{
  "best_global_step": 200,
  "best_metric": 0.997965707643127,
  "best_model_checkpoint": "models/tinybert-enron\\checkpoint-200",
  "epoch": 0.42238648363252373,
  "eval_steps": 200,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05279831045406547,
      "grad_norm": 0.7054851055145264,
      "learning_rate": 3.878627968337731e-06,
      "loss": 0.6916,
      "step": 50
    },
    {
      "epoch": 0.10559662090813093,
      "grad_norm": 4.758987903594971,
      "learning_rate": 7.836411609498681e-06,
      "loss": 0.6419,
      "step": 100
    },
    {
      "epoch": 0.1583949313621964,
      "grad_norm": 2.878147602081299,
      "learning_rate": 1.179419525065963e-05,
      "loss": 0.4382,
      "step": 150
    },
    {
      "epoch": 0.21119324181626187,
      "grad_norm": 0.9188410639762878,
      "learning_rate": 1.575197889182058e-05,
      "loss": 0.2162,
      "step": 200
    },
    {
      "epoch": 0.21119324181626187,
      "eval_accuracy": 0.997920997920998,
      "eval_f1": 0.997965707643127,
      "eval_loss": 0.11409526318311691,
      "eval_precision": 0.9959396751740139,
      "eval_recall": 1.0,
      "eval_runtime": 77.9734,
      "eval_samples_per_second": 43.181,
      "eval_steps_per_second": 2.706,
      "step": 200
    },
    {
      "epoch": 0.26399155227032733,
      "grad_norm": 0.42353588342666626,
      "learning_rate": 1.970976253298153e-05,
      "loss": 0.0759,
      "step": 250
    },
    {
      "epoch": 0.3167898627243928,
      "grad_norm": 0.22129850089550018,
      "learning_rate": 2.3667546174142482e-05,
      "loss": 0.0466,
      "step": 300
    },
    {
      "epoch": 0.36958817317845827,
      "grad_norm": 0.14293035864830017,
      "learning_rate": 2.762532981530343e-05,
      "loss": 0.0333,
      "step": 350
    },
    {
      "epoch": 0.42238648363252373,
      "grad_norm": 0.09417829662561417,
      "learning_rate": 2.982399530654151e-05,
      "loss": 0.015,
      "step": 400
    },
    {
      "epoch": 0.42238648363252373,
      "eval_accuracy": 0.9988119988119988,
      "eval_f1": 0.9988365328679465,
      "eval_loss": 0.012017497792840004,
      "eval_precision": 0.9976757699012202,
      "eval_recall": 1.0,
      "eval_runtime": 75.9348,
      "eval_samples_per_second": 44.341,
      "eval_steps_per_second": 2.779,
      "step": 400
    }
  ],
  "logging_steps": 50,
  "max_steps": 3788,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0005
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 91769575833600.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}