{
  "best_metric": 0.0012908950448036194,
  "best_model_checkpoint": "gender\\checkpoint-72",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 72,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.125,
      "grad_norm": 8.839544296264648,
      "learning_rate": 3.125e-06,
      "loss": 0.7543,
      "step": 1
    },
    {
      "epoch": 0.25,
      "grad_norm": Infinity,
      "learning_rate": 3.125e-06,
      "loss": 0.8194,
      "step": 2
    },
    {
      "epoch": 0.375,
      "grad_norm": 10.062314987182617,
      "learning_rate": 6.25e-06,
      "loss": 0.8397,
      "step": 3
    },
    {
      "epoch": 0.5,
      "grad_norm": 8.579401969909668,
      "learning_rate": 9.375000000000001e-06,
      "loss": 0.758,
      "step": 4
    },
    {
      "epoch": 0.625,
      "grad_norm": 12.681062698364258,
      "learning_rate": 1.25e-05,
      "loss": 0.9867,
      "step": 5
    },
    {
      "epoch": 0.75,
      "grad_norm": 13.662342071533203,
      "learning_rate": 1.5625e-05,
      "loss": 0.6524,
      "step": 6
    },
    {
      "epoch": 0.875,
      "grad_norm": 8.97331714630127,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.9147,
      "step": 7
    },
    {
      "epoch": 1.0,
      "grad_norm": 6.345348834991455,
      "learning_rate": 2.1875e-05,
      "loss": 0.4983,
      "step": 8
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.75,
      "eval_auc": 0.6875,
      "eval_f1": 0.0,
      "eval_loss": 0.6031913757324219,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.064,
      "eval_samples_per_second": 250.101,
      "eval_steps_per_second": 15.631,
      "step": 8
    },
    {
      "epoch": 1.125,
      "grad_norm": 8.304693222045898,
      "learning_rate": 2.5e-05,
      "loss": 0.6723,
      "step": 9
    },
    {
      "epoch": 1.25,
      "grad_norm": 5.756776809692383,
      "learning_rate": 2.8125000000000003e-05,
      "loss": 0.3328,
      "step": 10
    },
    {
      "epoch": 1.375,
      "grad_norm": 6.210690975189209,
      "learning_rate": 3.125e-05,
      "loss": 0.4256,
      "step": 11
    },
    {
      "epoch": 1.5,
      "grad_norm": 10.43043041229248,
      "learning_rate": 3.4375e-05,
      "loss": 0.6545,
      "step": 12
    },
    {
      "epoch": 1.625,
      "grad_norm": 4.654361248016357,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.2891,
      "step": 13
    },
    {
      "epoch": 1.75,
      "grad_norm": 7.63759183883667,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 0.4828,
      "step": 14
    },
    {
      "epoch": 1.875,
      "grad_norm": 6.132064342498779,
      "learning_rate": 4.375e-05,
      "loss": 0.4312,
      "step": 15
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.3374931812286377,
      "learning_rate": 4.6875e-05,
      "loss": 0.2086,
      "step": 16
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8125,
      "eval_auc": 1.0,
      "eval_f1": 0.4,
      "eval_loss": 0.3224067687988281,
      "eval_precision": 1.0,
      "eval_recall": 0.25,
      "eval_runtime": 0.0587,
      "eval_samples_per_second": 272.474,
      "eval_steps_per_second": 17.03,
      "step": 16
    },
    {
      "epoch": 2.125,
      "grad_norm": 3.077073335647583,
      "learning_rate": 5e-05,
      "loss": 0.1397,
      "step": 17
    },
    {
      "epoch": 2.25,
      "grad_norm": 4.40862512588501,
      "learning_rate": 4.965277777777778e-05,
      "loss": 0.3093,
      "step": 18
    },
    {
      "epoch": 2.375,
      "grad_norm": 3.4765329360961914,
      "learning_rate": 4.930555555555556e-05,
      "loss": 0.2167,
      "step": 19
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.5243409872055054,
      "learning_rate": 4.8958333333333335e-05,
      "loss": 0.0778,
      "step": 20
    },
    {
      "epoch": 2.625,
      "grad_norm": 3.61657977104187,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 0.1989,
      "step": 21
    },
    {
      "epoch": 2.75,
      "grad_norm": 3.2988128662109375,
      "learning_rate": 4.8263888888888895e-05,
      "loss": 0.197,
      "step": 22
    },
    {
      "epoch": 2.875,
      "grad_norm": 1.3049061298370361,
      "learning_rate": 4.791666666666667e-05,
      "loss": 0.0648,
      "step": 23
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.643069267272949,
      "learning_rate": 4.756944444444444e-05,
      "loss": 0.0701,
      "step": 24
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0625617504119873,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.0556,
      "eval_samples_per_second": 287.572,
      "eval_steps_per_second": 17.973,
