{
  "best_metric": 0.8116599606198099,
  "best_model_checkpoint": "final_models/structroberta_sx2_final/finetune/qqp/checkpoint-6800",
  "epoch": 3.5467980295566504,
  "global_step": 7200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "eval_accuracy": 0.7086541056632996,
      "eval_f1": 0.614392596967907,
      "eval_loss": 0.5525585412979126,
      "eval_mcc": 0.3913768984140464,
      "eval_runtime": 56.5108,
      "eval_samples_per_second": 475.82,
      "eval_steps_per_second": 59.493,
      "step": 400
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.876847290640394e-05,
      "loss": 0.5844,
      "step": 500
    },
    {
      "epoch": 0.39,
      "eval_accuracy": 0.7449514865875244,
      "eval_f1": 0.6675714978187106,
      "eval_loss": 0.5103132724761963,
      "eval_mcc": 0.46936219476259444,
      "eval_runtime": 56.7709,
      "eval_samples_per_second": 473.641,
      "eval_steps_per_second": 59.22,
      "step": 800
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.753694581280788e-05,
      "loss": 0.5275,
      "step": 1000
    },
    {
      "epoch": 0.59,
      "eval_accuracy": 0.7642530202865601,
      "eval_f1": 0.7277646553575263,
      "eval_loss": 0.484948068857193,
      "eval_mcc": 0.5208867129555503,
      "eval_runtime": 56.4156,
      "eval_samples_per_second": 476.624,
      "eval_steps_per_second": 59.593,
      "step": 1200
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.630541871921182e-05,
      "loss": 0.4894,
      "step": 1500
    },
    {
      "epoch": 0.79,
      "eval_accuracy": 0.7876455187797546,
      "eval_f1": 0.7582966474771418,
      "eval_loss": 0.44241347908973694,
      "eval_mcc": 0.5712551968689948,
      "eval_runtime": 56.6157,
      "eval_samples_per_second": 474.939,
      "eval_steps_per_second": 59.383,
      "step": 1600
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.507389162561577e-05,
      "loss": 0.4502,
      "step": 2000
    },
    {
      "epoch": 0.99,
      "eval_accuracy": 0.7965710759162903,
      "eval_f1": 0.7511147511147512,
      "eval_loss": 0.42830032110214233,
      "eval_mcc": 0.5800105484140912,
      "eval_runtime": 56.3774,
      "eval_samples_per_second": 476.947,
      "eval_steps_per_second": 59.634,
      "step": 2000
    },
    {
      "epoch": 1.18,
      "eval_accuracy": 0.8038231134414673,
      "eval_f1": 0.7768329314210771,
      "eval_loss": 0.4215456247329712,
      "eval_mcc": 0.6042518893599846,
      "eval_runtime": 56.4383,
      "eval_samples_per_second": 476.431,
      "eval_steps_per_second": 59.569,
      "step": 2400
    },
    {
      "epoch": 1.23,
      "learning_rate": 4.384236453201971e-05,
      "loss": 0.3907,
      "step": 2500
    },
    {
      "epoch": 1.38,
      "eval_accuracy": 0.8115957975387573,
      "eval_f1": 0.7812230091552944,
      "eval_loss": 0.4063948690891266,
      "eval_mcc": 0.6164914435664559,
      "eval_runtime": 56.8276,
      "eval_samples_per_second": 473.168,
      "eval_steps_per_second": 59.161,
      "step": 2800
    },
    {
      "epoch": 1.48,
      "learning_rate": 4.261083743842365e-05,
      "loss": 0.377,
      "step": 3000
    },
    {
      "epoch": 1.58,
      "eval_accuracy": 0.8172858953475952,
      "eval_f1": 0.7783442364087525,
      "eval_loss": 0.40149447321891785,
      "eval_mcc": 0.6233909091797747,
      "eval_runtime": 56.8714,
      "eval_samples_per_second": 472.804,
      "eval_steps_per_second": 59.116,
      "step": 3200
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.1379310344827587e-05,
      "loss": 0.3689,
      "step": 3500
    },
    {
      "epoch": 1.77,
      "eval_accuracy": 0.8182156085968018,
      "eval_f1": 0.7741219963031424,
      "eval_loss": 0.3932678699493408,
      "eval_mcc": 0.6242644613929623,
      "eval_runtime": 56.7004,
      "eval_samples_per_second": 474.23,
      "eval_steps_per_second": 59.294,
      "step": 3600
    },
    {
      "epoch": 1.97,
      "learning_rate": 4.014778325123153e-05,
      "loss": 0.3635,
