{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9996257951852314,
  "eval_steps": 500,
  "global_step": 3006,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 4.833666001330672e-05,
      "loss": 1.4437,
      "step": 100
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.6673320026613444e-05,
      "loss": 1.3823,
      "step": 200
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.5009980039920164e-05,
      "loss": 1.3499,
      "step": 300
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.3346640053226885e-05,
      "loss": 1.3187,
      "step": 400
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.1683300066533606e-05,
      "loss": 1.3217,
      "step": 500
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.0019960079840326e-05,
      "loss": 1.3004,
      "step": 600
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.835662009314704e-05,
      "loss": 1.2892,
      "step": 700
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.669328010645376e-05,
      "loss": 1.2834,
      "step": 800
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.502994011976048e-05,
      "loss": 1.274,
      "step": 900
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.33666001330672e-05,
      "loss": 1.2676,
      "step": 1000
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.170326014637392e-05,
      "loss": 1.2393,
      "step": 1100
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.003992015968064e-05,
      "loss": 1.2381,
      "step": 1200
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.837658017298736e-05,
      "loss": 1.2341,
      "step": 1300
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.671324018629408e-05,
      "loss": 1.2248,
      "step": 1400
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.5049900199600802e-05,
      "loss": 1.213,
      "step": 1500
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.338656021290752e-05,
      "loss": 1.2051,
      "step": 1600
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.172322022621424e-05,
      "loss": 1.2271,
      "step": 1700
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.0059880239520957e-05,
      "loss": 1.2158,
      "step": 1800
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.8396540252827678e-05,
      "loss": 1.2037,
      "step": 1900
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.67332002661344e-05,
      "loss": 1.1981,
      "step": 2000
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.506986027944112e-05,
      "loss": 1.1968,
      "step": 2100
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.3406520292747837e-05,
      "loss": 1.1906,
      "step": 2200
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.1743180306054557e-05,
      "loss": 1.1746,
      "step": 2300
    },
    {
      "epoch": 2.39,
      "learning_rate": 1.0079840319361278e-05,
      "loss": 1.1874,
      "step": 2400
    },
    {
      "epoch": 2.49,
      "learning_rate": 8.416500332667999e-06,
      "loss": 1.1763,
      "step": 2500
    },
    {
      "epoch": 2.59,
      "learning_rate": 6.753160345974717e-06,
      "loss": 1.1672,
      "step": 2600
    },
    {
      "epoch": 2.69,
      "learning_rate": 5.0898203592814375e-06,
      "loss": 1.1709,
      "step": 2700
    },
    {
      "epoch": 2.79,
      "learning_rate": 3.4264803725881573e-06,
      "loss": 1.1677,
      "step": 2800
    },
    {
      "epoch": 2.89,
      "learning_rate": 1.7631403858948771e-06,
      "loss": 1.1616,
      "step": 2900
    },
    {
      "epoch": 2.99,
      "learning_rate": 9.98003992015968e-08,
      "loss": 1.1609,
      "step": 3000
    },
    {
      "epoch": 3.0,
      "step": 3006,
      "total_flos": 5.378670905076864e+16,
      "train_loss": 1.2394252794231484,
      "train_runtime": 3602.0389,
      "train_samples_per_second": 106.833,
      "train_steps_per_second": 0.835
    }
  ],
  "logging_steps": 100,
  "max_steps": 3006,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 5.378670905076864e+16,
  "trial_name": null,
  "trial_params": null
}