{
  "best_metric": 0.19450587034225464,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-clinc-oos-plus/run-12/checkpoint-1785",
  "epoch": 14.875,
  "eval_steps": 119,
  "global_step": 1785,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9916666666666667,
      "grad_norm": 0.8180056214332581,
      "learning_rate": 1.8677777777777778e-05,
      "loss": 1.5139,
      "step": 119
    },
    {
      "epoch": 0.9916666666666667,
      "eval_accuracy": 0.1396774193548387,
      "eval_loss": 1.2963447570800781,
      "eval_runtime": 5.2191,
      "eval_samples_per_second": 593.972,
      "eval_steps_per_second": 4.79,
      "step": 119
    },
    {
      "epoch": 1.9833333333333334,
      "grad_norm": 1.3891874551773071,
      "learning_rate": 1.7355555555555558e-05,
      "loss": 1.1785,
      "step": 238
    },
    {
      "epoch": 1.9833333333333334,
      "eval_accuracy": 0.5116129032258064,
      "eval_loss": 0.8595607280731201,
      "eval_runtime": 5.2576,
      "eval_samples_per_second": 589.624,
      "eval_steps_per_second": 4.755,
      "step": 238
    },
    {
      "epoch": 2.975,
      "grad_norm": 1.339552640914917,
      "learning_rate": 1.6033333333333335e-05,
      "loss": 0.7933,
      "step": 357
    },
    {
      "epoch": 2.975,
      "eval_accuracy": 0.6690322580645162,
      "eval_loss": 0.5503354668617249,
      "eval_runtime": 5.2604,
      "eval_samples_per_second": 589.305,
      "eval_steps_per_second": 4.752,
      "step": 357
    },
    {
      "epoch": 3.966666666666667,
      "grad_norm": 1.4430162906646729,
      "learning_rate": 1.4711111111111111e-05,
      "loss": 0.5499,
      "step": 476
    },
    {
      "epoch": 3.966666666666667,
      "eval_accuracy": 0.734516129032258,
      "eval_loss": 0.3985496759414673,
      "eval_runtime": 5.2888,
      "eval_samples_per_second": 586.14,
      "eval_steps_per_second": 4.727,
      "step": 476
    },
    {
      "epoch": 4.958333333333333,
      "grad_norm": 1.265928864479065,
      "learning_rate": 1.338888888888889e-05,
      "loss": 0.4226,
      "step": 595
    },
    {
      "epoch": 4.958333333333333,
      "eval_accuracy": 0.7641935483870967,
      "eval_loss": 0.3224957585334778,
      "eval_runtime": 5.2387,
      "eval_samples_per_second": 591.752,
      "eval_steps_per_second": 4.772,
      "step": 595
    },
    {
      "epoch": 5.95,
      "grad_norm": 1.514481544494629,
      "learning_rate": 1.206666666666667e-05,
      "loss": 0.3466,
      "step": 714
    },
    {
      "epoch": 5.95,
      "eval_accuracy": 0.7909677419354839,
      "eval_loss": 0.2790695130825043,
      "eval_runtime": 5.2618,
      "eval_samples_per_second": 589.147,
      "eval_steps_per_second": 4.751,
      "step": 714
    },
    {
      "epoch": 6.941666666666666,
      "grad_norm": 1.1318318843841553,
      "learning_rate": 1.0744444444444446e-05,
      "loss": 0.3007,
      "step": 833
    },
    {
      "epoch": 6.941666666666666,
      "eval_accuracy": 0.805483870967742,
      "eval_loss": 0.2540387809276581,
      "eval_runtime": 5.309,
      "eval_samples_per_second": 583.91,
      "eval_steps_per_second": 4.709,
      "step": 833
    },
    {
      "epoch": 7.933333333333334,
      "grad_norm": 1.1625335216522217,
      "learning_rate": 9.422222222222222e-06,
      "loss": 0.2646,
      "step": 952
    },
    {
      "epoch": 7.933333333333334,
      "eval_accuracy": 0.8080645161290323,
