{
  "best_metric": 0.8062622309197651,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-27/checkpoint-192",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 192,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.020627737045288,
      "learning_rate": 0.00020460634625664984,
      "loss": 0.494,
      "step": 96
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7886497064579256,
      "eval_f1": 0.8032786885245903,
      "eval_loss": 0.4278793931007385,
      "eval_precision": 0.7512776831345827,
      "eval_recall": 0.863013698630137,
      "eval_runtime": 24.9337,
      "eval_samples_per_second": 40.989,
      "eval_steps_per_second": 1.283,
      "step": 96
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.554121732711792,
      "learning_rate": 0.00017903055297456864,
      "loss": 0.4258,
      "step": 192
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8062622309197651,
      "eval_f1": 0.8241563055062168,
      "eval_loss": 0.40374234318733215,
      "eval_precision": 0.7544715447154472,
      "eval_recall": 0.9080234833659491,
      "eval_runtime": 25.4225,
      "eval_samples_per_second": 40.201,
      "eval_steps_per_second": 1.259,
      "step": 192
    }
  ],
  "logging_steps": 500,
  "max_steps": 864,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "total_flos": 471390394560.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.718256826807231,
    "learning_rate": 0.0002301821395387311,
    "num_train_epochs": 9,
    "temperature": 6
  }
}