{
  "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": 0.6509677419354839,
      "eval_loss": 0.2873552143573761,
      "eval_runtime": 5.4953,
      "eval_samples_per_second": 564.118,
      "eval_steps_per_second": 11.828,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.6625721454620361,
      "learning_rate": 1.650593990216632e-05,
      "loss": 0.4591,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8429032258064516,
      "eval_loss": 0.11606641113758087,
      "eval_runtime": 5.7777,
      "eval_samples_per_second": 536.547,
      "eval_steps_per_second": 11.25,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8948387096774194,
      "eval_loss": 0.06758537143468857,
      "eval_runtime": 5.6402,
      "eval_samples_per_second": 549.628,
      "eval_steps_per_second": 11.524,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.5751062631607056,
      "learning_rate": 1.3011879804332637e-05,
      "loss": 0.1369,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2862,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "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": 260941334653608.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.8846264724466298,
    "num_train_epochs": 9,
    "temperature": 3
  }
}