{
  "best_metric": 0.8626692456479691,
  "best_model_checkpoint": "final_models/glue_models/structroberta_s2_50ep//finetune/sst2/checkpoint-3200",
  "epoch": 6.582278481012658,
  "global_step": 5200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "eval_accuracy": 0.7539370059967041,
      "eval_f1": 0.7803163444639719,
      "eval_loss": 0.5231051445007324,
      "eval_mcc": 0.5247106973194531,
      "eval_runtime": 1.0985,
      "eval_samples_per_second": 462.456,
      "eval_steps_per_second": 58.262,
      "step": 200
    },
    {
      "epoch": 0.51,
      "eval_accuracy": 0.8031495809555054,
      "eval_f1": 0.8148148148148149,
      "eval_loss": 0.40333232283592224,
      "eval_mcc": 0.6120025576737335,
      "eval_runtime": 1.1024,
      "eval_samples_per_second": 460.833,
      "eval_steps_per_second": 58.058,
      "step": 400
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.683544303797468e-05,
      "loss": 0.4182,
      "step": 500
    },
    {
      "epoch": 0.76,
      "eval_accuracy": 0.8444882035255432,
      "eval_f1": 0.8435643564356434,
      "eval_loss": 0.38440778851509094,
      "eval_mcc": 0.6889720757983125,
      "eval_runtime": 1.1045,
      "eval_samples_per_second": 459.935,
      "eval_steps_per_second": 57.945,
      "step": 600
    },
    {
      "epoch": 1.01,
      "eval_accuracy": 0.834645688533783,
      "eval_f1": 0.8372093023255814,
      "eval_loss": 0.43441784381866455,
      "eval_mcc": 0.6698566624509036,
      "eval_runtime": 1.1061,
      "eval_samples_per_second": 459.26,
      "eval_steps_per_second": 57.86,
      "step": 800
    },
    {
      "epoch": 1.27,
      "learning_rate": 4.367088607594937e-05,
      "loss": 0.2549,
      "step": 1000
    },
    {
      "epoch": 1.27,
      "eval_accuracy": 0.8385826945304871,
      "eval_f1": 0.8404669260700389,
      "eval_loss": 0.4155767261981964,
      "eval_mcc": 0.6775364473446112,
      "eval_runtime": 1.0923,
      "eval_samples_per_second": 465.066,
      "eval_steps_per_second": 58.591,
      "step": 1000
    },
    {
      "epoch": 1.52,
      "eval_accuracy": 0.834645688533783,
      "eval_f1": 0.8438661710037175,
      "eval_loss": 0.5223256349563599,
      "eval_mcc": 0.6748218010834892,
      "eval_runtime": 1.0975,
      "eval_samples_per_second": 462.872,
      "eval_steps_per_second": 58.315,
      "step": 1200
    },
    {
      "epoch": 1.77,
      "eval_accuracy": 0.8503937125205994,
      "eval_f1": 0.8515625,
      "eval_loss": 0.47026267647743225,
      "eval_mcc": 0.7010061668834338,
      "eval_runtime": 1.0838,
      "eval_samples_per_second": 468.727,
      "eval_steps_per_second": 59.052,
      "step": 1400
    },
    {
      "epoch": 1.9,
      "learning_rate": 4.050632911392405e-05,
      "loss": 0.1967,
      "step": 1500
    },
    {
      "epoch": 2.03,
      "eval_accuracy": 0.8582677245140076,
      "eval_f1": 0.8582677165354331,
      "eval_loss": 0.4532265067100525,
      "eval_mcc": 0.7165620398356971,
      "eval_runtime": 1.0715,
      "eval_samples_per_second": 474.092,
      "eval_steps_per_second": 59.728,
      "step": 1600
    },
    {
      "epoch": 2.28,
      "eval_accuracy": 0.8307086825370789,
      "eval_f1": 0.8333333333333334,
      "eval_loss": 0.5167694687843323,
      "eval_mcc": 0.6619776380575382,
      "eval_runtime": 1.0813,
      "eval_samples_per_second": 469.785,
