{
  "best_metric": 0.1703585386276245,
  "best_model_checkpoint": "/scratch/hlv8980/Attack_Benchmark/models/hyena/prom_300_all/origin/checkpoint-1800",
  "epoch": 4.0,
  "global_step": 2960,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14,
      "learning_rate": 2.952577319587629e-05,
      "loss": 0.5003,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.8494845360824743e-05,
      "loss": 0.2673,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_accuracy": 0.9069256756756757,
      "eval_f1": 0.9067711712586135,
      "eval_loss": 0.2377714067697525,
      "eval_matthews_correlation": 0.8159005194391875,
      "eval_precision": 0.9091506257526489,
      "eval_recall": 0.9067534153201929,
      "eval_runtime": 0.6377,
      "eval_samples_per_second": 9282.663,
      "eval_steps_per_second": 145.826,
      "step": 200
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.7463917525773194e-05,
      "loss": 0.2376,
      "step": 300
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.6443298969072166e-05,
      "loss": 0.2317,
      "step": 400
    },
    {
      "epoch": 0.54,
      "eval_accuracy": 0.9153716216216217,
      "eval_f1": 0.9153262748485617,
      "eval_loss": 0.21122267842292786,
      "eval_matthews_correlation": 0.8312740006363274,
      "eval_precision": 0.9159916610939429,
      "eval_recall": 0.9152826419144695,
      "eval_runtime": 0.6332,
      "eval_samples_per_second": 9350.059,
      "eval_steps_per_second": 146.884,
      "step": 400
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.5412371134020617e-05,
      "loss": 0.2187,
      "step": 500
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.4381443298969072e-05,
      "loss": 0.2085,
      "step": 600
    },
    {
      "epoch": 0.81,
      "eval_accuracy": 0.9222972972972973,
      "eval_f1": 0.9222684726839561,
      "eval_loss": 0.20111674070358276,
      "eval_matthews_correlation": 0.844926565348169,
      "eval_precision": 0.9226998491704375,
      "eval_recall": 0.9222268485735847,
      "eval_runtime": 0.631,
      "eval_samples_per_second": 9382.365,
      "eval_steps_per_second": 147.392,
      "step": 600
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.3350515463917527e-05,
      "loss": 0.192,
      "step": 700
    },
    {
      "epoch": 1.08,
      "learning_rate": 2.231958762886598e-05,
      "loss": 0.1928,
      "step": 800
    },
    {
      "epoch": 1.08,
      "eval_accuracy": 0.9307432432432432,
      "eval_f1": 0.9307370454989581,
      "eval_loss": 0.18229131400585175,
      "eval_matthews_correlation": 0.861849007421866,
      "eval_precision": 0.9310402320508868,
      "eval_recall": 0.9308088064424378,
      "eval_runtime": 0.6299,
      "eval_samples_per_second": 9398.535,
      "eval_steps_per_second": 147.646,
      "step": 800
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.1288659793814436e-05,
      "loss": 0.1731,
      "step": 900
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.0257731958762887e-05,
      "loss": 0.1695,
      "step": 1000
    },
    {
      "epoch": 1.35,
      "eval_accuracy": 0.9285472972972973,
      "eval_f1": 0.9285164389268092,
      "eval_loss": 0.18193063139915466,
      "eval_matthews_correlation": 0.8575116137972303,
      "eval_precision": 0.9290420069490232,
      "eval_recall": 0.928469797763007,
      "eval_runtime": 0.6331,
      "eval_samples_per_second": 9350.957,
      "eval_steps_per_second": 146.898,
      "step": 1000
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.9226804123711342e-05,
      "loss": 0.1718,
      "step": 1100
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.8195876288659793e-05,
      "loss": 0.1721,
      "step": 1200
    },
    {
      "epoch": 1.62,
      "eval_accuracy": 0.9265202702702703,
      "eval_f1": 0.9265084747697505,
      "eval_loss": 0.1794503927230835,
      "eval_matthews_correlation": 0.8531337899241861,
      "eval_precision": 0.9266527317858582,
      "eval_recall": 0.9264810754075489,
      "eval_runtime": 0.6317,
      "eval_samples_per_second": 9371.144,
      "eval_steps_per_second": 147.216,
      "step": 1200
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.7164948453608248e-05,
      "loss": 0.1744,
      "step": 1300
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.6134020618556702e-05,
      "loss": 0.1661,
      "step": 1400
    },
    {
      "epoch": 1.89,
      "eval_accuracy": 0.9305743243243243,
      "eval_f1": 0.9305549034596651,
      "eval_loss": 0.1741824597120285,
      "eval_matthews_correlation": 0.8613776877891709,
      "eval_precision": 0.9308617120011422,
      "eval_recall": 0.9305160451452759,
      "eval_runtime": 0.6318,
      "eval_samples_per_second": 9369.613,
      "eval_steps_per_second": 147.192,
      "step": 1400
    },
    {
      "epoch": 2.03,
      "learning_rate": 1.5103092783505155e-05,
      "loss": 0.1583,
      "step": 1500
    },
    {
      "epoch": 2.16,
      "learning_rate": 1.4072164948453608e-05,
