{
  "best_metric": 0.5108910891089109,
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-297",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2673,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.3744499087333679,
      "learning_rate": 1.7212091585793122e-05,
      "loss": 0.1576,
      "step": 297
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5108910891089109,
      "eval_f1": 0.127208480565371,
      "eval_loss": 0.13107798993587494,
      "eval_mcc": 0.04175421326407947,
      "eval_precision": 0.5806451612903226,
      "eval_recall": 0.07142857142857142,
      "eval_runtime": 0.9746,
      "eval_samples_per_second": 518.155,
      "eval_steps_per_second": 16.417,
      "step": 297
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2569155693054199,
      "learning_rate": 1.5060580137568982e-05,
      "loss": 0.1312,
      "step": 594
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5089108910891089,
      "eval_f1": 0.1205673758865248,
      "eval_loss": 0.12648388743400574,
      "eval_mcc": 0.03400602754322123,
      "eval_precision": 0.5666666666666667,
      "eval_recall": 0.06746031746031746,
      "eval_runtime": 0.9581,
      "eval_samples_per_second": 527.09,
      "eval_steps_per_second": 16.7,
      "step": 594
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3201127350330353,
      "learning_rate": 1.2909068689344842e-05,
      "loss": 0.129,
      "step": 891
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5089108910891089,
      "eval_f1": 0.1205673758865248,
      "eval_loss": 0.12576302886009216,
      "eval_mcc": 0.03400602754322123,
      "eval_precision": 0.5666666666666667,
      "eval_recall": 0.06746031746031746,
      "eval_runtime": 0.9394,
      "eval_samples_per_second": 537.563,
      "eval_steps_per_second": 17.032,
      "step": 891
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.31637096405029297,
      "learning_rate": 1.0757557241120703e-05,
      "loss": 0.1288,
      "step": 1188
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5089108910891089,
      "eval_f1": 0.1205673758865248,
      "eval_loss": 0.12486182153224945,
      "eval_mcc": 0.03400602754322123,
      "eval_precision": 0.5666666666666667,
      "eval_recall": 0.06746031746031746,
      "eval_runtime": 0.9225,
      "eval_samples_per_second": 547.443,
      "eval_steps_per_second": 17.345,
      "step": 1188
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.29955437779426575,
      "learning_rate": 8.606045792896561e-06,
      "loss": 0.1283,
      "step": 1485
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5089108910891089,
      "eval_f1": 0.1205673758865248,
      "eval_loss": 0.12472035735845566,
      "eval_mcc": 0.03400602754322123,
      "eval_precision": 0.5666666666666667,
      "eval_recall": 0.06746031746031746,
      "eval_runtime": 0.9304,
      "eval_samples_per_second": 542.772,
      "eval_steps_per_second": 17.197,
      "step": 1485
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.1616370677947998,
      "learning_rate": 6.454534344672421e-06,
      "loss": 0.1281,
      "step": 1782
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5069306930693069,
      "eval_f1": 0.11387900355871884,
      "eval_loss": 0.1247602105140686,
      "eval_mcc": 0.026022816184950434,
      "eval_precision": 0.5517241379310345,
      "eval_recall": 0.06349206349206349,
      "eval_runtime": 0.9404,
      "eval_samples_per_second": 536.994,
      "eval_steps_per_second": 17.014,
      "step": 1782
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.278909295797348,
      "learning_rate": 4.3030228964482805e-06,
      "loss": 0.1278,
      "step": 2079
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5069306930693069,
      "eval_f1": 0.11387900355871884,
      "eval_loss": 0.1246904581785202,
      "eval_mcc": 0.026022816184950434,
      "eval_precision": 0.5517241379310345,
      "eval_recall": 0.06349206349206349,
      "eval_runtime": 0.93,
      "eval_samples_per_second": 542.997,
      "eval_steps_per_second": 17.204,
      "step": 2079
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.24578748643398285,
      "learning_rate": 2.1515114482241403e-06,
      "loss": 0.1275,
      "step": 2376
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5069306930693069,
      "eval_f1": 0.11387900355871884,
      "eval_loss": 0.12453501671552658,
      "eval_mcc": 0.026022816184950434,
      "eval_precision": 0.5517241379310345,
      "eval_recall": 0.06349206349206349,
      "eval_runtime": 0.9337,
      "eval_samples_per_second": 540.841,
      "eval_steps_per_second": 17.136,
      "step": 2376
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.35805246233940125,
      "learning_rate": 0.0,
      "loss": 0.1277,
      "step": 2673
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.5069306930693069,
      "eval_f1": 0.11387900355871884,
      "eval_loss": 0.12456101179122925,
      "eval_mcc": 0.026022816184950434,
      "eval_precision": 0.5517241379310345,
      "eval_recall": 0.06349206349206349,
      "eval_runtime": 0.9241,
      "eval_samples_per_second": 546.48,
      "eval_steps_per_second": 17.314,
      "step": 2673
    }
  ],
  "logging_steps": 500,
  "max_steps": 2673,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "total_flos": 6576311393820.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.14400624333141754,
    "learning_rate": 1.9363603034017264e-05,
    "num_train_epochs": 9,
    "temperature": 24
  }
}