{
  "best_metric": 0.5446548032758927,
  "best_model_checkpoint": "tmp_ner_damsay_304130/run-36/checkpoint-4125",
  "epoch": 25.0,
  "eval_steps": 500,
  "global_step": 4125,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7470146314639639,
      "eval_loss": 1.2898669242858887,
      "eval_macro_f1": 0.060475942039181926,
      "eval_macro_precision": 0.09351501221756969,
      "eval_macro_recall": 0.06591547068187953,
      "eval_runtime": 3.9883,
      "eval_samples_per_second": 220.142,
      "eval_steps_per_second": 27.58,
      "step": 165
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8084088190052983,
      "eval_loss": 0.8025009632110596,
      "eval_macro_f1": 0.24340420766720258,
      "eval_macro_precision": 0.3139630221874961,
      "eval_macro_recall": 0.24833685017157406,
      "eval_runtime": 3.8063,
      "eval_samples_per_second": 230.671,
      "eval_steps_per_second": 28.9,
      "step": 330
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8305009177175213,
      "eval_loss": 0.6665005683898926,
      "eval_macro_f1": 0.37091081081224914,
      "eval_macro_precision": 0.4480773602522756,
      "eval_macro_recall": 0.36393297647770273,
      "eval_runtime": 3.7531,
      "eval_samples_per_second": 233.938,
      "eval_steps_per_second": 29.309,
      "step": 495
    },
    {
      "epoch": 3.0303030303030303,
      "grad_norm": 1.6078789234161377,
      "learning_rate": 7.735247090033069e-05,
      "loss": 1.4056,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8344504469693029,
      "eval_loss": 0.6422820091247559,
      "eval_macro_f1": 0.43071408069652817,
      "eval_macro_precision": 0.48878382034336376,
      "eval_macro_recall": 0.42148708788382616,
      "eval_runtime": 3.8104,
      "eval_samples_per_second": 230.421,
      "eval_steps_per_second": 28.868,
      "step": 660
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8393288401090858,
      "eval_loss": 0.6265012621879578,
      "eval_macro_f1": 0.47492811430942733,
      "eval_macro_precision": 0.5136390951479204,
      "eval_macro_recall": 0.46552778262584993,
      "eval_runtime": 3.749,
      "eval_samples_per_second": 234.199,
      "eval_steps_per_second": 29.342,
      "step": 825
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8411568442406724,
      "eval_loss": 0.6596290469169617,
      "eval_macro_f1": 0.4931684511043183,
      "eval_macro_precision": 0.5359461122068587,
      "eval_macro_recall": 0.48533559234357204,
      "eval_runtime": 3.8138,
      "eval_samples_per_second": 230.215,
      "eval_steps_per_second": 28.842,
      "step": 990
    },
    {
      "epoch": 6.0606060606060606,
      "grad_norm": 1.48198664188385,
      "learning_rate": 6.926120825385258e-05,
      "loss": 0.4174,
      "step": 1000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8377386251328275,
      "eval_loss": 0.6801306009292603,
      "eval_macro_f1": 0.5105261331060333,
      "eval_macro_precision": 0.5298621091537271,
      "eval_macro_recall": 0.5130394897405378,
      "eval_runtime": 3.743,
      "eval_samples_per_second": 234.574,
      "eval_steps_per_second": 29.389,
      "step": 1155
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8405512249856955,
      "eval_loss": 0.7128350138664246,
      "eval_macro_f1": 0.5145736070824514,
      "eval_macro_precision": 0.5338232435701135,
      "eval_macro_recall": 0.5148104452511267,
      "eval_runtime": 3.8105,
      "eval_samples_per_second": 230.418,
      "eval_steps_per_second": 28.868,
      "step": 1320
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8356208154681846,
      "eval_loss": 0.7495563626289368,
      "eval_macro_f1": 0.5078761754368146,
      "eval_macro_precision": 0.5215628937215542,
      "eval_macro_recall": 0.510509104208083,
      "eval_runtime": 3.8142,
