{
  "best_metric": 0.7375512595196251,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-428",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 428,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 4.634866237640381,
      "learning_rate": 0.00022230485769079655,
      "loss": 0.4904,
      "step": 214
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7223198594024605,
      "eval_f1": 0.4261501210653753,
      "eval_loss": 0.456611692905426,
      "eval_mcc": 0.31390897314151045,
      "eval_precision": 0.6848249027237354,
      "eval_recall": 0.3093145869947276,
      "eval_runtime": 3.1485,
      "eval_samples_per_second": 542.168,
      "eval_steps_per_second": 17.151,
      "step": 214
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.5362380743026733,
      "learning_rate": 0.000194516750479447,
      "loss": 0.4471,
      "step": 428
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7375512595196251,
      "eval_f1": 0.4628297362110312,
      "eval_loss": 0.44590938091278076,
      "eval_mcc": 0.3591774667498448,
      "eval_precision": 0.7283018867924528,
      "eval_recall": 0.3391915641476274,
      "eval_runtime": 3.1481,
      "eval_samples_per_second": 542.232,
      "eval_steps_per_second": 17.153,
      "step": 428
    }
  ],
  "logging_steps": 500,
  "max_steps": 1926,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "total_flos": 1049551328880.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.7932456774257669,
    "learning_rate": 0.00025009296490214613,
    "num_train_epochs": 9,
    "temperature": 23
  }
}