      "eval_steps_per_second": 59.186,
      "step": 1800
    },
    {
      "epoch": 2.53,
      "learning_rate": 3.7341772151898736e-05,
      "loss": 0.1348,
      "step": 2000
    },
    {
      "epoch": 2.53,
      "eval_accuracy": 0.8385826945304871,
      "eval_f1": 0.8498168498168498,
      "eval_loss": 0.5124529600143433,
      "eval_mcc": 0.6859086686135547,
      "eval_runtime": 1.0858,
      "eval_samples_per_second": 467.876,
      "eval_steps_per_second": 58.945,
      "step": 2000
    },
    {
      "epoch": 2.78,
      "eval_accuracy": 0.8425197005271912,
      "eval_f1": 0.8387096774193549,
      "eval_loss": 0.45541733503341675,
      "eval_mcc": 0.685517324398053,
      "eval_runtime": 1.0842,
      "eval_samples_per_second": 468.534,
      "eval_steps_per_second": 59.028,
      "step": 2200
    },
    {
      "epoch": 3.04,
      "eval_accuracy": 0.8307086825370789,
      "eval_f1": 0.8170212765957447,
      "eval_loss": 0.7158520221710205,
      "eval_mcc": 0.6679739948137614,
      "eval_runtime": 1.0782,
      "eval_samples_per_second": 471.16,
      "eval_steps_per_second": 59.359,
      "step": 2400
    },
    {
      "epoch": 3.16,
      "learning_rate": 3.4177215189873416e-05,
      "loss": 0.1222,
      "step": 2500
    },
    {
      "epoch": 3.29,
      "eval_accuracy": 0.8543307185173035,
      "eval_f1": 0.8549019607843138,
      "eval_loss": 0.5784336924552917,
      "eval_mcc": 0.7087628480087672,
      "eval_runtime": 1.0734,
      "eval_samples_per_second": 473.262,
      "eval_steps_per_second": 59.624,
      "step": 2600
    },
    {
      "epoch": 3.54,
      "eval_accuracy": 0.834645688533783,
      "eval_f1": 0.8372093023255814,
      "eval_loss": 0.623878538608551,
      "eval_mcc": 0.6698566624509036,
      "eval_runtime": 1.0761,
      "eval_samples_per_second": 472.087,
      "eval_steps_per_second": 59.476,
      "step": 2800
    },
    {
      "epoch": 3.8,
      "learning_rate": 3.10126582278481e-05,
      "loss": 0.0846,
      "step": 3000
    },
    {
      "epoch": 3.8,
      "eval_accuracy": 0.8464567065238953,
      "eval_f1": 0.8488372093023256,
      "eval_loss": 0.564211905002594,
      "eval_mcc": 0.6934937356309998,
      "eval_runtime": 1.0832,
      "eval_samples_per_second": 468.993,
      "eval_steps_per_second": 59.086,
      "step": 3000
    },
    {
      "epoch": 4.05,
      "eval_accuracy": 0.8602362275123596,
      "eval_f1": 0.8626692456479691,
      "eval_loss": 0.5327543020248413,
      "eval_mcc": 0.7211921679935971,
      "eval_runtime": 1.0843,
      "eval_samples_per_second": 468.514,
      "eval_steps_per_second": 59.025,
      "step": 3200
    },
    {
      "epoch": 4.3,
      "eval_accuracy": 0.834645688533783,
      "eval_f1": 0.8450184501845018,
      "eval_loss": 0.8166886568069458,
      "eval_mcc": 0.6762903456703597,
      "eval_runtime": 1.0816,
      "eval_samples_per_second": 469.696,
      "eval_steps_per_second": 59.174,
      "step": 3400
    },
    {
      "epoch": 4.43,
      "learning_rate": 2.7848101265822786e-05,
      "loss": 0.065,
      "step": 3500
    },
    {
      "epoch": 4.56,
      "eval_accuracy": 0.8385826945304871,
      "eval_f1": 0.8452830188679245,
      "eval_loss": 0.7407500743865967,
      "eval_mcc": 0.6803220026110445,
      "eval_runtime": 1.0847,
      "eval_samples_per_second": 468.341,
