{
  "best_metric": 4.561620226935377,
  "best_model_checkpoint": "./checkpoint-4000",
  "epoch": 1.0,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.800000000000001e-07,
      "loss": 0.6521,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.800000000000001e-07,
      "loss": 0.4515,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.46e-06,
      "loss": 0.2873,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9600000000000003e-06,
      "loss": 0.2034,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.46e-06,
      "loss": 0.2061,
      "step": 125
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.96e-06,
      "loss": 0.2546,
      "step": 150
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.46e-06,
      "loss": 0.325,
      "step": 175
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.96e-06,
      "loss": 0.1184,
      "step": 200
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.4600000000000005e-06,
      "loss": 0.1599,
      "step": 225
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.960000000000001e-06,
      "loss": 0.1254,
      "step": 250
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.460000000000001e-06,
      "loss": 0.361,
      "step": 275
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.9600000000000005e-06,
      "loss": 0.1701,
      "step": 300
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.460000000000001e-06,
      "loss": 0.1532,
      "step": 325
    },
    {
      "epoch": 0.09,
      "learning_rate": 6.96e-06,
      "loss": 0.1086,
      "step": 350
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.4600000000000006e-06,
      "loss": 0.0763,
      "step": 375
    },
    {
      "epoch": 0.1,
      "learning_rate": 7.960000000000002e-06,
      "loss": 0.1134,
      "step": 400
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.46e-06,
      "loss": 0.1014,
      "step": 425
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.94e-06,
      "loss": 0.2977,
      "step": 450
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.440000000000001e-06,
      "loss": 0.3106,
      "step": 475
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.940000000000001e-06,
      "loss": 0.1249,
      "step": 500
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.937142857142858e-06,
      "loss": 0.1412,
      "step": 525
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.865714285714285e-06,
      "loss": 0.1077,
      "step": 550
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.794285714285714e-06,
      "loss": 0.0803,
      "step": 575
    },
    {
      "epoch": 0.15,
      "learning_rate": 9.722857142857143e-06,
      "loss": 0.1111,
      "step": 600
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.651428571428572e-06,
      "loss": 0.1667,
      "step": 625
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.58e-06,
      "loss": 0.131,
      "step": 650
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.508571428571429e-06,
      "loss": 0.274,
      "step": 675
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.437142857142858e-06,
      "loss": 0.1309,
      "step": 700
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.365714285714287e-06,
      "loss": 0.1207,
      "step": 725
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.294285714285714e-06,
      "loss": 0.0882,
      "step": 750
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.222857142857143e-06,
      "loss": 0.1223,
      "step": 775
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.151428571428572e-06,
      "loss": 0.1185,
      "step": 800
    },
    {
      "epoch": 0.21,
      "learning_rate": 9.080000000000001e-06,
      "loss": 0.4117,
      "step": 825
    },
    {
      "epoch": 0.21,
      "learning_rate": 9.00857142857143e-06,
      "loss": 0.139,
      "step": 850
    },
    {
      "epoch": 0.22,
      "learning_rate": 8.937142857142857e-06,
      "loss": 0.079,
      "step": 875
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.865714285714287e-06,
      "loss": 0.1328,
      "step": 900
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.794285714285716e-06,
      "loss": 0.1391,
      "step": 925
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.722857142857145e-06,
      "loss": 0.1196,
      "step": 950
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.651428571428572e-06,
      "loss": 0.1083,
      "step": 975
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.580000000000001e-06,
      "loss": 0.1303,
      "step": 1000
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.12187333405017853,
      "eval_runtime": 6950.7062,
      "eval_samples_per_second": 0.349,
      "eval_steps_per_second": 0.044,
      "eval_wer": 6.36176168796884,
      "step": 1000
    },
    {
      "epoch": 0.26,
      "learning_rate": 8.511428571428571e-06,
      "loss": 0.1151,
      "step": 1025
    },
    {
      "epoch": 0.26,
      "learning_rate": 8.44e-06,
