{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.1446540880503147,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5922580645161291,
      "eval_loss": 0.20049375295639038,
      "eval_runtime": 14.0315,
      "eval_samples_per_second": 220.932,
      "eval_steps_per_second": 27.652,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.5469786524772644,
      "learning_rate": 1.685534591194969e-05,
      "loss": 0.3222,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8261290322580646,
      "eval_loss": 0.09613806009292603,
      "eval_runtime": 15.1555,
      "eval_samples_per_second": 204.546,
      "eval_steps_per_second": 25.601,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8887096774193548,
      "eval_loss": 0.06220310926437378,
      "eval_runtime": 15.2254,
      "eval_samples_per_second": 203.608,
      "eval_steps_per_second": 25.484,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.51106858253479,
      "learning_rate": 1.371069182389937e-05,
      "loss": 0.1109,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 3180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 260941334653608.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9569018778831712,
    "num_train_epochs": 10,
    "temperature": 10
  }
}