{
  "best_metric": 0.8084862385321101,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-1054",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1054,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.104732990264893,
      "learning_rate": 2.9453688815098063e-05,
      "loss": 1.6038,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7752293577981652,
      "eval_loss": 1.2298829555511475,
      "eval_runtime": 2.8117,
      "eval_samples_per_second": 310.129,
      "eval_steps_per_second": 2.49,
      "step": 527
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 2.5778963882284596e-05,
      "loss": 1.0293,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8084862385321101,
      "eval_loss": 1.0575315952301025,
      "eval_runtime": 2.8112,
      "eval_samples_per_second": 310.184,
      "eval_steps_per_second": 2.49,
      "step": 1054
    }
  ],
  "logging_steps": 500,
  "max_steps": 4743,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "total_flos": 16141525436100.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.698062417678107,
    "learning_rate": 3.3135399916985324e-05,
    "num_train_epochs": 9,
    "temperature": 29
  }
}