{
  "best_metric": 0.1110285148024559,
  "best_model_checkpoint": "./models/results_comb_47/checkpoint-400",
  "epoch": 0.887040887040887,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6898,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.668,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.2e-05,
      "loss": 0.6621,
      "step": 24
    },
    {
      "epoch": 0.06,
      "eval_accuracy": 0.5841623557500994,
      "eval_f1": 0.7375031399145943,
      "eval_loss": 0.6694099307060242,
      "eval_precision": 0.5841623557500994,
      "eval_recall": 1.0,
      "eval_runtime": 37.4974,
      "eval_samples_per_second": 201.054,
      "eval_steps_per_second": 25.148,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.6492,
      "step": 32
    },
    {
      "epoch": 0.09,
      "learning_rate": 2e-05,
      "loss": 0.6134,
      "step": 40
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.4e-05,
      "loss": 0.4686,
      "step": 48
    },
    {
      "epoch": 0.11,
      "eval_accuracy": 0.8306141398063404,
      "eval_f1": 0.8423262131127299,
      "eval_loss": 0.42581823468208313,
      "eval_precision": 0.9231393775372124,
      "eval_recall": 0.7745231607629428,
      "eval_runtime": 35.7786,
      "eval_samples_per_second": 210.712,
      "eval_steps_per_second": 26.357,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.394,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.3361,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 3.6e-05,
      "loss": 0.3008,
      "step": 72
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.8745191669982756,
      "eval_f1": 0.8824844720496895,
      "eval_loss": 0.31987154483795166,
      "eval_precision": 0.9742183214481623,
      "eval_recall": 0.8065395095367848,
      "eval_runtime": 37.2093,
      "eval_samples_per_second": 202.611,
      "eval_steps_per_second": 25.343,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 4e-05,
      "loss": 0.2948,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.3191,
      "step": 88
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.8e-05,
      "loss": 0.2392,
      "step": 96
    },
    {
      "epoch": 0.22,
      "eval_accuracy": 0.9039660432418093,
      "eval_f1": 0.9127710843373494,
      "eval_loss": 0.2560712695121765,
      "eval_precision": 0.9722792607802875,
      "eval_recall": 0.860127157129882,
      "eval_runtime": 37.338,
      "eval_samples_per_second": 201.912,
      "eval_steps_per_second": 25.256,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.957142857142857e-05,
      "loss": 0.2518,
      "step": 104
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.842857142857143e-05,
      "loss": 0.2504,
      "step": 112
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.728571428571429e-05,
      "loss": 0.1844,
      "step": 120
    },
    {
      "epoch": 0.28,
      "eval_accuracy": 0.933678206658708,
      "eval_f1": 0.9420894139448691,
      "eval_loss": 0.17439067363739014,
      "eval_precision": 0.9614657210401891,
      "eval_recall": 0.9234786557674841,
      "eval_runtime": 36.8175,
      "eval_samples_per_second": 204.767,
      "eval_steps_per_second": 25.613,
      "step": 125
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.6142857142857145e-05,
      "loss": 0.2195,
      "step": 128
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.5e-05,
      "loss": 0.1689,
      "step": 136
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.385714285714286e-05,
      "loss": 0.236,
      "step": 144
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.9385860193659636,
      "eval_f1": 0.9465913023416773,
      "eval_loss": 0.16091835498809814,
      "eval_precision": 0.9620164126611958,
      "eval_recall": 0.931653042688465,
      "eval_runtime": 37.7461,
      "eval_samples_per_second": 199.729,
      "eval_steps_per_second": 24.983,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.271428571428572e-05,
      "loss": 0.1789,
      "step": 152
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.1571428571428575e-05,
      "loss": 0.1828,
      "step": 160
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.042857142857143e-05,
      "loss": 0.1503,
      "step": 168
    },
    {
      "epoch": 0.39,
      "eval_accuracy": 0.9432285448998541,
      "eval_f1": 0.9514298683613254,
      "eval_loss": 0.1532103717327118,
      "eval_precision": 0.9509981851179673,
      "eval_recall": 0.9518619436875567,
      "eval_runtime": 37.8407,
      "eval_samples_per_second": 199.23,
      "eval_steps_per_second": 24.92,
      "step": 175
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.928571428571429e-05,
      "loss": 0.181,
      "step": 176
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.814285714285715e-05,
      "loss": 0.1557,
      "step": 184
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.7e-05,
      "loss": 0.1761,
      "step": 192
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.585714285714286e-05,
      "loss": 0.2321,
      "step": 200
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 0.9322191272051996,
      "eval_f1": 0.939173907868111,
      "eval_loss": 0.1640879511833191,
      "eval_precision": 0.9869902426820115,
      "eval_recall": 0.8957765667574932,
      "eval_runtime": 38.4884,
      "eval_samples_per_second": 195.877,
      "eval_steps_per_second": 24.501,
      "step": 200
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.471428571428571e-05,
      "loss": 0.1704,
      "step": 208
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.357142857142857e-05,
      "loss": 0.1672,
