{
  "best_metric": 0.6143730878829956,
  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_cola_256/checkpoint-335",
  "epoch": 10.0,
  "global_step": 670,
  "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": 0.6135,
      "step": 67
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6178305149078369,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 2.3985,
      "eval_samples_per_second": 434.859,
      "eval_steps_per_second": 3.752,
      "step": 67
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.8e-05,
      "loss": 0.6079,
      "step": 134
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6178404688835144,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 2.3137,
      "eval_samples_per_second": 450.793,
      "eval_steps_per_second": 3.89,
      "step": 134
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.7e-05,
      "loss": 0.6073,
      "step": 201
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6180546283721924,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 2.3821,
      "eval_samples_per_second": 437.857,
      "eval_steps_per_second": 3.778,
      "step": 201
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.6066,
      "step": 268
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6166877746582031,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 2.3898,
      "eval_samples_per_second": 436.431,
      "eval_steps_per_second": 3.766,
      "step": 268
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.5e-05,
      "loss": 0.6049,
      "step": 335
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6143730878829956,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 2.3274,
      "eval_samples_per_second": 448.138,
      "eval_steps_per_second": 3.867,
      "step": 335
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.5699,
      "step": 402
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.6194334030151367,
      "eval_matthews_correlation": 0.11961997719168747,
      "eval_runtime": 2.3303,
      "eval_samples_per_second": 447.588,
      "eval_steps_per_second": 3.862,
      "step": 402
    },
    {
      "epoch": 7.0,
      "learning_rate": 4.3e-05,
      "loss": 0.5015,
      "step": 469
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.6723787188529968,
      "eval_matthews_correlation": 0.11791061329376926,
      "eval_runtime": 2.3237,
      "eval_samples_per_second": 448.851,
      "eval_steps_per_second": 3.873,
      "step": 469
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.2e-05,
      "loss": 0.4668,
      "step": 536
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.772255539894104,
      "eval_matthews_correlation": 0.1197750004046856,
      "eval_runtime": 2.3904,
      "eval_samples_per_second": 436.335,
      "eval_steps_per_second": 3.765,
      "step": 536
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.1e-05,
      "loss": 0.4425,
      "step": 603
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.7052756547927856,
      "eval_matthews_correlation": 0.08097785992490644,
      "eval_runtime": 2.387,
      "eval_samples_per_second": 436.955,
      "eval_steps_per_second": 3.77,
      "step": 603
    },
    {
      "epoch": 10.0,
      "learning_rate": 4e-05,
      "loss": 0.4272,
      "step": 670
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.8388729095458984,
      "eval_matthews_correlation": 0.12073897875437987,
      "eval_runtime": 2.3848,
      "eval_samples_per_second": 437.357,
      "eval_steps_per_second": 3.774,
      "step": 670
    },
    {
      "epoch": 10.0,
      "step": 670,
      "total_flos": 2252431677194240.0,
      "train_loss": 0.5448204809160375,
      "train_runtime": 724.0778,
      "train_samples_per_second": 590.475,
      "train_steps_per_second": 4.627
    }
  ],
  "max_steps": 3350,
  "num_train_epochs": 50,
  "total_flos": 2252431677194240.0,
  "trial_name": null,
  "trial_params": null
}