{
  "best_metric": 0.6,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/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": 0.9984288811683655,
      "learning_rate": 9.995670829688553e-05,
      "loss": 0.5706,
      "step": 297
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5128712871287129,
      "eval_loss": 0.5624967217445374,
      "eval_runtime": 13.6049,
      "eval_samples_per_second": 37.119,
      "eval_steps_per_second": 1.176,
      "step": 297
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9848873615264893,
      "learning_rate": 4.9978354148442764e-05,
      "loss": 0.5602,
      "step": 594
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6,
      "eval_loss": 0.5566068291664124,
      "eval_runtime": 13.9891,
      "eval_samples_per_second": 36.099,
      "eval_steps_per_second": 1.144,
      "step": 594
    }
  ],
  "logging_steps": 500,
  "max_steps": 891,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1555686566280.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.7785816803005383,
    "learning_rate": 0.0001499350624453283,
    "num_train_epochs": 3,
    "temperature": 16
  }
}