{
  "best_metric": 0.7545871559633027,
  "best_model_checkpoint": "thesis/run-0/checkpoint-527",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 527,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 3.5143,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7545871559633027,
      "eval_loss": 2.760861396789551,
      "eval_runtime": 1.4145,
      "eval_samples_per_second": 616.482,
      "eval_steps_per_second": 4.949,
      "step": 527
    }
  ],
  "logging_steps": 500,
  "max_steps": 527,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 8057768762220.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.23538941618561682,
    "learning_rate": 3.0969456495664865e-05,
    "num_train_epochs": 1,
    "temperature": 16
  }
}