{
  "best_metric": 0.7994034079615475,
  "best_model_checkpoint": "hf-importance-production/checkpoint-674",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 674,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02967359050445104,
      "grad_norm": 168.60842895507812,
      "learning_rate": 2.9761904761904765e-07,
      "loss": 1.824,
      "step": 10
    },
    {
      "epoch": 0.05934718100890208,
      "grad_norm": 197.9370574951172,
      "learning_rate": 5.952380952380953e-07,
      "loss": 1.9581,
      "step": 20
    },
    {
      "epoch": 0.08902077151335312,
      "grad_norm": 18.61470603942871,
      "learning_rate": 8.928571428571429e-07,
      "loss": 1.3577,
      "step": 30
    },
    {
      "epoch": 0.11869436201780416,
      "grad_norm": 171.209228515625,
      "learning_rate": 1.1904761904761906e-06,
      "loss": 1.5439,
      "step": 40
    },
    {
      "epoch": 0.14836795252225518,
      "grad_norm": 30.70751953125,
      "learning_rate": 1.4880952380952381e-06,
      "loss": 0.935,
      "step": 50
    },
    {
      "epoch": 0.17804154302670624,
      "grad_norm": 1.3179957866668701,
      "learning_rate": 1.7857142857142859e-06,
      "loss": 0.863,
      "step": 60
    },
    {
      "epoch": 0.20771513353115728,
      "grad_norm": 46.17071533203125,
      "learning_rate": 2.0833333333333334e-06,
      "loss": 0.9118,
      "step": 70
    },
    {
      "epoch": 0.23738872403560832,
      "grad_norm": 136.59942626953125,
      "learning_rate": 2.380952380952381e-06,
      "loss": 1.3016,
      "step": 80
    },
    {
      "epoch": 0.26706231454005935,
      "grad_norm": 164.12306213378906,
      "learning_rate": 2.6785714285714285e-06,
      "loss": 1.3362,
      "step": 90
    },
    {
      "epoch": 0.29673590504451036,
      "grad_norm": 72.49063110351562,
      "learning_rate": 2.9761904761904763e-06,
      "loss": 0.7472,
      "step": 100
    },
    {
      "epoch": 0.3264094955489614,
      "grad_norm": 63.815528869628906,
      "learning_rate": 3.273809523809524e-06,
      "loss": 0.5805,
      "step": 110
    },
    {
      "epoch": 0.3560830860534125,
      "grad_norm": 97.9521255493164,
      "learning_rate": 3.5714285714285718e-06,
      "loss": 0.6095,
      "step": 120
    },
    {
      "epoch": 0.3857566765578635,
      "grad_norm": 46.075660705566406,
      "learning_rate": 3.869047619047619e-06,
      "loss": 0.9813,
      "step": 130
    },
    {
      "epoch": 0.41543026706231456,
      "grad_norm": 56.08775329589844,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.8756,
      "step": 140
    },
    {
      "epoch": 0.44510385756676557,
      "grad_norm": 41.81604766845703,
      "learning_rate": 4.464285714285715e-06,
      "loss": 1.0463,
      "step": 150
    },
    {
      "epoch": 0.47477744807121663,
      "grad_norm": 42.02016067504883,
      "learning_rate": 4.761904761904762e-06,
      "loss": 1.1095,
      "step": 160
    },
    {
      "epoch": 0.5044510385756676,
      "grad_norm": 92.67354583740234,
      "learning_rate": 5.05952380952381e-06,
      "loss": 1.0643,
      "step": 170
    },
    {
      "epoch": 0.5341246290801187,
      "grad_norm": 92.83062744140625,
      "learning_rate": 5.357142857142857e-06,
      "loss": 0.6986,
      "step": 180
    },
    {
      "epoch": 0.5637982195845698,
      "grad_norm": 37.39644241333008,
      "learning_rate": 5.654761904761905e-06,
      "loss": 1.1433,
      "step": 190
    },
    {
      "epoch": 0.5934718100890207,
      "grad_norm": 50.91009521484375,
      "learning_rate": 5.9523809523809525e-06,
      "loss": 0.7077,
      "step": 200
    },
    {
      "epoch": 0.6231454005934718,
      "grad_norm": 38.2639045715332,
      "learning_rate": 6.25e-06,
      "loss": 0.7619,
      "step": 210
    },
    {
      "epoch": 0.6528189910979229,
      "grad_norm": 2.9356582164764404,
      "learning_rate": 6.547619047619048e-06,
      "loss": 0.4398,
      "step": 220
    },
    {
      "epoch": 0.6824925816023739,
      "grad_norm": 49.96760940551758,
      "learning_rate": 6.845238095238096e-06,
      "loss": 1.1917,
      "step": 230
    },
    {
      "epoch": 0.712166172106825,
      "grad_norm": 73.6959228515625,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 0.4473,