      "step": 216
    },
    {
      "epoch": 0.5,
      "learning_rate": 3.242857142857143e-05,
      "loss": 0.1541,
      "step": 224
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.9460140602201883,
      "eval_f1": 0.9528006494259538,
      "eval_loss": 0.14619316160678864,
      "eval_precision": 0.9736904479734534,
      "eval_recall": 0.932788374205268,
      "eval_runtime": 37.8866,
      "eval_samples_per_second": 198.989,
      "eval_steps_per_second": 24.89,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.1285714285714285e-05,
      "loss": 0.1429,
      "step": 232
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.0142857142857146e-05,
      "loss": 0.1472,
      "step": 240
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.9e-05,
      "loss": 0.1539,
      "step": 248
    },
    {
      "epoch": 0.55,
      "eval_accuracy": 0.9534421010744131,
      "eval_f1": 0.9598352214212152,
      "eval_loss": 0.13435281813144684,
      "eval_precision": 0.9674740484429065,
      "eval_recall": 0.952316076294278,
      "eval_runtime": 38.0838,
      "eval_samples_per_second": 197.958,
      "eval_steps_per_second": 24.761,
      "step": 250
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.785714285714286e-05,
      "loss": 0.1281,
      "step": 256
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.6714285714285715e-05,
      "loss": 0.1528,
      "step": 264
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.5571428571428572e-05,
      "loss": 0.1374,
      "step": 272
    },
    {
      "epoch": 0.61,
      "eval_accuracy": 0.9566255471547951,
      "eval_f1": 0.963212959838002,
      "eval_loss": 0.11492959409952164,
      "eval_precision": 0.954515050167224,
      "eval_recall": 0.9720708446866485,
      "eval_runtime": 37.7762,
      "eval_samples_per_second": 199.57,
      "eval_steps_per_second": 24.963,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.442857142857143e-05,
      "loss": 0.1809,
      "step": 280
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.3285714285714287e-05,
      "loss": 0.0934,
      "step": 288
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.214285714285714e-05,
      "loss": 0.1319,
      "step": 296
    },
    {
      "epoch": 0.67,
      "eval_accuracy": 0.9579519830216209,
      "eval_f1": 0.9641037255123995,
      "eval_loss": 0.12962229549884796,
      "eval_precision": 0.9615992771628642,
      "eval_recall": 0.9666212534059946,
      "eval_runtime": 38.0269,
      "eval_samples_per_second": 198.255,
      "eval_steps_per_second": 24.798,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.1e-05,
      "loss": 0.1183,
      "step": 304
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.9857142857142856e-05,
      "loss": 0.1923,
      "step": 312
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.8714285714285714e-05,
      "loss": 0.12,
      "step": 320
    },
    {
      "epoch": 0.72,
      "eval_accuracy": 0.9566255471547951,
      "eval_f1": 0.9629209660959291,
      "eval_loss": 0.11410258710384369,
      "eval_precision": 0.9617214043035107,
      "eval_recall": 0.9641235240690281,
      "eval_runtime": 37.9137,
      "eval_samples_per_second": 198.846,
      "eval_steps_per_second": 24.872,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.757142857142857e-05,
      "loss": 0.1005,
      "step": 328
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.642857142857143e-05,
      "loss": 0.158,
      "step": 336
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.5285714285714286e-05,
      "loss": 0.1482,
      "step": 344
    },
    {
      "epoch": 0.78,
      "eval_accuracy": 0.9513198036874917,
      "eval_f1": 0.9592176908545395,
      "eval_loss": 0.12748490273952484,
      "eval_precision": 0.9392818280739935,
      "eval_recall": 0.9800181653042689,
      "eval_runtime": 35.7822,
      "eval_samples_per_second": 210.691,
      "eval_steps_per_second": 26.354,
      "step": 350
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.4142857142857143e-05,
      "loss": 0.1249,
      "step": 352
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.1238,
      "step": 360
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.2e-05,
      "loss": 0.1442,
      "step": 368
    },
    {
      "epoch": 0.83,
      "eval_accuracy": 0.9567581907414776,
      "eval_f1": 0.9633543165467626,
      "eval_loss": 0.11545209586620331,
      "eval_precision": 0.9539180765805877,
      "eval_recall": 0.9729791099000908,
      "eval_runtime": 35.8749,
      "eval_samples_per_second": 210.147,
      "eval_steps_per_second": 26.286,
      "step": 375
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.0857142857142858e-05,
      "loss": 0.1432,
      "step": 376
    },
    {
      "epoch": 0.85,
      "learning_rate": 9.714285714285715e-06,
      "loss": 0.1244,
      "step": 384
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.571428571428573e-06,
      "loss": 0.087,
      "step": 392
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.428571428571429e-06,
      "loss": 0.0992,
      "step": 400
    },
    {
      "epoch": 0.89,
      "eval_accuracy": 0.9596763496484945,
      "eval_f1": 0.9655015887426236,
      "eval_loss": 0.1110285148024559,
      "eval_precision": 0.9650635208711433,
      "eval_recall": 0.9659400544959128,
      "eval_runtime": 37.2559,
      "eval_samples_per_second": 202.357,
      "eval_steps_per_second": 25.311,
      "step": 400
    }
  ],
  "max_steps": 450,
  "num_train_epochs": 1,
  "total_flos": 4354487966208000.0,
  "trial_name": null,
  "trial_params": null
}