trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1422453249640382,
  "global_step": 4351,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 9.880633522535375e-07,
      "loss": 3.095,
      "step": 1000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.86918398092553e-07,
      "loss": 3.1041,
      "step": 2000
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.857217434943726e-07,
      "loss": 3.0942,
      "step": 3000
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.84473515518409e-07,
      "loss": 3.0985,
      "step": 4000
    }
  ],
  "max_steps": 305880,
  "num_train_epochs": 10,
  "total_flos": 1.577214365663232e+16,
  "trial_name": null,
  "trial_params": null
}