{
  "best_metric": 0.6546083688735962,
  "best_model_checkpoint": "models_gitignored/distilbert-base-uncased-finetuned-sentence-classification/checkpoint-12626",
  "epoch": 4.0,
  "global_step": 50504,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 1.984159670521147e-05,
      "loss": 1.177,
      "step": 500
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.968319341042294e-05,
      "loss": 0.9186,
      "step": 1000
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9524790115634406e-05,
      "loss": 0.8261,
      "step": 1500
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9366386820845877e-05,
      "loss": 0.8177,
      "step": 2000
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9207983526057344e-05,
      "loss": 0.7788,
      "step": 2500
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.904958023126881e-05,
      "loss": 0.7519,
      "step": 3000
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.889117693648028e-05,
      "loss": 0.7243,
      "step": 3500
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.8732773641691748e-05,
      "loss": 0.7431,
      "step": 4000
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.8574370346903215e-05,
      "loss": 0.7297,
      "step": 4500
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.8415967052114686e-05,
      "loss": 0.7061,
      "step": 5000
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.8257563757326153e-05,
      "loss": 0.698,
      "step": 5500
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.8099160462537623e-05,
      "loss": 0.7074,
      "step": 6000
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.794075716774909e-05,
      "loss": 0.6975,
      "step": 6500
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.7782353872960557e-05,
      "loss": 0.6943,
      "step": 7000
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.7623950578172028e-05,
      "loss": 0.7045,
      "step": 7500
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.7465547283383495e-05,
      "loss": 0.6764,
      "step": 8000
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.730714398859496e-05,
      "loss": 0.6722,
      "step": 8500
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.7148740693806432e-05,
      "loss": 0.6884,
      "step": 9000
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.69903373990179e-05,
      "loss": 0.6903,
      "step": 9500
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.683193410422937e-05,
      "loss": 0.6854,
      "step": 10000
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.667353080944084e-05,
      "loss": 0.6861,
      "step": 10500
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.6515127514652307e-05,
      "loss": 0.6894,
      "step": 11000
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.6356724219863774e-05,
      "loss": 0.6754,
      "step": 11500
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.6198320925075244e-05,
      "loss": 0.6918,
      "step": 12000
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.603991763028671e-05,
      "loss": 0.6746,
      "step": 12500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.778547431856752,
      "eval_f1": 0.7757136063142371,
      "eval_kappa": 0.7014269317598121,
      "eval_loss": 0.6546083688735962,
      "eval_precision": 0.7762465189891471,
      "eval_recall": 0.778547431856752,
      "eval_runtime": 150.616,
      "eval_samples_per_second": 191.699,
      "eval_steps_per_second": 23.968,
      "step": 12626
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.5881514335498182e-05,
      "loss": 0.5694,
      "step": 13000
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.572311104070965e-05,
      "loss": 0.5509,
      "step": 13500
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.5564707745921116e-05,
      "loss": 0.5466,
      "step": 14000
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.5406304451132586e-05,
      "loss": 0.5544,
      "step": 14500
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.5247901156344053e-05,
      "loss": 0.566,
      "step": 15000
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.5089497861555522e-05,
      "loss": 0.5773,
      "step": 15500
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.4931094566766991e-05,
      "loss": 0.6056,
      "step": 16000
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.4772691271978458e-05,
      "loss": 0.5532,
      "step": 16500
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.4614287977189927e-05,
      "loss": 0.5764,
      "step": 17000
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.4455884682401395e-05,
      "loss": 0.5499,
