{
  "best_metric": 0.2736915647983551,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-clinc-oos-plus/run-2/checkpoint-714",
  "epoch": 5.95,
  "eval_steps": 119,
  "global_step": 714,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9916666666666667,
      "grad_norm": 0.698729932308197,
      "learning_rate": 1.6694444444444446e-05,
      "loss": 0.6622,
      "step": 119
    },
    {
      "epoch": 0.9916666666666667,
      "eval_accuracy": 0.05806451612903226,
      "eval_loss": 0.5631250739097595,
      "eval_runtime": 5.3039,
      "eval_samples_per_second": 584.478,
      "eval_steps_per_second": 4.714,
      "step": 119
    },
    {
      "epoch": 1.9833333333333334,
      "grad_norm": 0.9459291696548462,
      "learning_rate": 1.338888888888889e-05,
      "loss": 0.5163,
      "step": 238
    },
    {
      "epoch": 1.9833333333333334,
      "eval_accuracy": 0.18161290322580645,
      "eval_loss": 0.4296840727329254,
      "eval_runtime": 5.2697,
      "eval_samples_per_second": 588.274,
      "eval_steps_per_second": 4.744,
      "step": 238
    },
    {
      "epoch": 2.975,
      "grad_norm": 1.3281234502792358,
      "learning_rate": 1.0083333333333334e-05,
      "loss": 0.4171,
      "step": 357
    },
    {
      "epoch": 2.975,
      "eval_accuracy": 0.3574193548387097,
      "eval_loss": 0.35349318385124207,
      "eval_runtime": 5.1875,
      "eval_samples_per_second": 597.596,
      "eval_steps_per_second": 4.819,
      "step": 357
    },
    {
      "epoch": 3.966666666666667,
      "grad_norm": 0.7127528786659241,
      "learning_rate": 6.777777777777779e-06,
      "loss": 0.3534,
      "step": 476
    },
    {
      "epoch": 3.966666666666667,
      "eval_accuracy": 0.46774193548387094,
      "eval_loss": 0.3053215444087982,
      "eval_runtime": 5.2822,
      "eval_samples_per_second": 586.875,
      "eval_steps_per_second": 4.733,
      "step": 476
    },
    {
      "epoch": 4.958333333333333,
      "grad_norm": 0.6603091359138489,
      "learning_rate": 3.4722222222222224e-06,
      "loss": 0.3177,
      "step": 595
    },
    {
      "epoch": 4.958333333333333,
      "eval_accuracy": 0.5312903225806451,
      "eval_loss": 0.2807427644729614,
      "eval_runtime": 5.2469,
      "eval_samples_per_second": 590.829,
      "eval_steps_per_second": 4.765,
      "step": 595
    },
    {
      "epoch": 5.95,
      "grad_norm": 0.7326369881629944,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 0.2997,
      "step": 714
    },
    {
      "epoch": 5.95,
      "eval_accuracy": 0.5503225806451613,
      "eval_loss": 0.2736915647983551,
      "eval_runtime": 5.2539,
      "eval_samples_per_second": 590.035,
      "eval_steps_per_second": 4.758,
      "step": 714
    }
  ],
  "logging_steps": 119,
  "max_steps": 720,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 119,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 545563432923180.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.29553321059794946,
    "num_train_epochs": 6,
    "temperature": 14
  }
}