{
  "best_metric": 0.42662088349566707,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1072",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1072,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.547015905380249,
      "eval_matthews_correlation": 0.21965396568843812,
      "eval_runtime": 0.7987,
      "eval_samples_per_second": 1305.815,
      "eval_steps_per_second": 82.631,
      "step": 268
    },
    {
      "epoch": 1.8656716417910446,
      "grad_norm": 5.013413906097412,
      "learning_rate": 2.4916450268020124e-06,
      "loss": 0.5406,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5194542407989502,
      "eval_matthews_correlation": 0.38878916468148733,
      "eval_runtime": 0.9473,
      "eval_samples_per_second": 1100.981,
      "eval_steps_per_second": 69.669,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.511012613773346,
      "eval_matthews_correlation": 0.4209176074686373,
      "eval_runtime": 1.7589,
      "eval_samples_per_second": 592.995,
      "eval_steps_per_second": 37.524,
      "step": 804
    },
    {
      "epoch": 3.7313432835820897,
      "grad_norm": 5.263833999633789,
      "learning_rate": 3.1363363973731624e-07,
      "loss": 0.4347,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5149170756340027,
      "eval_matthews_correlation": 0.42662088349566707,
      "eval_runtime": 0.9396,
      "eval_samples_per_second": 1109.992,
      "eval_steps_per_second": 70.239,
      "step": 1072
    }
  ],
  "logging_steps": 500,
  "max_steps": 1072,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 190264063081320.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.669656413866708e-06,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 32,
    "seed": 15
  }
}