{
  "best_metric": 0.16098131239414215,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-clinc-oos-plus/run-3/checkpoint-1547",
  "epoch": 12.891666666666667,
  "eval_steps": 119,
  "global_step": 1547,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9916666666666667,
      "grad_norm": 0.8229151964187622,
      "learning_rate": 1.8474358974358976e-05,
      "loss": 0.7547,
      "step": 119
    },
    {
      "epoch": 0.9916666666666667,
      "eval_accuracy": 0.05806451612903226,
      "eval_loss": 0.6397132277488708,
      "eval_runtime": 5.2726,
      "eval_samples_per_second": 587.944,
      "eval_steps_per_second": 4.741,
      "step": 119
    },
    {
      "epoch": 1.9833333333333334,
      "grad_norm": 0.8302074074745178,
      "learning_rate": 1.694871794871795e-05,
      "loss": 0.5809,
      "step": 238
    },
    {
      "epoch": 1.9833333333333334,
      "eval_accuracy": 0.2719354838709677,
      "eval_loss": 0.4648343324661255,
      "eval_runtime": 5.2864,
      "eval_samples_per_second": 586.41,
      "eval_steps_per_second": 4.729,
      "step": 238
    },
    {
      "epoch": 2.975,
      "grad_norm": 0.9633338451385498,
      "learning_rate": 1.5423076923076925e-05,
      "loss": 0.439,
      "step": 357
    },
    {
      "epoch": 2.975,
      "eval_accuracy": 0.5116129032258064,
      "eval_loss": 0.34660565853118896,
      "eval_runtime": 5.2338,
      "eval_samples_per_second": 592.302,
      "eval_steps_per_second": 4.777,
      "step": 357
    },
    {
      "epoch": 3.966666666666667,
      "grad_norm": 0.9026358723640442,
      "learning_rate": 1.3897435897435898e-05,
      "loss": 0.3438,
      "step": 476
    },
    {
      "epoch": 3.966666666666667,
      "eval_accuracy": 0.6358064516129033,
      "eval_loss": 0.27853256464004517,
      "eval_runtime": 5.3024,
      "eval_samples_per_second": 584.642,
      "eval_steps_per_second": 4.715,
      "step": 476
    },
    {
      "epoch": 4.958333333333333,
      "grad_norm": 0.9341942667961121,
      "learning_rate": 1.2371794871794874e-05,
      "loss": 0.2875,
      "step": 595
    },
    {
      "epoch": 4.958333333333333,
      "eval_accuracy": 0.7029032258064516,
      "eval_loss": 0.23647043108940125,
      "eval_runtime": 5.2502,
      "eval_samples_per_second": 590.453,
      "eval_steps_per_second": 4.762,
      "step": 595
    },
    {
      "epoch": 5.95,
      "grad_norm": 0.9973844289779663,
      "learning_rate": 1.0846153846153847e-05,
      "loss": 0.2494,
      "step": 714
    },
    {
      "epoch": 5.95,
      "eval_accuracy": 0.7335483870967742,
      "eval_loss": 0.21039870381355286,
      "eval_runtime": 5.252,
      "eval_samples_per_second": 590.253,
      "eval_steps_per_second": 4.76,
      "step": 714
    },
    {
      "epoch": 6.941666666666666,
      "grad_norm": 0.6948856115341187,
      "learning_rate": 9.320512820512821e-06,
      "loss": 0.2245,
      "step": 833
    },
    {
      "epoch": 6.941666666666666,
      "eval_accuracy": 0.7548387096774194,
      "eval_loss": 0.19484896957874298,
      "eval_runtime": 5.252,
      "eval_samples_per_second": 590.25,
      "eval_steps_per_second": 4.76,
      "step": 833
    },
    {
      "epoch": 7.933333333333334,
      "grad_norm": 0.8398630619049072,
      "learning_rate": 7.794871794871796e-06,
      "loss": 0.2056,
      "step": 952
    },
    {
      "epoch": 7.933333333333334,
      "eval_accuracy": 0.7638709677419355,
      "eval_loss": 0.1842084378004074,
      "eval_runtime": 5.2457,
      "eval_samples_per_second": 590.959,
      "eval_steps_per_second": 4.766,
      "step": 952
    },
    {
      "epoch": 8.925,
      "grad_norm": 0.6326949596405029,
      "learning_rate": 6.26923076923077e-06,
      "loss": 0.1936,
      "step": 1071
    },
    {
      "epoch": 8.925,
      "eval_accuracy": 0.7748387096774193,
      "eval_loss": 0.17528517544269562,
      "eval_runtime": 5.2596,
      "eval_samples_per_second": 589.395,
      "eval_steps_per_second": 4.753,
      "step": 1071
    },
    {
      "epoch": 9.916666666666666,
      "grad_norm": 0.953779935836792,
      "learning_rate": 4.743589743589744e-06,
      "loss": 0.183,
      "step": 1190
    },
    {
      "epoch": 9.916666666666666,
      "eval_accuracy": 0.7806451612903226,
      "eval_loss": 0.16899022459983826,
      "eval_runtime": 5.2384,
      "eval_samples_per_second": 591.781,
      "eval_steps_per_second": 4.772,
      "step": 1190
    },
    {
      "epoch": 10.908333333333333,
      "grad_norm": 0.7265395522117615,
      "learning_rate": 3.2179487179487186e-06,
      "loss": 0.1746,
      "step": 1309
    },
    {
      "epoch": 10.908333333333333,
      "eval_accuracy": 0.785483870967742,
      "eval_loss": 0.16413316130638123,
      "eval_runtime": 5.2583,
      "eval_samples_per_second": 589.547,
      "eval_steps_per_second": 4.754,
      "step": 1309
    },
    {
      "epoch": 11.9,
      "grad_norm": 0.70655357837677,
      "learning_rate": 1.6923076923076926e-06,
      "loss": 0.1714,
      "step": 1428
    },
    {
      "epoch": 11.9,
      "eval_accuracy": 0.7838709677419354,
      "eval_loss": 0.16201290488243103,
      "eval_runtime": 5.2735,
      "eval_samples_per_second": 587.849,
      "eval_steps_per_second": 4.741,
      "step": 1428
    },
    {
      "epoch": 12.891666666666667,
      "grad_norm": 0.671647310256958,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 0.1687,
      "step": 1547
    },
    {
      "epoch": 12.891666666666667,
      "eval_accuracy": 0.7870967741935484,
      "eval_loss": 0.16098131239414215,
      "eval_runtime": 5.3094,
      "eval_samples_per_second": 583.865,
      "eval_steps_per_second": 4.709,
      "step": 1547
    }
  ],
  "logging_steps": 119,
  "max_steps": 1560,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 13,
  "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": 1176872678392572.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.147000328655721,
    "num_train_epochs": 13,
    "temperature": 6
  }
}