{
  "best_metric": 0.8256880733944955,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-527",
  "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": 6.5331573486328125,
      "learning_rate": 0.00014562243502675204,
      "loss": 0.547,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8256880733944955,
      "eval_loss": 0.5717546343803406,
      "eval_runtime": 2.8071,
      "eval_samples_per_second": 310.639,
      "eval_steps_per_second": 2.494,
      "step": 527
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.755884647369385,
      "learning_rate": 0.0001248192300229303,
      "loss": 0.3165,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.823394495412844,
      "eval_loss": 0.6189394593238831,
      "eval_runtime": 2.8231,
      "eval_samples_per_second": 308.882,
      "eval_steps_per_second": 2.48,
      "step": 1054
    }
  ],
  "logging_steps": 500,
  "max_steps": 4216,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "total_flos": 16141525436100.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9318516048675823,
    "learning_rate": 0.00016642564003057375,
    "num_train_epochs": 8,
    "temperature": 23
  }
}