{
  "best_metric": 37.15599055412812,
  "best_model_checkpoint": "./whisper-small-finetuned/checkpoint-6000",
  "epoch": 1.20825,
  "eval_steps": 2000,
  "global_step": 6000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00625,
      "grad_norm": 11.4181547164917,
      "learning_rate": 4.7000000000000005e-07,
      "loss": 1.6163,
      "step": 50
    },
    {
      "epoch": 0.0125,
      "grad_norm": 7.794241428375244,
      "learning_rate": 9.7e-07,
      "loss": 1.3889,
      "step": 100
    },
    {
      "epoch": 0.01875,
      "grad_norm": 8.827476501464844,
      "learning_rate": 1.4700000000000001e-06,
      "loss": 1.2801,
      "step": 150
    },
    {
      "epoch": 0.025,
      "grad_norm": 6.476517200469971,
      "learning_rate": 1.97e-06,
      "loss": 1.2292,
      "step": 200
    },
    {
      "epoch": 0.03125,
      "grad_norm": 7.033958435058594,
      "learning_rate": 2.47e-06,
      "loss": 1.0831,
      "step": 250
    },
    {
      "epoch": 0.0375,
      "grad_norm": 6.324102401733398,
      "learning_rate": 2.97e-06,
      "loss": 1.0518,
      "step": 300
    },
    {
      "epoch": 0.04375,
      "grad_norm": 6.920722961425781,
      "learning_rate": 3.4700000000000002e-06,
      "loss": 0.9768,
      "step": 350
    },
    {
      "epoch": 0.05,
      "grad_norm": 6.655612468719482,
      "learning_rate": 3.97e-06,
      "loss": 0.9377,
      "step": 400
    },
    {
      "epoch": 0.05625,
      "grad_norm": 8.39956283569336,
      "learning_rate": 4.47e-06,
      "loss": 0.9107,
      "step": 450
    },
    {
      "epoch": 0.0625,
      "grad_norm": 6.610105514526367,
      "learning_rate": 4.970000000000001e-06,
      "loss": 0.9365,
      "step": 500
    },
    {
      "epoch": 0.06875,
      "grad_norm": 7.250374794006348,
      "learning_rate": 5.470000000000001e-06,
      "loss": 0.8301,
      "step": 550
    },
    {
      "epoch": 0.075,
      "grad_norm": 5.3105669021606445,
      "learning_rate": 5.9700000000000004e-06,
      "loss": 0.8703,
      "step": 600
    },
    {
      "epoch": 0.08125,
      "grad_norm": 5.701041221618652,
      "learning_rate": 6.470000000000001e-06,
      "loss": 0.8235,
      "step": 650
    },
    {
      "epoch": 0.0875,
      "grad_norm": 5.628653049468994,
      "learning_rate": 6.97e-06,
      "loss": 0.7949,
      "step": 700
    },
    {
      "epoch": 0.09375,
      "grad_norm": 6.777932643890381,
      "learning_rate": 7.4700000000000005e-06,
      "loss": 0.7607,
      "step": 750
    },
    {
      "epoch": 0.1,
      "grad_norm": 5.994093418121338,
      "learning_rate": 7.970000000000002e-06,
      "loss": 0.7144,
      "step": 800
    },
    {
      "epoch": 0.10625,
      "grad_norm": 7.069298267364502,
      "learning_rate": 8.47e-06,
      "loss": 0.807,
      "step": 850
    },
    {
      "epoch": 0.1125,
      "grad_norm": 4.62778902053833,
      "learning_rate": 8.97e-06,
      "loss": 0.7103,
      "step": 900
    },
    {
      "epoch": 0.11875,
      "grad_norm": 5.539309501647949,
      "learning_rate": 9.47e-06,
      "loss": 0.7273,
      "step": 950
    },
    {
      "epoch": 0.125,
      "grad_norm": 4.9156036376953125,
      "learning_rate": 9.970000000000001e-06,
      "loss": 0.6556,
      "step": 1000
    },
    {
      "epoch": 0.13125,
      "grad_norm": 5.073310375213623,
      "learning_rate": 9.932857142857145e-06,
