trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 1218,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "learning_rate": 2.7316636851520572e-05,
      "loss": 0.7965,
      "step": 200
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.194991055456172e-05,
      "loss": 0.5813,
      "step": 400
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.6583184257602862e-05,
      "loss": 0.5307,
      "step": 600
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.1216457960644007e-05,
      "loss": 0.4694,
      "step": 800
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.8497316636851525e-06,
      "loss": 0.4975,
      "step": 1000
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.83005366726297e-07,
      "loss": 0.4596,
      "step": 1200
    }
  ],
  "max_steps": 1218,
  "num_train_epochs": 1,
  "total_flos": 314939094934500.0,
  "trial_name": null,
  "trial_params": null
}