{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3407590759075907,
  "global_step": 26000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 4.957026952695269e-05,
      "loss": 2.2472,
      "step": 500
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9140539053905395e-05,
      "loss": 2.1914,
      "step": 1000
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.8710808580858085e-05,
      "loss": 2.2388,
      "step": 1500
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.828107810781078e-05,
      "loss": 2.1909,
      "step": 2000
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.785134763476348e-05,
      "loss": 2.1838,
      "step": 2500
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.7421617161716174e-05,
      "loss": 2.1969,
      "step": 3000
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.699188668866887e-05,
      "loss": 2.1822,
      "step": 3500
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.656215621562157e-05,
      "loss": 2.1603,
      "step": 4000
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.6132425742574256e-05,
      "loss": 2.1758,
      "step": 4500
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.570269526952696e-05,
      "loss": 2.1663,
      "step": 5000
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.527296479647965e-05,
      "loss": 2.1636,
      "step": 5500
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.4843234323432346e-05,
      "loss": 2.174,
      "step": 6000
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.441350385038504e-05,
      "loss": 2.1185,
      "step": 6500
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.398377337733773e-05,
      "loss": 2.1608,
      "step": 7000
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.3554042904290435e-05,
      "loss": 2.1546,
      "step": 7500
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.3124312431243124e-05,
      "loss": 2.1506,
      "step": 8000
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.269458195819582e-05,
      "loss": 2.173,
      "step": 8500
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.226485148514852e-05,
      "loss": 2.1712,
      "step": 9000
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.1835121012101214e-05,
      "loss": 2.1244,
      "step": 9500
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.14053905390539e-05,
      "loss": 2.1494,
      "step": 10000
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.0975660066006606e-05,
      "loss": 2.1062,
      "step": 10500
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.0545929592959296e-05,
      "loss": 2.1285,
      "step": 11000
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.0116199119912e-05,
      "loss": 2.1209,
      "step": 11500
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.968646864686469e-05,
      "loss": 2.1063,
      "step": 12000
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.925673817381738e-05,
      "loss": 2.1341,
      "step": 12500
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.882700770077008e-05,
      "loss": 2.1357,
      "step": 13000
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.839727722772277e-05,
      "loss": 2.1293,
      "step": 13500
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.796754675467547e-05,
      "loss": 2.0987,
      "step": 14000
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.7537816281628164e-05,
      "loss": 2.1369,
      "step": 14500
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.710808580858086e-05,
      "loss": 2.1097,
      "step": 15000
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.667835533553356e-05,
      "loss": 2.112,
      "step": 15500
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.624862486248625e-05,
      "loss": 2.154,
      "step": 16000
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.581889438943894e-05,
      "loss": 2.1025,
      "step": 16500
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.5389163916391646e-05,
      "loss": 2.1025,
      "step": 17000
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.4959433443344336e-05,
      "loss": 2.0768,
      "step": 17500
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.452970297029703e-05,
      "loss": 2.1338,
      "step": 18000
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.409997249724973e-05,
      "loss": 2.1078,
      "step": 18500
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.367024202420242e-05,
      "loss": 2.1177,
      "step": 19000
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.324051155115512e-05,
      "loss": 2.079,
      "step": 19500
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.281078107810781e-05,
      "loss": 2.0627,
      "step": 20000
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.238105060506051e-05,
      "loss": 2.0554,
      "step": 20500
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.1951320132013203e-05,
      "loss": 2.0506,
      "step": 21000
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.15215896589659e-05,
      "loss": 2.0923,
      "step": 21500
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.109185918591859e-05,
      "loss": 2.0678,
      "step": 22000
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.066212871287129e-05,
      "loss": 2.0934,
      "step": 22500
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.0232398239823982e-05,
      "loss": 2.0922,
      "step": 23000
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.9802667766776682e-05,
      "loss": 2.0181,
      "step": 23500
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.9372937293729375e-05,
      "loss": 2.0825,
      "step": 24000
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.8943206820682068e-05,
      "loss": 2.0344,
      "step": 24500
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.8513476347634764e-05,
      "loss": 2.0756,
      "step": 25000
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.8083745874587457e-05,
      "loss": 2.0481,
      "step": 25500
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.7654015401540157e-05,
      "loss": 2.119,
      "step": 26000
    }
  ],
  "max_steps": 58176,
  "num_train_epochs": 3,
  "total_flos": 2.6170085081088e+16,
  "trial_name": null,
  "trial_params": null
}