trainer_state (1).json

{
  "best_metric": 1.4497753381729126,
  "best_model_checkpoint": "flan-t5-small-wikitablequestion/checkpoint-1416",
  "epoch": 1.0,
  "global_step": 1416,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.35,
      "learning_rate": 3.234463276836158e-05,
      "loss": 1.8141,
      "step": 500
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.4689265536723165e-05,
      "loss": 1.6737,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 19.0,
      "eval_loss": 1.4497753381729126,
      "eval_rouge1": 3.0509,
      "eval_rouge2": 0.4526,
      "eval_rougeL": 3.008,
      "eval_rougeLsum": 3.013,
      "eval_runtime": 351.8402,
      "eval_samples_per_second": 12.347,
      "eval_steps_per_second": 1.543,
      "step": 1416
    }
  ],
  "max_steps": 1416,
  "num_train_epochs": 1,
  "total_flos": 2071584116195328.0,
  "trial_name": null,
  "trial_params": null
}