{
  "best_global_step": 3906,
  "best_metric": 0.0746106207370758,
  "best_model_checkpoint": "./results_albert_punctuation_casing/checkpoint-3906",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 5859,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2560163850486431,
      "grad_norm": 7.659163475036621,
      "learning_rate": 1.8296637651476362e-05,
      "loss": 0.17497076416015625,
      "step": 500
    },
    {
      "epoch": 0.5120327700972862,
      "grad_norm": 9.602242469787598,
      "learning_rate": 1.6589861751152075e-05,
      "loss": 0.09840100860595703,
      "step": 1000
    },
    {
      "epoch": 0.7680491551459293,
      "grad_norm": 2.2302889823913574,
      "learning_rate": 1.4883085850827787e-05,
      "loss": 0.08661653137207032,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_casing_accuracy": 0.5982128829536528,
      "eval_loss": 0.07590867578983307,
      "eval_overall_accuracy": 0.597888845247447,
      "eval_punctuation_accuracy": 0.5975648075412412,
      "eval_runtime": 11.014,
      "eval_samples_per_second": 709.096,
      "eval_steps_per_second": 44.398,
      "step": 1953
    },
    {
      "epoch": 1.0240655401945724,
      "grad_norm": 0.46477240324020386,
      "learning_rate": 1.3176309950503501e-05,
      "loss": 0.08205690765380859,
      "step": 2000
    },
    {
      "epoch": 1.2800819252432156,
      "grad_norm": 6.8253865242004395,
      "learning_rate": 1.1469534050179212e-05,
      "loss": 0.0625931053161621,
      "step": 2500
    },
    {
      "epoch": 1.5360983102918588,
      "grad_norm": 3.1819510459899902,
      "learning_rate": 9.762758149854925e-06,
      "loss": 0.06253623962402344,
      "step": 3000
    },
    {
      "epoch": 1.7921146953405018,
      "grad_norm": 4.698487281799316,
      "learning_rate": 8.055982249530637e-06,
      "loss": 0.053002174377441404,
      "step": 3500
    },
    {
      "epoch": 2.0,
      "eval_casing_accuracy": 0.5975058915946583,
      "eval_loss": 0.0746106207370758,
      "eval_overall_accuracy": 0.5965730557737627,
      "eval_punctuation_accuracy": 0.5956402199528672,
      "eval_runtime": 11.2558,
      "eval_samples_per_second": 693.865,
      "eval_steps_per_second": 43.444,
      "step": 3906
    },
    {
      "epoch": 2.048131080389145,
      "grad_norm": 0.29059869050979614,
      "learning_rate": 6.349206349206349e-06,
      "loss": 0.057237117767333985,
      "step": 4000
    },
    {
      "epoch": 2.3041474654377883,
      "grad_norm": 1.9593513011932373,
      "learning_rate": 4.642430448882062e-06,
      "loss": 0.03903835678100586,
      "step": 4500
    },
    {
      "epoch": 2.5601638504864312,
      "grad_norm": 4.75918436050415,
      "learning_rate": 2.9356545485577746e-06,
      "loss": 0.03857281112670898,
      "step": 5000
    },
    {
      "epoch": 2.8161802355350742,
      "grad_norm": 1.5033795833587646,
      "learning_rate": 1.228878648233487e-06,
      "loss": 0.03791716384887695,
      "step": 5500
    },
    {
      "epoch": 3.0,
      "eval_casing_accuracy": 0.5970542026708563,
      "eval_loss": 0.07589453458786011,
      "eval_overall_accuracy": 0.5967596229379419,
      "eval_punctuation_accuracy": 0.5964650432050275,
      "eval_runtime": 11.3344,
      "eval_samples_per_second": 689.056,
      "eval_steps_per_second": 43.143,
      "step": 5859
    }
  ],
  "logging_steps": 500,
  "max_steps": 5859,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}