{
  "best_metric": 0.8131115459882583,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/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": 2.648221731185913,
      "learning_rate": 0.0001778537404863438,
      "loss": 0.5789,
      "step": 96
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7700587084148728,
      "eval_f1": 0.8049792531120332,
      "eval_loss": 0.47850364446640015,
      "eval_precision": 0.6988472622478387,
      "eval_recall": 0.949119373776908,
      "eval_runtime": 31.8773,
      "eval_samples_per_second": 32.06,
      "eval_steps_per_second": 1.004,
      "step": 96
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.695119857788086,
      "learning_rate": 0.0001482114504052865,
      "loss": 0.4663,
      "step": 192
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8131115459882583,
      "eval_f1": 0.8323090430201932,
      "eval_loss": 0.42822203040122986,
      "eval_precision": 0.7547770700636943,
      "eval_recall": 0.9275929549902152,
      "eval_runtime": 31.0929,
      "eval_samples_per_second": 32.869,
      "eval_steps_per_second": 1.029,
      "step": 192
    }
  ],
  "logging_steps": 500,
  "max_steps": 672,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 471390394560.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9489576625421504,
    "learning_rate": 0.00020749603056740112,
    "num_train_epochs": 7,
    "temperature": 28
  }
}