{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.970954356846473,
  "eval_steps": 500,
  "global_step": 840,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "learning_rate": 9.920634920634922e-05,
      "loss": 1.911,
      "step": 96
    },
    {
      "epoch": 1.59,
      "learning_rate": 8.650793650793651e-05,
      "loss": 1.3199,
      "step": 192
    },
    {
      "epoch": 2.39,
      "learning_rate": 7.380952380952382e-05,
      "loss": 1.2762,
      "step": 288
    },
    {
      "epoch": 3.19,
      "learning_rate": 6.111111111111112e-05,
      "loss": 1.2343,
      "step": 384
    },
    {
      "epoch": 3.98,
      "learning_rate": 4.841269841269841e-05,
      "loss": 1.2014,
      "step": 480
    },
    {
      "epoch": 4.78,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.1511,
      "step": 576
    },
    {
      "epoch": 5.58,
      "learning_rate": 2.3015873015873015e-05,
      "loss": 1.1235,
      "step": 672
    },
    {
      "epoch": 6.37,
      "learning_rate": 1.0317460317460318e-05,
      "loss": 1.0968,
      "step": 768
    }
  ],
  "logging_steps": 96,
  "max_steps": 840,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 7.34660162224128e+16,
  "trial_name": null,
  "trial_params": null
}