{
  "best_metric": 0.10347278416156769,
  "best_model_checkpoint": "./models/results_comb_23/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": 0.6838,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6683,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.2e-05,
      "loss": 0.6398,
      "step": 24
    },
    {
      "epoch": 0.06,
      "eval_accuracy": 0.5841623557500994,
      "eval_f1": 0.7375031399145943,
      "eval_loss": 0.6682732701301575,
      "eval_precision": 0.5841623557500994,
      "eval_recall": 1.0,
      "eval_runtime": 47.6905,
      "eval_samples_per_second": 158.082,
      "eval_steps_per_second": 19.773,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.6571,
      "step": 32
    },
    {
      "epoch": 0.09,
      "learning_rate": 2e-05,
      "loss": 0.6052,
      "step": 40
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.4e-05,
      "loss": 0.4953,
      "step": 48
    },
    {
      "epoch": 0.11,
      "eval_accuracy": 0.8867223769730733,
      "eval_f1": 0.9052374611628939,
      "eval_loss": 0.3651227056980133,
      "eval_precision": 0.8851996527777778,
      "eval_recall": 0.9262034514078111,
      "eval_runtime": 47.4725,
      "eval_samples_per_second": 158.808,
      "eval_steps_per_second": 19.864,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.3792,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.2802,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 3.6e-05,
      "loss": 0.2595,
      "step": 72
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.9119246584427643,
      "eval_f1": 0.9219924812030076,
      "eval_loss": 0.21582257747650146,
      "eval_precision": 0.9552093476144109,
      "eval_recall": 0.8910081743869209,
      "eval_runtime": 47.5352,
      "eval_samples_per_second": 158.598,
      "eval_steps_per_second": 19.838,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 4e-05,
      "loss": 0.2839,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.2088,
      "step": 88
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.8e-05,
      "loss": 0.2128,
      "step": 96
    },
    {
      "epoch": 0.22,
      "eval_accuracy": 0.931157978511739,
      "eval_f1": 0.9428980085818022,
      "eval_loss": 0.18493123352527618,
      "eval_precision": 0.9146211312700107,
      "eval_recall": 0.9729791099000908,
      "eval_runtime": 47.5063,
      "eval_samples_per_second": 158.695,
      "eval_steps_per_second": 19.85,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.942857142857143e-05,
      "loss": 0.2927,
      "step": 104
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.828571428571429e-05,
      "loss": 0.2732,
      "step": 112
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.714285714285714e-05,
      "loss": 0.2793,
      "step": 120
    },
    {
      "epoch": 0.28,
      "eval_accuracy": 0.9335455630720255,
      "eval_f1": 0.9418186041110208,
      "eval_loss": 0.17004907131195068,
      "eval_precision": 0.9638697409080105,
      "eval_recall": 0.9207538601271571,
      "eval_runtime": 47.6934,
      "eval_samples_per_second": 158.072,
      "eval_steps_per_second": 19.772,
      "step": 125
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.2195,
      "step": 128
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.485714285714286e-05,
      "loss": 0.197,
      "step": 136
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.371428571428572e-05,
      "loss": 0.2501,
      "step": 144
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.9409736039262502,
      "eval_f1": 0.9507034452198958,
      "eval_loss": 0.1616438329219818,
      "eval_precision": 0.9281851611507679,
      "eval_recall": 0.9743415077202543,
      "eval_runtime": 47.5143,
      "eval_samples_per_second": 158.668,
      "eval_steps_per_second": 19.847,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.257142857142857e-05,
      "loss": 0.1977,
      "step": 152
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.1428571428571437e-05,
      "loss": 0.1873,
      "step": 160
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.028571428571429e-05,
      "loss": 0.1876,
      "step": 168
    },
    {
      "epoch": 0.39,
      "eval_accuracy": 0.9350046425255338,
      "eval_f1": 0.945116487455197,
      "eval_loss": 0.16360537707805634,
      "eval_precision": 0.9325817860300619,
      "eval_recall": 0.9579927338782924,
      "eval_runtime": 47.5692,
      "eval_samples_per_second": 158.485,
      "eval_steps_per_second": 19.824,
      "step": 175
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.9142857142857145e-05,
      "loss": 0.1954,
      "step": 176
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.8e-05,
      "loss": 0.1758,
      "step": 184
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.685714285714286e-05,
      "loss": 0.1847,
      "step": 192
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.1337,
      "step": 200
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 0.9501260114073484,
      "eval_f1": 0.9577243085225995,
      "eval_loss": 0.14026911556720734,
      "eval_precision": 0.9485523385300668,
      "eval_recall": 0.9670753860127157,
      "eval_runtime": 47.6318,
      "eval_samples_per_second": 158.277,
      "eval_steps_per_second": 19.798,
      "step": 200
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.4571428571428574e-05,
      "loss": 0.1665,
      "step": 208
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.342857142857143e-05,
      "loss": 0.1667,
      "step": 216
    },
    {
      "epoch": 0.5,
