{
  "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": 0.6758064516129032,
      "eval_loss": 0.40983492136001587,
      "eval_runtime": 5.3091,
      "eval_samples_per_second": 583.902,
      "eval_steps_per_second": 12.243,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.86518794298172,
      "learning_rate": 1.606918238993711e-05,
      "loss": 0.645,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8412903225806452,
      "eval_loss": 0.142293781042099,
      "eval_runtime": 5.7053,
      "eval_samples_per_second": 543.354,
      "eval_steps_per_second": 11.393,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8938709677419355,
      "eval_loss": 0.07486626505851746,
      "eval_runtime": 5.5666,
      "eval_samples_per_second": 556.891,
      "eval_steps_per_second": 11.677,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.7068584561347961,
      "learning_rate": 1.2138364779874214e-05,
      "loss": 0.1671,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9141935483870968,
      "eval_loss": 0.053671687841415405,
      "eval_runtime": 5.5136,
      "eval_samples_per_second": 562.245,
      "eval_steps_per_second": 11.789,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.464497447013855,
      "learning_rate": 8.207547169811321e-06,
      "loss": 0.0849,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9238709677419354,
      "eval_loss": 0.04483605548739433,
      "eval_runtime": 5.4578,
      "eval_samples_per_second": 567.99,
      "eval_steps_per_second": 11.909,
      "step": 1590
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9261290322580645,
      "eval_loss": 0.04038877785205841,
      "eval_runtime": 5.3046,
      "eval_samples_per_second": 584.395,
      "eval_steps_per_second": 12.253,
      "step": 1908
    },
    {
      "epoch": 6.289308176100629,
      "grad_norm": 0.36644139885902405,
      "learning_rate": 4.276729559748428e-06,
      "loss": 0.0648,
      "step": 2000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9312903225806451,
      "eval_loss": 0.038099613040685654,
      "eval_runtime": 5.6154,
      "eval_samples_per_second": 552.055,
      "eval_steps_per_second": 11.575,
      "step": 2226
    },
    {
      "epoch": 7.861635220125786,
      "grad_norm": 0.39690807461738586,
      "learning_rate": 3.459119496855346e-07,
      "loss": 0.0579,
      "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": 0.6467525448555197,
    "num_train_epochs": 8,
    "temperature": 2
  }
}