      "loss": 0.7311,
      "step": 1050
    },
    {
      "epoch": 0.1375,
      "grad_norm": 6.0137553215026855,
      "learning_rate": 9.861428571428572e-06,
      "loss": 0.6972,
      "step": 1100
    },
    {
      "epoch": 0.14375,
      "grad_norm": 6.463374137878418,
      "learning_rate": 9.790000000000001e-06,
      "loss": 0.6923,
      "step": 1150
    },
    {
      "epoch": 0.15,
      "grad_norm": 4.6144185066223145,
      "learning_rate": 9.71857142857143e-06,
      "loss": 0.5852,
      "step": 1200
    },
    {
      "epoch": 0.15625,
      "grad_norm": 6.625977516174316,
      "learning_rate": 9.647142857142857e-06,
      "loss": 0.6973,
      "step": 1250
    },
    {
      "epoch": 0.1625,
      "grad_norm": 5.229981899261475,
      "learning_rate": 9.575714285714286e-06,
      "loss": 0.6833,
      "step": 1300
    },
    {
      "epoch": 0.16875,
      "grad_norm": 4.967216491699219,
      "learning_rate": 9.504285714285715e-06,
      "loss": 0.7299,
      "step": 1350
    },
    {
      "epoch": 0.175,
      "grad_norm": 5.4233551025390625,
      "learning_rate": 9.432857142857143e-06,
      "loss": 0.7372,
      "step": 1400
    },
    {
      "epoch": 0.18125,
      "grad_norm": 5.350655555725098,
      "learning_rate": 9.361428571428572e-06,
      "loss": 0.6854,
      "step": 1450
    },
    {
      "epoch": 0.1875,
      "grad_norm": 4.796384811401367,
      "learning_rate": 9.29e-06,
      "loss": 0.5997,
      "step": 1500
    },
    {
      "epoch": 0.19375,
      "grad_norm": 4.787758827209473,
      "learning_rate": 9.218571428571428e-06,
      "loss": 0.6864,
      "step": 1550
    },
    {
      "epoch": 0.2,
      "grad_norm": 4.423880100250244,
      "learning_rate": 9.147142857142857e-06,
      "loss": 0.6138,
      "step": 1600
    },
    {
      "epoch": 0.20625,
      "grad_norm": 4.9922895431518555,
      "learning_rate": 9.075714285714286e-06,
      "loss": 0.6438,
      "step": 1650
    },
    {
      "epoch": 0.2125,
      "grad_norm": 5.809079170227051,
      "learning_rate": 9.004285714285715e-06,
      "loss": 0.6138,
      "step": 1700
    },
    {
      "epoch": 0.21875,
      "grad_norm": 4.862271785736084,
      "learning_rate": 8.932857142857143e-06,
      "loss": 0.6552,
      "step": 1750
    },
    {
      "epoch": 0.225,
      "grad_norm": 4.329502105712891,
      "learning_rate": 8.861428571428572e-06,
      "loss": 0.6638,
      "step": 1800
    },
    {
      "epoch": 0.23125,
      "grad_norm": 4.74673318862915,
      "learning_rate": 8.79e-06,
      "loss": 0.7205,
      "step": 1850
    },
    {
      "epoch": 0.2375,
      "grad_norm": 5.6587114334106445,
      "learning_rate": 8.71857142857143e-06,
      "loss": 0.6283,
      "step": 1900
    },
    {
      "epoch": 0.24375,
      "grad_norm": 4.025678634643555,
      "learning_rate": 8.647142857142859e-06,
      "loss": 0.5727,
      "step": 1950
    },
    {
      "epoch": 0.25,
      "grad_norm": 5.050192356109619,
      "learning_rate": 8.575714285714286e-06,
      "loss": 0.67,
      "step": 2000
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.6608728766441345,
      "eval_runtime": 3982.4181,
      "eval_samples_per_second": 1.089,
      "eval_steps_per_second": 0.136,
      "eval_wer": 40.78878971053452,
      "step": 2000
    },
    {
      "epoch": 0.25625,