      "learning_rate": 3.228571428571428e-05,
      "loss": 0.1778,
      "step": 224
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.8956094972808065,
      "eval_f1": 0.9173926734543928,
      "eval_loss": 0.2989156246185303,
      "eval_precision": 0.8530158110482139,
      "eval_recall": 0.9922797456857403,
      "eval_runtime": 47.5798,
      "eval_samples_per_second": 158.45,
      "eval_steps_per_second": 19.819,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.114285714285715e-05,
      "loss": 0.2196,
      "step": 232
    },
    {
      "epoch": 0.53,
      "learning_rate": 3e-05,
      "loss": 0.1774,
      "step": 240
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.885714285714286e-05,
      "loss": 0.1502,
      "step": 248
    },
    {
      "epoch": 0.55,
      "eval_accuracy": 0.954105319007826,
      "eval_f1": 0.9604842393787117,
      "eval_loss": 0.12666857242584229,
      "eval_precision": 0.9662224264705882,
      "eval_recall": 0.9548138056312443,
      "eval_runtime": 47.5514,
      "eval_samples_per_second": 158.544,
      "eval_steps_per_second": 19.831,
      "step": 250
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.7714285714285716e-05,
      "loss": 0.1264,
      "step": 256
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.6571428571428576e-05,
      "loss": 0.1431,
      "step": 264
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.542857142857143e-05,
      "loss": 0.1386,
      "step": 272
    },
    {
      "epoch": 0.61,
      "eval_accuracy": 0.9562276163947473,
      "eval_f1": 0.9631696428571428,
      "eval_loss": 0.11829638481140137,
      "eval_precision": 0.9471027216856892,
      "eval_recall": 0.9797910990009082,
      "eval_runtime": 47.5189,
      "eval_samples_per_second": 158.653,
      "eval_steps_per_second": 19.845,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.4285714285714288e-05,
      "loss": 0.1334,
      "step": 280
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.3142857142857145e-05,
      "loss": 0.1468,
      "step": 288
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.1233,
      "step": 296
    },
    {
      "epoch": 0.67,
      "eval_accuracy": 0.9538400318344608,
      "eval_f1": 0.9613933880630131,
      "eval_loss": 0.13518454134464264,
      "eval_precision": 0.9399132321041215,
      "eval_recall": 0.9838782924613987,
      "eval_runtime": 47.6619,
      "eval_samples_per_second": 158.177,
      "eval_steps_per_second": 19.785,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.0857142857142857e-05,
      "loss": 0.1453,
      "step": 304
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.9714285714285714e-05,
      "loss": 0.1354,
      "step": 312
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.8571428571428572e-05,
      "loss": 0.1745,
      "step": 320
    },
    {
      "epoch": 0.72,
      "eval_accuracy": 0.957288765088208,
      "eval_f1": 0.9632420091324201,
      "eval_loss": 0.11527514457702637,
      "eval_precision": 0.9685491276400368,
      "eval_recall": 0.9579927338782924,
      "eval_runtime": 47.6858,
      "eval_samples_per_second": 158.098,
      "eval_steps_per_second": 19.775,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.742857142857143e-05,
      "loss": 0.1349,
      "step": 328
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.6285714285714287e-05,
      "loss": 0.1105,
      "step": 336
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.5142857142857144e-05,
      "loss": 0.1101,
      "step": 344
    },
    {
      "epoch": 0.78,
      "eval_accuracy": 0.9611354291020029,
      "eval_f1": 0.9667536593668444,
      "eval_loss": 0.11785919219255447,
      "eval_precision": 0.9662054887729644,
      "eval_recall": 0.9673024523160763,
      "eval_runtime": 47.5837,
      "eval_samples_per_second": 158.437,
      "eval_steps_per_second": 19.818,
      "step": 350
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.1148,
      "step": 352
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.2857142857142857e-05,
      "loss": 0.0959,
      "step": 360
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.1714285714285715e-05,
      "loss": 0.1335,
      "step": 368
    },
    {
      "epoch": 0.83,
      "eval_accuracy": 0.9571561215015254,
      "eval_f1": 0.9628778301344673,
      "eval_loss": 0.12226755917072296,
      "eval_precision": 0.9748661857109612,
      "eval_recall": 0.951180744777475,
      "eval_runtime": 47.5828,
      "eval_samples_per_second": 158.44,
      "eval_steps_per_second": 19.818,
      "step": 375
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.0571428571428572e-05,
      "loss": 0.1663,
      "step": 376
    },
    {
      "epoch": 0.85,
      "learning_rate": 9.42857142857143e-06,
      "loss": 0.1249,
      "step": 384
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.285714285714285e-06,
      "loss": 0.1338,
      "step": 392
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.142857142857143e-06,
      "loss": 0.0969,
      "step": 400
    },
    {
      "epoch": 0.89,
      "eval_accuracy": 0.9628597957288765,
      "eval_f1": 0.9683972911963884,
      "eval_loss": 0.10347278416156769,
      "eval_precision": 0.9627468581687613,
      "eval_recall": 0.9741144414168937,
      "eval_runtime": 47.716,
      "eval_samples_per_second": 157.997,
      "eval_steps_per_second": 19.763,
      "step": 400
    }
  ],
  "max_steps": 450,
  "num_train_epochs": 1,
  "total_flos": 4354487966208000.0,
  "trial_name": null,
  "trial_params": null
}