{
  "best_metric": 0.6313058518304987,
  "best_model_checkpoint": "logs/indian_ner/roberta-base/seed_1/checkpoint-1376",
  "epoch": 19.0,
  "eval_steps": 500,
  "global_step": 1634,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7997455985661011,
      "eval_f1": 0.14692321878650028,
      "eval_loss": 0.35509759187698364,
      "eval_precision": 0.08916579614982838,
      "eval_recall": 0.41710296684118675,
      "eval_runtime": 3.1945,
      "eval_samples_per_second": 336.207,
      "eval_steps_per_second": 2.817,
      "step": 86
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8326539658678076,
      "eval_f1": 0.2069869669160176,
      "eval_loss": 0.23829466104507446,
      "eval_precision": 0.1328449811918432,
      "eval_recall": 0.46841186736474694,
      "eval_runtime": 3.449,
      "eval_samples_per_second": 311.39,
      "eval_steps_per_second": 2.609,
      "step": 172
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8921588467134997,
      "eval_f1": 0.29748962245503063,
      "eval_loss": 0.21593649685382843,
      "eval_precision": 0.20750034468495795,
      "eval_recall": 0.525305410122164,
      "eval_runtime": 2.5646,
      "eval_samples_per_second": 418.778,
      "eval_steps_per_second": 3.509,
      "step": 258
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.902517996010523,
      "eval_f1": 0.325260250690461,
      "eval_loss": 0.2013314664363861,
      "eval_precision": 0.23377614903038632,
      "eval_recall": 0.5343804537521815,
      "eval_runtime": 2.5624,
      "eval_samples_per_second": 419.138,
      "eval_steps_per_second": 3.512,
      "step": 344
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9131180557563142,
      "eval_f1": 0.3645869640989892,
      "eval_loss": 0.1926085650920868,
      "eval_precision": 0.27324973876698017,
      "eval_recall": 0.5476439790575917,
      "eval_runtime": 2.6037,
      "eval_samples_per_second": 412.492,
      "eval_steps_per_second": 3.457,
      "step": 430
    },
    {
      "epoch": 5.813953488372093,
      "grad_norm": 3.6987311840057373,
      "learning_rate": 2.1313953488372093e-05,
      "loss": 0.396,
      "step": 500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9134071482948358,
      "eval_f1": 0.37776752767527666,
      "eval_loss": 0.20021429657936096,
      "eval_precision": 0.28207335973824693,
      "eval_recall": 0.5717277486910994,
      "eval_runtime": 6.6862,
      "eval_samples_per_second": 160.629,
      "eval_steps_per_second": 1.346,
      "step": 516
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9267054050668285,
      "eval_f1": 0.440271772699197,
      "eval_loss": 0.21028228104114532,
      "eval_precision": 0.3407265774378585,
      "eval_recall": 0.6219895287958115,
      "eval_runtime": 2.6496,
      "eval_samples_per_second": 405.343,
      "eval_steps_per_second": 3.397,
      "step": 602
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9255972170024959,
      "eval_f1": 0.4397892931520274,
      "eval_loss": 0.1943674236536026,
      "eval_precision": 0.33880709701774253,
      "eval_recall": 0.6265270506108203,
      "eval_runtime": 2.5685,
      "eval_samples_per_second": 418.146,
      "eval_steps_per_second": 3.504,
      "step": 688
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9290759638827055,
      "eval_f1": 0.4493577075098814,
      "eval_loss": 0.21183457970619202,
      "eval_precision": 0.3477346587650545,
      "eval_recall": 0.6349040139616056,
      "eval_runtime": 6.3809,
      "eval_samples_per_second": 168.314,
      "eval_steps_per_second": 1.41,
      "step": 774
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9396182051207925,
      "eval_f1": 0.5092445853143158,
      "eval_loss": 0.22744828462600708,
      "eval_precision": 0.4096027193541534,
      "eval_recall": 0.6729493891797557,
      "eval_runtime": 2.6036,
      "eval_samples_per_second": 412.506,
      "eval_steps_per_second": 3.457,
      "step": 860
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.9450338720090968,