      "loss": 0.113,
      "step": 1050
    },
    {
      "epoch": 0.27,
      "learning_rate": 8.36857142857143e-06,
      "loss": 0.0866,
      "step": 1075
    },
    {
      "epoch": 0.28,
      "learning_rate": 8.297142857142859e-06,
      "loss": 0.0873,
      "step": 1100
    },
    {
      "epoch": 0.28,
      "learning_rate": 8.225714285714288e-06,
      "loss": 0.1041,
      "step": 1125
    },
    {
      "epoch": 0.29,
      "learning_rate": 8.154285714285715e-06,
      "loss": 0.2313,
      "step": 1150
    },
    {
      "epoch": 0.29,
      "learning_rate": 8.082857142857144e-06,
      "loss": 0.2704,
      "step": 1175
    },
    {
      "epoch": 0.3,
      "learning_rate": 8.011428571428573e-06,
      "loss": 0.2215,
      "step": 1200
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.94e-06,
      "loss": 0.2238,
      "step": 1225
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.86857142857143e-06,
      "loss": 0.5506,
      "step": 1250
    },
    {
      "epoch": 0.32,
      "learning_rate": 7.797142857142858e-06,
      "loss": 0.1451,
      "step": 1275
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.725714285714286e-06,
      "loss": 0.116,
      "step": 1300
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.654285714285715e-06,
      "loss": 0.3363,
      "step": 1325
    },
    {
      "epoch": 0.34,
      "learning_rate": 7.5828571428571444e-06,
      "loss": 0.109,
      "step": 1350
    },
    {
      "epoch": 0.34,
      "learning_rate": 7.511428571428572e-06,
      "loss": 0.1077,
      "step": 1375
    },
    {
      "epoch": 0.35,
      "learning_rate": 7.440000000000001e-06,
      "loss": 0.0927,
      "step": 1400
    },
    {
      "epoch": 0.36,
      "learning_rate": 7.36857142857143e-06,
      "loss": 0.074,
      "step": 1425
    },
    {
      "epoch": 0.36,
      "learning_rate": 7.297142857142858e-06,
      "loss": 0.1369,
      "step": 1450
    },
    {
      "epoch": 0.37,
      "learning_rate": 7.225714285714286e-06,
      "loss": 0.1043,
      "step": 1475
    },
    {
      "epoch": 0.38,
      "learning_rate": 7.154285714285715e-06,
      "loss": 0.0997,
      "step": 1500
    },
    {
      "epoch": 0.38,
      "learning_rate": 7.082857142857143e-06,
      "loss": 0.0757,
      "step": 1525
    },
    {
      "epoch": 0.39,
      "learning_rate": 7.011428571428572e-06,
      "loss": 0.0928,
      "step": 1550
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.9400000000000005e-06,
      "loss": 0.0726,
      "step": 1575
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.868571428571429e-06,
      "loss": 0.0723,
      "step": 1600
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.797142857142858e-06,
      "loss": 0.1479,
      "step": 1625
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.725714285714287e-06,
      "loss": 0.0664,
      "step": 1650
    },
    {
      "epoch": 0.42,
      "learning_rate": 6.654285714285716e-06,
      "loss": 0.1177,
      "step": 1675
    },
    {
      "epoch": 0.42,
      "learning_rate": 6.582857142857143e-06,
      "loss": 0.2685,
      "step": 1700
    },
    {
      "epoch": 0.43,
      "learning_rate": 6.511428571428572e-06,
      "loss": 0.2067,
      "step": 1725
    },
    {
      "epoch": 0.44,
      "learning_rate": 6.440000000000001e-06,
      "loss": 0.0782,
      "step": 1750
    },
    {
      "epoch": 0.44,
      "learning_rate": 6.368571428571429e-06,
      "loss": 0.0838,
      "step": 1775
    },
    {
      "epoch": 0.45,
      "learning_rate": 6.297142857142857e-06,
      "loss": 0.188,
      "step": 1800
    },
    {
      "epoch": 0.46,
      "learning_rate": 6.225714285714286e-06,
      "loss": 0.3572,
      "step": 1825
    },
    {
      "epoch": 0.46,
      "learning_rate": 6.1542857142857145e-06,
      "loss": 0.1352,
      "step": 1850
    },
    {
      "epoch": 0.47,
      "learning_rate": 6.0828571428571435e-06,
      "loss": 0.082,
      "step": 1875
    },
    {
      "epoch": 0.47,
      "learning_rate": 6.011428571428572e-06,
      "loss": 0.0891,
      "step": 1900
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.94e-06,
      "loss": 0.0739,
      "step": 1925
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.868571428571429e-06,
      "loss": 0.0702,
      "step": 1950
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.797142857142858e-06,
      "loss": 0.1163,
      "step": 1975
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.725714285714287e-06,
      "loss": 0.0751,
      "step": 2000
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.10329055041074753,
      "eval_runtime": 6831.581,
      "eval_samples_per_second": 0.355,
      "eval_steps_per_second": 0.044,
      "eval_wer": 5.390462338490352,
      "step": 2000
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.654285714285714e-06,
      "loss": 0.1457,
      "step": 2025
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.582857142857143e-06,