      "loss": 0.1338,
      "step": 1600
    },
    {
      "epoch": 2.16,
      "eval_accuracy": 0.9304054054054054,
      "eval_f1": 0.9304047620053097,
      "eval_loss": 0.17852620780467987,
      "eval_matthews_correlation": 0.8609218830772938,
      "eval_precision": 0.9304812834224598,
      "eval_recall": 0.9304406006160657,
      "eval_runtime": 0.6302,
      "eval_samples_per_second": 9393.152,
      "eval_steps_per_second": 147.561,
      "step": 1600
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.3041237113402063e-05,
      "loss": 0.1335,
      "step": 1700
    },
    {
      "epoch": 2.43,
      "learning_rate": 1.2010309278350516e-05,
      "loss": 0.1408,
      "step": 1800
    },
    {
      "epoch": 2.43,
      "eval_accuracy": 0.9346283783783784,
      "eval_f1": 0.9346282272897191,
      "eval_loss": 0.1703585386276245,
      "eval_matthews_correlation": 0.8693294755878224,
      "eval_precision": 0.9346729983126492,
      "eval_recall": 0.9346564774321559,
      "eval_runtime": 0.6327,
      "eval_samples_per_second": 9357.223,
      "eval_steps_per_second": 146.997,
      "step": 1800
    },
    {
      "epoch": 2.57,
      "learning_rate": 1.0979381443298969e-05,
      "loss": 0.1305,
      "step": 1900
    },
    {
      "epoch": 2.7,
      "learning_rate": 9.948453608247423e-06,
      "loss": 0.1327,
      "step": 2000
    },
    {
      "epoch": 2.7,
      "eval_accuracy": 0.9320945945945946,
      "eval_f1": 0.9320702808163623,
      "eval_loss": 0.17678610980510712,
      "eval_matthews_correlation": 0.8645162095639252,
      "eval_precision": 0.9324903713392922,
      "eval_recall": 0.9320259629621006,
      "eval_runtime": 0.6318,
      "eval_samples_per_second": 9370.362,
      "eval_steps_per_second": 147.203,
      "step": 2000
    },
    {
      "epoch": 2.84,
      "learning_rate": 8.917525773195876e-06,
      "loss": 0.1383,
      "step": 2100
    },
    {
      "epoch": 2.97,
      "learning_rate": 7.886597938144331e-06,
      "loss": 0.1349,
      "step": 2200
    },
    {
      "epoch": 2.97,
      "eval_accuracy": 0.9314189189189189,
      "eval_f1": 0.931405108497465,
      "eval_loss": 0.17303186655044556,
      "eval_matthews_correlation": 0.8629769834124407,
      "eval_precision": 0.9316043715098153,
      "eval_recall": 0.9313726430147498,
      "eval_runtime": 0.6315,
      "eval_samples_per_second": 9375.096,
      "eval_steps_per_second": 147.278,
      "step": 2200
    },
    {
      "epoch": 3.11,
      "learning_rate": 6.855670103092783e-06,
      "loss": 0.107,
      "step": 2300
    },
    {
      "epoch": 3.24,
      "learning_rate": 5.824742268041238e-06,
      "loss": 0.1078,
      "step": 2400
    },
    {
      "epoch": 3.24,
      "eval_accuracy": 0.933445945945946,
      "eval_f1": 0.9334457560427207,
      "eval_loss": 0.1805320531129837,
      "eval_matthews_correlation": 0.8669684363132942,
      "eval_precision": 0.9334936190107457,
      "eval_recall": 0.9334748175064179,
      "eval_runtime": 0.6309,
      "eval_samples_per_second": 9383.323,
      "eval_steps_per_second": 147.407,
      "step": 2400
    },
    {
      "epoch": 3.38,
      "learning_rate": 4.793814432989691e-06,
      "loss": 0.1021,
      "step": 2500
    },
    {
      "epoch": 3.51,
      "learning_rate": 3.7628865979381445e-06,
      "loss": 0.0988,
      "step": 2600
    },
    {
      "epoch": 3.51,
      "eval_accuracy": 0.9349662162162162,
      "eval_f1": 0.9349650564155023,
      "eval_loss": 0.18175145983695984,
      "eval_matthews_correlation": 0.8699305930502206,
      "eval_precision": 0.9349634348264717,
      "eval_recall": 0.9349671582317172,
      "eval_runtime": 0.6305,
      "eval_samples_per_second": 9389.323,
      "eval_steps_per_second": 147.501,
      "step": 2600
    },
    {
      "epoch": 3.65,
      "learning_rate": 2.731958762886598e-06,
      "loss": 0.0999,
      "step": 2700
    },
    {
      "epoch": 3.78,
      "learning_rate": 1.7113402061855671e-06,
      "loss": 0.1004,
      "step": 2800
    },
    {
      "epoch": 3.78,
      "eval_accuracy": 0.9329391891891892,
      "eval_f1": 0.9329386361870509,
      "eval_loss": 0.17983320355415344,
      "eval_matthews_correlation": 0.8658837145627207,
      "eval_precision": 0.9329372370839953,
      "eval_recall": 0.932946477528031,
      "eval_runtime": 0.631,
      "eval_samples_per_second": 9381.465,
      "eval_steps_per_second": 147.378,
      "step": 2800
    },
    {
      "epoch": 3.92,
      "learning_rate": 6.804123711340206e-07,
      "loss": 0.1008,
      "step": 2900
    },
    {
      "epoch": 4.0,
      "step": 2960,
      "total_flos": 952582879051776.0,
      "train_loss": 0.16742652557991647,
      "train_runtime": 112.7822,
      "train_samples_per_second": 1679.556,
      "train_steps_per_second": 26.245
    }
  ],
  "max_steps": 2960,
  "num_train_epochs": 4,
  "total_flos": 952582879051776.0,
  "trial_name": null,
  "trial_params": null
}