      "eval_f1": 0.5512627986348123,
      "eval_loss": 0.23177774250507355,
      "eval_precision": 0.45269058295964126,
      "eval_recall": 0.7047120418848167,
      "eval_runtime": 2.5671,
      "eval_samples_per_second": 418.363,
      "eval_steps_per_second": 3.506,
      "step": 946
    },
    {
      "epoch": 11.627906976744185,
      "grad_norm": 2.9459869861602783,
      "learning_rate": 1.2593023255813954e-05,
      "loss": 0.0715,
      "step": 1000
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9442533221550885,
      "eval_f1": 0.541422935655013,
      "eval_loss": 0.2438974231481552,
      "eval_precision": 0.44360231832367364,
      "eval_recall": 0.6945898778359512,
      "eval_runtime": 2.5676,
      "eval_samples_per_second": 418.287,
      "eval_steps_per_second": 3.505,
      "step": 1032
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9460360594759716,
      "eval_f1": 0.5802113352545629,
      "eval_loss": 0.2385331243276596,
      "eval_precision": 0.47806422433288104,
      "eval_recall": 0.737870855148342,
      "eval_runtime": 2.5597,
      "eval_samples_per_second": 419.581,
      "eval_steps_per_second": 3.516,
      "step": 1118
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.9460071502221195,
      "eval_f1": 0.5560439560439561,
      "eval_loss": 0.24203675985336304,
      "eval_precision": 0.45843714609286523,
      "eval_recall": 0.706457242582897,
      "eval_runtime": 2.5735,
      "eval_samples_per_second": 417.328,
      "eval_steps_per_second": 3.497,
      "step": 1204
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.9501604463588795,
      "eval_f1": 0.5943502824858757,
      "eval_loss": 0.245487779378891,
      "eval_precision": 0.4991696322657177,
      "eval_recall": 0.7343804537521815,
      "eval_runtime": 2.5639,
      "eval_samples_per_second": 418.898,
      "eval_steps_per_second": 3.51,
      "step": 1290
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.9571950314629046,
      "eval_f1": 0.6313058518304987,
      "eval_loss": 0.25131794810295105,
      "eval_precision": 0.537687208445863,
      "eval_recall": 0.7643979057591623,
      "eval_runtime": 2.5566,
      "eval_samples_per_second": 420.083,
      "eval_steps_per_second": 3.52,
      "step": 1376
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.9557784780241488,
      "eval_f1": 0.6291390728476821,
      "eval_loss": 0.26701298356056213,
      "eval_precision": 0.5354079882381769,
      "eval_recall": 0.7626527050610821,
      "eval_runtime": 2.5575,
      "eval_samples_per_second": 419.947,
      "eval_steps_per_second": 3.519,
      "step": 1462
    },
    {
      "epoch": 17.441860465116278,
      "grad_norm": 0.8599265813827515,
      "learning_rate": 3.8720930232558145e-06,
      "loss": 0.0344,
      "step": 1500
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.9505266302410068,
      "eval_f1": 0.596600566572238,
      "eval_loss": 0.26870501041412354,
      "eval_precision": 0.5020262216924911,
      "eval_recall": 0.7350785340314137,
      "eval_runtime": 4.3379,
      "eval_samples_per_second": 247.585,
      "eval_steps_per_second": 2.075,
      "step": 1548
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.9547473813034218,
      "eval_f1": 0.619456366237482,
      "eval_loss": 0.2665688395500183,
      "eval_precision": 0.5248484848484849,
      "eval_recall": 0.7556719022687609,
      "eval_runtime": 2.5569,
      "eval_samples_per_second": 420.037,
      "eval_steps_per_second": 3.52,
      "step": 1634
    },
    {
      "epoch": 19.0,
      "step": 1634,
      "total_flos": 5.459952374908416e+16,
      "train_loss": 0.15556327351158078,
      "train_runtime": 746.2434,
      "train_samples_per_second": 294.676,
      "train_steps_per_second": 2.305
    }
  ],
  "logging_steps": 500,
  "max_steps": 1720,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "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": 5.459952374908416e+16,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}