{
  "best_metric": 0.5039642659976749,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1605",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1605,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.93,
      "grad_norm": 4.838195323944092,
      "learning_rate": 2.542737154981418e-05,
      "loss": 0.5194,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.49024975299835205,
      "eval_matthews_correlation": 0.43262718467553657,
      "eval_runtime": 2.2476,
      "eval_samples_per_second": 464.059,
      "eval_steps_per_second": 29.365,
      "step": 535
    },
    {
      "epoch": 1.87,
      "grad_norm": 5.74407434463501,
      "learning_rate": 1.3921773563472922e-05,
      "loss": 0.3182,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5491473078727722,
      "eval_matthews_correlation": 0.49357249556059846,
      "eval_runtime": 1.7076,
      "eval_samples_per_second": 610.785,
      "eval_steps_per_second": 38.65,
      "step": 1070
    },
    {
      "epoch": 2.8,
      "grad_norm": 18.21695899963379,
      "learning_rate": 2.416175577131664e-06,
      "loss": 0.1905,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7505267858505249,
      "eval_matthews_correlation": 0.5039642659976749,
      "eval_runtime": 0.7556,
      "eval_samples_per_second": 1380.405,
      "eval_steps_per_second": 87.351,
      "step": 1605
    }
  ],
  "logging_steps": 500,
  "max_steps": 1605,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 128908113493284.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 3.693296953615544e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 16,
    "seed": 9
  }
}