{
  "best_metric": 0.8182447038478167,
  "best_model_checkpoint": "final_models/glue_models/structroberta_s2_final//finetune/qqp/checkpoint-9600",
  "epoch": 4.7290640394088665,
  "global_step": 9600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "eval_accuracy": 0.7285135388374329,
      "eval_f1": 0.6788102780711017,
      "eval_loss": 0.5273743271827698,
      "eval_mcc": 0.44373753898319895,
      "eval_runtime": 52.3791,
      "eval_samples_per_second": 513.354,
      "eval_steps_per_second": 64.186,
      "step": 400
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.876847290640394e-05,
      "loss": 0.5651,
      "step": 500
    },
    {
      "epoch": 0.39,
      "eval_accuracy": 0.7599390149116516,
      "eval_f1": 0.6933346002185378,
      "eval_loss": 0.48232948780059814,
      "eval_mcc": 0.5015541735435936,
      "eval_runtime": 52.3511,
      "eval_samples_per_second": 513.628,
      "eval_steps_per_second": 64.22,
      "step": 800
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.753694581280788e-05,
      "loss": 0.4957,
      "step": 1000
    },
    {
      "epoch": 0.59,
      "eval_accuracy": 0.7784224152565002,
      "eval_f1": 0.7293048614266242,
      "eval_loss": 0.4581160545349121,
      "eval_mcc": 0.542554696937411,
      "eval_runtime": 52.3159,
      "eval_samples_per_second": 513.974,
      "eval_steps_per_second": 64.263,
      "step": 1200
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.630541871921182e-05,
      "loss": 0.4616,
      "step": 1500
    },
    {
      "epoch": 0.79,
      "eval_accuracy": 0.7962735891342163,
      "eval_f1": 0.7594836670179136,
      "eval_loss": 0.43172687292099,
      "eval_mcc": 0.582852877479166,
      "eval_runtime": 52.3144,
      "eval_samples_per_second": 513.989,
      "eval_steps_per_second": 64.265,
      "step": 1600
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.507389162561577e-05,
      "loss": 0.4345,
      "step": 2000
    },
    {
      "epoch": 0.99,
      "eval_accuracy": 0.7980214953422546,
      "eval_f1": 0.7422768471503821,
      "eval_loss": 0.4275752305984497,
      "eval_mcc": 0.5817912489010888,
      "eval_runtime": 52.3547,
      "eval_samples_per_second": 513.593,
      "eval_steps_per_second": 64.216,
      "step": 2000
    },
    {
      "epoch": 1.18,
      "eval_accuracy": 0.8100338578224182,
      "eval_f1": 0.7739022662889519,
      "eval_loss": 0.4070776104927063,
      "eval_mcc": 0.6101111570276126,
      "eval_runtime": 52.603,
      "eval_samples_per_second": 511.169,
      "eval_steps_per_second": 63.913,
      "step": 2400
    },
    {
      "epoch": 1.23,
      "learning_rate": 4.384236453201971e-05,
      "loss": 0.3724,
      "step": 2500
    },
    {
      "epoch": 1.38,
      "eval_accuracy": 0.815277636051178,
      "eval_f1": 0.7796850742958528,
      "eval_loss": 0.4088333547115326,
      "eval_mcc": 0.6206627379992179,
      "eval_runtime": 52.4,
      "eval_samples_per_second": 513.148,
      "eval_steps_per_second": 64.16,
      "step": 2800
    },
    {
      "epoch": 1.48,
      "learning_rate": 4.261083743842365e-05,
      "loss": 0.3577,
      "step": 3000
    },
    {
      "epoch": 1.58,
      "eval_accuracy": 0.8183643817901611,
      "eval_f1": 0.7709408123065379,
      "eval_loss": 0.4194847047328949,
      "eval_mcc": 0.6244513021568135,
      "eval_runtime": 52.3303,
      "eval_samples_per_second": 513.832,
      "eval_steps_per_second": 64.246,
      "step": 3200
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.1379310344827587e-05,
