{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.716981132075472,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6083870967741936,
      "eval_loss": 0.26111724972724915,
      "eval_runtime": 5.07,
      "eval_samples_per_second": 611.445,
      "eval_steps_per_second": 12.821,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.612690269947052,
      "learning_rate": 1.371069182389937e-05,
      "loss": 0.4067,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8261290322580646,
      "eval_loss": 0.1251312643289566,
      "eval_runtime": 5.2675,
      "eval_samples_per_second": 588.512,
      "eval_steps_per_second": 12.34,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8719354838709678,
      "eval_loss": 0.08443494886159897,
      "eval_runtime": 5.1546,
      "eval_samples_per_second": 601.399,
      "eval_steps_per_second": 12.61,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.5761224031448364,
      "learning_rate": 7.421383647798742e-06,
      "loss": 0.1453,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8880645161290323,
      "eval_loss": 0.06863659620285034,
      "eval_runtime": 5.2147,
      "eval_samples_per_second": 594.479,
      "eval_steps_per_second": 12.465,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.40807998180389404,
      "learning_rate": 1.1320754716981133e-06,
      "loss": 0.0989,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1590,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 391368939443328.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.006505868879858823,
    "num_train_epochs": 5,
    "temperature": 4
  }
}