{
  "best_metric": 57.432241955619986,
  "best_model_checkpoint": "./whisper-small-taiwanese/checkpoint-1000",
  "epoch": 0.40024014408645187,
  "eval_steps": 1000,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010006003602161296,
      "grad_norm": 109.48521423339844,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 6.8807,
      "step": 25
    },
    {
      "epoch": 0.020012007204322592,
      "grad_norm": 42.216487884521484,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 4.497,
      "step": 50
    },
    {
      "epoch": 0.03001801080648389,
      "grad_norm": 27.714574813842773,
      "learning_rate": 3e-06,
      "loss": 2.7985,
      "step": 75
    },
    {
      "epoch": 0.040024014408645184,
      "grad_norm": 23.248937606811523,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.3833,
      "step": 100
    },
    {
      "epoch": 0.05003001801080648,
      "grad_norm": 23.658485412597656,
      "learning_rate": 5e-06,
      "loss": 2.0665,
      "step": 125
    },
    {
      "epoch": 0.06003602161296778,
      "grad_norm": 21.089982986450195,
      "learning_rate": 6e-06,
      "loss": 1.9045,
      "step": 150
    },
    {
      "epoch": 0.07004202521512908,
      "grad_norm": 18.6699275970459,
      "learning_rate": 7e-06,
      "loss": 1.6847,
      "step": 175
    },
    {
      "epoch": 0.08004802881729037,
      "grad_norm": 15.449170112609863,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.6389,
      "step": 200
    },
    {
      "epoch": 0.09005403241945167,
      "grad_norm": 17.781686782836914,
      "learning_rate": 9e-06,
      "loss": 1.5051,
      "step": 225
    },
    {
      "epoch": 0.10006003602161297,
      "grad_norm": 15.56966495513916,
      "learning_rate": 1e-05,
      "loss": 1.4749,
      "step": 250
    },
    {
      "epoch": 0.11006603962377426,
      "grad_norm": 15.92287826538086,
      "learning_rate": 9.888790035587188e-06,
      "loss": 1.4282,
      "step": 275
    },
    {
      "epoch": 0.12007204322593557,
      "grad_norm": 14.765883445739746,
      "learning_rate": 9.777580071174379e-06,
      "loss": 1.4726,
      "step": 300
    },
    {
      "epoch": 0.13007804682809687,
      "grad_norm": 14.611676216125488,
      "learning_rate": 9.666370106761567e-06,
      "loss": 1.4161,
      "step": 325
    },
    {
      "epoch": 0.14008405043025815,
      "grad_norm": 16.033353805541992,
      "learning_rate": 9.555160142348756e-06,
      "loss": 1.4788,
      "step": 350
    },
    {
      "epoch": 0.15009005403241946,
      "grad_norm": 15.476993560791016,
      "learning_rate": 9.443950177935945e-06,
      "loss": 1.3807,
      "step": 375
    },
    {
      "epoch": 0.16009605763458074,
      "grad_norm": 14.746112823486328,
      "learning_rate": 9.332740213523132e-06,
      "loss": 1.39,
      "step": 400
    },
    {
      "epoch": 0.17010206123674204,
      "grad_norm": 13.24761962890625,
      "learning_rate": 9.221530249110321e-06,
      "loss": 1.3481,
      "step": 425
    },
    {
      "epoch": 0.18010806483890335,
      "grad_norm": 14.889138221740723,
      "learning_rate": 9.110320284697509e-06,
      "loss": 1.3308,
      "step": 450
    },
    {
      "epoch": 0.19011406844106463,
      "grad_norm": 14.253582000732422,
      "learning_rate": 8.999110320284698e-06,
      "loss": 1.3334,
      "step": 475
    },
    {
      "epoch": 0.20012007204322593,
      "grad_norm": 12.704729080200195,
      "learning_rate": 8.887900355871887e-06,
      "loss": 1.2165,
      "step": 500
    },
    {
      "epoch": 0.21012607564538724,
      "grad_norm": 15.88697624206543,
      "learning_rate": 8.776690391459075e-06,
      "loss": 1.3287,
      "step": 525
    },
    {
