{
  "best_metric": 0.71,
  "best_model_checkpoint": "phi-finetuned-spam/run-0/checkpoint-116",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 116,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.65,
      "eval_loss": 0.6889538764953613,
      "eval_runtime": 7.7266,
      "eval_samples_per_second": 12.942,
      "eval_steps_per_second": 6.471,
      "step": 29
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.69,
      "eval_loss": 0.60980224609375,
      "eval_runtime": 7.7051,
      "eval_samples_per_second": 12.978,
      "eval_steps_per_second": 6.489,
      "step": 58
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7,
      "eval_loss": 0.597959578037262,
      "eval_runtime": 7.6821,
      "eval_samples_per_second": 13.017,
      "eval_steps_per_second": 6.509,
      "step": 87
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 36.34635925292969,
      "learning_rate": 8.826610509962089e-07,
      "loss": 0.8422,
      "step": 100
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.71,
      "eval_loss": 0.600787341594696,
      "eval_runtime": 7.5969,
      "eval_samples_per_second": 13.163,
      "eval_steps_per_second": 6.582,
      "step": 116
    }
  ],
  "logging_steps": 100,
  "max_steps": 116,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.45500656746496e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 6.399292619722514e-06,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 32,
    "seed": 18
  }
}