trainer_state.json

{
  "best_metric": 0.38396790623664856,
  "best_model_checkpoint": "topic_model/checkpoint-2855",
  "epoch": 1.0,
  "global_step": 2855,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18,
      "learning_rate": 1.649737302977233e-05,
      "loss": 0.793,
      "step": 500
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.2994746059544661e-05,
      "loss": 0.4523,
      "step": 1000
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.492119089316989e-06,
      "loss": 0.4045,
      "step": 1500
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.989492119089317e-06,
      "loss": 0.3818,
      "step": 2000
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.4868651488616464e-06,
      "loss": 0.3745,
      "step": 2500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8704293400680795,
      "eval_loss": 0.38396790623664856,
      "eval_runtime": 14.2779,
      "eval_samples_per_second": 637.837,
      "eval_steps_per_second": 39.922,
      "step": 2855
    }
  ],
  "max_steps": 2855,
  "num_train_epochs": 1,
  "total_flos": 495932362009212.0,
  "trial_name": null,
  "trial_params": null
}