trainer_state.json

{
  "best_metric": 0.6077491044998169,
  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_cola_128/checkpoint-402",
  "epoch": 11.0,
  "global_step": 737,
  "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": 0.6155,
      "step": 67
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6180391907691956,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 2.3423,
      "eval_samples_per_second": 445.288,
      "eval_steps_per_second": 3.842,
      "step": 67
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.8e-05,
      "loss": 0.6079,
      "step": 134
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6180055737495422,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 2.3294,
      "eval_samples_per_second": 447.764,
      "eval_steps_per_second": 3.864,
      "step": 134
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.7e-05,
      "loss": 0.6074,
      "step": 201
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.618085503578186,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 2.3307,
      "eval_samples_per_second": 447.507,
      "eval_steps_per_second": 3.862,
      "step": 201
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.607,
      "step": 268
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6173203587532043,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 2.3328,
      "eval_samples_per_second": 447.106,
      "eval_steps_per_second": 3.858,
      "step": 268
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.5e-05,
      "loss": 0.6064,
      "step": 335
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.617998480796814,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 2.3214,
      "eval_samples_per_second": 449.294,
      "eval_steps_per_second": 3.877,
      "step": 335
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6021,
      "step": 402
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.6077491044998169,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 2.3317,
      "eval_samples_per_second": 447.314,
      "eval_steps_per_second": 3.86,
      "step": 402
    },
    {
      "epoch": 7.0,
      "learning_rate": 4.3e-05,
      "loss": 0.5484,
      "step": 469
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.6392526030540466,
      "eval_matthews_correlation": 0.06876909773769338,
      "eval_runtime": 2.3248,
      "eval_samples_per_second": 448.634,
      "eval_steps_per_second": 3.871,
      "step": 469
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.2e-05,
      "loss": 0.4961,
      "step": 536
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.6882135272026062,
      "eval_matthews_correlation": 0.08513541026842135,
      "eval_runtime": 2.3384,
      "eval_samples_per_second": 446.026,
      "eval_steps_per_second": 3.849,
      "step": 536
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.1e-05,
      "loss": 0.4656,
      "step": 603
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.6623390913009644,
      "eval_matthews_correlation": 0.11162331444159394,
      "eval_runtime": 2.3292,
      "eval_samples_per_second": 447.802,
      "eval_steps_per_second": 3.864,
      "step": 603
    },
    {
      "epoch": 10.0,
      "learning_rate": 4e-05,
      "loss": 0.448,
      "step": 670
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.7584222555160522,
      "eval_matthews_correlation": 0.10885779554312716,
      "eval_runtime": 2.3245,
      "eval_samples_per_second": 448.697,
      "eval_steps_per_second": 3.872,
      "step": 670
    },
    {
      "epoch": 11.0,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.4358,
      "step": 737
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.7178416848182678,
      "eval_matthews_correlation": 0.12989481801728855,
      "eval_runtime": 2.324,
      "eval_samples_per_second": 448.792,
      "eval_steps_per_second": 3.873,
      "step": 737
    },
    {
      "epoch": 11.0,
      "step": 737,
      "total_flos": 2241905819648000.0,
      "train_loss": 0.5491012045292226,
      "train_runtime": 753.3806,
      "train_samples_per_second": 567.509,
      "train_steps_per_second": 4.447
    }
  ],
  "max_steps": 3350,
  "num_train_epochs": 50,
  "total_flos": 2241905819648000.0,
  "trial_name": null,
  "trial_params": null
}