{
  "best_metric": 0.61527419090271,
  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_cola/checkpoint-268",
  "epoch": 9.0,
  "global_step": 603,
  "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": 0.6122,
      "step": 67
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6183971762657166,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.7411,
      "eval_samples_per_second": 599.045,
      "eval_steps_per_second": 5.169,
      "step": 67
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.8e-05,
      "loss": 0.6078,
      "step": 134
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6179646253585815,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.7343,
      "eval_samples_per_second": 601.399,
      "eval_steps_per_second": 5.189,
      "step": 134
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.7e-05,
      "loss": 0.607,
      "step": 201
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6185427904129028,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.7316,
      "eval_samples_per_second": 602.316,
      "eval_steps_per_second": 5.197,
      "step": 201
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.6052,
      "step": 268
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.61527419090271,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.7366,
      "eval_samples_per_second": 600.599,
      "eval_steps_per_second": 5.183,
      "step": 268
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.5e-05,
      "loss": 0.5822,
      "step": 335
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6292034983634949,
      "eval_matthews_correlation": 0.05057353484097579,
      "eval_runtime": 1.7382,
      "eval_samples_per_second": 600.051,
      "eval_steps_per_second": 5.178,
      "step": 335
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.5193,
      "step": 402
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.6421763896942139,
      "eval_matthews_correlation": 0.074290264269209,
      "eval_runtime": 1.7355,
      "eval_samples_per_second": 600.967,
      "eval_steps_per_second": 5.186,
      "step": 402
    },
    {
      "epoch": 7.0,
      "learning_rate": 4.3e-05,
      "loss": 0.4783,
      "step": 469
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.7020387649536133,
      "eval_matthews_correlation": 0.06292685160191117,
      "eval_runtime": 1.7327,
      "eval_samples_per_second": 601.938,
      "eval_steps_per_second": 5.194,
      "step": 469
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.2e-05,
      "loss": 0.4504,
      "step": 536
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.7421594858169556,
      "eval_matthews_correlation": 0.08342146557730178,
      "eval_runtime": 1.7355,
      "eval_samples_per_second": 600.992,
      "eval_steps_per_second": 5.186,
      "step": 536
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.1e-05,
      "loss": 0.4315,
      "step": 603
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.6915299296379089,
      "eval_matthews_correlation": 0.08118499547243287,
      "eval_runtime": 1.743,
      "eval_samples_per_second": 598.381,
      "eval_steps_per_second": 5.163,
      "step": 603
    },
    {
      "epoch": 9.0,
      "step": 603,
      "total_flos": 2412992519995392.0,
      "train_loss": 0.543749636876247,
      "train_runtime": 541.9676,
      "train_samples_per_second": 788.885,
      "train_steps_per_second": 6.181
    }
  ],
  "max_steps": 3350,
  "num_train_epochs": 50,
  "total_flos": 2412992519995392.0,
  "trial_name": null,
  "trial_params": null
}