      "step": 24
    },
    {
      "epoch": 3.125,
      "grad_norm": 3.6841492652893066,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.1321,
      "step": 25
    },
    {
      "epoch": 3.25,
      "grad_norm": 0.8644580841064453,
      "learning_rate": 4.6875e-05,
      "loss": 0.0245,
      "step": 26
    },
    {
      "epoch": 3.375,
      "grad_norm": 0.6396610736846924,
      "learning_rate": 4.652777777777778e-05,
      "loss": 0.0204,
      "step": 27
    },
    {
      "epoch": 3.5,
      "grad_norm": 5.226676940917969,
      "learning_rate": 4.618055555555556e-05,
      "loss": 0.0882,
      "step": 28
    },
    {
      "epoch": 3.625,
      "grad_norm": 3.9581685066223145,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 0.091,
      "step": 29
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.2740299105644226,
      "learning_rate": 4.5486111111111114e-05,
      "loss": 0.0087,
      "step": 30
    },
    {
      "epoch": 3.875,
      "grad_norm": 0.6588912010192871,
      "learning_rate": 4.5138888888888894e-05,
      "loss": 0.0175,
      "step": 31
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.047511577606201,
      "learning_rate": 4.4791666666666673e-05,
      "loss": 0.0809,
      "step": 32
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.01665613055229187,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.0561,
      "eval_samples_per_second": 285.035,
      "eval_steps_per_second": 17.815,
      "step": 32
    },
    {
      "epoch": 4.125,
      "grad_norm": 3.6106154918670654,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.098,
      "step": 33
    },
    {
      "epoch": 4.25,
      "grad_norm": 0.26180651783943176,
      "learning_rate": 4.4097222222222226e-05,
      "loss": 0.0072,
      "step": 34
    },
    {
      "epoch": 4.375,
      "grad_norm": 0.784140408039093,
      "learning_rate": 4.375e-05,
      "loss": 0.0209,
      "step": 35
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.07298047840595245,
      "learning_rate": 4.340277777777778e-05,
      "loss": 0.0025,
      "step": 36
    },
    {
      "epoch": 4.625,
      "grad_norm": 0.06727258116006851,
      "learning_rate": 4.305555555555556e-05,
      "loss": 0.0025,
      "step": 37
    },
    {
      "epoch": 4.75,
      "grad_norm": 0.21512272953987122,
      "learning_rate": 4.270833333333333e-05,
      "loss": 0.0048,
      "step": 38
    },
    {
      "epoch": 4.875,
      "grad_norm": 0.19965760409832,
      "learning_rate": 4.236111111111111e-05,
      "loss": 0.0051,
      "step": 39
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.27846547961235046,
      "learning_rate": 4.201388888888889e-05,
      "loss": 0.0049,
      "step": 40
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.009060055017471313,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.0529,
      "eval_samples_per_second": 302.334,
      "eval_steps_per_second": 18.896,
      "step": 40
    },
    {
      "epoch": 5.125,
      "grad_norm": 2.1866636276245117,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.0473,
      "step": 41
    },
    {
      "epoch": 5.25,
      "grad_norm": 3.711268186569214,
      "learning_rate": 4.1319444444444445e-05,
      "loss": 0.061,
      "step": 42
    },
    {
      "epoch": 5.375,
      "grad_norm": 0.03193037211894989,
      "learning_rate": 4.0972222222222225e-05,
      "loss": 0.0011,
      "step": 43
    },
    {
      "epoch": 5.5,
      "grad_norm": 0.0857921689748764,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 0.0021,
      "step": 44
    },
    {
      "epoch": 5.625,
      "grad_norm": 0.10865919291973114,
      "learning_rate": 4.027777777777778e-05,
      "loss": 0.0028,
      "step": 45
    },
    {
      "epoch": 5.75,
      "grad_norm": 0.11789407581090927,
      "learning_rate": 3.993055555555556e-05,
      "loss": 0.0035,
      "step": 46
    },
    {
      "epoch": 5.875,
      "grad_norm": 0.051877208054065704,
      "learning_rate": 3.958333333333333e-05,
      "loss": 0.0009,
      "step": 47
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.9682751893997192,
      "learning_rate": 3.923611111111111e-05,
      "loss": 0.0112,
      "step": 48
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.01014169305562973,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.0571,
      "eval_samples_per_second": 280.203,
      "eval_steps_per_second": 17.513,
      "step": 48
    },
    {
      "epoch": 6.125,
      "grad_norm": 0.2799108922481537,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.0042,
