checkpoint-254/trainer_state.json

{
  "best_metric": 50.0309,
  "best_model_checkpoint": "Models/pegasus-large-Abstract-Title/checkpoint-254",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 254,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3937007874015748,
      "grad_norm": 3.240441083908081,
      "learning_rate": 3.7007874015748034e-05,
      "loss": 4.8906,
      "step": 100
    },
    {
      "epoch": 0.7874015748031497,
      "grad_norm": 3.40730881690979,
      "learning_rate": 3.388976377952756e-05,
      "loss": 4.3578,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 16.8757,
      "eval_loss": 3.328967571258545,
      "eval_rouge1": 50.0309,
      "eval_rouge2": 29.2309,
      "eval_rougeL": 43.011,
      "eval_rougeLsum": 43.0318,
      "eval_runtime": 143.0833,
      "eval_samples_per_second": 7.087,
      "eval_steps_per_second": 0.224,
      "step": 254
    }
  ],
  "logging_steps": 100,
  "max_steps": 1270,
  "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": 1.173122552168448e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}