{
  "best_metric": 0.6799937037620022,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-3176",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 3176,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.4442338943481445,
      "learning_rate": 4.032885899938537e-05,
      "loss": 0.6141,
      "step": 1588
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6636234849677318,
      "eval_f1": 0.3630402384500745,
      "eval_loss": 0.6011130809783936,
      "eval_mcc": 0.16570379533034763,
      "eval_precision": 0.4921212121212121,
      "eval_recall": 0.28760330578512394,
      "eval_runtime": 23.3169,
      "eval_samples_per_second": 544.926,
      "eval_steps_per_second": 17.069,
      "step": 1588
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.0027925968170166,
      "learning_rate": 3.360738249948781e-05,
      "loss": 0.5959,
      "step": 3176
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6799937037620022,
      "eval_f1": 0.26447178002894356,
      "eval_loss": 0.5925843119621277,
      "eval_mcc": 0.1656860671477833,
      "eval_precision": 0.5653518948182521,
      "eval_recall": 0.17260920897284535,
      "eval_runtime": 23.4673,
      "eval_samples_per_second": 541.433,
      "eval_steps_per_second": 16.96,
      "step": 3176
    }
  ],
  "logging_steps": 500,
  "max_steps": 11116,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 7817788152600.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9830537825786697,
    "learning_rate": 4.7050335499282935e-05,
    "num_train_epochs": 7,
    "temperature": 17
  }
}