{
  "best_metric": 0.47896393100906826,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-536",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 536,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.5264953970909119,
      "eval_matthews_correlation": 0.3429695650358,
      "eval_runtime": 0.34,
      "eval_samples_per_second": 3068.067,
      "eval_steps_per_second": 194.144,
      "step": 134
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5003471374511719,
      "eval_matthews_correlation": 0.4231731541032522,
      "eval_runtime": 0.3582,
      "eval_samples_per_second": 2911.918,
      "eval_steps_per_second": 184.263,
      "step": 268
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5117089748382568,
      "eval_matthews_correlation": 0.4445067035273154,
      "eval_runtime": 0.3618,
      "eval_samples_per_second": 2882.875,
      "eval_steps_per_second": 182.425,
      "step": 402
    },
    {
      "epoch": 3.73,
      "grad_norm": 3.712400197982788,
      "learning_rate": 7.65019922522248e-07,
      "loss": 0.4486,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5077244639396667,
      "eval_matthews_correlation": 0.47896393100906826,
      "eval_runtime": 0.3802,
      "eval_samples_per_second": 2743.294,
      "eval_steps_per_second": 173.593,
      "step": 536
    }
  ],
  "logging_steps": 500,
  "max_steps": 536,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 209572221336984.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.1390296624220138e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 64,
    "seed": 11
  }
}