run-3/checkpoint-480/trainer_state.json

{
  "best_metric": 0.8816270566727605,
  "best_model_checkpoint": "distilbert-hate_speech18\\run-3\\checkpoint-480",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 480,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 2.741556032723218e-06,
      "loss": 0.3969,
      "step": 240
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8606032906764168,
      "eval_loss": 0.38725385069847107,
      "eval_runtime": 13.634,
      "eval_samples_per_second": 160.481,
      "eval_steps_per_second": 5.061,
      "step": 240
    },
    {
      "epoch": 2.0,
      "learning_rate": 2.0561670245424133e-06,
      "loss": 0.3833,
      "step": 480
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8816270566727605,
      "eval_loss": 0.3825770616531372,
      "eval_runtime": 13.6065,
      "eval_samples_per_second": 160.806,
      "eval_steps_per_second": 5.071,
      "step": 480
    }
  ],
  "logging_steps": 500,
  "max_steps": 1200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 328019606410944.0,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.3534065692399305,
    "learning_rate": 3.4269450409040222e-06,
    "num_train_epochs": 5,
    "per_device_eval_batch_size": 32,
    "per_device_train_batch_size": 32,
    "temperature": 11
  }
}