      "step": 240
    },
    {
      "epoch": 0.7418397626112759,
      "grad_norm": 52.25584411621094,
      "learning_rate": 7.440476190476191e-06,
      "loss": 1.3084,
      "step": 250
    },
    {
      "epoch": 0.771513353115727,
      "grad_norm": 66.60286712646484,
      "learning_rate": 7.738095238095238e-06,
      "loss": 0.9924,
      "step": 260
    },
    {
      "epoch": 0.8011869436201781,
      "grad_norm": 61.88084411621094,
      "learning_rate": 8.035714285714286e-06,
      "loss": 0.9188,
      "step": 270
    },
    {
      "epoch": 0.8308605341246291,
      "grad_norm": 32.82881546020508,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.5267,
      "step": 280
    },
    {
      "epoch": 0.8605341246290801,
      "grad_norm": 50.554412841796875,
      "learning_rate": 8.630952380952381e-06,
      "loss": 0.8353,
      "step": 290
    },
    {
      "epoch": 0.8902077151335311,
      "grad_norm": 74.67025756835938,
      "learning_rate": 8.92857142857143e-06,
      "loss": 0.7204,
      "step": 300
    },
    {
      "epoch": 0.9198813056379822,
      "grad_norm": 73.39923095703125,
      "learning_rate": 9.226190476190477e-06,
      "loss": 1.5639,
      "step": 310
    },
    {
      "epoch": 0.9495548961424333,
      "grad_norm": 43.86273193359375,
      "learning_rate": 9.523809523809525e-06,
      "loss": 0.6084,
      "step": 320
    },
    {
      "epoch": 0.9792284866468842,
      "grad_norm": 60.18267822265625,
      "learning_rate": 9.821428571428573e-06,
      "loss": 0.8311,
      "step": 330
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.72,
      "eval_f1": 0.6758345853065657,
      "eval_f1_macro": 0.5593865060621974,
      "eval_loss": 1.2557945251464844,
      "eval_precision": 0.7713116348671903,
      "eval_precision_macro": 0.7813692480359148,
      "eval_recall": 0.72,
      "eval_recall_macro": 0.5248060178139268,
      "eval_runtime": 247.1233,
      "eval_samples_per_second": 1.821,
      "eval_steps_per_second": 0.457,
      "step": 337
    },
    {
      "epoch": 1.0089020771513353,
      "grad_norm": 86.58915710449219,
      "learning_rate": 9.88165680473373e-06,
      "loss": 0.9621,
      "step": 340
    },
    {
      "epoch": 1.0385756676557865,
      "grad_norm": 46.461692810058594,
      "learning_rate": 9.585798816568049e-06,
      "loss": 0.5792,
      "step": 350
    },
    {
      "epoch": 1.0682492581602374,
      "grad_norm": 49.093719482421875,
      "learning_rate": 9.289940828402368e-06,
      "loss": 0.6038,
      "step": 360
    },
    {
      "epoch": 1.0979228486646884,
      "grad_norm": 43.62152862548828,
      "learning_rate": 8.994082840236687e-06,
      "loss": 0.6391,
      "step": 370
    },
    {
      "epoch": 1.1275964391691395,
      "grad_norm": 14.27550983428955,
      "learning_rate": 8.698224852071006e-06,
      "loss": 0.573,
      "step": 380
    },
    {
      "epoch": 1.1572700296735905,
      "grad_norm": 67.1692123413086,
      "learning_rate": 8.402366863905327e-06,
      "loss": 0.409,
      "step": 390
    },
    {
      "epoch": 1.1869436201780414,
      "grad_norm": 43.99798583984375,
      "learning_rate": 8.106508875739646e-06,
      "loss": 0.4652,
      "step": 400
    },
    {
      "epoch": 1.2166172106824926,
      "grad_norm": 29.33543586730957,
      "learning_rate": 7.810650887573965e-06,
      "loss": 0.2783,
      "step": 410
    },
    {
      "epoch": 1.2462908011869436,
      "grad_norm": 61.13819885253906,
      "learning_rate": 7.5147928994082845e-06,
      "loss": 0.8814,
      "step": 420
    },
    {
      "epoch": 1.2759643916913945,
      "grad_norm": 37.44241714477539,
      "learning_rate": 7.218934911242604e-06,
      "loss": 0.4763,
      "step": 430
    },
    {
      "epoch": 1.3056379821958457,
      "grad_norm": 58.24061965942383,
      "learning_rate": 6.923076923076923e-06,
      "loss": 0.9232,
      "step": 440
    },
    {
      "epoch": 1.3353115727002967,
      "grad_norm": 0.6983101963996887,
      "learning_rate": 6.627218934911244e-06,
      "loss": 0.3548,
      "step": 450
    },
    {
      "epoch": 1.3649851632047478,
      "grad_norm": 81.1714096069336,
      "learning_rate": 6.331360946745563e-06,
      "loss": 1.1273,
      "step": 460
    },