      "step": 17500
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.4297481387612864e-05,
      "loss": 0.5695,
      "step": 18000
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.4139078092824333e-05,
      "loss": 0.5823,
      "step": 18500
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.39806747980358e-05,
      "loss": 0.5329,
      "step": 19000
    },
    {
      "epoch": 1.54,
      "learning_rate": 1.3822271503247269e-05,
      "loss": 0.5661,
      "step": 19500
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.3663868208458737e-05,
      "loss": 0.5851,
      "step": 20000
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.3505464913670206e-05,
      "loss": 0.5859,
      "step": 20500
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.3347061618881673e-05,
      "loss": 0.5569,
      "step": 21000
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.3188658324093142e-05,
      "loss": 0.5473,
      "step": 21500
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.303025502930461e-05,
      "loss": 0.5635,
      "step": 22000
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.287185173451608e-05,
      "loss": 0.5848,
      "step": 22500
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.2713448439727546e-05,
      "loss": 0.5885,
      "step": 23000
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.2555045144939015e-05,
      "loss": 0.5502,
      "step": 23500
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.2396641850150484e-05,
      "loss": 0.5999,
      "step": 24000
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.2238238555361953e-05,
      "loss": 0.5639,
      "step": 24500
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.207983526057342e-05,
      "loss": 0.5664,
      "step": 25000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7842274789595817,
      "eval_f1": 0.7824161012799614,
      "eval_kappa": 0.7102691347246439,
      "eval_loss": 0.7084277868270874,
      "eval_precision": 0.7870631351341026,
      "eval_recall": 0.7842274789595817,
      "eval_runtime": 152.0087,
      "eval_samples_per_second": 189.943,
      "eval_steps_per_second": 23.749,
      "step": 25252
    },
    {
      "epoch": 2.02,
      "learning_rate": 1.1921431965784888e-05,
      "loss": 0.4751,
      "step": 25500
    },
    {
      "epoch": 2.06,
      "learning_rate": 1.1763028670996357e-05,
      "loss": 0.4208,
      "step": 26000
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.1604625376207826e-05,
      "loss": 0.4563,
      "step": 26500
    },
    {
      "epoch": 2.14,
      "learning_rate": 1.1446222081419293e-05,
      "loss": 0.4513,
      "step": 27000
    },
    {
      "epoch": 2.18,
      "learning_rate": 1.1287818786630762e-05,
      "loss": 0.4385,
      "step": 27500
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.112941549184223e-05,
      "loss": 0.4493,
      "step": 28000
    },
    {
      "epoch": 2.26,
      "learning_rate": 1.0971012197053699e-05,
      "loss": 0.4533,
      "step": 28500
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.0812608902265168e-05,
      "loss": 0.4365,
      "step": 29000
    },
    {
      "epoch": 2.34,
      "learning_rate": 1.0654205607476635e-05,
      "loss": 0.4205,
      "step": 29500
    },
    {
      "epoch": 2.38,
      "learning_rate": 1.0495802312688104e-05,
      "loss": 0.4538,
      "step": 30000
    },
    {
      "epoch": 2.42,
      "learning_rate": 1.0337399017899574e-05,
      "loss": 0.4653,
      "step": 30500
    },
    {
      "epoch": 2.46,
      "learning_rate": 1.0178995723111043e-05,
      "loss": 0.436,
      "step": 31000
    },
    {
      "epoch": 2.49,
      "learning_rate": 1.0020592428322511e-05,
      "loss": 0.4249,
      "step": 31500
    },
    {
      "epoch": 2.53,
      "learning_rate": 9.862189133533979e-06,
      "loss": 0.4441,
      "step": 32000
    },
    {
      "epoch": 2.57,
      "learning_rate": 9.703785838745447e-06,
      "loss": 0.4544,
      "step": 32500
    },
    {
      "epoch": 2.61,
      "learning_rate": 9.545382543956914e-06,
      "loss": 0.446,
      "step": 33000
    },
    {
      "epoch": 2.65,
      "learning_rate": 9.386979249168383e-06,
      "loss": 0.4457,
      "step": 33500
    },
    {
      "epoch": 2.69,
      "learning_rate": 9.228575954379852e-06,
      "loss": 0.4472,
      "step": 34000
    },
    {
      "epoch": 2.73,
      "learning_rate": 9.07017265959132e-06,
      "loss": 0.4728,
      "step": 34500
    },
    {
      "epoch": 2.77,
      "learning_rate": 8.911769364802788e-06,
      "loss": 0.4455,
      "step": 35000
    },
    {
      "epoch": 2.81,
