0,
      "loss": 0.0379,
      "step": 48500
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0,
      "loss": 0.0386,
      "step": 49000
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0,
      "loss": 0.0402,
      "step": 49500
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0,
      "loss": 0.0357,
      "step": 50000
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0,
      "loss": 0.0379,
      "step": 50500
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0,
      "loss": 0.0378,
      "step": 51000
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0,
      "loss": 0.0363,
      "step": 51500
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0,
      "loss": 0.0379,
      "step": 52000
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0,
      "loss": 0.0413,
      "step": 52500
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0,
      "loss": 0.0343,
      "step": 53000
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0,
      "loss": 0.0363,
      "step": 53500
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0,
      "loss": 0.0371,
      "step": 54000
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0,
      "loss": 0.0357,
      "step": 54500
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0,
      "loss": 0.0388,
      "step": 55000
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0,
      "loss": 0.0362,
      "step": 55500
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0,
      "loss": 0.0355,
      "step": 56000
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0,
      "loss": 0.0365,
      "step": 56500
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0,
      "loss": 0.0395,
      "step": 57000
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0,
      "loss": 0.039,
      "step": 57500
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0,
      "loss": 0.0363,
      "step": 58000
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0,
      "loss": 0.0394,
      "step": 58500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0,
      "loss": 0.0368,
      "step": 59000
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0,
      "loss": 0.0384,
      "step": 59500
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0,
      "loss": 0.0369,
      "step": 60000
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0,
      "loss": 0.0381,
      "step": 60500
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0,
      "loss": 0.0389,
      "step": 61000
    }
  ],
  "max_steps": 73718,
  "num_train_epochs": 1,
  "total_flos": 6.373662140871475e+16,
  "trial_name": null,
  "trial_params": null
}