checkpoint-254/trainer_state.json

{
  "best_metric": 46.7551,
  "best_model_checkpoint": "Models/bart-base-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": 7.6463422775268555,
      "learning_rate": 3.697637795275591e-05,
      "loss": 3.0716,
      "step": 100
    },
    {
      "epoch": 0.7874015748031497,
      "grad_norm": 4.727579116821289,
      "learning_rate": 3.3826771653543314e-05,
      "loss": 1.9716,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 17.1893,
      "eval_loss": 1.94315505027771,
      "eval_rouge1": 46.7551,
      "eval_rouge2": 26.2207,
      "eval_rougeL": 40.5839,
      "eval_rougeLsum": 40.5779,
      "eval_runtime": 33.994,
      "eval_samples_per_second": 29.829,
      "eval_steps_per_second": 0.941,
      "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": 2475530020454400.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}