{
  "best_metric": 0.8949205118262893,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-1935",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 2580,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.1594387292861938,
      "learning_rate": 0.0003669096859466192,
      "loss": 0.3104,
      "step": 645
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8937572702597906,
      "eval_f1": 0.17717717717717715,
      "eval_loss": 0.29782024025917053,
      "eval_mcc": 0.22004174832122259,
      "eval_precision": 0.6082474226804123,
      "eval_recall": 0.10369068541300527,
      "eval_runtime": 9.922,
      "eval_samples_per_second": 519.854,
      "eval_steps_per_second": 16.327,
      "step": 645
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.089403510093689,
      "learning_rate": 0.0003210459752032918,
      "loss": 0.2989,
      "step": 1290
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8937572702597906,
      "eval_f1": 0.1217948717948718,
      "eval_loss": 0.29260244965553284,
      "eval_mcc": 0.19240131656369383,
      "eval_precision": 0.6909090909090909,
      "eval_recall": 0.06678383128295255,
      "eval_runtime": 9.8986,
      "eval_samples_per_second": 521.085,
      "eval_steps_per_second": 16.366,
      "step": 1290
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7798711657524109,
      "learning_rate": 0.00027518226445996435,
      "loss": 0.2922,
      "step": 1935
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8949205118262893,
      "eval_f1": 0.09666666666666668,
      "eval_loss": 0.2949424088001251,
      "eval_mcc": 0.20481355074293853,
      "eval_precision": 0.9354838709677419,
      "eval_recall": 0.050966608084358524,
      "eval_runtime": 9.9157,
      "eval_samples_per_second": 520.185,
      "eval_steps_per_second": 16.338,
      "step": 1935
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.8487693071365356,
      "learning_rate": 0.000229318553716637,
      "loss": 0.2851,
      "step": 2580
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8937572702597906,
      "eval_f1": 0.3251231527093596,
      "eval_loss": 0.2875448167324066,
      "eval_mcc": 0.3072493162328444,
      "eval_precision": 0.5432098765432098,
      "eval_recall": 0.23198594024604569,
      "eval_runtime": 9.9077,
      "eval_samples_per_second": 520.607,
      "eval_steps_per_second": 16.351,
      "step": 2580
    }
  ],
  "logging_steps": 500,
  "max_steps": 5805,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "total_flos": 6347770130400.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.8984215980104533,
    "learning_rate": 0.0004127733966899466,
    "num_train_epochs": 9,
    "temperature": 29
  }
}