{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.382329945269742,
  "eval_steps": 500,
  "global_step": 12000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 0.6904,
      "step": 1000
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001,
      "loss": 0.5373,
      "step": 2000
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0001,
      "loss": 0.4889,
      "step": 3000
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.0001,
      "loss": 0.4631,
      "step": 4000
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.0001,
      "loss": 0.4379,
      "step": 5000
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.0001,
      "loss": 0.4208,
      "step": 6000
    },
    {
      "epoch": 5.47,
      "learning_rate": 0.0001,
      "loss": 0.407,
      "step": 7000
    },
    {
      "epoch": 6.25,
      "learning_rate": 0.0001,
      "loss": 0.3962,
      "step": 8000
    },
    {
      "epoch": 7.04,
      "learning_rate": 0.0001,
      "loss": 0.3891,
      "step": 9000
    },
    {
      "epoch": 7.82,
      "learning_rate": 0.0001,
      "loss": 0.3771,
      "step": 10000
    },
    {
      "epoch": 8.6,
      "learning_rate": 0.0001,
      "loss": 0.371,
      "step": 11000
    },
    {
      "epoch": 9.38,
      "learning_rate": 0.0001,
      "loss": 0.3644,
      "step": 12000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 12790,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "total_flos": 87654664241152.0,
  "trial_name": null,
  "trial_params": null
}