{
  "best_metric": 0.6475247524752475,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-594",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 594,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.1475601196289062,
      "learning_rate": 0.00023316325483820226,
      "loss": 0.6759,
      "step": 297
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5623762376237624,
      "eval_f1": 0.3402985074626866,
      "eval_loss": 0.672980785369873,
      "eval_mcc": 0.1665189802603812,
      "eval_precision": 0.6867469879518072,
      "eval_recall": 0.2261904761904762,
      "eval_runtime": 0.9357,
      "eval_samples_per_second": 539.729,
      "eval_steps_per_second": 17.1,
      "step": 297
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.315560817718506,
      "learning_rate": 0.0001865306038705618,
      "loss": 0.6336,
      "step": 594
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6475247524752475,
      "eval_f1": 0.6941580756013745,
      "eval_loss": 0.623160719871521,
      "eval_mcc": 0.3106524830468984,
      "eval_precision": 0.6121212121212121,
      "eval_recall": 0.8015873015873016,
      "eval_runtime": 0.9321,
      "eval_samples_per_second": 541.793,
      "eval_steps_per_second": 17.166,
      "step": 594
    }
  ],
  "logging_steps": 500,
  "max_steps": 1782,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "total_flos": 1461402531960.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9735237137483809,
    "learning_rate": 0.0002797959058058427,
    "num_train_epochs": 6,
    "temperature": 49
  }
}