checkpoint-400/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.307692307692308,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.08,
      "learning_rate": 0.0002,
      "loss": 8.5245,
      "step": 100
    },
    {
      "epoch": 6.15,
      "learning_rate": 0.0002,
      "loss": 7.3261,
      "step": 200
    },
    {
      "epoch": 9.23,
      "learning_rate": 0.0002,
      "loss": 6.6792,
      "step": 300
    },
    {
      "epoch": 12.31,
      "learning_rate": 0.0002,
      "loss": 5.9569,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 500,
  "num_train_epochs": 16,
  "save_steps": 100,
  "total_flos": 1.988078576612352e+16,
  "trial_name": null,
  "trial_params": null
}