{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.999214042441708,
  "eval_steps": 500,
  "global_step": 1431,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21,
      "learning_rate": 4.650593990216632e-05,
      "loss": 1.3096,
      "step": 100
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.301187980433264e-05,
      "loss": 1.2305,
      "step": 200
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.9517819706498955e-05,
      "loss": 1.1942,
      "step": 300
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.602375960866527e-05,
      "loss": 1.1705,
      "step": 400
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.252969951083159e-05,
      "loss": 1.152,
      "step": 500
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.9035639412997907e-05,
      "loss": 1.1318,
      "step": 600
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.554157931516422e-05,
      "loss": 1.1211,
      "step": 700
    },
    {
      "epoch": 1.68,
      "learning_rate": 2.204751921733054e-05,
      "loss": 1.1145,
      "step": 800
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.8553459119496856e-05,
      "loss": 1.1184,
      "step": 900
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.5059399021663173e-05,
      "loss": 1.1012,
      "step": 1000
    },
    {
      "epoch": 2.31,
      "learning_rate": 1.1565338923829489e-05,
      "loss": 1.1053,
      "step": 1100
    },
    {
      "epoch": 2.52,
      "learning_rate": 8.071278825995808e-06,
      "loss": 1.1016,
      "step": 1200
    },
    {
      "epoch": 2.72,
      "learning_rate": 4.577218728162125e-06,
      "loss": 1.1131,
      "step": 1300
    },
    {
      "epoch": 2.93,
      "learning_rate": 1.0831586303284416e-06,
      "loss": 1.1086,
      "step": 1400
    },
    {
      "epoch": 3.0,
      "step": 1431,
      "total_flos": 4.3173778473741864e+16,
      "train_loss": 1.1470813844522174,
      "train_runtime": 3794.0646,
      "train_samples_per_second": 72.43,
      "train_steps_per_second": 0.377
    }
  ],
  "logging_steps": 100,
  "max_steps": 1431,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 4.3173778473741864e+16,
  "trial_name": null,
  "trial_params": null
}