trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.459016393442623,
  "global_step": 4500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.27,
      "learning_rate": 1.8907103825136616e-05,
      "loss": 0.4115,
      "step": 500
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.7814207650273227e-05,
      "loss": 0.3067,
      "step": 1000
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6721311475409837e-05,
      "loss": 0.2982,
      "step": 1500
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.5628415300546448e-05,
      "loss": 0.2788,
      "step": 2000
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.4535519125683062e-05,
      "loss": 0.2543,
      "step": 2500
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.3442622950819673e-05,
      "loss": 0.254,
      "step": 3000
    },
    {
      "epoch": 1.91,
      "learning_rate": 1.2349726775956286e-05,
      "loss": 0.253,
      "step": 3500
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.1256830601092897e-05,
      "loss": 0.214,
      "step": 4000
    },
    {
      "epoch": 2.46,
      "learning_rate": 1.0163934426229509e-05,
      "loss": 0.2061,
      "step": 4500
    }
  ],
  "max_steps": 9150,
  "num_train_epochs": 5,
  "total_flos": 9536063094448128.0,
  "trial_name": null,
  "trial_params": null
}