      "grad_norm": 5.174773216247559,
      "learning_rate": 8.504285714285715e-06,
      "loss": 0.7296,
      "step": 2050
    },
    {
      "epoch": 0.2625,
      "grad_norm": 4.204230308532715,
      "learning_rate": 8.432857142857144e-06,
      "loss": 0.6267,
      "step": 2100
    },
    {
      "epoch": 0.26875,
      "grad_norm": 4.041508674621582,
      "learning_rate": 8.361428571428573e-06,
      "loss": 0.6318,
      "step": 2150
    },
    {
      "epoch": 0.275,
      "grad_norm": 4.373353958129883,
      "learning_rate": 8.29e-06,
      "loss": 0.6095,
      "step": 2200
    },
    {
      "epoch": 0.28125,
      "grad_norm": 5.110273361206055,
      "learning_rate": 8.21857142857143e-06,
      "loss": 0.6114,
      "step": 2250
    },
    {
      "epoch": 0.2875,
      "grad_norm": 7.183779239654541,
      "learning_rate": 8.147142857142858e-06,
      "loss": 0.6142,
      "step": 2300
    },
    {
      "epoch": 0.29375,
      "grad_norm": 4.0610551834106445,
      "learning_rate": 8.075714285714287e-06,
      "loss": 0.5791,
      "step": 2350
    },
    {
      "epoch": 0.3,
      "grad_norm": 4.765223503112793,
      "learning_rate": 8.004285714285715e-06,
      "loss": 0.6245,
      "step": 2400
    },
    {
      "epoch": 0.30625,
      "grad_norm": 5.459305763244629,
      "learning_rate": 7.932857142857144e-06,
      "loss": 0.6329,
      "step": 2450
    },
    {
      "epoch": 0.3125,
      "grad_norm": 4.936705112457275,
      "learning_rate": 7.861428571428573e-06,
      "loss": 0.6021,
      "step": 2500
    },
    {
      "epoch": 0.31875,
      "grad_norm": 4.05385684967041,
      "learning_rate": 7.790000000000002e-06,
      "loss": 0.6026,
      "step": 2550
    },
    {
      "epoch": 0.325,
      "grad_norm": 4.764458179473877,
      "learning_rate": 7.72e-06,
      "loss": 0.6191,
      "step": 2600
    },
    {
      "epoch": 0.33125,
      "grad_norm": 4.8262434005737305,
      "learning_rate": 7.64857142857143e-06,
      "loss": 0.6451,
      "step": 2650
    },
    {
      "epoch": 0.3375,
      "grad_norm": 5.038938522338867,
      "learning_rate": 7.577142857142857e-06,
      "loss": 0.6515,
      "step": 2700
    },
    {
      "epoch": 0.34375,
      "grad_norm": 6.03196907043457,
      "learning_rate": 7.505714285714286e-06,
      "loss": 0.6328,
      "step": 2750
    },
    {
      "epoch": 0.35,
      "grad_norm": 4.219414710998535,
      "learning_rate": 7.434285714285715e-06,
      "loss": 0.6202,
      "step": 2800
    },
    {
      "epoch": 0.35625,
      "grad_norm": 4.451348781585693,
      "learning_rate": 7.362857142857144e-06,
      "loss": 0.6193,
      "step": 2850
    },
    {
      "epoch": 0.3625,
      "grad_norm": 4.656250953674316,
      "learning_rate": 7.291428571428571e-06,
      "loss": 0.5295,
      "step": 2900
    },
    {
      "epoch": 0.36875,
      "grad_norm": 14.434591293334961,
      "learning_rate": 7.22e-06,
      "loss": 0.6179,
      "step": 2950
    },
    {
      "epoch": 0.375,
      "grad_norm": 4.388996124267578,
      "learning_rate": 7.148571428571429e-06,
      "loss": 0.5695,
      "step": 3000
    },
    {
      "epoch": 0.38125,
      "grad_norm": 4.346401214599609,
      "learning_rate": 7.077142857142858e-06,
      "loss": 0.5755,
      "step": 3050
    },
    {
      "epoch": 0.3875,
      "grad_norm": 4.0902252197265625,
