{
  "best_metric": 0.541095890410959,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/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": 0.22234170138835907,
      "learning_rate": 0.0005297032666879207,
      "loss": 0.151,
      "step": 96
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5371819960861057,
      "eval_f1": 0.19420783645655879,
      "eval_loss": 0.13462358713150024,
      "eval_precision": 0.75,
      "eval_recall": 0.11154598825831702,
      "eval_runtime": 28.032,
      "eval_samples_per_second": 36.458,
      "eval_steps_per_second": 1.142,
      "step": 96
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.0766675472259521,
      "learning_rate": 0.00026485163334396037,
      "loss": 0.1364,
      "step": 192
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.541095890410959,
      "eval_f1": 0.20373514431239387,
      "eval_loss": 0.1334332674741745,
      "eval_precision": 0.7692307692307693,
      "eval_recall": 0.11741682974559686,
      "eval_runtime": 28.1007,
      "eval_samples_per_second": 36.369,
      "eval_steps_per_second": 1.139,
      "step": 192
    }
  ],
  "logging_steps": 500,
  "max_steps": 288,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 471390394560.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.1651966098176283,
    "learning_rate": 0.0007945549000318812,
    "num_train_epochs": 3,
    "temperature": 11
  }
}