checkpoint-1016/trainer_state.json

{
  "best_metric": 48.0115,
  "best_model_checkpoint": "Models/bart-base-Abstract-Title/checkpoint-1016",
  "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": 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
    },
    {
      "epoch": 1.1811023622047245,
      "grad_norm": 4.367326736450195,
      "learning_rate": 3.067716535433071e-05,
      "loss": 1.7492,
      "step": 300
    },
    {
      "epoch": 1.574803149606299,
      "grad_norm": 4.451642990112305,
      "learning_rate": 2.7527559055118113e-05,
      "loss": 1.6464,
      "step": 400
    },
    {
      "epoch": 1.968503937007874,
      "grad_norm": 4.022191047668457,
      "learning_rate": 2.4377952755905516e-05,
      "loss": 1.642,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 16.0178,
      "eval_loss": 1.8481199741363525,
      "eval_rouge1": 46.9335,
      "eval_rouge2": 26.4562,
      "eval_rougeL": 41.1114,
      "eval_rougeLsum": 41.1786,
      "eval_runtime": 33.2681,
      "eval_samples_per_second": 30.48,
      "eval_steps_per_second": 0.962,
      "step": 508
    },
    {
      "epoch": 2.362204724409449,
      "grad_norm": 4.143003463745117,
      "learning_rate": 2.1228346456692915e-05,
      "loss": 1.4583,
      "step": 600
    },
    {
      "epoch": 2.7559055118110236,
      "grad_norm": 4.937542915344238,
      "learning_rate": 1.8078740157480318e-05,
      "loss": 1.4681,
      "step": 700
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 17.2623,
      "eval_loss": 1.8553646802902222,
      "eval_rouge1": 47.7845,
      "eval_rouge2": 26.9773,
      "eval_rougeL": 41.578,
      "eval_rougeLsum": 41.6324,
      "eval_runtime": 33.7632,
      "eval_samples_per_second": 30.033,
      "eval_steps_per_second": 0.948,
      "step": 762
    },
    {
      "epoch": 3.1496062992125986,
      "grad_norm": 3.757479429244995,
      "learning_rate": 1.4929133858267717e-05,
      "loss": 1.4317,
      "step": 800
    },
    {
      "epoch": 3.543307086614173,
      "grad_norm": 4.290562629699707,
      "learning_rate": 1.177952755905512e-05,
      "loss": 1.351,
      "step": 900
    },
    {
      "epoch": 3.937007874015748,
      "grad_norm": 4.114262580871582,
      "learning_rate": 8.629921259842521e-06,
      "loss": 1.3492,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 17.211,
      "eval_loss": 1.8518580198287964,
      "eval_rouge1": 48.0115,
      "eval_rouge2": 26.8668,
      "eval_rougeL": 41.7509,
      "eval_rougeLsum": 41.7639,
      "eval_runtime": 34.142,
      "eval_samples_per_second": 29.699,
      "eval_steps_per_second": 0.937,
      "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": 9902120081817600.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}