      "loss": 0.3508,
      "step": 3500
    },
    {
      "epoch": 1.77,
      "eval_accuracy": 0.8219718337059021,
      "eval_f1": 0.7793907553343471,
      "eval_loss": 0.3924076557159424,
      "eval_mcc": 0.6321434549442672,
      "eval_runtime": 52.3776,
      "eval_samples_per_second": 513.368,
      "eval_steps_per_second": 64.188,
      "step": 3600
    },
    {
      "epoch": 1.97,
      "learning_rate": 4.014778325123153e-05,
      "loss": 0.3482,
      "step": 4000
    },
    {
      "epoch": 1.97,
      "eval_accuracy": 0.8285172581672668,
      "eval_f1": 0.7950393385784771,
      "eval_loss": 0.3821839690208435,
      "eval_mcc": 0.6476609486444006,
      "eval_runtime": 52.4185,
      "eval_samples_per_second": 512.968,
      "eval_steps_per_second": 64.138,
      "step": 4000
    },
    {
      "epoch": 2.17,
      "eval_accuracy": 0.8318271636962891,
      "eval_f1": 0.7981610426709517,
      "eval_loss": 0.4135289788246155,
      "eval_mcc": 0.6541252204741957,
      "eval_runtime": 52.3538,
      "eval_samples_per_second": 513.602,
      "eval_steps_per_second": 64.217,
      "step": 4400
    },
    {
      "epoch": 2.22,
      "learning_rate": 3.891625615763547e-05,
      "loss": 0.2674,
      "step": 4500
    },
    {
      "epoch": 2.36,
      "eval_accuracy": 0.832124650478363,
      "eval_f1": 0.7885318092382648,
      "eval_loss": 0.4241204261779785,
      "eval_mcc": 0.6532604645809198,
      "eval_runtime": 52.317,
      "eval_samples_per_second": 513.963,
      "eval_steps_per_second": 64.262,
      "step": 4800
    },
    {
      "epoch": 2.46,
      "learning_rate": 3.768472906403941e-05,
      "loss": 0.2675,
      "step": 5000
    },
    {
      "epoch": 2.56,
      "eval_accuracy": 0.8314180374145508,
      "eval_f1": 0.7988283850352818,
      "eval_loss": 0.3950100243091583,
      "eval_mcc": 0.6537612657210461,
      "eval_runtime": 52.3502,
      "eval_samples_per_second": 513.637,
      "eval_steps_per_second": 64.221,
      "step": 5200
    },
    {
      "epoch": 2.71,
      "learning_rate": 3.645320197044335e-05,
      "loss": 0.2675,
      "step": 5500
    },
    {
      "epoch": 2.76,
      "eval_accuracy": 0.8390420079231262,
      "eval_f1": 0.8080028391447077,
      "eval_loss": 0.3883987367153168,
      "eval_mcc": 0.6694540753123261,
      "eval_runtime": 52.3719,
      "eval_samples_per_second": 513.424,
      "eval_steps_per_second": 64.195,
      "step": 5600
    },
    {
      "epoch": 2.96,
      "learning_rate": 3.522167487684729e-05,
      "loss": 0.2697,
      "step": 6000
    },
    {
      "epoch": 2.96,
      "eval_accuracy": 0.8381866216659546,
      "eval_f1": 0.8078604548465443,
      "eval_loss": 0.3748666048049927,
      "eval_mcc": 0.668109270008498,
      "eval_runtime": 52.4002,
      "eval_samples_per_second": 513.147,
      "eval_steps_per_second": 64.16,
      "step": 6000
    },
    {
      "epoch": 3.15,
      "eval_accuracy": 0.8381122350692749,
      "eval_f1": 0.8102358428876585,
      "eval_loss": 0.43886855244636536,
      "eval_mcc": 0.669352918279841,
      "eval_runtime": 52.3858,
      "eval_samples_per_second": 513.288,
      "eval_steps_per_second": 64.178,
      "step": 6400
    },
    {
      "epoch": 3.2,
      "learning_rate": 3.399014778325123e-05,
      "loss": 0.201,
      "step": 6500
    },
    {
      "epoch": 3.35,
      "eval_accuracy": 0.84197998046875,
      "eval_f1": 0.8148503202753933,
      "eval_loss": 0.45135924220085144,
