run-1/checkpoint-879/trainer_state.json

{
  "best_metric": 0.7585616438356164,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-1/checkpoint-879",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 879,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.714041095890411,
      "eval_loss": 0.71292644739151,
      "eval_runtime": 3.3595,
      "eval_samples_per_second": 173.834,
      "eval_steps_per_second": 11.013,
      "step": 293
    },
    {
      "epoch": 1.71,
      "grad_norm": 8.596644401550293,
      "learning_rate": 1.7747741226076666e-06,
      "loss": 0.7782,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.75,
      "eval_loss": 0.5617372989654541,
      "eval_runtime": 3.3611,
      "eval_samples_per_second": 173.75,
      "eval_steps_per_second": 11.008,
      "step": 586
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7585616438356164,
      "eval_loss": 0.5336253643035889,
      "eval_runtime": 3.3416,
      "eval_samples_per_second": 174.767,
      "eval_steps_per_second": 11.073,
      "step": 879
    }
  ],
  "logging_steps": 500,
  "max_steps": 879,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 632183474186820.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.116164785678467e-06,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 16,
    "seed": 11
  }
}