{
  "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": 0.5783870967741935,
      "eval_loss": 0.2046278566122055,
      "eval_runtime": 5.6717,
      "eval_samples_per_second": 546.572,
      "eval_steps_per_second": 11.46,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.5409613251686096,
      "learning_rate": 1.4758909853249476e-05,
      "loss": 0.3241,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8125806451612904,
      "eval_loss": 0.10322821140289307,
      "eval_runtime": 6.1936,
      "eval_samples_per_second": 500.513,
      "eval_steps_per_second": 10.495,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8687096774193548,
      "eval_loss": 0.0720166265964508,
      "eval_runtime": 5.6413,
      "eval_samples_per_second": 549.518,
      "eval_steps_per_second": 11.522,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.46297112107276917,
      "learning_rate": 9.517819706498952e-06,
      "loss": 0.1192,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8912903225806451,
      "eval_loss": 0.058526117354631424,
      "eval_runtime": 5.7211,
      "eval_samples_per_second": 541.849,
      "eval_steps_per_second": 11.361,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.3392227292060852,
      "learning_rate": 4.276729559748428e-06,
      "loss": 0.0816,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1908,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 0.1698724421938158,
    "num_train_epochs": 6,
    "temperature": 11
  }
}