      "loss": 0.2301,
      "step": 2050
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.511428571428572e-06,
      "loss": 0.1268,
      "step": 2075
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.4400000000000004e-06,
      "loss": 0.0593,
      "step": 2100
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.368571428571429e-06,
      "loss": 0.0815,
      "step": 2125
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.297142857142858e-06,
      "loss": 0.0908,
      "step": 2150
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.225714285714286e-06,
      "loss": 0.1282,
      "step": 2175
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.154285714285715e-06,
      "loss": 0.1269,
      "step": 2200
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.082857142857144e-06,
      "loss": 0.1063,
      "step": 2225
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.011428571428571e-06,
      "loss": 0.0867,
      "step": 2250
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.94e-06,
      "loss": 0.0746,
      "step": 2275
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.868571428571429e-06,
      "loss": 0.0794,
      "step": 2300
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.797142857142857e-06,
      "loss": 0.4292,
      "step": 2325
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.725714285714286e-06,
      "loss": 0.2346,
      "step": 2350
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.6542857142857145e-06,
      "loss": 0.0712,
      "step": 2375
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.5828571428571435e-06,
      "loss": 0.0567,
      "step": 2400
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.511428571428572e-06,
      "loss": 0.0548,
      "step": 2425
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.440000000000001e-06,
      "loss": 0.0599,
      "step": 2450
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.368571428571429e-06,
      "loss": 0.068,
      "step": 2475
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.297142857142858e-06,
      "loss": 0.4456,
      "step": 2500
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.225714285714286e-06,
      "loss": 0.1059,
      "step": 2525
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.154285714285714e-06,
      "loss": 0.1816,
      "step": 2550
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.082857142857143e-06,
      "loss": 0.1162,
      "step": 2575
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.011428571428571e-06,
      "loss": 0.1061,
      "step": 2600
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.94e-06,
      "loss": 0.1751,
      "step": 2625
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.8685714285714286e-06,
      "loss": 0.259,
      "step": 2650
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.7971428571428576e-06,
      "loss": 0.1915,
      "step": 2675
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.7257142857142857e-06,
      "loss": 0.0778,
      "step": 2700
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.6542857142857148e-06,
      "loss": 0.0664,
      "step": 2725
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.582857142857143e-06,
      "loss": 0.12,
      "step": 2750
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.511428571428572e-06,
      "loss": 0.0841,
      "step": 2775
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.44e-06,
      "loss": 0.1226,
      "step": 2800
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.3685714285714287e-06,
      "loss": 0.1037,
      "step": 2825
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.2971428571428577e-06,
      "loss": 0.068,
      "step": 2850
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.225714285714286e-06,
      "loss": 0.0879,
      "step": 2875
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.154285714285715e-06,
      "loss": 0.0941,
      "step": 2900
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.082857142857143e-06,
      "loss": 0.0577,
      "step": 2925
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.0114285714285716e-06,
      "loss": 0.0587,
      "step": 2950
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.9400000000000002e-06,
      "loss": 0.0486,
      "step": 2975
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.868571428571429e-06,
      "loss": 0.0613,
      "step": 3000
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.09700169414281845,
      "eval_runtime": 6788.178,
      "eval_samples_per_second": 0.357,
      "eval_steps_per_second": 0.045,
      "eval_wer": 4.91925762843566,
      "step": 3000
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.797142857142857e-06,
      "loss": 0.0781,
      "step": 3025
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.725714285714286e-06,
      "loss": 0.0807,
      "step": 3050
