{
  "best_metric": 0.6666666666666666,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-214",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1070,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.1204113960266113,
      "learning_rate": 1.1932465475413847e-05,
      "loss": 0.4261,
      "step": 214
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_f1": 0.0,
      "eval_loss": 0.4023595452308655,
      "eval_mcc": 0.0,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 3.137,
      "eval_samples_per_second": 544.145,
      "eval_steps_per_second": 17.214,
      "step": 214
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9375726580619812,
      "learning_rate": 8.949349106560385e-06,
      "loss": 0.4016,
      "step": 428
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_f1": 0.0,
      "eval_loss": 0.3956427276134491,
      "eval_mcc": 0.0,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 3.1414,
      "eval_samples_per_second": 543.38,
      "eval_steps_per_second": 17.19,
      "step": 428
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.8432106971740723,
      "learning_rate": 5.966232737706924e-06,
      "loss": 0.3966,
      "step": 642
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_f1": 0.0,
      "eval_loss": 0.3900800049304962,
      "eval_mcc": 0.0,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 3.1509,
      "eval_samples_per_second": 541.745,
      "eval_steps_per_second": 17.138,
      "step": 642
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.893604040145874,
      "learning_rate": 2.983116368853462e-06,
      "loss": 0.392,
      "step": 856
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_f1": 0.0,
      "eval_loss": 0.3844773471355438,
      "eval_mcc": 0.0,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 3.1529,
      "eval_samples_per_second": 541.412,
      "eval_steps_per_second": 17.127,
      "step": 856
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.7249462604522705,
      "learning_rate": 0.0,
      "loss": 0.3883,
      "step": 1070
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_f1": 0.0,
      "eval_loss": 0.3832436501979828,
      "eval_mcc": 0.0,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 3.1455,
      "eval_samples_per_second": 542.682,
      "eval_steps_per_second": 17.167,
      "step": 1070
    }
  ],
  "logging_steps": 500,
  "max_steps": 1070,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 2623878322200.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.6118639206182097,
    "learning_rate": 1.4915581844267308e-05,
    "num_train_epochs": 5,
    "temperature": 15
  }
}