{
  "best_metric": 27.669968330975003,
  "best_model_checkpoint": "./whisper-tiny-vi-fineturn/checkpoint-2000",
  "epoch": 0.7207207207207207,
  "eval_steps": 1000,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009009009009009009,
      "grad_norm": 10.494871139526367,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.8487,
      "step": 25
    },
    {
      "epoch": 0.018018018018018018,
      "grad_norm": 10.84449291229248,
      "learning_rate": 9.800000000000001e-07,
      "loss": 0.7876,
      "step": 50
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 10.360834121704102,
      "learning_rate": 1.48e-06,
      "loss": 0.8057,
      "step": 75
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 9.328907012939453,
      "learning_rate": 1.98e-06,
      "loss": 0.7504,
      "step": 100
    },
    {
      "epoch": 0.04504504504504504,
      "grad_norm": 9.900914192199707,
      "learning_rate": 2.4800000000000004e-06,
      "loss": 0.7021,
      "step": 125
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 9.46710205078125,
      "learning_rate": 2.9800000000000003e-06,
      "loss": 0.7816,
      "step": 150
    },
    {
      "epoch": 0.06306306306306306,
      "grad_norm": 9.913366317749023,
      "learning_rate": 3.48e-06,
      "loss": 0.8077,
      "step": 175
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 13.700247764587402,
      "learning_rate": 3.980000000000001e-06,
      "loss": 0.7839,
      "step": 200
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 11.470396995544434,
      "learning_rate": 4.48e-06,
      "loss": 0.7804,
      "step": 225
    },
    {
      "epoch": 0.09009009009009009,
      "grad_norm": 11.012725830078125,
      "learning_rate": 4.980000000000001e-06,
      "loss": 0.7711,
      "step": 250
    },
    {
      "epoch": 0.0990990990990991,
      "grad_norm": 10.982479095458984,
      "learning_rate": 5.480000000000001e-06,
      "loss": 0.7393,
      "step": 275
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 10.573739051818848,
      "learning_rate": 5.98e-06,
      "loss": 0.7652,
      "step": 300
    },
    {
      "epoch": 0.11711711711711711,
      "grad_norm": 12.227848052978516,
      "learning_rate": 6.480000000000001e-06,
      "loss": 0.7491,
      "step": 325
    },
    {
      "epoch": 0.12612612612612611,
      "grad_norm": 10.227517127990723,
      "learning_rate": 6.98e-06,
      "loss": 0.7118,
      "step": 350
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 10.990806579589844,
      "learning_rate": 7.48e-06,
      "loss": 0.7254,
      "step": 375
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 10.145050048828125,
      "learning_rate": 7.980000000000002e-06,
      "loss": 0.7042,
      "step": 400
    },
    {
      "epoch": 0.15315315315315314,
      "grad_norm": 11.466766357421875,
      "learning_rate": 8.48e-06,
      "loss": 0.7292,
      "step": 425
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 10.937430381774902,
      "learning_rate": 8.98e-06,
      "loss": 0.681,
      "step": 450
    },
    {
      "epoch": 0.17117117117117117,
      "grad_norm": 10.47399616241455,
      "learning_rate": 9.48e-06,
      "loss": 0.696,
      "step": 475
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 9.956053733825684,
      "learning_rate": 9.980000000000001e-06,
      "loss": 0.6752,
      "step": 500
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 12.427406311035156,
      "learning_rate": 9.96932907348243e-06,
      "loss": 0.6816,
      "step": 525
    },
    {
      "epoch": 0.1981981981981982,
      "grad_norm": 10.781158447265625,
      "learning_rate": 9.937380191693291e-06,
      "loss": 0.6572,
      "step": 550
    },
    {
      "epoch": 0.2072072072072072,
      "grad_norm": 12.120624542236328,
      "learning_rate": 9.905431309904154e-06,
      "loss": 0.6687,
      "step": 575
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 11.765815734863281,
      "learning_rate": 9.873482428115016e-06,
      "loss": 0.6626,
      "step": 600
    },
    {
      "epoch": 0.22522522522522523,
      "grad_norm": 10.940831184387207,
      "learning_rate": 9.841533546325879e-06,
      "loss": 0.6334,
      "step": 625
    },
    {
      "epoch": 0.23423423423423423,
      "grad_norm": 11.88543701171875,
      "learning_rate": 9.809584664536742e-06,
      "loss": 0.643,
      "step": 650
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 10.71240520477295,
      "learning_rate": 9.777635782747604e-06,
      "loss": 0.6243,
      "step": 675
    },
    {
      "epoch": 0.25225225225225223,
      "grad_norm": 11.13901424407959,
      "learning_rate": 9.745686900958467e-06,
      "loss": 0.6508,
