{
  "best_metric": 0.8722264728385616,
  "best_model_checkpoint": "distilbert-base-multilingual-cased-aoe-hyper/run-3/checkpoint-328",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 328,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 1.4140416383743286,
      "learning_rate": 9.720486892282597e-06,
      "loss": 0.5947,
      "step": 10
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.7245877981185913,
      "learning_rate": 9.477474719975531e-06,
      "loss": 0.5154,
      "step": 20
    },
    {
      "epoch": 0.36585365853658536,
      "grad_norm": 0.9261638522148132,
      "learning_rate": 9.234462547668467e-06,
      "loss": 0.479,
      "step": 30
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 1.6241005659103394,
      "learning_rate": 8.991450375361402e-06,
      "loss": 0.4377,
      "step": 40
    },
    {
      "epoch": 0.6097560975609756,
      "grad_norm": 1.7590631246566772,
      "learning_rate": 8.748438203054338e-06,
      "loss": 0.4112,
      "step": 50
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 2.0623185634613037,
      "learning_rate": 8.505426030747272e-06,
      "loss": 0.3754,
      "step": 60
    },
    {
      "epoch": 0.8536585365853658,
      "grad_norm": 1.2114999294281006,
      "learning_rate": 8.262413858440207e-06,
      "loss": 0.3731,
      "step": 70
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 1.9598636627197266,
      "learning_rate": 8.019401686133143e-06,
      "loss": 0.3791,
      "step": 80
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8607498087222647,
      "eval_f1": 0.7225609756097561,
      "eval_loss": 0.33913305401802063,
      "eval_precision": 0.688953488372093,
      "eval_recall": 0.7596153846153846,
      "eval_runtime": 4.8898,
      "eval_samples_per_second": 267.29,
      "eval_steps_per_second": 16.77,
      "step": 82
    },
    {
      "epoch": 1.0975609756097562,
      "grad_norm": 1.7537786960601807,
      "learning_rate": 7.776389513826078e-06,
      "loss": 0.3125,
      "step": 90
    },
    {
      "epoch": 1.2195121951219512,
      "grad_norm": 4.089900493621826,
      "learning_rate": 7.533377341519012e-06,
      "loss": 0.332,
      "step": 100
    },
    {
      "epoch": 1.3414634146341464,
      "grad_norm": 1.488580346107483,
      "learning_rate": 7.290365169211947e-06,
      "loss": 0.286,
      "step": 110
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 1.6245107650756836,
      "learning_rate": 7.0473529969048826e-06,
      "loss": 0.2952,
      "step": 120
    },
    {
      "epoch": 1.5853658536585367,
      "grad_norm": 2.5228676795959473,
      "learning_rate": 6.804340824597818e-06,
      "loss": 0.2956,
      "step": 130
    },
    {
      "epoch": 1.7073170731707317,
      "grad_norm": 5.439332008361816,
      "learning_rate": 6.561328652290753e-06,
      "loss": 0.2699,
      "step": 140
    },
    {
      "epoch": 1.8292682926829267,
      "grad_norm": 6.190291404724121,
      "learning_rate": 6.318316479983688e-06,
      "loss": 0.2851,
      "step": 150
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 2.851015567779541,
      "learning_rate": 6.075304307676622e-06,
      "loss": 0.2729,
      "step": 160
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8684009181331293,
      "eval_f1": 0.7329192546583851,
      "eval_loss": 0.29830601811408997,
      "eval_precision": 0.7108433734939759,
      "eval_recall": 0.7564102564102564,
      "eval_runtime": 4.8964,
      "eval_samples_per_second": 266.931,
      "eval_steps_per_second": 16.747,
      "step": 164
    },
    {
      "epoch": 2.073170731707317,
      "grad_norm": 1.8465652465820312,
