{
  "best_metric": 0.8003913894324853,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-38/checkpoint-192",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 192,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.8633686304092407,
      "learning_rate": 0.00011164310281576651,
      "loss": 0.584,
      "step": 96
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7690802348336595,
      "eval_f1": 0.7993197278911565,
      "eval_loss": 0.48832422494888306,
      "eval_precision": 0.706766917293233,
      "eval_recall": 0.9197651663405088,
      "eval_runtime": 28.3969,
      "eval_samples_per_second": 35.99,
      "eval_steps_per_second": 1.127,
      "step": 96
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.9557557106018066,
      "learning_rate": 9.76877149637957e-05,
      "loss": 0.4827,
      "step": 192
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8003913894324853,
      "eval_f1": 0.8222996515679443,
      "eval_loss": 0.44451940059661865,
      "eval_precision": 0.7409733124018838,
      "eval_recall": 0.923679060665362,
      "eval_runtime": 28.5294,
      "eval_samples_per_second": 35.823,
      "eval_steps_per_second": 1.122,
      "step": 192
    }
  ],
  "logging_steps": 500,
  "max_steps": 864,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "total_flos": 471390394560.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.8898885181069172,
    "learning_rate": 0.00012559849066773733,
    "num_train_epochs": 9,
    "temperature": 3
  }
}