{
  "best_metric": 0.9736752799728511,
  "best_model_checkpoint": ".//debugged_pl_lfg_ses_udpipe_8_0.1_0.00002_20_04-22-24_18-53/checkpoint-31050",
  "epoch": 20.0,
  "global_step": 34500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.9509,
      "step": 1725
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8865587721297774,
      "eval_f1": 0.8524143302180686,
      "eval_loss": 0.5842600464820862,
      "eval_precision": 0.8554958475818271,
      "eval_recall": 0.8493549325831797,
      "eval_runtime": 5.7832,
      "eval_samples_per_second": 298.45,
      "eval_steps_per_second": 37.349,
      "step": 1725
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.914893617021277e-05,
      "loss": 0.4208,
      "step": 3450
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.946052731555353,
      "eval_f1": 0.9297769156159069,
      "eval_loss": 0.28943386673927307,
      "eval_precision": 0.9296867423140336,
      "eval_recall": 0.9298671064118731,
      "eval_runtime": 5.7466,
      "eval_samples_per_second": 300.35,
      "eval_steps_per_second": 37.587,
      "step": 3450
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.8085106382978724e-05,
      "loss": 0.2129,
      "step": 5175
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9627687865663703,
      "eval_f1": 0.9506687342508238,
      "eval_loss": 0.21297234296798706,
      "eval_precision": 0.9498402246538201,
      "eval_recall": 0.9514986904646425,
      "eval_runtime": 5.693,
      "eval_samples_per_second": 303.181,
      "eval_steps_per_second": 37.942,
      "step": 5175
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.7021276595744682e-05,
      "loss": 0.1294,
      "step": 6900
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9690752982296178,
      "eval_f1": 0.9602559131446299,
      "eval_loss": 0.17777125537395477,
      "eval_precision": 0.959604766056379,
      "eval_recall": 0.9609079445145019,
      "eval_runtime": 5.7272,
      "eval_samples_per_second": 301.371,
      "eval_steps_per_second": 37.715,
      "step": 6900
    },
    {
      "epoch": 5.0,
      "learning_rate": 1.595744680851064e-05,
      "loss": 0.0853,
      "step": 8625
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9732543119823721,
      "eval_f1": 0.9641592705756826,
      "eval_loss": 0.16290150582790375,
      "eval_precision": 0.9641125121241513,
      "eval_recall": 0.9642060335629062,
      "eval_runtime": 5.694,
      "eval_samples_per_second": 303.126,
      "eval_steps_per_second": 37.935,
      "step": 8625
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.4893617021276596e-05,
      "loss": 0.0615,
      "step": 10350
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9752298457564015,
      "eval_f1": 0.9663466201144408,
      "eval_loss": 0.1701485961675644,
      "eval_precision": 0.9661592165228352,
      "eval_recall": 0.9665340964206034,
      "eval_runtime": 5.7163,
      "eval_samples_per_second": 301.944,
      "eval_steps_per_second": 37.787,
      "step": 10350
    },
    {
      "epoch": 7.0,
      "learning_rate": 1.3829787234042556e-05,
      "loss": 0.0386,
      "step": 12075
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9772813615986627,
      "eval_f1": 0.9689392838106314,
      "eval_loss": 0.1559772491455078,
      "eval_precision": 0.9680480247869868,
      "eval_recall": 0.9698321854690076,
      "eval_runtime": 5.707,
      "eval_samples_per_second": 302.438,
      "eval_steps_per_second": 37.849,
      "step": 12075
    },
    {
      "epoch": 8.0,
      "learning_rate": 1.2765957446808513e-05,
      "loss": 0.0282,
      "step": 13800
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.978573056758605,
      "eval_f1": 0.9707664711300722,
      "eval_loss": 0.1493660807609558,
      "eval_precision": 0.9703430897460749,
      "eval_recall": 0.9711902221359977,
      "eval_runtime": 5.9566,
      "eval_samples_per_second": 289.764,
      "eval_steps_per_second": 36.262,
      "step": 13800
    },
    {
      "epoch": 9.0,
      "learning_rate": 1.170212765957447e-05,
      "loss": 0.0185,
      "step": 15525
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9787250208950687,
      "eval_f1": 0.9719136551055058,
      "eval_loss": 0.15606926381587982,
      "eval_precision": 0.9720551135261013,
      "eval_recall": 0.971772237850422,
      "eval_runtime": 5.6783,
      "eval_samples_per_second": 303.963,
      "eval_steps_per_second": 38.039,
      "step": 15525
    },
    {
      "epoch": 10.0,
      "learning_rate": 1.0638297872340426e-05,
      "loss": 0.0121,
      "step": 17250
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9780411822809817,
      "eval_f1": 0.9706581308501868,
      "eval_loss": 0.16370074450969696,
      "eval_precision": 0.9706110572259942,
      "eval_recall": 0.9707052090406441,
      "eval_runtime": 5.6771,
      "eval_samples_per_second": 304.028,
      "eval_steps_per_second": 38.048,
      "step": 17250
    },
    {
      "epoch": 11.0,
      "learning_rate": 9.574468085106385e-06,
      "loss": 0.009,
      "step": 18975
