{
  "best_global_step": 1000,
  "best_metric": 0.7299026676279741,
  "best_model_checkpoint": "./hpo_Buzzeitor_longformer-base-4096-bne-es/trial_0/checkpoint-1000",
  "epoch": 4.82771896053898,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.48123195380173245,
      "grad_norm": 2.3587965965270996,
      "learning_rate": 2.4559035121953966e-05,
      "loss": 0.6174,
      "step": 100
    },
    {
      "epoch": 0.48123195380173245,
      "eval_accuracy": 0.6756756756756757,
      "eval_f1": 0.6636363636363636,
      "eval_loss": 0.6910868883132935,
      "eval_precision": 0.662606978275181,
      "eval_recall": 0.6721254355400696,
      "eval_runtime": 2.3792,
      "eval_samples_per_second": 93.307,
      "eval_steps_per_second": 15.551,
      "step": 100
    },
    {
      "epoch": 0.9624639076034649,
      "grad_norm": 3.7914035320281982,
      "learning_rate": 2.3529306186022982e-05,
      "loss": 0.5708,
      "step": 200
    },
    {
      "epoch": 0.9624639076034649,
      "eval_accuracy": 0.6666666666666666,
      "eval_f1": 0.6554819226574952,
      "eval_loss": 0.7087554931640625,
      "eval_precision": 0.6552459016393443,
      "eval_recall": 0.6649825783972125,
      "eval_runtime": 2.4015,
      "eval_samples_per_second": 92.444,
      "eval_steps_per_second": 15.407,
      "step": 200
    },
    {
      "epoch": 1.4475457170356112,
      "grad_norm": 18.273841857910156,
      "learning_rate": 2.2499577250091998e-05,
      "loss": 0.5561,
      "step": 300
    },
    {
      "epoch": 1.4475457170356112,
      "eval_accuracy": 0.7207207207207207,
      "eval_f1": 0.671409472880061,
      "eval_loss": 0.6270285248756409,
      "eval_precision": 0.7086640211640212,
      "eval_recall": 0.6648954703832752,
      "eval_runtime": 2.4,
      "eval_samples_per_second": 92.502,
      "eval_steps_per_second": 15.417,
      "step": 300
    },
    {
      "epoch": 1.9287776708373436,
      "grad_norm": 34.575313568115234,
      "learning_rate": 2.1480145603520324e-05,
      "loss": 0.5025,
      "step": 400
    },
    {
      "epoch": 1.9287776708373436,
      "eval_accuracy": 0.7207207207207207,
      "eval_f1": 0.6564839772386942,
      "eval_loss": 0.645313560962677,
      "eval_precision": 0.7231869254341164,
      "eval_recall": 0.6522648083623693,
      "eval_runtime": 2.3956,
      "eval_samples_per_second": 92.671,
      "eval_steps_per_second": 15.445,
      "step": 400
    },
    {
      "epoch": 2.41385948026949,
      "grad_norm": 31.36258888244629,
      "learning_rate": 2.045041666758934e-05,
      "loss": 0.4304,
      "step": 500
    },
    {
      "epoch": 2.41385948026949,
      "eval_accuracy": 0.6801801801801802,
      "eval_f1": 0.6252407332556646,
      "eval_loss": 0.8638490438461304,
      "eval_precision": 0.6532934131736527,
      "eval_recall": 0.6226480836236934,
      "eval_runtime": 2.403,
      "eval_samples_per_second": 92.386,
      "eval_steps_per_second": 15.398,
      "step": 500
    },
    {
      "epoch": 2.8950914340712224,
      "grad_norm": 28.394620895385742,
      "learning_rate": 1.942068773165836e-05,
      "loss": 0.3904,
      "step": 600
    },
    {
      "epoch": 2.8950914340712224,
      "eval_accuracy": 0.7117117117117117,
      "eval_f1": 0.6935817805383022,
      "eval_loss": 0.765376091003418,
      "eval_precision": 0.69203146374829,
      "eval_recall": 0.6956445993031359,
      "eval_runtime": 2.3963,
      "eval_samples_per_second": 92.644,
      "eval_steps_per_second": 15.441,
      "step": 600
    },
    {
      "epoch": 3.3801732435033687,
      "grad_norm": 2.409611463546753,
      "learning_rate": 1.839095879572737e-05,
      "loss": 0.2937,
      "step": 700
    },
    {
      "epoch": 3.3801732435033687,
      "eval_accuracy": 0.6441441441441441,
      "eval_f1": 0.6437899867980095,
      "eval_loss": 1.1262925863265991,
      "eval_precision": 0.6769874123511024,
      "eval_recall": 0.6824912891986062,
      "eval_runtime": 2.4008,
      "eval_samples_per_second": 92.469,
      "eval_steps_per_second": 15.412,
      "step": 700
    },
    {
      "epoch": 3.861405197305101,
      "grad_norm": 116.25942993164062,
      "learning_rate": 1.736122985979639e-05,
      "loss": 0.2703,
      "step": 800
    },
    {
      "epoch": 3.861405197305101,
      "eval_accuracy": 0.7207207207207207,
      "eval_f1": 0.7057968536251711,
      "eval_loss": 1.0032894611358643,
      "eval_precision": 0.7032828282828283,
      "eval_recall": 0.7103658536585367,
      "eval_runtime": 2.3859,
      "eval_samples_per_second": 93.047,
      "eval_steps_per_second": 15.508,
      "step": 800
    },
    {
      "epoch": 4.346487006737247,
      "grad_norm": 136.07870483398438,
      "learning_rate": 1.6331500923865403e-05,
      "loss": 0.2418,
      "step": 900
    },
    {
      "epoch": 4.346487006737247,
      "eval_accuracy": 0.7342342342342343,
      "eval_f1": 0.691048472697252,
      "eval_loss": 1.0043816566467285,
      "eval_precision": 0.7236044657097289,
      "eval_recall": 0.6831881533101045,
      "eval_runtime": 2.4,
      "eval_samples_per_second": 92.5,
      "eval_steps_per_second": 15.417,
      "step": 900
    },
    {
      "epoch": 4.82771896053898,
      "grad_norm": 120.01212310791016,
      "learning_rate": 1.5312069277293732e-05,
      "loss": 0.2207,
      "step": 1000
    },
    {
      "epoch": 4.82771896053898,
      "eval_accuracy": 0.7567567567567568,
      "eval_f1": 0.7299026676279741,
      "eval_loss": 0.9589651226997375,
      "eval_precision": 0.7414473684210526,
      "eval_recall": 0.723780487804878,
      "eval_runtime": 2.385,
      "eval_samples_per_second": 93.083,
      "eval_steps_per_second": 15.514,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 2484,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "save_steps": 100,
  "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": 9795381765152256.0,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}