    {
      "epoch": 1.3946587537091988,
      "grad_norm": 9.78393840789795,
      "learning_rate": 6.035502958579882e-06,
      "loss": 0.5734,
      "step": 470
    },
    {
      "epoch": 1.4243323442136497,
      "grad_norm": 3.354196071624756,
      "learning_rate": 5.739644970414202e-06,
      "loss": 0.4616,
      "step": 480
    },
    {
      "epoch": 1.454005934718101,
      "grad_norm": 30.13648796081543,
      "learning_rate": 5.443786982248521e-06,
      "loss": 1.4066,
      "step": 490
    },
    {
      "epoch": 1.4836795252225519,
      "grad_norm": 56.0758056640625,
      "learning_rate": 5.14792899408284e-06,
      "loss": 0.5536,
      "step": 500
    },
    {
      "epoch": 1.513353115727003,
      "grad_norm": 41.43285369873047,
      "learning_rate": 4.85207100591716e-06,
      "loss": 0.3679,
      "step": 510
    },
    {
      "epoch": 1.543026706231454,
      "grad_norm": 45.90950012207031,
      "learning_rate": 4.55621301775148e-06,
      "loss": 0.4564,
      "step": 520
    },
    {
      "epoch": 1.572700296735905,
      "grad_norm": 75.42010498046875,
      "learning_rate": 4.2603550295858e-06,
      "loss": 0.6049,
      "step": 530
    },
    {
      "epoch": 1.6023738872403561,
      "grad_norm": 115.4093246459961,
      "learning_rate": 3.964497041420119e-06,
      "loss": 0.4721,
      "step": 540
    },
    {
      "epoch": 1.632047477744807,
      "grad_norm": 105.15296936035156,
      "learning_rate": 3.668639053254438e-06,
      "loss": 0.5965,
      "step": 550
    },
    {
      "epoch": 1.6617210682492582,
      "grad_norm": 28.678022384643555,
      "learning_rate": 3.3727810650887576e-06,
      "loss": 0.629,
      "step": 560
    },
    {
      "epoch": 1.6913946587537092,
      "grad_norm": 8.347318649291992,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 0.8679,
      "step": 570
    },
    {
      "epoch": 1.7210682492581602,
      "grad_norm": 78.90312194824219,
      "learning_rate": 2.7810650887573965e-06,
      "loss": 0.6902,
      "step": 580
    },
    {
      "epoch": 1.7507418397626113,
      "grad_norm": 58.25022506713867,
      "learning_rate": 2.485207100591716e-06,
      "loss": 0.2924,
      "step": 590
    },
    {
      "epoch": 1.7804154302670623,
      "grad_norm": 6.382408618927002,
      "learning_rate": 2.1893491124260358e-06,
      "loss": 0.5099,
      "step": 600
    },
    {
      "epoch": 1.8100890207715135,
      "grad_norm": 42.28348159790039,
      "learning_rate": 1.8934911242603552e-06,
      "loss": 0.2495,
      "step": 610
    },
    {
      "epoch": 1.8397626112759644,
      "grad_norm": 53.895606994628906,
      "learning_rate": 1.5976331360946749e-06,
      "loss": 0.3869,
      "step": 620
    },
    {
      "epoch": 1.8694362017804154,
      "grad_norm": 19.67365074157715,
      "learning_rate": 1.301775147928994e-06,
      "loss": 0.4416,
      "step": 630
    },
    {
      "epoch": 1.8991097922848663,
      "grad_norm": 6.208206653594971,
      "learning_rate": 1.0059171597633138e-06,
      "loss": 0.2573,
      "step": 640
    },
    {
      "epoch": 1.9287833827893175,
      "grad_norm": 76.81669616699219,
      "learning_rate": 7.100591715976332e-07,
      "loss": 0.9684,
      "step": 650
    },
    {
      "epoch": 1.9584569732937687,
      "grad_norm": 70.443115234375,
      "learning_rate": 4.1420118343195276e-07,
      "loss": 0.7257,
      "step": 660
    },
    {
      "epoch": 1.9881305637982196,
      "grad_norm": 18.408775329589844,
      "learning_rate": 1.183431952662722e-07,
      "loss": 0.4501,
      "step": 670
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8044444444444444,
      "eval_f1": 0.7994034079615475,
      "eval_f1_macro": 0.7226974575811784,
      "eval_loss": 0.6364149451255798,
      "eval_precision": 0.7989471347051534,
      "eval_precision_macro": 0.7605190105677089,
      "eval_recall": 0.8044444444444444,
      "eval_recall_macro": 0.697208985138428,
      "eval_runtime": 247.0192,
      "eval_samples_per_second": 1.822,
      "eval_steps_per_second": 0.457,
      "step": 674
    }
  ],
  "logging_steps": 10,
  "max_steps": 674,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 708827547359232.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}