{
  "best_metric": 0.5776590704917908,
  "best_model_checkpoint": "BERT-WMM/run-15/checkpoint-534",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1068,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7577464788732394,
      "eval_loss": 0.6081846952438354,
      "eval_runtime": 2.4313,
      "eval_samples_per_second": 876.086,
      "eval_steps_per_second": 55.115,
      "step": 267
    },
    {
      "epoch": 1.87,
      "grad_norm": 9.532360076904297,
      "learning_rate": 9.65168237740807e-06,
      "loss": 0.6057,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7657276995305164,
      "eval_loss": 0.5776590704917908,
      "eval_runtime": 2.4531,
      "eval_samples_per_second": 868.299,
      "eval_steps_per_second": 54.625,
      "step": 534
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7690140845070422,
      "eval_loss": 0.6647635102272034,
      "eval_runtime": 2.4548,
      "eval_samples_per_second": 867.692,
      "eval_steps_per_second": 54.587,
      "step": 801
    },
    {
      "epoch": 3.75,
      "grad_norm": 26.327552795410156,
      "learning_rate": 3.872231852014017e-06,
      "loss": 0.2807,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7615023474178404,
      "eval_loss": 0.758091151714325,
      "eval_runtime": 2.4532,
      "eval_samples_per_second": 868.264,
      "eval_steps_per_second": 54.623,
      "step": 1068
    }
  ],
  "logging_steps": 500,
  "max_steps": 1335,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 883767136544712.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "num_train_epochs": 5
  }
}