      "eval_loss": 0.23807008564472198,
      "eval_runtime": 5.6673,
      "eval_samples_per_second": 546.998,
      "eval_steps_per_second": 4.411,
      "step": 952
    },
    {
      "epoch": 8.925,
      "grad_norm": 0.9929422736167908,
      "learning_rate": 8.1e-06,
      "loss": 0.2418,
      "step": 1071
    },
    {
      "epoch": 8.925,
      "eval_accuracy": 0.8241935483870968,
      "eval_loss": 0.2234683483839035,
      "eval_runtime": 5.2893,
      "eval_samples_per_second": 586.085,
      "eval_steps_per_second": 4.726,
      "step": 1071
    },
    {
      "epoch": 9.916666666666666,
      "grad_norm": 1.3932344913482666,
      "learning_rate": 6.777777777777779e-06,
      "loss": 0.2228,
      "step": 1190
    },
    {
      "epoch": 9.916666666666666,
      "eval_accuracy": 0.8296774193548387,
      "eval_loss": 0.21503257751464844,
      "eval_runtime": 5.2284,
      "eval_samples_per_second": 592.916,
      "eval_steps_per_second": 4.782,
      "step": 1190
    },
    {
      "epoch": 10.908333333333333,
      "grad_norm": 1.1120707988739014,
      "learning_rate": 5.455555555555556e-06,
      "loss": 0.2071,
      "step": 1309
    },
    {
      "epoch": 10.908333333333333,
      "eval_accuracy": 0.832258064516129,
      "eval_loss": 0.20633584260940552,
      "eval_runtime": 5.269,
      "eval_samples_per_second": 588.344,
      "eval_steps_per_second": 4.745,
      "step": 1309
    },
    {
      "epoch": 11.9,
      "grad_norm": 1.1221190690994263,
      "learning_rate": 4.133333333333333e-06,
      "loss": 0.1991,
      "step": 1428
    },
    {
      "epoch": 11.9,
      "eval_accuracy": 0.834516129032258,
      "eval_loss": 0.20154178142547607,
      "eval_runtime": 5.2955,
      "eval_samples_per_second": 585.399,
      "eval_steps_per_second": 4.721,
      "step": 1428
    },
    {
      "epoch": 12.891666666666667,
      "grad_norm": 0.9445534348487854,
      "learning_rate": 2.811111111111111e-06,
      "loss": 0.1911,
      "step": 1547
    },
    {
      "epoch": 12.891666666666667,
      "eval_accuracy": 0.837741935483871,
      "eval_loss": 0.19792121648788452,
      "eval_runtime": 5.2725,
      "eval_samples_per_second": 587.958,
      "eval_steps_per_second": 4.742,
      "step": 1547
    },
    {
      "epoch": 13.883333333333333,
      "grad_norm": 0.9927912950515747,
      "learning_rate": 1.4888888888888888e-06,
      "loss": 0.1855,
      "step": 1666
    },
    {
      "epoch": 13.883333333333333,
      "eval_accuracy": 0.8403225806451613,
      "eval_loss": 0.1957916021347046,
      "eval_runtime": 5.2457,
      "eval_samples_per_second": 590.96,
      "eval_steps_per_second": 4.766,
      "step": 1666
    },
    {
      "epoch": 14.875,
      "grad_norm": 0.9268798828125,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 0.1824,
      "step": 1785
    },
    {
      "epoch": 14.875,
      "eval_accuracy": 0.8403225806451613,
      "eval_loss": 0.19450587034225464,
      "eval_runtime": 5.2577,
      "eval_samples_per_second": 589.606,
      "eval_steps_per_second": 4.755,
      "step": 1785
    }
  ],
  "logging_steps": 119,
  "max_steps": 1800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "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": 1358349105005256.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.502732251510764,
    "num_train_epochs": 15,
    "temperature": 2
  }
}