      "learning_rate": 7.0057142857142865e-06,
      "loss": 0.6107,
      "step": 3100
    },
    {
      "epoch": 0.39375,
      "grad_norm": 4.089328289031982,
      "learning_rate": 6.934285714285715e-06,
      "loss": 0.5957,
      "step": 3150
    },
    {
      "epoch": 0.4,
      "grad_norm": 5.215518951416016,
      "learning_rate": 6.862857142857144e-06,
      "loss": 0.5947,
      "step": 3200
    },
    {
      "epoch": 0.40625,
      "grad_norm": 4.511919975280762,
      "learning_rate": 6.791428571428572e-06,
      "loss": 0.6286,
      "step": 3250
    },
    {
      "epoch": 0.4125,
      "grad_norm": 4.459268569946289,
      "learning_rate": 6.720000000000001e-06,
      "loss": 0.6103,
      "step": 3300
    },
    {
      "epoch": 0.41875,
      "grad_norm": 4.5081868171691895,
      "learning_rate": 6.648571428571429e-06,
      "loss": 0.6093,
      "step": 3350
    },
    {
      "epoch": 0.425,
      "grad_norm": 5.564323425292969,
      "learning_rate": 6.577142857142857e-06,
      "loss": 0.5998,
      "step": 3400
    },
    {
      "epoch": 0.43125,
      "grad_norm": 4.530568599700928,
      "learning_rate": 6.505714285714286e-06,
      "loss": 0.5917,
      "step": 3450
    },
    {
      "epoch": 0.4375,
      "grad_norm": 5.0652079582214355,
      "learning_rate": 6.434285714285715e-06,
      "loss": 0.5956,
      "step": 3500
    },
    {
      "epoch": 0.44375,
      "grad_norm": 5.318765163421631,
      "learning_rate": 6.3628571428571426e-06,
      "loss": 0.6545,
      "step": 3550
    },
    {
      "epoch": 0.45,
      "grad_norm": 4.156691074371338,
      "learning_rate": 6.2914285714285716e-06,
      "loss": 0.6077,
      "step": 3600
    },
    {
      "epoch": 0.45625,
      "grad_norm": 4.188990116119385,
      "learning_rate": 6.220000000000001e-06,
      "loss": 0.6151,
      "step": 3650
    },
    {
      "epoch": 0.4625,
      "grad_norm": 4.593184471130371,
      "learning_rate": 6.14857142857143e-06,
      "loss": 0.6372,
      "step": 3700
    },
    {
      "epoch": 0.46875,
      "grad_norm": 6.544657230377197,
      "learning_rate": 6.077142857142858e-06,
      "loss": 0.633,
      "step": 3750
    },
    {
      "epoch": 0.475,
      "grad_norm": 4.2101521492004395,
      "learning_rate": 6.005714285714286e-06,
      "loss": 0.564,
      "step": 3800
    },
    {
      "epoch": 0.48125,
      "grad_norm": 4.94673490524292,
      "learning_rate": 5.934285714285715e-06,
      "loss": 0.631,
      "step": 3850
    },
    {
      "epoch": 0.4875,
      "grad_norm": 5.893890380859375,
      "learning_rate": 5.862857142857143e-06,
      "loss": 0.5977,
      "step": 3900
    },
    {
      "epoch": 0.49375,
      "grad_norm": 4.555218696594238,
      "learning_rate": 5.791428571428572e-06,
      "loss": 0.6037,
      "step": 3950
    },
    {
      "epoch": 0.5,
      "grad_norm": 4.622659683227539,
      "learning_rate": 5.72e-06,
      "loss": 0.6431,
      "step": 4000
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.5986924767494202,
      "eval_runtime": 3981.5379,
      "eval_samples_per_second": 1.09,
      "eval_steps_per_second": 0.136,
      "eval_wer": 40.029852519641764,
      "step": 4000
    },
    {
      "epoch": 0.50625,
      "grad_norm": 5.098015785217285,
      "learning_rate": 5.6485714285714285e-06,
      "loss": 0.6914,
