checkpoint-780/trainer_state.json

{
  "best_metric": 0.36502676602307105,
  "best_model_checkpoint": "./flan-t5-dialogsum/checkpoint-780",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 780,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.31267526745796204,
      "eval_rouge1": 0.44388160380951946,
      "eval_rouge2": 0.17811053634418733,
      "eval_rougeL": 0.35470174491389483,
      "eval_rougeLsum": 0.35400351619004,
      "eval_runtime": 73.2026,
      "eval_samples_per_second": 6.83,
      "eval_steps_per_second": 0.219,
      "step": 390
    },
    {
      "epoch": 1.282051282051282,
      "grad_norm": 0.25125354528427124,
      "learning_rate": 0.00022307692307692306,
      "loss": 0.3886,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.3003218472003937,
      "eval_rouge1": 0.4481724027358116,
      "eval_rouge2": 0.18706683962522586,
      "eval_rougeL": 0.36502676602307105,
      "eval_rougeLsum": 0.3646421437489298,
      "eval_runtime": 65.5308,
      "eval_samples_per_second": 7.63,
      "eval_steps_per_second": 0.244,
      "step": 780
    }
  ],
  "logging_steps": 500,
  "max_steps": 1950,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4632391377223680.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}