{
  "best_metric": 0.8056872037914692,
  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-wol/checkpoint-2000",
  "epoch": 91.52542372881356,
  "global_step": 5400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.39,
      "eval_accuracy_score": 0.9890510948905109,
      "eval_f1": 0.7586206896551724,
      "eval_loss": 0.06563546508550644,
      "eval_precision": 0.8191489361702128,
      "eval_recall": 0.7064220183486238,
      "eval_runtime": 3.7154,
      "eval_samples_per_second": 71.864,
      "eval_steps_per_second": 9.151,
      "step": 200
    },
    {
      "epoch": 6.78,
      "eval_accuracy_score": 0.989507299270073,
      "eval_f1": 0.8076923076923077,
      "eval_loss": 0.07390450686216354,
      "eval_precision": 0.8484848484848485,
      "eval_recall": 0.7706422018348624,
      "eval_runtime": 3.7144,
      "eval_samples_per_second": 71.883,
      "eval_steps_per_second": 9.154,
      "step": 400
    },
    {
      "epoch": 8.47,
      "learning_rate": 4.865771812080537e-05,
      "loss": 0.0928,
      "step": 500
    },
    {
      "epoch": 10.17,
      "eval_accuracy_score": 0.989507299270073,
      "eval_f1": 0.7926267281105991,
      "eval_loss": 0.0707671046257019,
      "eval_precision": 0.7962962962962963,
      "eval_recall": 0.7889908256880734,
      "eval_runtime": 3.7124,
      "eval_samples_per_second": 71.921,
      "eval_steps_per_second": 9.159,
      "step": 600
    },
    {
      "epoch": 13.56,
      "eval_accuracy_score": 0.9890510948905109,
      "eval_f1": 0.7924528301886793,
      "eval_loss": 0.08138999342918396,
      "eval_precision": 0.8155339805825242,
      "eval_recall": 0.7706422018348624,
      "eval_runtime": 3.7153,
      "eval_samples_per_second": 71.864,
      "eval_steps_per_second": 9.151,
      "step": 800
    },
    {
      "epoch": 16.95,
      "learning_rate": 4.697986577181208e-05,
      "loss": 0.0031,
      "step": 1000
    },
    {
      "epoch": 16.95,
      "eval_accuracy_score": 0.9879105839416058,
      "eval_f1": 0.7555555555555554,
      "eval_loss": 0.09191697090864182,
      "eval_precision": 0.7327586206896551,
      "eval_recall": 0.7798165137614679,
      "eval_runtime": 3.7121,
      "eval_samples_per_second": 71.926,
      "eval_steps_per_second": 9.159,
      "step": 1000
    },
    {
      "epoch": 20.34,
      "eval_accuracy_score": 0.9890510948905109,
      "eval_f1": 0.7927927927927928,
      "eval_loss": 0.08485409617424011,
      "eval_precision": 0.7787610619469026,
      "eval_recall": 0.8073394495412844,
      "eval_runtime": 3.7118,
      "eval_samples_per_second": 71.933,
      "eval_steps_per_second": 9.16,
      "step": 1200
    },
    {
      "epoch": 23.73,
      "eval_accuracy_score": 0.9888229927007299,
      "eval_f1": 0.7665198237885462,
      "eval_loss": 0.08115804940462112,
      "eval_precision": 0.7372881355932204,
      "eval_recall": 0.7981651376146789,
      "eval_runtime": 3.7091,
      "eval_samples_per_second": 71.984,
      "eval_steps_per_second": 9.167,
      "step": 1400
    },
    {
      "epoch": 25.42,
      "learning_rate": 4.530201342281879e-05,
      "loss": 0.0017,
      "step": 1500
    },
    {
      "epoch": 27.12,
      "eval_accuracy_score": 0.9890510948905109,
      "eval_f1": 0.8018433179723502,
      "eval_loss": 0.09983422607183456,
      "eval_precision": 0.8055555555555556,
      "eval_recall": 0.7981651376146789,
      "eval_runtime": 3.7138,
      "eval_samples_per_second": 71.894,
      "eval_steps_per_second": 9.155,
      "step": 1600
    },
    {
      "epoch": 30.51,
      "eval_accuracy_score": 0.9881386861313869,
      "eval_f1": 0.7873303167420814,
      "eval_loss": 0.09764721244573593,
      "eval_precision": 0.7767857142857143,
      "eval_recall": 0.7981651376146789,
      "eval_runtime": 3.7105,
      "eval_samples_per_second": 71.957,
      "eval_steps_per_second": 9.163,
      "step": 1800
    },
    {
      "epoch": 33.9,
