{
  "best_metric": 0.6988037147804187,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-14292",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 14292,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.0594383478164673,
      "learning_rate": 8.902447569795288e-05,
      "loss": 0.5725,
      "step": 1588
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6804659216118369,
      "eval_f1": 0.3575949367088608,
      "eval_loss": 0.5597381591796875,
      "eval_mcc": 0.19612047304332003,
      "eval_precision": 0.5419664268585132,
      "eval_recall": 0.2668240850059032,
      "eval_runtime": 23.4624,
      "eval_samples_per_second": 541.547,
      "eval_steps_per_second": 16.963,
      "step": 1588
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.540066123008728,
      "learning_rate": 7.789641623570877e-05,
      "loss": 0.5555,
      "step": 3176
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6874704863843853,
      "eval_f1": 0.2603836841124977,
      "eval_loss": 0.5536655783653259,
      "eval_mcc": 0.18799631789309962,
      "eval_precision": 0.6164021164021164,
      "eval_recall": 0.16505312868949232,
      "eval_runtime": 23.2494,
      "eval_samples_per_second": 546.509,
      "eval_steps_per_second": 17.119,
      "step": 3176
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.06575608253479,
      "learning_rate": 6.676835677346465e-05,
      "loss": 0.5493,
      "step": 4764
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6873130804344404,
      "eval_f1": 0.267379679144385,
      "eval_loss": 0.5435917377471924,
      "eval_mcc": 0.18869269284566614,
      "eval_precision": 0.6102693602693603,
      "eval_recall": 0.17119244391971664,
      "eval_runtime": 23.3586,
      "eval_samples_per_second": 543.954,
      "eval_steps_per_second": 17.039,
      "step": 4764
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.0746259689331055,
      "learning_rate": 5.564029731122055e-05,
      "loss": 0.543,
      "step": 6352
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6910908232331182,
      "eval_f1": 0.36064505619807785,
      "eval_loss": 0.5372793674468994,
      "eval_mcc": 0.22096514058006989,
      "eval_precision": 0.5814075630252101,
      "eval_recall": 0.2613931523022432,
      "eval_runtime": 23.311,
      "eval_samples_per_second": 545.065,
      "eval_steps_per_second": 17.073,
      "step": 6352
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.557748794555664,
      "learning_rate": 4.451223784897644e-05,
      "loss": 0.5374,
      "step": 7940
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6961278136313552,
      "eval_f1": 0.36839522329461794,
      "eval_loss": 0.5319377183914185,
      "eval_mcc": 0.23523702656150358,
      "eval_precision": 0.5995740149094781,
      "eval_recall": 0.26587957497048403,
      "eval_runtime": 23.5602,
      "eval_samples_per_second": 539.299,
      "eval_steps_per_second": 16.893,
      "step": 7940
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.728196620941162,
      "learning_rate": 3.3384178386732324e-05,
      "loss": 0.5341,
      "step": 9528
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6946324571068786,
      "eval_f1": 0.42279083606069623,
      "eval_loss": 0.5333712100982666,
      "eval_mcc": 0.2491393222028609,
      "eval_precision": 0.5713711298753519,
      "eval_recall": 0.33553719008264465,
      "eval_runtime": 23.3995,
      "eval_samples_per_second": 543.002,
      "eval_steps_per_second": 17.009,
      "step": 9528
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.6901352405548096,
      "learning_rate": 2.225611892448822e-05,
      "loss": 0.5312,
      "step": 11116
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6938454273571542,
      "eval_f1": 0.4832624867162594,
      "eval_loss": 0.5355043411254883,
      "eval_mcc": 0.27487985905109846,
      "eval_precision": 0.552383844518676,
      "eval_recall": 0.4295159386068477,
      "eval_runtime": 23.5503,
      "eval_samples_per_second": 539.525,
      "eval_steps_per_second": 16.9,
      "step": 11116
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.672201156616211,
      "learning_rate": 1.112805946224411e-05,
      "loss": 0.5288,
      "step": 12704
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6979379820557217,
      "eval_f1": 0.42613636363636365,
      "eval_loss": 0.5302781462669373,
      "eval_mcc": 0.2569293292783036,
      "eval_precision": 0.5809213208316347,
      "eval_recall": 0.3364817001180638,
      "eval_runtime": 23.502,
      "eval_samples_per_second": 540.634,
      "eval_steps_per_second": 16.935,
      "step": 12704
    },
    {
      "epoch": 9.0,
      "grad_norm": 1.6605579853057861,
      "learning_rate": 0.0,
      "loss": 0.5269,
      "step": 14292
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.6988037147804187,
      "eval_f1": 0.4386093589555523,
      "eval_loss": 0.5291692018508911,
      "eval_mcc": 0.2632234170463615,
      "eval_precision": 0.5790085205267235,
      "eval_recall": 0.3530106257378985,
      "eval_runtime": 23.2847,
      "eval_samples_per_second": 545.68,
      "eval_steps_per_second": 17.093,
      "step": 14292
    }
  ],
  "logging_steps": 500,
  "max_steps": 14292,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "total_flos": 35180046686700.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9165014388792823,
    "learning_rate": 0.00010015253516019699,
    "num_train_epochs": 9,
    "temperature": 13
  }
}