      "eval_steps_per_second": 59.004,
      "step": 3600
    },
    {
      "epoch": 4.81,
      "eval_accuracy": 0.834645688533783,
      "eval_f1": 0.8384615384615384,
      "eval_loss": 0.6380051970481873,
      "eval_mcc": 0.6703766309280716,
      "eval_runtime": 1.0846,
      "eval_samples_per_second": 468.368,
      "eval_steps_per_second": 59.007,
      "step": 3800
    },
    {
      "epoch": 5.06,
      "learning_rate": 2.468354430379747e-05,
      "loss": 0.0601,
      "step": 4000
    },
    {
      "epoch": 5.06,
      "eval_accuracy": 0.8425197005271912,
      "eval_f1": 0.8496240601503758,
      "eval_loss": 0.7719384431838989,
      "eval_mcc": 0.6887765705877247,
      "eval_runtime": 1.0798,
      "eval_samples_per_second": 470.438,
      "eval_steps_per_second": 59.268,
      "step": 4000
    },
    {
      "epoch": 5.32,
      "eval_accuracy": 0.8543307185173035,
      "eval_f1": 0.859848484848485,
      "eval_loss": 0.7159872651100159,
      "eval_mcc": 0.7114280702270771,
      "eval_runtime": 1.0773,
      "eval_samples_per_second": 471.539,
      "eval_steps_per_second": 59.406,
      "step": 4200
    },
    {
      "epoch": 5.57,
      "eval_accuracy": 0.8425197005271912,
      "eval_f1": 0.8443579766536965,
      "eval_loss": 0.6608069539070129,
      "eval_mcc": 0.6854135160080981,
      "eval_runtime": 1.0746,
      "eval_samples_per_second": 472.729,
      "eval_steps_per_second": 59.556,
      "step": 4400
    },
    {
      "epoch": 5.7,
      "learning_rate": 2.1518987341772153e-05,
      "loss": 0.041,
      "step": 4500
    },
    {
      "epoch": 5.82,
      "eval_accuracy": 0.8562992215156555,
      "eval_f1": 0.8598848368522072,
      "eval_loss": 0.7154455780982971,
      "eval_mcc": 0.7139062005896402,
      "eval_runtime": 1.0715,
      "eval_samples_per_second": 474.092,
      "eval_steps_per_second": 59.728,
      "step": 4600
    },
    {
      "epoch": 6.08,
      "eval_accuracy": 0.8287401795387268,
      "eval_f1": 0.8391866913123845,
      "eval_loss": 0.9410210251808167,
      "eval_mcc": 0.6639879844977076,
      "eval_runtime": 1.0783,
      "eval_samples_per_second": 471.114,
      "eval_steps_per_second": 59.353,
      "step": 4800
    },
    {
      "epoch": 6.33,
      "learning_rate": 1.8354430379746836e-05,
      "loss": 0.0332,
      "step": 5000
    },
    {
      "epoch": 6.33,
      "eval_accuracy": 0.8484252095222473,
      "eval_f1": 0.8481262327416174,
      "eval_loss": 0.8442137241363525,
      "eval_mcc": 0.6968557943649227,
      "eval_runtime": 1.074,
      "eval_samples_per_second": 472.992,
      "eval_steps_per_second": 59.59,
      "step": 5000
    },
    {
      "epoch": 6.58,
      "eval_accuracy": 0.8307086825370789,
      "eval_f1": 0.8424908424908425,
      "eval_loss": 0.9499196410179138,
      "eval_mcc": 0.6699715312084875,
      "eval_runtime": 1.0843,
      "eval_samples_per_second": 468.484,
      "eval_steps_per_second": 59.022,
      "step": 5200
    },
    {
      "epoch": 6.58,
      "step": 5200,
      "total_flos": 3.046823046955008e+16,
      "train_loss": 0.13669625529876123,
      "train_runtime": 1803.9314,
      "train_samples_per_second": 280.099,
      "train_steps_per_second": 4.379
    }
  ],
  "max_steps": 7900,
  "num_train_epochs": 10,
  "total_flos": 3.046823046955008e+16,
  "trial_name": null,
  "trial_params": null
}