      "learning_rate": 4.36241610738255e-05,
      "loss": 0.0022,
      "step": 2000
    },
    {
      "epoch": 33.9,
      "eval_accuracy_score": 0.9890510948905109,
      "eval_f1": 0.8056872037914692,
      "eval_loss": 0.11199253052473068,
      "eval_precision": 0.8333333333333334,
      "eval_recall": 0.7798165137614679,
      "eval_runtime": 3.7052,
      "eval_samples_per_second": 72.061,
      "eval_steps_per_second": 9.176,
      "step": 2000
    },
    {
      "epoch": 37.29,
      "eval_accuracy_score": 0.9879105839416058,
      "eval_f1": 0.7982062780269058,
      "eval_loss": 0.10247013717889786,
      "eval_precision": 0.7807017543859649,
      "eval_recall": 0.8165137614678899,
      "eval_runtime": 3.6997,
      "eval_samples_per_second": 72.169,
      "eval_steps_per_second": 9.19,
      "step": 2200
    },
    {
      "epoch": 40.68,
      "eval_accuracy_score": 0.988594890510949,
      "eval_f1": 0.7782805429864253,
      "eval_loss": 0.10762448608875275,
      "eval_precision": 0.7678571428571429,
      "eval_recall": 0.7889908256880734,
      "eval_runtime": 3.7002,
      "eval_samples_per_second": 72.159,
      "eval_steps_per_second": 9.189,
      "step": 2400
    },
    {
      "epoch": 42.37,
      "learning_rate": 4.194630872483222e-05,
      "loss": 0.0012,
      "step": 2500
    },
    {
      "epoch": 44.07,
      "eval_accuracy_score": 0.990191605839416,
      "eval_f1": 0.7999999999999999,
      "eval_loss": 0.10491974651813507,
      "eval_precision": 0.8316831683168316,
      "eval_recall": 0.7706422018348624,
      "eval_runtime": 3.7018,
      "eval_samples_per_second": 72.126,
      "eval_steps_per_second": 9.185,
      "step": 2600
    },
    {
      "epoch": 47.46,
      "eval_accuracy_score": 0.9888229927007299,
      "eval_f1": 0.8093023255813954,
      "eval_loss": 0.10662327706813812,
      "eval_precision": 0.8207547169811321,
      "eval_recall": 0.7981651376146789,
      "eval_runtime": 3.7086,
      "eval_samples_per_second": 71.995,
      "eval_steps_per_second": 9.168,
      "step": 2800
    },
    {
      "epoch": 50.85,
      "learning_rate": 4.026845637583892e-05,
      "loss": 0.0011,
      "step": 3000
    },
    {
      "epoch": 50.85,
      "eval_accuracy_score": 0.9881386861313869,
      "eval_f1": 0.7866108786610879,
      "eval_loss": 0.11663952469825745,
      "eval_precision": 0.7230769230769231,
      "eval_recall": 0.8623853211009175,
      "eval_runtime": 3.6964,
      "eval_samples_per_second": 72.232,
      "eval_steps_per_second": 9.198,
      "step": 3000
    },
    {
      "epoch": 54.24,
      "eval_accuracy_score": 0.989963503649635,
      "eval_f1": 0.821917808219178,
      "eval_loss": 0.11120918393135071,
      "eval_precision": 0.8181818181818182,
      "eval_recall": 0.8256880733944955,
      "eval_runtime": 3.6897,
      "eval_samples_per_second": 72.364,
      "eval_steps_per_second": 9.215,
      "step": 3200
    },
    {
      "epoch": 57.63,
      "eval_accuracy_score": 0.989279197080292,
      "eval_f1": 0.8195121951219513,
      "eval_loss": 0.11466681212186813,
      "eval_precision": 0.875,
      "eval_recall": 0.7706422018348624,
      "eval_runtime": 3.701,
      "eval_samples_per_second": 72.144,
      "eval_steps_per_second": 9.187,
      "step": 3400
    },
    {
      "epoch": 59.32,
      "learning_rate": 3.859060402684564e-05,
      "loss": 0.0011,
      "step": 3500
    },
    {
      "epoch": 61.02,
      "eval_accuracy_score": 0.988594890510949,
      "eval_f1": 0.7962085308056872,
      "eval_loss": 0.10891496390104294,
      "eval_precision": 0.8235294117647058,
      "eval_recall": 0.7706422018348624,
      "eval_runtime": 3.6933,
      "eval_samples_per_second": 72.293,
      "eval_steps_per_second": 9.206,
      "step": 3600
    },
    {
      "epoch": 64.41,
      "eval_accuracy_score": 0.989279197080292,
      "eval_f1": 0.8018867924528301,
      "eval_loss": 0.0993962213397026,
