run-1/checkpoint-1072/trainer_state.json

{
  "best_metric": 0.5290831606897504,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1072",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1072,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.4801884889602661,
      "eval_matthews_correlation": 0.4522326299878879,
      "eval_runtime": 0.6893,
      "eval_samples_per_second": 1513.095,
      "eval_steps_per_second": 95.747,
      "step": 268
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.0329146614031314e-05,
      "loss": 0.4583,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5012368559837341,
      "eval_matthews_correlation": 0.4810794261012942,
      "eval_runtime": 1.1504,
      "eval_samples_per_second": 906.647,
      "eval_steps_per_second": 57.372,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5001268982887268,
      "eval_matthews_correlation": 0.5202123212283704,
      "eval_runtime": 0.6949,
      "eval_samples_per_second": 1500.847,
      "eval_steps_per_second": 94.972,
      "step": 804
    },
    {
      "epoch": 3.73,
      "learning_rate": 4.180845058060293e-06,
      "loss": 0.2539,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.561569333076477,
      "eval_matthews_correlation": 0.5290831606897504,
      "eval_runtime": 1.2387,
      "eval_samples_per_second": 842.006,
      "eval_steps_per_second": 53.281,
      "step": 1072
    }
  ],
  "logging_steps": 500,
  "max_steps": 1340,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 191113458530124.0,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.6477448170002332e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 32,
    "seed": 34
  }
}