{
  "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": 0.5806451612903226,
      "eval_loss": 0.19493919610977173,
      "eval_runtime": 1.9997,
      "eval_samples_per_second": 1550.211,
      "eval_steps_per_second": 32.504,
      "step": 318
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.613143265247345,
      "learning_rate": 1.550763701707098e-05,
      "loss": 0.312,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8112903225806452,
      "eval_loss": 0.0981183648109436,
      "eval_runtime": 2.2229,
      "eval_samples_per_second": 1394.575,
      "eval_steps_per_second": 29.241,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.87,
      "eval_loss": 0.06753243505954742,
      "eval_runtime": 3.5523,
      "eval_samples_per_second": 872.665,
      "eval_steps_per_second": 18.298,
      "step": 954
    },
    {
      "epoch": 3.14,
      "grad_norm": 0.5029990077018738,
      "learning_rate": 1.101527403414196e-05,
      "loss": 0.1131,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2226,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 260941334653608.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.25369877696009957,
    "num_train_epochs": 7,
    "temperature": 16
  }
}