{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2226,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5793548387096774,
      "eval_loss": 0.20042110979557037,
      "eval_runtime": 5.4295,
      "eval_samples_per_second": 570.955,
      "eval_steps_per_second": 11.972,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.5317145586013794,
      "learning_rate": 1.550763701707098e-05,
      "loss": 0.3197,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8148387096774193,
      "eval_loss": 0.09952177852392197,
      "eval_runtime": 5.6253,
      "eval_samples_per_second": 551.079,
      "eval_steps_per_second": 11.555,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8722580645161291,
      "eval_loss": 0.06819746643304825,
      "eval_runtime": 5.4054,
      "eval_samples_per_second": 573.499,
      "eval_steps_per_second": 12.025,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.45249998569488525,
      "learning_rate": 1.101527403414196e-05,
      "loss": 0.1151,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8938709677419355,
      "eval_loss": 0.05422666668891907,
      "eval_runtime": 5.4496,
      "eval_samples_per_second": 568.852,
      "eval_steps_per_second": 11.928,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.3192004859447479,
      "learning_rate": 6.522911051212939e-06,
      "loss": 0.0764,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9012903225806451,
      "eval_loss": 0.04611504450440407,
      "eval_runtime": 5.7511,
      "eval_samples_per_second": 539.027,
      "eval_steps_per_second": 11.302,
      "step": 1590
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9041935483870968,
      "eval_loss": 0.04200603440403938,
      "eval_runtime": 5.406,
      "eval_samples_per_second": 573.439,
      "eval_steps_per_second": 12.024,
      "step": 1908
    },
    {
      "epoch": 6.289308176100629,
      "grad_norm": 0.2962014079093933,
      "learning_rate": 2.0305480682839176e-06,
      "loss": 0.0629,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2226,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 520991326672152.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.7983650996847113,
    "num_train_epochs": 7,
    "temperature": 12
  }
}