{
  "best_metric": 0.6131083965301514,
  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_cola/checkpoint-238",
  "epoch": 12.0,
  "global_step": 408,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.9e-05,
      "loss": 0.6197,
      "step": 34
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6238651871681213,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.0726,
      "eval_samples_per_second": 972.413,
      "eval_steps_per_second": 4.662,
      "step": 34
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.8e-05,
      "loss": 0.6078,
      "step": 68
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6178815364837646,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.0582,
      "eval_samples_per_second": 985.593,
      "eval_steps_per_second": 4.725,
      "step": 68
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.7e-05,
      "loss": 0.6064,
      "step": 102
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6179934144020081,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.3387,
      "eval_samples_per_second": 779.113,
      "eval_steps_per_second": 3.735,
      "step": 102
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.6073,
      "step": 136
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6175711750984192,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.1189,
      "eval_samples_per_second": 932.188,
      "eval_steps_per_second": 4.469,
      "step": 136
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.5e-05,
      "loss": 0.6069,
      "step": 170
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6172661781311035,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.1205,
      "eval_samples_per_second": 930.859,
      "eval_steps_per_second": 4.462,
      "step": 170
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6043,
      "step": 204
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.6166184544563293,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.2344,
      "eval_samples_per_second": 844.955,
      "eval_steps_per_second": 4.051,
      "step": 204
    },
    {
      "epoch": 7.0,
      "learning_rate": 4.3e-05,
      "loss": 0.6004,
      "step": 238
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.6131083965301514,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.1421,
      "eval_samples_per_second": 913.231,
      "eval_steps_per_second": 4.378,
      "step": 238
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.2e-05,
      "loss": 0.5842,
      "step": 272
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.6240708231925964,
      "eval_matthews_correlation": 0.0951039122870703,
      "eval_runtime": 1.1486,
      "eval_samples_per_second": 908.065,
      "eval_steps_per_second": 4.353,
      "step": 272
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.1e-05,
      "loss": 0.5192,
      "step": 306
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.6361746191978455,
      "eval_matthews_correlation": 0.059760920069176514,
      "eval_runtime": 1.2007,
      "eval_samples_per_second": 868.661,
      "eval_steps_per_second": 4.164,
      "step": 306
    },
    {
      "epoch": 10.0,
      "learning_rate": 4e-05,
      "loss": 0.4884,
      "step": 340
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.7009902596473694,
      "eval_matthews_correlation": 0.08008155523655092,
      "eval_runtime": 1.1475,
      "eval_samples_per_second": 908.97,
      "eval_steps_per_second": 4.357,
      "step": 340
    },
    {
      "epoch": 11.0,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.4559,
      "step": 374
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.6731011867523193,
      "eval_matthews_correlation": 0.09051190856095573,
      "eval_runtime": 1.1134,
      "eval_samples_per_second": 936.763,
      "eval_steps_per_second": 4.491,
      "step": 374
    },
    {
      "epoch": 12.0,
      "learning_rate": 3.8e-05,
      "loss": 0.4367,
      "step": 408
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.6893478035926819,
      "eval_matthews_correlation": 0.09007205990892461,
      "eval_runtime": 1.2098,
      "eval_samples_per_second": 862.13,
      "eval_steps_per_second": 4.133,
      "step": 408
    },
    {
      "epoch": 12.0,
      "step": 408,
      "total_flos": 3258721140473856.0,
      "train_loss": 0.5614397408915501,
      "train_runtime": 434.3841,
      "train_samples_per_second": 984.267,
      "train_steps_per_second": 3.914
    }
  ],
  "max_steps": 1700,
  "num_train_epochs": 50,
  "total_flos": 3258721140473856.0,
  "trial_name": null,
  "trial_params": null
}