      "epoch": 0.22013207924754852,
      "grad_norm": 14.44924259185791,
      "learning_rate": 8.665480427046264e-06,
      "loss": 1.2703,
      "step": 550
    },
    {
      "epoch": 0.23013808284970982,
      "grad_norm": 14.054677963256836,
      "learning_rate": 8.554270462633453e-06,
      "loss": 1.2672,
      "step": 575
    },
    {
      "epoch": 0.24014408645187113,
      "grad_norm": 13.702735900878906,
      "learning_rate": 8.44306049822064e-06,
      "loss": 1.2378,
      "step": 600
    },
    {
      "epoch": 0.25015009005403244,
      "grad_norm": 14.676765441894531,
      "learning_rate": 8.33185053380783e-06,
      "loss": 1.2931,
      "step": 625
    },
    {
      "epoch": 0.26015609365619374,
      "grad_norm": 13.052374839782715,
      "learning_rate": 8.220640569395019e-06,
      "loss": 1.3236,
      "step": 650
    },
    {
      "epoch": 0.270162097258355,
      "grad_norm": 13.95486068725586,
      "learning_rate": 8.109430604982206e-06,
      "loss": 1.2376,
      "step": 675
    },
    {
      "epoch": 0.2801681008605163,
      "grad_norm": 14.28099536895752,
      "learning_rate": 7.998220640569395e-06,
      "loss": 1.3243,
      "step": 700
    },
    {
      "epoch": 0.2901741044626776,
      "grad_norm": 14.832662582397461,
      "learning_rate": 7.887010676156584e-06,
      "loss": 1.2232,
      "step": 725
    },
    {
      "epoch": 0.3001801080648389,
      "grad_norm": 14.478935241699219,
      "learning_rate": 7.775800711743774e-06,
      "loss": 1.2879,
      "step": 750
    },
    {
      "epoch": 0.3101861116670002,
      "grad_norm": 16.196550369262695,
      "learning_rate": 7.664590747330961e-06,
      "loss": 1.2468,
      "step": 775
    },
    {
      "epoch": 0.32019211526916147,
      "grad_norm": 13.101941108703613,
      "learning_rate": 7.55338078291815e-06,
      "loss": 1.1145,
      "step": 800
    },
    {
      "epoch": 0.3301981188713228,
      "grad_norm": 14.249147415161133,
      "learning_rate": 7.4421708185053385e-06,
      "loss": 1.2034,
      "step": 825
    },
    {
      "epoch": 0.3402041224734841,
      "grad_norm": 15.098295211791992,
      "learning_rate": 7.330960854092527e-06,
      "loss": 1.2092,
      "step": 850
    },
    {
      "epoch": 0.3502101260756454,
      "grad_norm": 13.058671951293945,
      "learning_rate": 7.219750889679717e-06,
      "loss": 1.1856,
      "step": 875
    },
    {
      "epoch": 0.3602161296778067,
      "grad_norm": 11.38603687286377,
      "learning_rate": 7.108540925266904e-06,
      "loss": 1.2102,
      "step": 900
    },
    {
      "epoch": 0.370222133279968,
      "grad_norm": 12.42940616607666,
      "learning_rate": 6.9973309608540925e-06,
      "loss": 1.2559,
      "step": 925
    },
    {
      "epoch": 0.38022813688212925,
      "grad_norm": 14.474142074584961,
      "learning_rate": 6.886120996441281e-06,
      "loss": 1.1712,
      "step": 950
    },
    {
      "epoch": 0.39023414048429056,
      "grad_norm": 13.687834739685059,
      "learning_rate": 6.774911032028471e-06,
      "loss": 1.1358,
      "step": 975
    },
    {
      "epoch": 0.40024014408645187,
      "grad_norm": 13.932642936706543,
      "learning_rate": 6.663701067615659e-06,
      "loss": 1.2118,
      "step": 1000
    },
    {
      "epoch": 0.40024014408645187,
      "eval_cer": 57.432241955619986,
      "eval_loss": 1.1271804571151733,
      "eval_runtime": 1754.8626,
      "eval_samples_per_second": 2.261,
      "eval_steps_per_second": 0.283,
      "step": 1000
    }
  ],
  "logging_steps": 25,
  "max_steps": 2498,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "total_flos": 4.61736640512e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}