{
  "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": 0.5858064516129032,
      "eval_loss": 0.20023050904273987,
      "eval_runtime": 5.4304,
      "eval_samples_per_second": 570.856,
      "eval_steps_per_second": 11.97,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.5323805212974548,
      "learning_rate": 1.606918238993711e-05,
      "loss": 0.3211,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.817741935483871,
      "eval_loss": 0.09780898690223694,
      "eval_runtime": 5.6251,
      "eval_samples_per_second": 551.101,
      "eval_steps_per_second": 11.555,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8761290322580645,
      "eval_loss": 0.06598751991987228,
      "eval_runtime": 5.3523,
      "eval_samples_per_second": 579.185,
      "eval_steps_per_second": 12.144,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.45211926102638245,
      "learning_rate": 1.2138364779874214e-05,
      "loss": 0.1134,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8970967741935484,
      "eval_loss": 0.05154659226536751,
      "eval_runtime": 5.4338,
      "eval_samples_per_second": 570.506,
      "eval_steps_per_second": 11.962,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.31171318888664246,
      "learning_rate": 8.207547169811321e-06,
      "loss": 0.0736,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9051612903225806,
      "eval_loss": 0.04292130842804909,
      "eval_runtime": 5.5921,
      "eval_samples_per_second": 554.351,
      "eval_steps_per_second": 11.623,
      "step": 1590
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9090322580645162,
      "eval_loss": 0.03817291185259819,
      "eval_runtime": 5.3716,
      "eval_samples_per_second": 577.105,
      "eval_steps_per_second": 12.101,
      "step": 1908
    },
    {
      "epoch": 6.289308176100629,
      "grad_norm": 0.2767144441604614,
      "learning_rate": 4.276729559748428e-06,
      "loss": 0.0589,
      "step": 2000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9135483870967742,
      "eval_loss": 0.03585055470466614,
      "eval_runtime": 5.5797,
      "eval_samples_per_second": 555.585,
      "eval_steps_per_second": 11.649,
      "step": 2226
    },
    {
      "epoch": 7.861635220125786,
      "grad_norm": 0.27693912386894226,
      "learning_rate": 3.459119496855346e-07,
      "loss": 0.0529,
      "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": 0.1709217232718393,
    "num_train_epochs": 8,
    "temperature": 11
  }
}