{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 4690,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.53,
      "learning_rate": 0.0008933901918976545,
      "loss": 0.801,
      "step": 500
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0007867803837953092,
      "loss": 0.6595,
      "step": 1000
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0006801705756929638,
      "loss": 0.6103,
      "step": 1500
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0005735607675906183,
      "loss": 0.5796,
      "step": 2000
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00046695095948827295,
      "loss": 0.5603,
      "step": 2500
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0003603411513859275,
      "loss": 0.5365,
      "step": 3000
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0002537313432835821,
      "loss": 0.5067,
      "step": 3500
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.00014712153518123668,
      "loss": 0.4672,
      "step": 4000
    },
    {
      "epoch": 4.8,
      "learning_rate": 4.051172707889126e-05,
      "loss": 0.4445,
      "step": 4500
    }
  ],
  "logging_steps": 500,
  "max_steps": 4690,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.2698042499072e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}