{
  "best_global_step": 550,
  "best_metric": 0.9458296266430395,
  "best_model_checkpoint": "models/ner_model/checkpoint-550",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 550,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 6.7610626220703125,
      "learning_rate": 2.7e-06,
      "loss": 3.1763,
      "step": 10
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 8.019376754760742,
      "learning_rate": 5.7000000000000005e-06,
      "loss": 3.0538,
      "step": 20
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 8.582132339477539,
      "learning_rate": 8.7e-06,
      "loss": 2.7102,
      "step": 30
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 7.020857810974121,
      "learning_rate": 1.1700000000000001e-05,
      "loss": 1.9306,
      "step": 40
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 6.591127872467041,
      "learning_rate": 1.47e-05,
      "loss": 1.5462,
      "step": 50
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 6.085566520690918,
      "learning_rate": 1.77e-05,
      "loss": 1.158,
      "step": 60
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 10.360540390014648,
      "learning_rate": 2.07e-05,
      "loss": 0.88,
      "step": 70
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 4.375982761383057,
      "learning_rate": 2.37e-05,
      "loss": 0.6575,
      "step": 80
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 10.760860443115234,
      "learning_rate": 2.6700000000000002e-05,
      "loss": 0.6622,
      "step": 90
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 8.98079776763916,
      "learning_rate": 2.97e-05,
      "loss": 0.6058,
      "step": 100
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.706189155578613,
      "learning_rate": 2.94e-05,
      "loss": 0.509,
      "step": 110
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8916666666666667,
      "eval_entity_accuracy": 0.8543662742950999,
      "eval_f1": 0.8670505036976651,
      "eval_loss": 0.38678058981895447,
      "eval_precision": 0.861471336118019,
      "eval_recall": 0.8916666666666667,
      "eval_runtime": 2.6176,
      "eval_samples_per_second": 166.949,
      "eval_steps_per_second": 10.697,
      "step": 110
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 4.655617713928223,
      "learning_rate": 2.873333333333333e-05,
      "loss": 0.3582,
      "step": 120
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 6.469715118408203,
      "learning_rate": 2.8066666666666667e-05,
      "loss": 0.4039,
      "step": 130
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 6.508236408233643,
      "learning_rate": 2.7400000000000002e-05,
      "loss": 0.3456,
      "step": 140
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 7.3737874031066895,
      "learning_rate": 2.6733333333333334e-05,
      "loss": 0.4672,
      "step": 150
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 6.929003715515137,
      "learning_rate": 2.606666666666667e-05,
      "loss": 0.3472,
      "step": 160
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 5.1204986572265625,
      "learning_rate": 2.54e-05,
      "loss": 0.3808,
      "step": 170
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 3.2450709342956543,
      "learning_rate": 2.4733333333333333e-05,
      "loss": 0.2377,
      "step": 180
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 3.943157196044922,
      "learning_rate": 2.4066666666666664e-05,
      "loss": 0.34,
      "step": 190
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 4.091476917266846,
      "learning_rate": 2.3400000000000003e-05,
      "loss": 0.3028,
      "step": 200
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 7.115076541900635,
      "learning_rate": 2.2733333333333335e-05,
      "loss": 0.4381,
      "step": 210
    },
    {
      "epoch": 2.0,
      "grad_norm": 17.910232543945312,
      "learning_rate": 2.2066666666666667e-05,
      "loss": 0.2634,
      "step": 220
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9202830188679245,
      "eval_entity_accuracy": 0.8863947440459896,
      "eval_f1": 0.9039013364488941,
      "eval_loss": 0.2899700701236725,
      "eval_precision": 0.9016844893810626,
      "eval_recall": 0.9202830188679245,
      "eval_runtime": 2.6518,
      "eval_samples_per_second": 164.792,
      "eval_steps_per_second": 10.559,
      "step": 220
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 11.105402946472168,
      "learning_rate": 2.1400000000000002e-05,
      "loss": 0.2834,
      "step": 230
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 6.341246604919434,
      "learning_rate": 2.0733333333333334e-05,
      "loss": 0.2477,
      "step": 240
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 4.475722312927246,
      "learning_rate": 2.0066666666666665e-05,
      "loss": 0.2042,
      "step": 250
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 3.8562307357788086,
      "learning_rate": 1.9399999999999997e-05,
      "loss": 0.2935,
      "step": 260
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 3.3338725566864014,
      "learning_rate": 1.8733333333333336e-05,
      "loss": 0.2232,
      "step": 270
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 3.610917568206787,
      "learning_rate": 1.8066666666666668e-05,
      "loss": 0.2578,
      "step": 280
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 6.411995887756348,
      "learning_rate": 1.74e-05,
      "loss": 0.2617,
      "step": 290
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 18.01243782043457,