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.980092698123243,
      "eval_f1": 0.9730646255207829,
      "eval_loss": 0.16124163568019867,
      "eval_precision": 0.9719345785347915,
      "eval_recall": 0.9741973033271898,
      "eval_runtime": 5.7113,
      "eval_samples_per_second": 302.21,
      "eval_steps_per_second": 37.82,
      "step": 18975
    },
    {
      "epoch": 12.0,
      "learning_rate": 8.510638297872341e-06,
      "loss": 0.0054,
      "step": 20700
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9798647519185473,
      "eval_f1": 0.9722235687624218,
      "eval_loss": 0.16270558536052704,
      "eval_precision": 0.9717054263565892,
      "eval_recall": 0.9727422640411291,
      "eval_runtime": 5.6846,
      "eval_samples_per_second": 303.625,
      "eval_steps_per_second": 37.997,
      "step": 20700
    },
    {
      "epoch": 13.0,
      "learning_rate": 7.446808510638298e-06,
      "loss": 0.0037,
      "step": 22425
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9797127877820835,
      "eval_f1": 0.9724619412392127,
      "eval_loss": 0.16694003343582153,
      "eval_precision": 0.9720849084036057,
      "eval_recall": 0.9728392666601998,
      "eval_runtime": 5.7799,
      "eval_samples_per_second": 298.62,
      "eval_steps_per_second": 37.371,
      "step": 22425
    },
    {
      "epoch": 14.0,
      "learning_rate": 6.382978723404256e-06,
      "loss": 0.003,
      "step": 24150
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.9802446622597067,
      "eval_f1": 0.9736280783401202,
      "eval_loss": 0.172398179769516,
      "eval_precision": 0.9731563135962787,
      "eval_recall": 0.9741003007081191,
      "eval_runtime": 5.692,
      "eval_samples_per_second": 303.234,
      "eval_steps_per_second": 37.948,
      "step": 24150
    },
    {
      "epoch": 15.0,
      "learning_rate": 5.319148936170213e-06,
      "loss": 0.0025,
      "step": 25875
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.9797127877820835,
      "eval_f1": 0.9731904784990547,
      "eval_loss": 0.17340978980064392,
      "eval_precision": 0.972766039930219,
      "eval_recall": 0.9736152876127655,
      "eval_runtime": 5.8159,
      "eval_samples_per_second": 296.774,
      "eval_steps_per_second": 37.14,
      "step": 25875
    },
    {
      "epoch": 16.0,
      "learning_rate": 4.255319148936171e-06,
      "loss": 0.0013,
      "step": 27600
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.9797127877820835,
      "eval_f1": 0.9722626321404325,
      "eval_loss": 0.17289231717586517,
      "eval_precision": 0.9720740812566664,
      "eval_recall": 0.9724512561839169,
      "eval_runtime": 5.6818,
      "eval_samples_per_second": 303.779,
      "eval_steps_per_second": 38.016,
      "step": 27600
    },
    {
      "epoch": 17.0,
      "learning_rate": 3.191489361702128e-06,
      "loss": 0.0012,
      "step": 29325
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.979256895372692,
      "eval_f1": 0.9718466831419296,
      "eval_loss": 0.1769685000181198,
      "eval_precision": 0.9709527498063517,
      "eval_recall": 0.9727422640411291,
      "eval_runtime": 5.7574,
      "eval_samples_per_second": 299.79,
      "eval_steps_per_second": 37.517,
      "step": 29325
    },
    {
      "epoch": 18.0,
      "learning_rate": 2.1276595744680853e-06,
      "loss": 0.0007,
      "step": 31050
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.9805485905326343,
      "eval_f1": 0.9736752799728511,
      "eval_loss": 0.1760159134864807,
      "eval_precision": 0.9732506299670479,
      "eval_recall": 0.9741003007081191,
      "eval_runtime": 5.6794,
      "eval_samples_per_second": 303.906,
      "eval_steps_per_second": 38.032,
      "step": 31050
    },
    {
      "epoch": 19.0,
      "learning_rate": 1.0638297872340427e-06,
      "loss": 0.0006,
      "step": 32775
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.9798647519185473,
      "eval_f1": 0.9726532195500388,
      "eval_loss": 0.17594818770885468,
      "eval_precision": 0.9723703344643723,
      "eval_recall": 0.9729362692792706,
      "eval_runtime": 5.6628,
      "eval_samples_per_second": 304.794,
      "eval_steps_per_second": 38.143,
      "step": 32775
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.0,
      "loss": 0.0008,
      "step": 34500
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.9806245726008662,
      "eval_f1": 0.9734367426078526,
      "eval_loss": 0.17481693625450134,
      "eval_precision": 0.9728708458482705,
      "eval_recall": 0.9740032980890484,
      "eval_runtime": 5.6773,
      "eval_samples_per_second": 304.018,
      "eval_steps_per_second": 38.046,
      "step": 34500
    },
    {
      "epoch": 20.0,
      "step": 34500,
      "total_flos": 1.113724904504184e+16,
      "train_loss": 0.1493213151641514,
      "train_runtime": 7920.1249,
      "train_samples_per_second": 34.84,
      "train_steps_per_second": 4.356
    }
  ],
  "max_steps": 34500,
  "num_train_epochs": 20,
  "total_flos": 1.113724904504184e+16,
  "trial_name": null,
  "trial_params": null
}