{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 1655,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3,
      "learning_rate": 2.951807228915663e-05,
      "loss": 4.4788,
      "step": 100
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.892545332437878e-05,
      "loss": 2.4769,
      "step": 200
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.5567494963062465e-05,
      "loss": 2.3399,
      "step": 300
    },
    {
      "epoch": 1.21,
      "learning_rate": 4.220953660174614e-05,
      "loss": 2.1886,
      "step": 400
    },
    {
      "epoch": 1.51,
      "learning_rate": 3.885157824042982e-05,
      "loss": 2.1455,
      "step": 500
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.54936198791135e-05,
      "loss": 2.1173,
      "step": 600
    },
    {
      "epoch": 2.11,
      "learning_rate": 3.213566151779718e-05,
      "loss": 2.0583,
      "step": 700
    },
    {
      "epoch": 2.42,
      "learning_rate": 2.8777703156480862e-05,
      "loss": 1.9753,
      "step": 800
    },
    {
      "epoch": 2.72,
      "learning_rate": 2.541974479516454e-05,
      "loss": 1.9841,
      "step": 900
    },
    {
      "epoch": 3.02,
      "learning_rate": 2.2061786433848224e-05,
      "loss": 1.963,
      "step": 1000
    },
    {
      "epoch": 3.32,
      "learning_rate": 1.87038280725319e-05,
      "loss": 1.8706,
      "step": 1100
    },
    {
      "epoch": 3.63,
      "learning_rate": 1.534586971121558e-05,
      "loss": 1.884,
      "step": 1200
    },
    {
      "epoch": 3.93,
      "learning_rate": 1.198791134989926e-05,
      "loss": 1.8814,
      "step": 1300
    },
    {
      "epoch": 4.23,
      "learning_rate": 8.629952988582941e-06,
      "loss": 1.828,
      "step": 1400
    },
    {
      "epoch": 4.53,
      "learning_rate": 5.271994627266622e-06,
      "loss": 1.8145,
      "step": 1500
    },
    {
      "epoch": 4.83,
      "learning_rate": 1.9140362659503023e-06,
      "loss": 1.8219,
      "step": 1600
    },
    {
      "epoch": 5.0,
      "step": 1655,
      "total_flos": 5.477940459823104e+16,
      "train_loss": 2.1648097335031746,
      "train_runtime": 1785.4315,
      "train_samples_per_second": 118.646,
      "train_steps_per_second": 0.927
    }
  ],
  "max_steps": 1655,
  "num_train_epochs": 5,
  "total_flos": 5.477940459823104e+16,
  "trial_name": null,
  "trial_params": null
}