      "learning_rate": 5.832292135369558e-06,
      "loss": 0.2559,
      "step": 170
    },
    {
      "epoch": 2.1951219512195124,
      "grad_norm": 1.781294822692871,
      "learning_rate": 5.5892799630624935e-06,
      "loss": 0.2523,
      "step": 180
    },
    {
      "epoch": 2.317073170731707,
      "grad_norm": 4.9645256996154785,
      "learning_rate": 5.346267790755428e-06,
      "loss": 0.2737,
      "step": 190
    },
    {
      "epoch": 2.4390243902439024,
      "grad_norm": 2.3662397861480713,
      "learning_rate": 5.103255618448363e-06,
      "loss": 0.2607,
      "step": 200
    },
    {
      "epoch": 2.5609756097560976,
      "grad_norm": 3.443523645401001,
      "learning_rate": 4.8602434461412986e-06,
      "loss": 0.2301,
      "step": 210
    },
    {
      "epoch": 2.682926829268293,
      "grad_norm": 4.988992691040039,
      "learning_rate": 4.617231273834233e-06,
      "loss": 0.2451,
      "step": 220
    },
    {
      "epoch": 2.8048780487804876,
      "grad_norm": 6.013027667999268,
      "learning_rate": 4.374219101527169e-06,
      "loss": 0.2386,
      "step": 230
    },
    {
      "epoch": 2.926829268292683,
      "grad_norm": 4.056751728057861,
      "learning_rate": 4.131206929220104e-06,
      "loss": 0.236,
      "step": 240
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8661055853098699,
      "eval_f1": 0.7422680412371134,
      "eval_loss": 0.30293241143226624,
      "eval_precision": 0.6866485013623979,
      "eval_recall": 0.8076923076923077,
      "eval_runtime": 4.9202,
      "eval_samples_per_second": 265.637,
      "eval_steps_per_second": 16.666,
      "step": 246
    },
    {
      "epoch": 3.048780487804878,
      "grad_norm": 5.498621940612793,
      "learning_rate": 3.888194756913039e-06,
      "loss": 0.2761,
      "step": 250
    },
    {
      "epoch": 3.1707317073170733,
      "grad_norm": 2.0462112426757812,
      "learning_rate": 3.6451825846059735e-06,
      "loss": 0.2074,
      "step": 260
    },
    {
      "epoch": 3.292682926829268,
      "grad_norm": 4.663333892822266,
      "learning_rate": 3.402170412298909e-06,
      "loss": 0.2357,
      "step": 270
    },
    {
      "epoch": 3.4146341463414633,
      "grad_norm": 4.013532638549805,
      "learning_rate": 3.159158239991844e-06,
      "loss": 0.2385,
      "step": 280
    },
    {
      "epoch": 3.5365853658536586,
      "grad_norm": 4.440213680267334,
      "learning_rate": 2.916146067684779e-06,
      "loss": 0.226,
      "step": 290
    },
    {
      "epoch": 3.658536585365854,
      "grad_norm": 4.662286758422852,
      "learning_rate": 2.673133895377714e-06,
      "loss": 0.2129,
      "step": 300
    },
    {
      "epoch": 3.7804878048780486,
      "grad_norm": 4.345000267028809,
      "learning_rate": 2.4301217230706493e-06,
      "loss": 0.2366,
      "step": 310
    },
    {
      "epoch": 3.902439024390244,
      "grad_norm": 2.3199422359466553,
      "learning_rate": 2.1871095507635844e-06,
      "loss": 0.2462,
      "step": 320
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8722264728385616,
      "eval_f1": 0.7481146304675717,
      "eval_loss": 0.3029697835445404,
      "eval_precision": 0.7065527065527065,
      "eval_recall": 0.7948717948717948,
      "eval_runtime": 4.8827,
      "eval_samples_per_second": 267.68,
      "eval_steps_per_second": 16.794,
      "step": 328
    }
  ],
  "logging_steps": 10,
  "max_steps": 410,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2704984280555520.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 9.963499064589662e-06,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 64,
    "seed": 9
  }
}