{
  "best_metric": 0.7169614984391259,
  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-1\\checkpoint-726",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 726,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 2.129804403689448e-05,
      "loss": 0.4131,
      "step": 121
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6368366285119667,
      "eval_loss": 0.4047480523586273,
      "eval_runtime": 5.4349,
      "eval_samples_per_second": 353.639,
      "eval_steps_per_second": 2.944,
      "step": 121
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.7748370030745404e-05,
      "loss": 0.3945,
      "step": 242
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6899063475546305,
      "eval_loss": 0.38732439279556274,
      "eval_runtime": 5.3621,
      "eval_samples_per_second": 358.443,
      "eval_steps_per_second": 2.984,
      "step": 242
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.4198696024596321e-05,
      "loss": 0.3823,
      "step": 363
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7018730489073881,
      "eval_loss": 0.3818596303462982,
      "eval_runtime": 5.4466,
      "eval_samples_per_second": 352.882,
      "eval_steps_per_second": 2.938,
      "step": 363
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.064902201844724e-05,
      "loss": 0.3756,
      "step": 484
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7101977107180021,
      "eval_loss": 0.37931492924690247,
      "eval_runtime": 5.4367,
      "eval_samples_per_second": 353.52,
      "eval_steps_per_second": 2.943,
      "step": 484
    },
    {
      "epoch": 5.0,
      "learning_rate": 7.099348012298161e-06,
      "loss": 0.3727,
      "step": 605
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7127991675338189,
      "eval_loss": 0.37749114632606506,
      "eval_runtime": 5.3835,
      "eval_samples_per_second": 357.016,
      "eval_steps_per_second": 2.972,
      "step": 605
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.5496740061490804e-06,
      "loss": 0.369,
      "step": 726
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7169614984391259,
      "eval_loss": 0.3764614760875702,
      "eval_runtime": 5.3772,
      "eval_samples_per_second": 357.435,
      "eval_steps_per_second": 2.976,
      "step": 726
    }
  ],
  "logging_steps": 500,
  "max_steps": 847,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 16472407904580.0,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.6084476315511869,
    "learning_rate": 2.4847718043043563e-05,
    "num_train_epochs": 7,
    "temperature": 19
  }
}