run-9/checkpoint-363/trainer_state.json

{
  "best_metric": 0.7601456815816857,
  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-9\\checkpoint-363",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 363,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.0002622085234877425,
      "loss": 0.236,
      "step": 121
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7580645161290323,
      "eval_loss": 0.2295788824558258,
      "eval_runtime": 5.3953,
      "eval_samples_per_second": 356.235,
      "eval_steps_per_second": 2.966,
      "step": 121
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00013110426174387126,
      "loss": 0.2239,
      "step": 242
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.759105098855359,
      "eval_loss": 0.2274383157491684,
      "eval_runtime": 5.4149,
      "eval_samples_per_second": 354.944,
      "eval_steps_per_second": 2.955,
      "step": 242
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.2174,
      "step": 363
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7601456815816857,
      "eval_loss": 0.22863133251667023,
      "eval_runtime": 5.482,
      "eval_samples_per_second": 350.6,
      "eval_steps_per_second": 2.919,
      "step": 363
    }
  ],
  "logging_steps": 500,
  "max_steps": 363,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 8247964642380.0,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.3527253554518407,
    "learning_rate": 0.0003933127852316138,
    "num_train_epochs": 3,
    "temperature": 26
  }
}