{
  "best_metric": 0.908256880733945,
  "best_model_checkpoint": "electra-distilled-sst\\run-15\\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": 19.587562561035156,
      "learning_rate": 4.871658725828052e-05,
      "loss": 0.8727,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.908256880733945,
      "eval_loss": 0.579243004322052,
      "eval_runtime": 1.4486,
      "eval_samples_per_second": 601.96,
      "eval_steps_per_second": 4.832,
      "step": 527
    },
    {
      "epoch": 2.0,
      "grad_norm": 29.514617919921875,
      "learning_rate": 4.175896083955048e-05,
      "loss": 0.4502,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9013761467889908,
      "eval_loss": 0.6629878878593445,
      "eval_runtime": 1.4564,
      "eval_samples_per_second": 598.751,
      "eval_steps_per_second": 4.806,
      "step": 1054
    }
  ],
  "logging_steps": 500,
  "max_steps": 4216,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "total_flos": 373776249469380.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.8465908351909457,
    "learning_rate": 5.5661011349840285e-05,
    "num_train_epochs": 8,
    "temperature": 22
  }
}