      "eval_samples_per_second": 230.191,
      "eval_steps_per_second": 28.839,
      "step": 1485
    },
    {
      "epoch": 9.090909090909092,
      "grad_norm": 1.2219234704971313,
      "learning_rate": 6.116994560737448e-05,
      "loss": 0.207,
      "step": 1500
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8404137531302713,
      "eval_loss": 0.7915265560150146,
      "eval_macro_f1": 0.5284150089162629,
      "eval_macro_precision": 0.5652985249581868,
      "eval_macro_recall": 0.5173389157983858,
      "eval_runtime": 3.8115,
      "eval_samples_per_second": 230.354,
      "eval_steps_per_second": 28.86,
      "step": 1650
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.8365311020784258,
      "eval_loss": 0.8357340097427368,
      "eval_macro_f1": 0.5241371167696747,
      "eval_macro_precision": 0.5418612467571973,
      "eval_macro_recall": 0.5268409732620435,
      "eval_runtime": 3.8104,
      "eval_samples_per_second": 230.422,
      "eval_steps_per_second": 28.868,
      "step": 1815
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.83948488924227,
      "eval_loss": 0.860895574092865,
      "eval_macro_f1": 0.5274542995604197,
      "eval_macro_precision": 0.5642301005555995,
      "eval_macro_recall": 0.5189445167674911,
      "eval_runtime": 3.7927,
      "eval_samples_per_second": 231.498,
      "eval_steps_per_second": 29.003,
      "step": 1980
    },
    {
      "epoch": 12.121212121212121,
      "grad_norm": 1.4894951581954956,
      "learning_rate": 5.307868296089637e-05,
      "loss": 0.1106,
      "step": 2000
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.837367079577627,
      "eval_loss": 0.8975165486335754,
      "eval_macro_f1": 0.5324199411604539,
      "eval_macro_precision": 0.545792242605528,
      "eval_macro_recall": 0.5377469764932828,
      "eval_runtime": 3.7913,
      "eval_samples_per_second": 231.585,
      "eval_steps_per_second": 29.014,
      "step": 2145
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.831667570760851,
      "eval_loss": 0.9421281218528748,
      "eval_macro_f1": 0.5262611445373023,
      "eval_macro_precision": 0.5347627543444692,
      "eval_macro_recall": 0.5417363003088691,
      "eval_runtime": 3.804,
      "eval_samples_per_second": 230.807,
      "eval_steps_per_second": 28.917,
      "step": 2310
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.8381064552324761,
      "eval_loss": 0.9438627362251282,
      "eval_macro_f1": 0.5348984394876934,
      "eval_macro_precision": 0.546671824271427,
      "eval_macro_recall": 0.5379298790499474,
      "eval_runtime": 3.8089,
      "eval_samples_per_second": 230.516,
      "eval_steps_per_second": 28.88,
      "step": 2475
    },
    {
      "epoch": 15.151515151515152,
      "grad_norm": 0.9380698800086975,
      "learning_rate": 4.498742031441827e-05,
      "loss": 0.0622,
      "step": 2500
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.835973783745625,
      "eval_loss": 0.9927621483802795,
      "eval_macro_f1": 0.5346150876236929,
      "eval_macro_precision": 0.5412591223724303,
      "eval_macro_recall": 0.5415646974890974,
      "eval_runtime": 3.8119,
      "eval_samples_per_second": 230.328,
      "eval_steps_per_second": 28.857,
      "step": 2640
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.8385114398876446,
      "eval_loss": 1.00917387008667,
      "eval_macro_f1": 0.5375529028664181,
      "eval_macro_precision": 0.5691165677941541,
      "eval_macro_recall": 0.5349126486369854,
      "eval_runtime": 3.8075,
      "eval_samples_per_second": 230.599,
      "eval_steps_per_second": 28.891,
      "step": 2805
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.8392285228091816,
      "eval_loss": 1.0304529666900635,
      "eval_macro_f1": 0.5373729743137114,