      "step": 49
    },
    {
      "epoch": 6.25,
      "grad_norm": 0.02485131472349167,
      "learning_rate": 3.854166666666667e-05,
      "loss": 0.0006,
      "step": 50
    },
    {
      "epoch": 6.375,
      "grad_norm": 0.07226316630840302,
      "learning_rate": 3.8194444444444444e-05,
      "loss": 0.0021,
      "step": 51
    },
    {
      "epoch": 6.5,
      "grad_norm": 0.14999447762966156,
      "learning_rate": 3.7847222222222224e-05,
      "loss": 0.0034,
      "step": 52
    },
    {
      "epoch": 6.625,
      "grad_norm": 0.24165014922618866,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.0032,
      "step": 53
    },
    {
      "epoch": 6.75,
      "grad_norm": 8.056694030761719,
      "learning_rate": 3.715277777777778e-05,
      "loss": 0.0603,
      "step": 54
    },
    {
      "epoch": 6.875,
      "grad_norm": 0.07370386272668839,
      "learning_rate": 3.6805555555555556e-05,
      "loss": 0.0015,
      "step": 55
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.02779821865260601,
      "learning_rate": 3.6458333333333336e-05,
      "loss": 0.0007,
      "step": 56
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0030152201652526855,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.0532,
      "eval_samples_per_second": 300.996,
      "eval_steps_per_second": 18.812,
      "step": 56
    },
    {
      "epoch": 7.125,
      "grad_norm": 11.091121673583984,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.4382,
      "step": 57
    },
    {
      "epoch": 7.25,
      "grad_norm": 0.02736804261803627,
      "learning_rate": 3.576388888888889e-05,
      "loss": 0.0007,
      "step": 58
    },
    {
      "epoch": 7.375,
      "grad_norm": 0.06560361385345459,
      "learning_rate": 3.541666666666667e-05,
      "loss": 0.0012,
      "step": 59
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.033276110887527466,
      "learning_rate": 3.506944444444444e-05,
      "loss": 0.0009,
      "step": 60
    },
    {
      "epoch": 7.625,
      "grad_norm": 0.02789870649576187,
      "learning_rate": 3.472222222222222e-05,
      "loss": 0.0009,
      "step": 61
    },
    {
      "epoch": 7.75,
      "grad_norm": 0.024605700746178627,
      "learning_rate": 3.4375e-05,
      "loss": 0.0007,
      "step": 62
    },
    {
      "epoch": 7.875,
      "grad_norm": 1.4100219011306763,
      "learning_rate": 3.402777777777778e-05,
      "loss": 0.0241,
      "step": 63
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.01102516334503889,
      "learning_rate": 3.368055555555556e-05,
      "loss": 0.0004,
      "step": 64
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0015663951635360718,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.06,
      "eval_samples_per_second": 266.724,
      "eval_steps_per_second": 16.67,
      "step": 64
    },
    {
      "epoch": 8.125,
      "grad_norm": 0.025314731523394585,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0009,
      "step": 65
    },
    {
      "epoch": 8.25,
      "grad_norm": 0.019100826233625412,
      "learning_rate": 3.2986111111111115e-05,
      "loss": 0.0006,
      "step": 66
    },
    {
      "epoch": 8.375,
      "grad_norm": 0.3341350555419922,
      "learning_rate": 3.263888888888889e-05,
      "loss": 0.0059,
      "step": 67
    },
    {
      "epoch": 8.5,
      "grad_norm": 0.47374579310417175,
      "learning_rate": 3.229166666666667e-05,
      "loss": 0.0046,
      "step": 68
    },
    {
      "epoch": 8.625,
      "grad_norm": 0.030372226610779762,
      "learning_rate": 3.194444444444444e-05,
      "loss": 0.0011,
      "step": 69
    },
    {
      "epoch": 8.75,
      "grad_norm": 0.02839597873389721,
      "learning_rate": 3.159722222222222e-05,
      "loss": 0.0008,
      "step": 70
    },
    {
      "epoch": 8.875,
      "grad_norm": 0.0297985952347517,
      "learning_rate": 3.125e-05,
      "loss": 0.001,
      "step": 71
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.019845914095640182,
      "learning_rate": 3.090277777777778e-05,
      "loss": 0.0007,
      "step": 72
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 1.0,
      "eval_auc": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.0012908950448036194,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.0567,
      "eval_samples_per_second": 282.131,
      "eval_steps_per_second": 17.633,
      "step": 72
    }
  ],
  "logging_steps": 1,
  "max_steps": 160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.463538601800499e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}