{
  "best_metric": 50.4476,
  "best_model_checkpoint": "Models/pegasus-large-Abstract-Title/checkpoint-508",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1016,
  "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
    },
    {
      "epoch": 1.1811023622047245,
      "grad_norm": 6.57772970199585,
      "learning_rate": 3.077165354330709e-05,
      "loss": 3.9304,
      "step": 300
    },
    {
      "epoch": 1.574803149606299,
      "grad_norm": 18.435937881469727,
      "learning_rate": 2.762204724409449e-05,
      "loss": 2.6346,
      "step": 400
    },
    {
      "epoch": 1.968503937007874,
      "grad_norm": 21.01703453063965,
      "learning_rate": 2.447244094488189e-05,
      "loss": 1.6471,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 16.6193,
      "eval_loss": 1.685731053352356,
      "eval_rouge1": 50.4476,
      "eval_rouge2": 29.4801,
      "eval_rougeL": 43.48,
      "eval_rougeLsum": 43.5274,
      "eval_runtime": 139.8015,
      "eval_samples_per_second": 7.253,
      "eval_steps_per_second": 0.229,
      "step": 508
    },
    {
      "epoch": 2.362204724409449,
      "grad_norm": 3.1496286392211914,
      "learning_rate": 2.1322834645669294e-05,
      "loss": 1.5102,
      "step": 600
    },
    {
      "epoch": 2.7559055118110236,
      "grad_norm": 3.0442636013031006,
      "learning_rate": 1.8173228346456696e-05,
      "loss": 1.514,
      "step": 700
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 16.9951,
      "eval_loss": 1.6632518768310547,
      "eval_rouge1": 50.3732,
      "eval_rouge2": 29.3543,
      "eval_rougeL": 43.3121,
      "eval_rougeLsum": 43.3186,
      "eval_runtime": 140.8191,
      "eval_samples_per_second": 7.201,
      "eval_steps_per_second": 0.227,
      "step": 762
    },
    {
      "epoch": 3.1496062992125986,
      "grad_norm": 2.718595504760742,
      "learning_rate": 1.5023622047244096e-05,
      "loss": 1.4836,
      "step": 800
    },
    {
      "epoch": 3.543307086614173,
      "grad_norm": 2.8752331733703613,
      "learning_rate": 1.1905511811023622e-05,
      "loss": 1.4507,
      "step": 900
    },
    {
      "epoch": 3.937007874015748,
      "grad_norm": 3.04589581489563,
      "learning_rate": 8.755905511811024e-06,
      "loss": 1.4487,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 16.8698,
      "eval_loss": 1.6590015888214111,
      "eval_rouge1": 50.3899,
      "eval_rouge2": 29.166,
      "eval_rougeL": 43.3594,
      "eval_rougeLsum": 43.3533,
      "eval_runtime": 141.2833,
      "eval_samples_per_second": 7.177,
      "eval_steps_per_second": 0.226,
      "step": 1016
    }
  ],
  "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": 4.692490208673792e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}