      "learning_rate": 1.6733333333333335e-05,
      "loss": 0.2323,
      "step": 300
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 6.243415832519531,
      "learning_rate": 1.6066666666666666e-05,
      "loss": 0.2226,
      "step": 310
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 3.8026018142700195,
      "learning_rate": 1.5399999999999998e-05,
      "loss": 0.1841,
      "step": 320
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.6072797775268555,
      "learning_rate": 1.4733333333333333e-05,
      "loss": 0.2261,
      "step": 330
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9429245283018868,
      "eval_entity_accuracy": 0.9280043799616753,
      "eval_f1": 0.9367311510359461,
      "eval_loss": 0.22553826868534088,
      "eval_precision": 0.9404566874612201,
      "eval_recall": 0.9429245283018868,
      "eval_runtime": 2.6044,
      "eval_samples_per_second": 167.791,
      "eval_steps_per_second": 10.751,
      "step": 330
    },
    {
      "epoch": 3.090909090909091,
      "grad_norm": 3.598348617553711,
      "learning_rate": 1.4066666666666667e-05,
      "loss": 0.2008,
      "step": 340
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 3.3810553550720215,
      "learning_rate": 1.34e-05,
      "loss": 0.1801,
      "step": 350
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 2.5113697052001953,
      "learning_rate": 1.2733333333333334e-05,
      "loss": 0.1917,
      "step": 360
    },
    {
      "epoch": 3.3636363636363638,
      "grad_norm": 5.911487102508545,
      "learning_rate": 1.2066666666666666e-05,
      "loss": 0.1861,
      "step": 370
    },
    {
      "epoch": 3.4545454545454546,
      "grad_norm": 4.358926296234131,
      "learning_rate": 1.1400000000000001e-05,
      "loss": 0.1568,
      "step": 380
    },
    {
      "epoch": 3.5454545454545454,
      "grad_norm": 3.0283701419830322,
      "learning_rate": 1.0733333333333333e-05,
      "loss": 0.2127,
      "step": 390
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 8.457649230957031,
      "learning_rate": 1.0066666666666666e-05,
      "loss": 0.1752,
      "step": 400
    },
    {
      "epoch": 3.7272727272727275,
      "grad_norm": 2.7831077575683594,
      "learning_rate": 9.400000000000001e-06,
      "loss": 0.2328,
      "step": 410
    },
    {
      "epoch": 3.8181818181818183,
      "grad_norm": 2.8275463581085205,
      "learning_rate": 8.733333333333333e-06,
      "loss": 0.1345,
      "step": 420
    },
    {
      "epoch": 3.909090909090909,
      "grad_norm": 2.621518850326538,
      "learning_rate": 8.066666666666667e-06,
      "loss": 0.1343,
      "step": 430
    },
    {
      "epoch": 4.0,
      "grad_norm": 12.00428295135498,
      "learning_rate": 7.4e-06,
      "loss": 0.1415,
      "step": 440
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9476415094339623,
      "eval_entity_accuracy": 0.9277306323569668,
      "eval_f1": 0.940876969962022,
      "eval_loss": 0.20769040286540985,
      "eval_precision": 0.9463580459003759,
      "eval_recall": 0.9476415094339623,
      "eval_runtime": 2.6645,
      "eval_samples_per_second": 164.008,
      "eval_steps_per_second": 10.509,
      "step": 440
    },
    {
      "epoch": 4.090909090909091,
      "grad_norm": 4.293393611907959,
      "learning_rate": 6.733333333333334e-06,
      "loss": 0.1635,
      "step": 450
    },
    {
      "epoch": 4.181818181818182,
      "grad_norm": 6.984195709228516,
      "learning_rate": 6.0666666666666665e-06,
      "loss": 0.1462,
      "step": 460
    },
    {
      "epoch": 4.2727272727272725,
      "grad_norm": 2.344493865966797,
      "learning_rate": 5.4e-06,
      "loss": 0.1356,
      "step": 470
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 2.468249797821045,
      "learning_rate": 4.7333333333333335e-06,
      "loss": 0.1248,
      "step": 480
    },
    {
      "epoch": 4.454545454545454,
      "grad_norm": 1.7062819004058838,
      "learning_rate": 4.066666666666667e-06,
      "loss": 0.0904,
      "step": 490
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 1.412717580795288,
      "learning_rate": 3.4e-06,
      "loss": 0.1255,
      "step": 500
    },
    {
      "epoch": 4.636363636363637,
      "grad_norm": 2.9533627033233643,
      "learning_rate": 2.7333333333333336e-06,
      "loss": 0.1249,
      "step": 510
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 11.376725196838379,
      "learning_rate": 2.0666666666666666e-06,
      "loss": 0.1459,
      "step": 520
    },
    {
      "epoch": 4.818181818181818,
      "grad_norm": 24.830320358276367,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.1765,
      "step": 530
    },
    {
      "epoch": 4.909090909090909,
      "grad_norm": 3.52287220954895,
      "learning_rate": 7.333333333333334e-07,
      "loss": 0.192,
      "step": 540
    },
    {
      "epoch": 5.0,
      "grad_norm": 28.654787063598633,
      "learning_rate": 6.666666666666667e-08,
      "loss": 0.1539,
      "step": 550
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9511006289308176,
      "eval_entity_accuracy": 0.9370380509170545,
      "eval_f1": 0.9458296266430395,
      "eval_loss": 0.18345355987548828,
      "eval_precision": 0.9486871211363513,
      "eval_recall": 0.9511006289308176,
      "eval_runtime": 2.7757,
      "eval_samples_per_second": 157.438,
      "eval_steps_per_second": 10.088,
      "step": 550
    }
  ],
  "logging_steps": 10,
  "max_steps": 550,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 571021163627520.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}