{
  "best_metric": 0.9059633027522935,
  "best_model_checkpoint": "electra-distilled-sst\\run-41\\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": 43.335304260253906,
      "learning_rate": 5.1826206877294654e-05,
      "loss": 2.5123,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9059633027522935,
      "eval_loss": 1.4461896419525146,
      "eval_runtime": 1.4486,
      "eval_samples_per_second": 601.959,
      "eval_steps_per_second": 4.832,
      "step": 527
    },
    {
      "epoch": 2.0,
      "grad_norm": 75.06561279296875,
      "learning_rate": 2.5962181286069005e-05,
      "loss": 1.1875,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8944954128440367,
      "eval_loss": 1.6673099994659424,
      "eval_runtime": 1.452,
      "eval_samples_per_second": 600.556,
      "eval_steps_per_second": 4.821,
      "step": 1054
    }
  ],
  "logging_steps": 500,
  "max_steps": 1581,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 373776249469380.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.1884860164172123,
    "learning_rate": 7.759207677367693e-05,
    "num_train_epochs": 3,
    "temperature": 9
  }
}