trainer_state.json

{
  "best_metric": 1.4576960802078247,
  "best_model_checkpoint": "./BART_Laymen_Simplified/checkpoint-1131",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1131,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 21.0,
      "eval_loss": 1.5324106216430664,
      "eval_rouge1": 14.9977,
      "eval_rouge2": 6.3024,
      "eval_rougeL": 12.297,
      "eval_rougeLsum": 14.1112,
      "eval_runtime": 67.3983,
      "eval_samples_per_second": 14.837,
      "eval_steps_per_second": 0.935,
      "step": 377
    },
    {
      "epoch": 1.3262599469496021,
      "grad_norm": 2.989149570465088,
      "learning_rate": 1.9785500146532294e-05,
      "loss": 1.7307,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 21.0,
      "eval_loss": 1.4828866720199585,
      "eval_rouge1": 16.2715,
      "eval_rouge2": 6.9803,
      "eval_rougeL": 13.2115,
      "eval_rougeLsum": 15.2881,
      "eval_runtime": 67.2034,
      "eval_samples_per_second": 14.88,
      "eval_steps_per_second": 0.937,
      "step": 754
    },
    {
      "epoch": 2.6525198938992043,
      "grad_norm": 2.8204739093780518,
      "learning_rate": 1.9147839684218636e-05,
      "loss": 1.4725,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 21.0,
      "eval_loss": 1.4576960802078247,
      "eval_rouge1": 15.9447,
      "eval_rouge2": 7.2635,
      "eval_rougeL": 13.128,
      "eval_rougeLsum": 14.9815,
      "eval_runtime": 67.4721,
      "eval_samples_per_second": 14.821,
      "eval_steps_per_second": 0.934,
      "step": 1131
    }
  ],
  "logging_steps": 500,
  "max_steps": 7540,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.918991962459341e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}