      "step": 4050
    },
    {
      "epoch": 0.5125,
      "grad_norm": 5.3102312088012695,
      "learning_rate": 5.5771428571428575e-06,
      "loss": 0.6189,
      "step": 4100
    },
    {
      "epoch": 0.51875,
      "grad_norm": 4.711716651916504,
      "learning_rate": 5.5057142857142865e-06,
      "loss": 0.6726,
      "step": 4150
    },
    {
      "epoch": 0.525,
      "grad_norm": 4.459558963775635,
      "learning_rate": 5.4342857142857155e-06,
      "loss": 0.6484,
      "step": 4200
    },
    {
      "epoch": 0.53125,
      "grad_norm": 5.451053619384766,
      "learning_rate": 5.362857142857143e-06,
      "loss": 0.5951,
      "step": 4250
    },
    {
      "epoch": 0.5375,
      "grad_norm": 3.955195665359497,
      "learning_rate": 5.291428571428572e-06,
      "loss": 0.5998,
      "step": 4300
    },
    {
      "epoch": 1.002,
      "grad_norm": 4.236627578735352,
      "learning_rate": 5.220000000000001e-06,
      "loss": 0.572,
      "step": 4350
    },
    {
      "epoch": 1.00825,
      "grad_norm": 5.792555332183838,
      "learning_rate": 5.14857142857143e-06,
      "loss": 0.5485,
      "step": 4400
    },
    {
      "epoch": 1.0145,
      "grad_norm": 4.863269329071045,
      "learning_rate": 5.077142857142857e-06,
      "loss": 0.538,
      "step": 4450
    },
    {
      "epoch": 1.02075,
      "grad_norm": 5.243031024932861,
      "learning_rate": 5.005714285714286e-06,
      "loss": 0.6561,
      "step": 4500
    },
    {
      "epoch": 1.027,
      "grad_norm": 4.527797698974609,
      "learning_rate": 4.934285714285715e-06,
      "loss": 0.5889,
      "step": 4550
    },
    {
      "epoch": 1.03325,
      "grad_norm": 4.516623020172119,
      "learning_rate": 4.862857142857143e-06,
      "loss": 0.5596,
      "step": 4600
    },
    {
      "epoch": 1.0395,
      "grad_norm": 4.004039287567139,
      "learning_rate": 4.7914285714285715e-06,
      "loss": 0.5699,
      "step": 4650
    },
    {
      "epoch": 1.04575,
      "grad_norm": 4.805927276611328,
      "learning_rate": 4.7200000000000005e-06,
      "loss": 0.5761,
      "step": 4700
    },
    {
      "epoch": 1.052,
      "grad_norm": 4.1281962394714355,
      "learning_rate": 4.648571428571429e-06,
      "loss": 0.5827,
      "step": 4750
    },
    {
      "epoch": 1.05825,
      "grad_norm": 4.829611778259277,
      "learning_rate": 4.577142857142858e-06,
      "loss": 0.5865,
      "step": 4800
    },
    {
      "epoch": 1.0645,
      "grad_norm": 3.7667906284332275,
      "learning_rate": 4.505714285714286e-06,
      "loss": 0.5711,
      "step": 4850
    },
    {
      "epoch": 1.07075,
      "grad_norm": 4.786715984344482,
      "learning_rate": 4.434285714285715e-06,
      "loss": 0.5728,
      "step": 4900
    },
    {
      "epoch": 1.077,
      "grad_norm": 4.958069801330566,
      "learning_rate": 4.362857142857143e-06,
      "loss": 0.5611,
      "step": 4950
    },
    {
      "epoch": 1.08325,
      "grad_norm": 3.8642232418060303,
      "learning_rate": 4.291428571428572e-06,
      "loss": 0.5695,
      "step": 5000
    },
    {
      "epoch": 1.0895,
      "grad_norm": 4.423571586608887,
      "learning_rate": 4.22e-06,
      "loss": 0.5213,
      "step": 5050
    },
    {
      "epoch": 1.09575,
      "grad_norm": 4.207879066467285,
      "learning_rate": 4.148571428571429e-06,
