{
  "best_metric": 16.5460205078125,
  "best_model_checkpoint": "hBERTv1_new_pretrain_cola/checkpoint-201",
  "epoch": 8.0,
  "global_step": 536,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.00049,
      "loss": 17.7846,
      "step": 67
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 16.576702117919922,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.9107,
      "eval_samples_per_second": 545.874,
      "eval_steps_per_second": 4.71,
      "step": 67
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00048,
      "loss": 17.5238,
      "step": 134
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 16.567354202270508,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.9081,
      "eval_samples_per_second": 546.627,
      "eval_steps_per_second": 4.717,
      "step": 134
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00047,
      "loss": 17.4369,
      "step": 201
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 16.5460205078125,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.9122,
      "eval_samples_per_second": 545.459,
      "eval_steps_per_second": 4.707,
      "step": 201
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00046,
      "loss": 17.0194,
      "step": 268
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 16.574783325195312,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.911,
      "eval_samples_per_second": 545.784,
      "eval_steps_per_second": 4.71,
      "step": 268
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00045000000000000004,
      "loss": 17.1371,
      "step": 335
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 16.56974983215332,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.9125,
      "eval_samples_per_second": 545.364,
      "eval_steps_per_second": 4.706,
      "step": 335
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00044,
      "loss": 17.4193,
      "step": 402
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 16.57382583618164,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.9111,
      "eval_samples_per_second": 545.751,
      "eval_steps_per_second": 4.709,
      "step": 402
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.00043,
      "loss": 17.2534,
      "step": 469
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 16.577661514282227,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.9094,
      "eval_samples_per_second": 546.245,
      "eval_steps_per_second": 4.714,
      "step": 469
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.00042,
      "loss": 17.56,
      "step": 536
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 16.573345184326172,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.9063,
      "eval_samples_per_second": 547.146,
      "eval_steps_per_second": 4.721,
      "step": 536
    },
    {
      "epoch": 8.0,
      "step": 536,
      "total_flos": 1.0131004291284992e+16,
      "train_loss": 17.391823156556086,
      "train_runtime": 416.7234,
      "train_samples_per_second": 1025.98,
      "train_steps_per_second": 8.039
    }
  ],
  "max_steps": 3350,
  "num_train_epochs": 50,
  "total_flos": 1.0131004291284992e+16,
  "trial_name": null,
  "trial_params": null
}