      "eval_mcc": 0.6773127279657783,
      "eval_runtime": 52.3499,
      "eval_samples_per_second": 513.64,
      "eval_steps_per_second": 64.222,
      "step": 6800
    },
    {
      "epoch": 3.45,
      "learning_rate": 3.275862068965517e-05,
      "loss": 0.1952,
      "step": 7000
    },
    {
      "epoch": 3.55,
      "eval_accuracy": 0.8422403335571289,
      "eval_f1": 0.8114834236956716,
      "eval_loss": 0.4344791769981384,
      "eval_mcc": 0.67587759010705,
      "eval_runtime": 52.3592,
      "eval_samples_per_second": 513.548,
      "eval_steps_per_second": 64.21,
      "step": 7200
    },
    {
      "epoch": 3.69,
      "learning_rate": 3.152709359605912e-05,
      "loss": 0.1935,
      "step": 7500
    },
    {
      "epoch": 3.74,
      "eval_accuracy": 0.8433560132980347,
      "eval_f1": 0.8172826652785007,
      "eval_loss": 0.4027557373046875,
      "eval_mcc": 0.6806843267469705,
      "eval_runtime": 52.467,
      "eval_samples_per_second": 512.494,
      "eval_steps_per_second": 64.078,
      "step": 7600
    },
    {
      "epoch": 3.94,
      "learning_rate": 3.0295566502463057e-05,
      "loss": 0.1979,
      "step": 8000
    },
    {
      "epoch": 3.94,
      "eval_accuracy": 0.8457361459732056,
      "eval_f1": 0.8150361187906895,
      "eval_loss": 0.4362601339817047,
      "eval_mcc": 0.6828095359569987,
      "eval_runtime": 52.375,
      "eval_samples_per_second": 513.394,
      "eval_steps_per_second": 64.191,
      "step": 8000
    },
    {
      "epoch": 4.14,
      "eval_accuracy": 0.8406411409378052,
      "eval_f1": 0.8119541844033878,
      "eval_loss": 0.4881964325904846,
      "eval_mcc": 0.6737691323117093,
      "eval_runtime": 52.3705,
      "eval_samples_per_second": 513.438,
      "eval_steps_per_second": 64.196,
      "step": 8400
    },
    {
      "epoch": 4.19,
      "learning_rate": 2.9064039408866993e-05,
      "loss": 0.1456,
      "step": 8500
    },
    {
      "epoch": 4.33,
      "eval_accuracy": 0.8454014658927917,
      "eval_f1": 0.8155641332800924,
      "eval_loss": 0.505477786064148,
      "eval_mcc": 0.682503608511531,
      "eval_runtime": 52.3839,
      "eval_samples_per_second": 513.306,
      "eval_steps_per_second": 64.18,
      "step": 8800
    },
    {
      "epoch": 4.43,
      "learning_rate": 2.7832512315270936e-05,
      "loss": 0.1379,
      "step": 9000
    },
    {
      "epoch": 4.53,
      "eval_accuracy": 0.8446948528289795,
      "eval_f1": 0.8108866950457387,
      "eval_loss": 0.47982802987098694,
      "eval_mcc": 0.6798065059175836,
      "eval_runtime": 52.4432,
      "eval_samples_per_second": 512.726,
      "eval_steps_per_second": 64.107,
      "step": 9200
    },
    {
      "epoch": 4.68,
      "learning_rate": 2.660098522167488e-05,
      "loss": 0.1396,
      "step": 9500
    },
    {
      "epoch": 4.73,
      "eval_accuracy": 0.8436535596847534,
      "eval_f1": 0.8182447038478167,
      "eval_loss": 0.4731481373310089,
      "eval_mcc": 0.681741240221474,
      "eval_runtime": 52.3629,
      "eval_samples_per_second": 513.513,
      "eval_steps_per_second": 64.206,
      "step": 9600
    },
    {
      "epoch": 4.73,
      "step": 9600,
      "total_flos": 9.609924849312154e+16,
      "train_loss": 0.29670360455910366,
      "train_runtime": 6262.587,
      "train_samples_per_second": 388.814,
      "train_steps_per_second": 3.241
    }
  ],
  "max_steps": 20300,
  "num_train_epochs": 10,
  "total_flos": 9.609924849312154e+16,
  "trial_name": null,
  "trial_params": null
}