      "loss": 0.5132,
      "step": 5100
    },
    {
      "epoch": 1.102,
      "grad_norm": 4.761569499969482,
      "learning_rate": 4.0771428571428574e-06,
      "loss": 0.5234,
      "step": 5150
    },
    {
      "epoch": 1.10825,
      "grad_norm": 4.476335525512695,
      "learning_rate": 4.0057142857142864e-06,
      "loss": 0.5797,
      "step": 5200
    },
    {
      "epoch": 1.1145,
      "grad_norm": 3.8417840003967285,
      "learning_rate": 3.934285714285715e-06,
      "loss": 0.4683,
      "step": 5250
    },
    {
      "epoch": 1.12075,
      "grad_norm": 3.265429735183716,
      "learning_rate": 3.862857142857143e-06,
      "loss": 0.4727,
      "step": 5300
    },
    {
      "epoch": 1.127,
      "grad_norm": 4.57379674911499,
      "learning_rate": 3.7914285714285722e-06,
      "loss": 0.5032,
      "step": 5350
    },
    {
      "epoch": 1.13325,
      "grad_norm": 5.103521823883057,
      "learning_rate": 3.7200000000000004e-06,
      "loss": 0.5116,
      "step": 5400
    },
    {
      "epoch": 1.1395,
      "grad_norm": 4.07943058013916,
      "learning_rate": 3.648571428571429e-06,
      "loss": 0.4916,
      "step": 5450
    },
    {
      "epoch": 1.14575,
      "grad_norm": 4.684885501861572,
      "learning_rate": 3.5771428571428576e-06,
      "loss": 0.4923,
      "step": 5500
    },
    {
      "epoch": 1.152,
      "grad_norm": 3.8068909645080566,
      "learning_rate": 3.505714285714286e-06,
      "loss": 0.4273,
      "step": 5550
    },
    {
      "epoch": 1.15825,
      "grad_norm": 4.139249324798584,
      "learning_rate": 3.4342857142857143e-06,
      "loss": 0.5505,
      "step": 5600
    },
    {
      "epoch": 1.1645,
      "grad_norm": 5.06072998046875,
      "learning_rate": 3.3628571428571433e-06,
      "loss": 0.4919,
      "step": 5650
    },
    {
      "epoch": 1.17075,
      "grad_norm": 4.353974342346191,
      "learning_rate": 3.2914285714285715e-06,
      "loss": 0.5165,
      "step": 5700
    },
    {
      "epoch": 1.177,
      "grad_norm": 4.245412826538086,
      "learning_rate": 3.2200000000000005e-06,
      "loss": 0.543,
      "step": 5750
    },
    {
      "epoch": 1.18325,
      "grad_norm": 3.9986581802368164,
      "learning_rate": 3.1485714285714287e-06,
      "loss": 0.5065,
      "step": 5800
    },
    {
      "epoch": 1.1895,
      "grad_norm": 4.012422561645508,
      "learning_rate": 3.0771428571428573e-06,
      "loss": 0.4563,
      "step": 5850
    },
    {
      "epoch": 1.19575,
      "grad_norm": 3.4883952140808105,
      "learning_rate": 3.005714285714286e-06,
      "loss": 0.517,
      "step": 5900
    },
    {
      "epoch": 1.202,
      "grad_norm": 3.5395171642303467,
      "learning_rate": 2.9342857142857144e-06,
      "loss": 0.4525,
      "step": 5950
    },
    {
      "epoch": 1.20825,
      "grad_norm": 4.436487674713135,
      "learning_rate": 2.8628571428571435e-06,
      "loss": 0.476,
      "step": 6000
    },
    {
      "epoch": 1.20825,
      "eval_loss": 0.577191948890686,
      "eval_runtime": 3956.9016,
      "eval_samples_per_second": 1.096,
      "eval_steps_per_second": 0.137,
      "eval_wer": 37.15599055412812,
      "step": 6000
    }
  ],
  "logging_steps": 50,
  "max_steps": 8000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.385036770295808e+19,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}