run-1/checkpoint-242/trainer_state.json

{
  "best_metric": 0.6899063475546305,
  "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-1\\checkpoint-242",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 242,
  "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
    }
  ],
  "logging_steps": 500,
  "max_steps": 847,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 5509305756660.0,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.6084476315511869,
    "learning_rate": 2.4847718043043563e-05,
    "num_train_epochs": 7,
    "temperature": 19
  }
}