      "eval_precision": 0.8252427184466019,
      "eval_recall": 0.7798165137614679,
      "eval_runtime": 3.6945,
      "eval_samples_per_second": 72.27,
      "eval_steps_per_second": 9.203,
      "step": 3800
    },
    {
      "epoch": 67.8,
      "learning_rate": 3.6912751677852356e-05,
      "loss": 0.0012,
      "step": 4000
    },
    {
      "epoch": 67.8,
      "eval_accuracy_score": 0.9867700729927007,
      "eval_f1": 0.7439613526570049,
      "eval_loss": 0.13062410056591034,
      "eval_precision": 0.7857142857142857,
      "eval_recall": 0.7064220183486238,
      "eval_runtime": 3.689,
      "eval_samples_per_second": 72.378,
      "eval_steps_per_second": 9.217,
      "step": 4000
    },
    {
      "epoch": 71.19,
      "eval_accuracy_score": 0.9883667883211679,
      "eval_f1": 0.7889908256880734,
      "eval_loss": 0.10526341944932938,
      "eval_precision": 0.7889908256880734,
      "eval_recall": 0.7889908256880734,
      "eval_runtime": 3.6853,
      "eval_samples_per_second": 72.451,
      "eval_steps_per_second": 9.226,
      "step": 4200
    },
    {
      "epoch": 74.58,
      "eval_accuracy_score": 0.9904197080291971,
      "eval_f1": 0.8169014084507041,
      "eval_loss": 0.08558077365159988,
      "eval_precision": 0.8365384615384616,
      "eval_recall": 0.7981651376146789,
      "eval_runtime": 3.6968,
      "eval_samples_per_second": 72.224,
      "eval_steps_per_second": 9.197,
      "step": 4400
    },
    {
      "epoch": 76.27,
      "learning_rate": 3.523489932885906e-05,
      "loss": 0.001,
      "step": 4500
    },
    {
      "epoch": 77.97,
      "eval_accuracy_score": 0.9883667883211679,
      "eval_f1": 0.7733333333333334,
      "eval_loss": 0.11534098535776138,
      "eval_precision": 0.75,
      "eval_recall": 0.7981651376146789,
      "eval_runtime": 3.7034,
      "eval_samples_per_second": 72.096,
      "eval_steps_per_second": 9.181,
      "step": 4600
    },
    {
      "epoch": 81.36,
      "eval_accuracy_score": 0.9879105839416058,
      "eval_f1": 0.7762557077625571,
      "eval_loss": 0.10414384305477142,
      "eval_precision": 0.7727272727272727,
      "eval_recall": 0.7798165137614679,
      "eval_runtime": 3.7039,
      "eval_samples_per_second": 72.087,
      "eval_steps_per_second": 9.18,
      "step": 4800
    },
    {
      "epoch": 84.75,
      "learning_rate": 3.3557046979865775e-05,
      "loss": 0.0006,
      "step": 5000
    },
    {
      "epoch": 84.75,
      "eval_accuracy_score": 0.9869981751824818,
      "eval_f1": 0.7565217391304349,
      "eval_loss": 0.10606261342763901,
      "eval_precision": 0.71900826446281,
      "eval_recall": 0.7981651376146789,
      "eval_runtime": 3.6946,
      "eval_samples_per_second": 72.268,
      "eval_steps_per_second": 9.203,
      "step": 5000
    },
    {
      "epoch": 88.14,
      "eval_accuracy_score": 0.9883667883211679,
      "eval_f1": 0.7685185185185185,
      "eval_loss": 0.10869959741830826,
      "eval_precision": 0.7757009345794392,
      "eval_recall": 0.7614678899082569,
      "eval_runtime": 3.7012,
      "eval_samples_per_second": 72.139,
      "eval_steps_per_second": 9.186,
      "step": 5200
    },
    {
      "epoch": 91.53,
      "eval_accuracy_score": 0.988594890510949,
      "eval_f1": 0.7813953488372094,
      "eval_loss": 0.12209474295377731,
      "eval_precision": 0.7924528301886793,
      "eval_recall": 0.7706422018348624,
      "eval_runtime": 3.6806,
      "eval_samples_per_second": 72.542,
      "eval_steps_per_second": 9.238,
      "step": 5400
    },
    {
      "epoch": 91.53,
      "step": 5400,
      "total_flos": 2.237534270977997e+16,
      "train_loss": 0.009840657206045256,
      "train_runtime": 6068.7812,
      "train_samples_per_second": 79.093,
      "train_steps_per_second": 2.472
    }
  ],
  "max_steps": 15000,
  "num_train_epochs": 255,
  "total_flos": 2.237534270977997e+16,
  "trial_name": null,
  "trial_params": null
}