{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09818253223659809,
  "eval_steps": 500,
  "global_step": 4500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.992872157045291e-05,
      "loss": 0.6371,
      "step": 500
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9855988479078326e-05,
      "loss": 0.2287,
      "step": 1000
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9783255387703745e-05,
      "loss": 0.1475,
      "step": 1500
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.971052229632916e-05,
      "loss": 0.1033,
      "step": 2000
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.963778920495458e-05,
      "loss": 0.1562,
      "step": 2500
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9565056113579996e-05,
      "loss": 0.107,
      "step": 3000
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9492323022205415e-05,
      "loss": 0.0692,
      "step": 3500
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.941958993083083e-05,
      "loss": 0.0909,
      "step": 4000
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.934685683945625e-05,
      "loss": 0.1167,
      "step": 4500
    }
  ],
  "logging_steps": 500,
  "max_steps": 137499,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 7618727116800000.0,
  "trial_name": null,
  "trial_params": null
}