      "step": 700
    },
    {
      "epoch": 0.26126126126126126,
      "grad_norm": 10.958165168762207,
      "learning_rate": 9.71373801916933e-06,
      "loss": 0.6181,
      "step": 725
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 9.51022720336914,
      "learning_rate": 9.681789137380192e-06,
      "loss": 0.5921,
      "step": 750
    },
    {
      "epoch": 0.27927927927927926,
      "grad_norm": 9.750580787658691,
      "learning_rate": 9.649840255591055e-06,
      "loss": 0.5823,
      "step": 775
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 11.01555061340332,
      "learning_rate": 9.617891373801918e-06,
      "loss": 0.6049,
      "step": 800
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 10.571298599243164,
      "learning_rate": 9.585942492012781e-06,
      "loss": 0.5972,
      "step": 825
    },
    {
      "epoch": 0.3063063063063063,
      "grad_norm": 12.41274642944336,
      "learning_rate": 9.553993610223643e-06,
      "loss": 0.6094,
      "step": 850
    },
    {
      "epoch": 0.3153153153153153,
      "grad_norm": 9.085636138916016,
      "learning_rate": 9.522044728434506e-06,
      "loss": 0.5506,
      "step": 875
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 10.402972221374512,
      "learning_rate": 9.49009584664537e-06,
      "loss": 0.6005,
      "step": 900
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 9.706883430480957,
      "learning_rate": 9.45814696485623e-06,
      "loss": 0.5913,
      "step": 925
    },
    {
      "epoch": 0.34234234234234234,
      "grad_norm": 8.113255500793457,
      "learning_rate": 9.426198083067092e-06,
      "loss": 0.595,
      "step": 950
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 8.200972557067871,
      "learning_rate": 9.394249201277957e-06,
      "loss": 0.5817,
      "step": 975
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 11.214420318603516,
      "learning_rate": 9.362300319488819e-06,
      "loss": 0.5706,
      "step": 1000
    },
    {
      "epoch": 0.36036036036036034,
      "eval_loss": 0.5766128897666931,
      "eval_runtime": 658.086,
      "eval_samples_per_second": 2.699,
      "eval_steps_per_second": 0.337,
      "eval_wer": 32.68984569772926,
      "step": 1000
    },
    {
      "epoch": 0.36936936936936937,
      "grad_norm": 10.865961074829102,
      "learning_rate": 9.330351437699682e-06,
      "loss": 0.5844,
      "step": 1025
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 9.064363479614258,
      "learning_rate": 9.298402555910543e-06,
      "loss": 0.5815,
      "step": 1050
    },
    {
      "epoch": 0.38738738738738737,
      "grad_norm": 9.748988151550293,
      "learning_rate": 9.266453674121407e-06,
      "loss": 0.56,
      "step": 1075
    },
    {
      "epoch": 0.3963963963963964,
      "grad_norm": 10.780916213989258,
      "learning_rate": 9.23450479233227e-06,
      "loss": 0.5336,
      "step": 1100
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 9.80115795135498,
      "learning_rate": 9.202555910543131e-06,
      "loss": 0.5584,
      "step": 1125
    },
    {
      "epoch": 0.4144144144144144,
      "grad_norm": 9.904963493347168,
      "learning_rate": 9.170607028753994e-06,
      "loss": 0.5557,
      "step": 1150
    },
    {
      "epoch": 0.42342342342342343,
      "grad_norm": 9.095471382141113,
      "learning_rate": 9.138658146964858e-06,
      "loss": 0.5513,
      "step": 1175
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 12.989034652709961,
      "learning_rate": 9.106709265175719e-06,
      "loss": 0.5657,
      "step": 1200
    },
    {
      "epoch": 0.44144144144144143,
      "grad_norm": 10.82030200958252,
      "learning_rate": 9.074760383386582e-06,
      "loss": 0.5187,
      "step": 1225
    },
    {
      "epoch": 0.45045045045045046,
      "grad_norm": 9.127603530883789,
      "learning_rate": 9.042811501597446e-06,
      "loss": 0.5325,
      "step": 1250
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 8.192268371582031,
      "learning_rate": 9.010862619808307e-06,
      "loss": 0.5311,
      "step": 1275
    },
    {
      "epoch": 0.46846846846846846,
      "grad_norm": 11.229754447937012,
      "learning_rate": 8.97891373801917e-06,
      "loss": 0.5477,
      "step": 1300
    },
    {
      "epoch": 0.4774774774774775,
      "grad_norm": 10.28305721282959,
      "learning_rate": 8.946964856230033e-06,
      "loss": 0.5408,
      "step": 1325
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 11.308509826660156,
      "learning_rate": 8.915015974440895e-06,
      "loss": 0.512,
      "step": 1350
    },
    {
      "epoch": 0.4954954954954955,
      "grad_norm": 9.181129455566406,
