{
  "best_metric": 0.8724862888482633,
  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-18\\checkpoint-2874",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 2874,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 3.465716376002269e-05,
      "loss": 0.4791,
      "step": 958
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8670018281535649,
      "eval_loss": 0.4717980623245239,
      "eval_runtime": 10.7271,
      "eval_samples_per_second": 203.97,
      "eval_steps_per_second": 1.678,
      "step": 958
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.7328581880011345e-05,
      "loss": 0.4594,
      "step": 1916
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8679159049360147,
      "eval_loss": 0.4765470027923584,
      "eval_runtime": 10.6457,
      "eval_samples_per_second": 205.528,
      "eval_steps_per_second": 1.691,
      "step": 1916
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.4504,
      "step": 2874
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8724862888482633,
      "eval_loss": 0.471828430891037,
      "eval_runtime": 10.7233,
      "eval_samples_per_second": 204.041,
      "eval_steps_per_second": 1.679,
      "step": 2874
    }
  ],
  "logging_steps": 500,
  "max_steps": 2874,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2922632109696.0,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 5.198574564003404e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 8,
    "seed": 39
  }
}