      "eval_macro_precision": 0.5576924127069764,
      "eval_macro_recall": 0.539334821981497,
      "eval_runtime": 3.8101,
      "eval_samples_per_second": 230.437,
      "eval_steps_per_second": 28.87,
      "step": 2970
    },
    {
      "epoch": 18.181818181818183,
      "grad_norm": 1.10272216796875,
      "learning_rate": 3.689615766794016e-05,
      "loss": 0.0365,
      "step": 3000
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.8382290652656922,
      "eval_loss": 1.0565452575683594,
      "eval_macro_f1": 0.5382182396542954,
      "eval_macro_precision": 0.5617383574248755,
      "eval_macro_recall": 0.5399115920507231,
      "eval_runtime": 3.8119,
      "eval_samples_per_second": 230.33,
      "eval_steps_per_second": 28.857,
      "step": 3135
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.8372110304444428,
      "eval_loss": 1.0832605361938477,
      "eval_macro_f1": 0.5426999278930784,
      "eval_macro_precision": 0.5539906546541987,
      "eval_macro_recall": 0.5517989175520424,
      "eval_runtime": 3.8083,
      "eval_samples_per_second": 230.549,
      "eval_steps_per_second": 28.884,
      "step": 3300
    },
    {
      "epoch": 21.0,
      "eval_accuracy": 0.839499751064478,
      "eval_loss": 1.0868653059005737,
      "eval_macro_f1": 0.53917903306677,
      "eval_macro_precision": 0.5749497192899481,
      "eval_macro_recall": 0.5373986303762837,
      "eval_runtime": 3.8141,
      "eval_samples_per_second": 230.199,
      "eval_steps_per_second": 28.84,
      "step": 3465
    },
    {
      "epoch": 21.21212121212121,
      "grad_norm": 0.46956342458724976,
      "learning_rate": 2.8804895021462055e-05,
      "loss": 0.0224,
      "step": 3500
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.8391096282315175,
      "eval_loss": 1.1133960485458374,
      "eval_macro_f1": 0.5443083566401578,
      "eval_macro_precision": 0.5641662348298077,
      "eval_macro_recall": 0.5481264782508153,
      "eval_runtime": 3.813,
      "eval_samples_per_second": 230.266,
      "eval_steps_per_second": 28.849,
      "step": 3630
    },
    {
      "epoch": 23.0,
      "eval_accuracy": 0.838050723399196,
      "eval_loss": 1.1350845098495483,
      "eval_macro_f1": 0.544210275681084,
      "eval_macro_precision": 0.5622845529634525,
      "eval_macro_recall": 0.5482077780076627,
      "eval_runtime": 3.8169,
      "eval_samples_per_second": 230.032,
      "eval_steps_per_second": 28.82,
      "step": 3795
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.838050723399196,
      "eval_loss": 1.1593064069747925,
      "eval_macro_f1": 0.5416925123679783,
      "eval_macro_precision": 0.5680966862603153,
      "eval_macro_recall": 0.5448186956610225,
      "eval_runtime": 3.8224,
      "eval_samples_per_second": 229.699,
      "eval_steps_per_second": 28.778,
      "step": 3960
    },
    {
      "epoch": 24.242424242424242,
      "grad_norm": 0.9432898759841919,
      "learning_rate": 2.071363237498395e-05,
      "loss": 0.0149,
      "step": 4000
    },
    {
      "epoch": 25.0,
      "eval_accuracy": 0.8398712966196785,
      "eval_loss": 1.1621172428131104,
      "eval_macro_f1": 0.5446548032758927,
      "eval_macro_precision": 0.572924667254898,
      "eval_macro_recall": 0.5453082375999836,
      "eval_runtime": 3.8202,
      "eval_samples_per_second": 229.832,
      "eval_steps_per_second": 28.794,
      "step": 4125
    }
  ],
  "logging_steps": 500,
  "max_steps": 5280,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 32,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.745821766419731e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 7.86794379743531e-05,
    "per_device_train_batch_size": 16,
    "warmup_ratio": 0.07903396276412193,
    "weight_decay": 0.06816454557507429
  }
}