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.654285714285714e-06,
      "loss": 0.1322,
      "step": 3075
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.582857142857143e-06,
      "loss": 0.3381,
      "step": 3100
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.5114285714285718e-06,
      "loss": 0.1083,
      "step": 3125
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.4400000000000004e-06,
      "loss": 0.0692,
      "step": 3150
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.3685714285714285e-06,
      "loss": 0.237,
      "step": 3175
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.297142857142857e-06,
      "loss": 0.178,
      "step": 3200
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.2257142857142857e-06,
      "loss": 0.0748,
      "step": 3225
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.1542857142857147e-06,
      "loss": 0.0661,
      "step": 3250
    },
    {
      "epoch": 0.82,
      "learning_rate": 2.0828571428571433e-06,
      "loss": 0.0694,
      "step": 3275
    },
    {
      "epoch": 0.82,
      "learning_rate": 2.0114285714285715e-06,
      "loss": 0.0856,
      "step": 3300
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.94e-06,
      "loss": 0.1095,
      "step": 3325
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.8685714285714289e-06,
      "loss": 0.0858,
      "step": 3350
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0745,
      "step": 3375
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.7285714285714287e-06,
      "loss": 0.0733,
      "step": 3400
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.657142857142857e-06,
      "loss": 0.0549,
      "step": 3425
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.5857142857142857e-06,
      "loss": 0.2172,
      "step": 3450
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.5142857142857145e-06,
      "loss": 0.2124,
      "step": 3475
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.442857142857143e-06,
      "loss": 0.1138,
      "step": 3500
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.3714285714285717e-06,
      "loss": 0.081,
      "step": 3525
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.3e-06,
      "loss": 0.0686,
      "step": 3550
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.2285714285714286e-06,
      "loss": 0.0637,
      "step": 3575
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.1571428571428572e-06,
      "loss": 0.0654,
      "step": 3600
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.0857142857142858e-06,
      "loss": 0.1011,
      "step": 3625
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.0142857142857144e-06,
      "loss": 0.2169,
      "step": 3650
    },
    {
      "epoch": 0.92,
      "learning_rate": 9.42857142857143e-07,
      "loss": 0.1365,
      "step": 3675
    },
    {
      "epoch": 0.93,
      "learning_rate": 8.714285714285716e-07,
      "loss": 0.2004,
      "step": 3700
    },
    {
      "epoch": 0.93,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.0842,
      "step": 3725
    },
    {
      "epoch": 0.94,
      "learning_rate": 7.285714285714287e-07,
      "loss": 0.0529,
      "step": 3750
    },
    {
      "epoch": 0.94,
      "learning_rate": 6.571428571428571e-07,
      "loss": 0.1639,
      "step": 3775
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.857142857142857e-07,
      "loss": 0.1324,
      "step": 3800
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.142857142857143e-07,
      "loss": 0.0956,
      "step": 3825
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.4285714285714286e-07,
      "loss": 0.1126,
      "step": 3850
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.7142857142857145e-07,
      "loss": 0.0956,
      "step": 3875
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.1001,
      "step": 3900
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.285714285714286e-07,
      "loss": 0.4695,
      "step": 3925
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.5714285714285717e-07,
      "loss": 0.1176,
      "step": 3950
    },
    {
      "epoch": 0.99,
      "learning_rate": 8.571428571428573e-08,
      "loss": 0.0856,
      "step": 3975
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.4285714285714288e-08,
      "loss": 0.0796,
      "step": 4000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.09033442288637161,
      "eval_runtime": 6797.8014,
      "eval_samples_per_second": 0.357,
      "eval_steps_per_second": 0.045,
      "eval_wer": 4.561620226935377,
      "step": 4000
    },
    {
      "epoch": 1.0,
      "step": 4000,
      "total_flos": 5.435317813248e+20,
      "train_loss": 0.14483159190416336,
      "train_runtime": 109034.6521,
      "train_samples_per_second": 2.348,
      "train_steps_per_second": 0.037
    }
  ],
  "max_steps": 4000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 5.435317813248e+20,
  "trial_name": null,
  "trial_params": null
}