{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.861635220125786,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6464516129032258,
      "eval_loss": 0.2894870638847351,
      "eval_runtime": 5.1625,
      "eval_samples_per_second": 600.482,
      "eval_steps_per_second": 12.591,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.6621634364128113,
      "learning_rate": 1.606918238993711e-05,
      "loss": 0.4605,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8416129032258064,
      "eval_loss": 0.11869335174560547,
      "eval_runtime": 5.2214,
      "eval_samples_per_second": 593.71,
      "eval_steps_per_second": 12.449,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8912903225806451,
      "eval_loss": 0.0700218454003334,
      "eval_runtime": 5.1185,
      "eval_samples_per_second": 605.652,
      "eval_steps_per_second": 12.699,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.5828885436058044,
      "learning_rate": 1.2138364779874214e-05,
      "loss": 0.1397,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9077419354838709,
      "eval_loss": 0.05109017714858055,
      "eval_runtime": 5.3994,
      "eval_samples_per_second": 574.138,
      "eval_steps_per_second": 12.038,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.38680753111839294,
      "learning_rate": 8.207547169811321e-06,
      "loss": 0.0802,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9164516129032259,
      "eval_loss": 0.04168670251965523,
      "eval_runtime": 5.2289,
      "eval_samples_per_second": 592.857,
      "eval_steps_per_second": 12.431,
      "step": 1590
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9241935483870968,
      "eval_loss": 0.03709598630666733,
      "eval_runtime": 5.1496,
      "eval_samples_per_second": 601.985,
      "eval_steps_per_second": 12.622,
      "step": 1908
    },
    {
      "epoch": 6.289308176100629,
      "grad_norm": 0.32195693254470825,
      "learning_rate": 4.276729559748428e-06,
      "loss": 0.0619,
      "step": 2000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9264516129032258,
      "eval_loss": 0.0347614511847496,
      "eval_runtime": 5.37,
      "eval_samples_per_second": 577.286,
      "eval_steps_per_second": 12.104,
      "step": 2226
    },
    {
      "epoch": 7.861635220125786,
      "grad_norm": 0.33459800481796265,
      "learning_rate": 3.459119496855346e-07,
      "loss": 0.0552,
      "step": 2500
    }
  ],
  "logging_steps": 500,
  "max_steps": 2544,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 651155886807636.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.6565754742921168,
    "num_train_epochs": 8,
    "temperature": 3
  }
}