      "step": 4000
    },
    {
      "epoch": 1.97,
      "eval_accuracy": 0.8267692923545837,
      "eval_f1": 0.7970900853807283,
      "eval_loss": 0.3838008642196655,
      "eval_mcc": 0.6462575029978364,
      "eval_runtime": 56.8764,
      "eval_samples_per_second": 472.762,
      "eval_steps_per_second": 59.111,
      "step": 4000
    },
    {
      "epoch": 2.17,
      "eval_accuracy": 0.8200007677078247,
      "eval_f1": 0.7987860646877858,
      "eval_loss": 0.41626259684562683,
      "eval_mcc": 0.6408222382018317,
      "eval_runtime": 56.8313,
      "eval_samples_per_second": 473.137,
      "eval_steps_per_second": 59.158,
      "step": 4400
    },
    {
      "epoch": 2.22,
      "learning_rate": 3.891625615763547e-05,
      "loss": 0.2955,
      "step": 4500
    },
    {
      "epoch": 2.36,
      "eval_accuracy": 0.831083357334137,
      "eval_f1": 0.7944238254729791,
      "eval_loss": 0.4071265459060669,
      "eval_mcc": 0.651700327408142,
      "eval_runtime": 56.5102,
      "eval_samples_per_second": 475.825,
      "eval_steps_per_second": 59.494,
      "step": 4800
    },
    {
      "epoch": 2.46,
      "learning_rate": 3.768472906403941e-05,
      "loss": 0.2929,
      "step": 5000
    },
    {
      "epoch": 2.56,
      "eval_accuracy": 0.8340585231781006,
      "eval_f1": 0.8102407076635196,
      "eval_loss": 0.39103031158447266,
      "eval_mcc": 0.6647668434223991,
      "eval_runtime": 56.9146,
      "eval_samples_per_second": 472.445,
      "eval_steps_per_second": 59.071,
      "step": 5200
    },
    {
      "epoch": 2.71,
      "learning_rate": 3.645320197044335e-05,
      "loss": 0.2895,
      "step": 5500
    },
    {
      "epoch": 2.76,
      "eval_accuracy": 0.8280337452888489,
      "eval_f1": 0.8053544367738678,
      "eval_loss": 0.39237213134765625,
      "eval_mcc": 0.6544461740844153,
      "eval_runtime": 56.5155,
      "eval_samples_per_second": 475.781,
      "eval_steps_per_second": 59.488,
      "step": 5600
    },
    {
      "epoch": 2.96,
      "learning_rate": 3.522167487684729e-05,
      "loss": 0.2888,
      "step": 6000
    },
    {
      "epoch": 2.96,
      "eval_accuracy": 0.8361039757728577,
      "eval_f1": 0.8108827189632236,
      "eval_loss": 0.3707721531391144,
      "eval_mcc": 0.6674362482296753,
      "eval_runtime": 56.3098,
      "eval_samples_per_second": 477.519,
      "eval_steps_per_second": 59.705,
      "step": 6000
    },
    {
      "epoch": 3.15,
      "eval_accuracy": 0.8345048427581787,
      "eval_f1": 0.8052857267874332,
      "eval_loss": 0.4219077229499817,
      "eval_mcc": 0.6615341824981482,
      "eval_runtime": 56.4491,
      "eval_samples_per_second": 476.34,
      "eval_steps_per_second": 59.558,
      "step": 6400
    },
    {
      "epoch": 3.2,
      "learning_rate": 3.399014778325123e-05,
      "loss": 0.2296,
      "step": 6500
    },
    {
      "epoch": 3.35,
      "eval_accuracy": 0.8363643288612366,
      "eval_f1": 0.8116599606198099,
      "eval_loss": 0.41765111684799194,
      "eval_mcc": 0.6683672120496021,
      "eval_runtime": 56.4613,
      "eval_samples_per_second": 476.237,
      "eval_steps_per_second": 59.545,
      "step": 6800
    },
    {
      "epoch": 3.45,
      "learning_rate": 3.275862068965517e-05,
      "loss": 0.2251,
      "step": 7000
    },
    {
      "epoch": 3.55,
      "eval_accuracy": 0.8376287817955017,
      "eval_f1": 0.8089612321694233,
      "eval_loss": 0.4220374524593353,
      "eval_mcc": 0.6679266160668449,
      "eval_runtime": 56.3914,
      "eval_samples_per_second": 476.828,
      "eval_steps_per_second": 59.619,
      "step": 7200
    },
    {
      "epoch": 3.55,
      "step": 7200,
      "total_flos": 7.91177802915502e+16,
      "train_loss": 0.36522457705603706,
      "train_runtime": 4971.062,
      "train_samples_per_second": 489.831,
      "train_steps_per_second": 4.084
    }
  ],
  "max_steps": 20300,
  "num_train_epochs": 10,
  "total_flos": 7.91177802915502e+16,
  "trial_name": null,
  "trial_params": null
}