      "learning_rate": 8.883067092651758e-06,
      "loss": 0.5217,
      "step": 1375
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 11.323354721069336,
      "learning_rate": 8.85111821086262e-06,
      "loss": 0.5382,
      "step": 1400
    },
    {
      "epoch": 0.5135135135135135,
      "grad_norm": 11.462235450744629,
      "learning_rate": 8.819169329073483e-06,
      "loss": 0.5093,
      "step": 1425
    },
    {
      "epoch": 0.5225225225225225,
      "grad_norm": 10.261285781860352,
      "learning_rate": 8.787220447284346e-06,
      "loss": 0.519,
      "step": 1450
    },
    {
      "epoch": 0.5315315315315315,
      "grad_norm": 9.729991912841797,
      "learning_rate": 8.755271565495208e-06,
      "loss": 0.5126,
      "step": 1475
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 8.688796043395996,
      "learning_rate": 8.72332268370607e-06,
      "loss": 0.5186,
      "step": 1500
    },
    {
      "epoch": 0.5495495495495496,
      "grad_norm": 9.77303695678711,
      "learning_rate": 8.691373801916934e-06,
      "loss": 0.5134,
      "step": 1525
    },
    {
      "epoch": 0.5585585585585585,
      "grad_norm": 8.375865936279297,
      "learning_rate": 8.659424920127795e-06,
      "loss": 0.5183,
      "step": 1550
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 12.362218856811523,
      "learning_rate": 8.627476038338659e-06,
      "loss": 0.513,
      "step": 1575
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 11.089631080627441,
      "learning_rate": 8.595527156549522e-06,
      "loss": 0.516,
      "step": 1600
    },
    {
      "epoch": 0.5855855855855856,
      "grad_norm": 7.185488224029541,
      "learning_rate": 8.563578274760385e-06,
      "loss": 0.5121,
      "step": 1625
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 11.619331359863281,
      "learning_rate": 8.531629392971247e-06,
      "loss": 0.5059,
      "step": 1650
    },
    {
      "epoch": 0.6036036036036037,
      "grad_norm": 9.36999797821045,
      "learning_rate": 8.49968051118211e-06,
      "loss": 0.4905,
      "step": 1675
    },
    {
      "epoch": 0.6126126126126126,
      "grad_norm": 8.326366424560547,
      "learning_rate": 8.467731629392973e-06,
      "loss": 0.5201,
      "step": 1700
    },
    {
      "epoch": 0.6216216216216216,
      "grad_norm": 10.786980628967285,
      "learning_rate": 8.435782747603835e-06,
      "loss": 0.4845,
      "step": 1725
    },
    {
      "epoch": 0.6306306306306306,
      "grad_norm": 9.193384170532227,
      "learning_rate": 8.403833865814696e-06,
      "loss": 0.4781,
      "step": 1750
    },
    {
      "epoch": 0.6396396396396397,
      "grad_norm": 18.21417808532715,
      "learning_rate": 8.37188498402556e-06,
      "loss": 0.4955,
      "step": 1775
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 9.539066314697266,
      "learning_rate": 8.339936102236422e-06,
      "loss": 0.5021,
      "step": 1800
    },
    {
      "epoch": 0.6576576576576577,
      "grad_norm": 8.467971801757812,
      "learning_rate": 8.307987220447286e-06,
      "loss": 0.4816,
      "step": 1825
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 7.224285125732422,
      "learning_rate": 8.276038338658147e-06,
      "loss": 0.4792,
      "step": 1850
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 8.476410865783691,
      "learning_rate": 8.24408945686901e-06,
      "loss": 0.4789,
      "step": 1875
    },
    {
      "epoch": 0.6846846846846847,
      "grad_norm": 9.13045597076416,
      "learning_rate": 8.212140575079874e-06,
      "loss": 0.472,
      "step": 1900
    },
    {
      "epoch": 0.6936936936936937,
      "grad_norm": 8.297953605651855,
      "learning_rate": 8.180191693290735e-06,
      "loss": 0.4782,
      "step": 1925
    },
    {
      "epoch": 0.7027027027027027,
      "grad_norm": 11.37833023071289,
      "learning_rate": 8.148242811501598e-06,
      "loss": 0.4647,
      "step": 1950
    },
    {
      "epoch": 0.7117117117117117,
      "grad_norm": 12.008112907409668,
      "learning_rate": 8.116293929712461e-06,
      "loss": 0.4855,
      "step": 1975
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 9.05832576751709,
      "learning_rate": 8.084345047923323e-06,
      "loss": 0.4946,
      "step": 2000
    },
    {
      "epoch": 0.7207207207207207,
      "eval_loss": 0.48097866773605347,
      "eval_runtime": 556.9583,
      "eval_samples_per_second": 3.189,
      "eval_steps_per_second": 0.399,
      "eval_wer": 27.669968330975003,
      "step": 2000
    }
  ],
  "logging_steps": 25,
  "max_steps": 8325,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.8780432384e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}