      "learning_rate": 8.753366070014258e-06,
      "loss": 0.4622,
      "step": 35500
    },
    {
      "epoch": 2.85,
      "learning_rate": 8.594962775225727e-06,
      "loss": 0.4566,
      "step": 36000
    },
    {
      "epoch": 2.89,
      "learning_rate": 8.436559480437194e-06,
      "loss": 0.4185,
      "step": 36500
    },
    {
      "epoch": 2.93,
      "learning_rate": 8.278156185648662e-06,
      "loss": 0.4351,
      "step": 37000
    },
    {
      "epoch": 2.97,
      "learning_rate": 8.119752890860131e-06,
      "loss": 0.4566,
      "step": 37500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7792747549613827,
      "eval_f1": 0.7780530572128844,
      "eval_kappa": 0.7039084509242337,
      "eval_loss": 0.7550320029258728,
      "eval_precision": 0.7813618395098462,
      "eval_recall": 0.7792747549613827,
      "eval_runtime": 151.5948,
      "eval_samples_per_second": 190.462,
      "eval_steps_per_second": 23.813,
      "step": 37878
    },
    {
      "epoch": 3.01,
      "learning_rate": 7.9613495960716e-06,
      "loss": 0.4023,
      "step": 38000
    },
    {
      "epoch": 3.05,
      "learning_rate": 7.802946301283067e-06,
      "loss": 0.3119,
      "step": 38500
    },
    {
      "epoch": 3.09,
      "learning_rate": 7.644543006494536e-06,
      "loss": 0.3205,
      "step": 39000
    },
    {
      "epoch": 3.13,
      "learning_rate": 7.4861397117060044e-06,
      "loss": 0.35,
      "step": 39500
    },
    {
      "epoch": 3.17,
      "learning_rate": 7.327736416917472e-06,
      "loss": 0.3333,
      "step": 40000
    },
    {
      "epoch": 3.21,
      "learning_rate": 7.169333122128941e-06,
      "loss": 0.3563,
      "step": 40500
    },
    {
      "epoch": 3.25,
      "learning_rate": 7.010929827340409e-06,
      "loss": 0.3388,
      "step": 41000
    },
    {
      "epoch": 3.29,
      "learning_rate": 6.852526532551878e-06,
      "loss": 0.3422,
      "step": 41500
    },
    {
      "epoch": 3.33,
      "learning_rate": 6.6941232377633456e-06,
      "loss": 0.3336,
      "step": 42000
    },
    {
      "epoch": 3.37,
      "learning_rate": 6.535719942974814e-06,
      "loss": 0.3433,
      "step": 42500
    },
    {
      "epoch": 3.41,
      "learning_rate": 6.377316648186282e-06,
      "loss": 0.3574,
      "step": 43000
    },
    {
      "epoch": 3.45,
      "learning_rate": 6.218913353397751e-06,
      "loss": 0.3105,
      "step": 43500
    },
    {
      "epoch": 3.48,
      "learning_rate": 6.060510058609219e-06,
      "loss": 0.3545,
      "step": 44000
    },
    {
      "epoch": 3.52,
      "learning_rate": 5.9021067638206875e-06,
      "loss": 0.3469,
      "step": 44500
    },
    {
      "epoch": 3.56,
      "learning_rate": 5.7437034690321554e-06,
      "loss": 0.35,
      "step": 45000
    },
    {
      "epoch": 3.6,
      "learning_rate": 5.585300174243625e-06,
      "loss": 0.3425,
      "step": 45500
    },
    {
      "epoch": 3.64,
      "learning_rate": 5.426896879455094e-06,
      "loss": 0.3203,
      "step": 46000
    },
    {
      "epoch": 3.68,
      "learning_rate": 5.268493584666562e-06,
      "loss": 0.3549,
      "step": 46500
    },
    {
      "epoch": 3.72,
      "learning_rate": 5.11009028987803e-06,
      "loss": 0.3326,
      "step": 47000
    },
    {
      "epoch": 3.76,
      "learning_rate": 4.951686995089498e-06,
      "loss": 0.3328,
      "step": 47500
    },
    {
      "epoch": 3.8,
      "learning_rate": 4.793283700300967e-06,
      "loss": 0.3376,
      "step": 48000
    },
    {
      "epoch": 3.84,
      "learning_rate": 4.634880405512435e-06,
      "loss": 0.3285,
      "step": 48500
    },
    {
      "epoch": 3.88,
      "learning_rate": 4.476477110723904e-06,
      "loss": 0.361,
      "step": 49000
    },
    {
      "epoch": 3.92,
      "learning_rate": 4.3180738159353715e-06,
      "loss": 0.3487,
      "step": 49500
    },
    {
      "epoch": 3.96,
      "learning_rate": 4.15967052114684e-06,
      "loss": 0.3511,
      "step": 50000
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.001267226358309e-06,
      "loss": 0.3528,
      "step": 50500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7778201087521214,
      "eval_f1": 0.7760540283760836,
      "eval_kappa": 0.7007853270915267,
      "eval_loss": 0.9983726739883423,
      "eval_precision": 0.7770574865770817,
      "eval_recall": 0.7778201087521214,
      "eval_runtime": 151.818,
      "eval_samples_per_second": 190.182,
      "eval_steps_per_second": 23.778,
      "step": 50504
    }
  ],
  "max_steps": 63130,
  "num_train_epochs": 5,
  "total_flos": 5.330919857118713e+16,
  "trial_name": null,
  "trial_params": null
}