{
  "best_metric": 9.234234234234235,
  "best_model_checkpoint": "./Malasar_DICT_ASR/checkpoint-1000",
  "epoch": 6.0,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.9728,
      "step": 25
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.2566,
      "step": 50
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.1228,
      "step": 75
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.063,
      "step": 100
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.0586,
      "step": 125
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.9e-06,
      "loss": 0.0457,
      "step": 150
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.043,
      "step": 175
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0409,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.4e-06,
      "loss": 0.0428,
      "step": 225
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.0379,
      "step": 250
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.400000000000001e-06,
      "loss": 0.037,
      "step": 275
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.9e-06,
      "loss": 0.0361,
      "step": 300
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.0319,
      "step": 325
    },
    {
      "epoch": 0.7,
      "learning_rate": 6.9e-06,
      "loss": 0.0367,
      "step": 350
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.4e-06,
      "loss": 0.0298,
      "step": 375
    },
    {
      "epoch": 0.8,
      "learning_rate": 7.9e-06,
      "loss": 0.0356,
      "step": 400
    },
    {
      "epoch": 0.85,
      "learning_rate": 8.400000000000001e-06,
      "loss": 0.0326,
      "step": 425
    },
    {
      "epoch": 0.9,
      "learning_rate": 8.900000000000001e-06,
      "loss": 0.0329,
      "step": 450
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.4e-06,
      "loss": 0.0339,
      "step": 475
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.9e-06,
      "loss": 0.0276,
      "step": 500
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.942857142857145e-06,
      "loss": 0.0217,
      "step": 525
    },
    {
      "epoch": 1.1,
      "learning_rate": 9.871428571428572e-06,
      "loss": 0.0291,
      "step": 550
    },
    {
      "epoch": 1.15,
      "learning_rate": 9.800000000000001e-06,
      "loss": 0.0233,
      "step": 575
    },
    {
      "epoch": 1.2,
      "learning_rate": 9.72857142857143e-06,
      "loss": 0.0248,
      "step": 600
    },
    {
      "epoch": 1.25,
      "learning_rate": 9.657142857142859e-06,
      "loss": 0.026,
      "step": 625
    },
    {
      "epoch": 1.3,
      "learning_rate": 9.585714285714286e-06,
      "loss": 0.0295,
      "step": 650
    },
    {
      "epoch": 1.35,
      "learning_rate": 9.514285714285715e-06,
      "loss": 0.0197,
      "step": 675
    },
    {
      "epoch": 1.4,
      "learning_rate": 9.442857142857144e-06,
      "loss": 0.0193,
      "step": 700
    },
    {
      "epoch": 1.45,
      "learning_rate": 9.371428571428572e-06,
      "loss": 0.0242,
      "step": 725
    },
    {
      "epoch": 1.5,
      "learning_rate": 9.3e-06,
      "loss": 0.0237,
      "step": 750
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.22857142857143e-06,
      "loss": 0.0144,
      "step": 775
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.157142857142857e-06,
      "loss": 0.0295,
      "step": 800
    },
    {
      "epoch": 1.65,
      "learning_rate": 9.085714285714286e-06,
      "loss": 0.0189,
      "step": 825
    },
    {
      "epoch": 1.7,
      "learning_rate": 9.014285714285715e-06,
      "loss": 0.019,
      "step": 850
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.942857142857142e-06,
      "loss": 0.0213,
      "step": 875
    },
    {
      "epoch": 1.8,
      "learning_rate": 8.871428571428571e-06,
      "loss": 0.0138,
      "step": 900
    },
    {
      "epoch": 1.85,
      "learning_rate": 8.8e-06,
      "loss": 0.0145,
      "step": 925
    },
    {
      "epoch": 1.9,
      "learning_rate": 8.72857142857143e-06,
      "loss": 0.0163,
      "step": 950
    },
    {
      "epoch": 1.95,
      "learning_rate": 8.657142857142858e-06,
      "loss": 0.0139,
      "step": 975
    },
    {
      "epoch": 2.0,
      "learning_rate": 8.585714285714286e-06,
      "loss": 0.0202,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.01898282766342163,
      "eval_runtime": 780.8874,
      "eval_samples_per_second": 2.274,
      "eval_steps_per_second": 0.142,
      "eval_wer": 9.234234234234235,
      "step": 1000
    },
    {
      "epoch": 2.05,
      "learning_rate": 8.514285714285715e-06,
      "loss": 0.0131,
      "step": 1025
    },
    {
      "epoch": 2.1,
      "learning_rate": 8.442857142857144e-06,
      "loss": 0.0092,
      "step": 1050
    },
    {
      "epoch": 2.15,
      "learning_rate": 8.371428571428573e-06,
      "loss": 0.012,
      "step": 1075
    },
    {
      "epoch": 2.2,
      "learning_rate": 8.3e-06,
      "loss": 0.01,
      "step": 1100
    },
    {
      "epoch": 2.25,
      "learning_rate": 8.22857142857143e-06,
      "loss": 0.008,
      "step": 1125
    },
    {
      "epoch": 2.3,
      "learning_rate": 8.157142857142858e-06,
      "loss": 0.0104,
      "step": 1150
    },
    {
      "epoch": 2.35,
      "learning_rate": 8.085714285714287e-06,
      "loss": 0.0109,
      "step": 1175
    },
    {
      "epoch": 2.4,
      "learning_rate": 8.014285714285715e-06,
      "loss": 0.0162,
      "step": 1200
    },
    {
      "epoch": 2.45,
      "learning_rate": 7.942857142857144e-06,
      "loss": 0.0176,
      "step": 1225
    },
    {
      "epoch": 2.5,
      "learning_rate": 7.871428571428573e-06,
      "loss": 0.0094,
      "step": 1250
    },
    {
      "epoch": 2.55,
      "learning_rate": 7.800000000000002e-06,
      "loss": 0.0082,
      "step": 1275
    },
    {
      "epoch": 2.6,
      "learning_rate": 7.72857142857143e-06,
      "loss": 0.0132,
      "step": 1300
    },
    {
      "epoch": 2.65,
      "learning_rate": 7.657142857142858e-06,
      "loss": 0.0128,
      "step": 1325
    },
    {
      "epoch": 2.7,
      "learning_rate": 7.585714285714286e-06,
      "loss": 0.013,
      "step": 1350
    },
    {
      "epoch": 2.75,
      "learning_rate": 7.514285714285715e-06,
      "loss": 0.0087,
      "step": 1375
    },
    {
      "epoch": 2.8,
      "learning_rate": 7.442857142857144e-06,
      "loss": 0.0073,
      "step": 1400
    },
    {
      "epoch": 2.85,
      "learning_rate": 7.371428571428571e-06,
      "loss": 0.0108,
      "step": 1425
    },
    {
      "epoch": 2.9,
      "learning_rate": 7.3e-06,
      "loss": 0.0092,
      "step": 1450
    },
    {
      "epoch": 2.95,
      "learning_rate": 7.2285714285714294e-06,
      "loss": 0.01,
      "step": 1475
    },
    {
      "epoch": 3.0,
      "learning_rate": 7.1571428571428584e-06,
      "loss": 0.013,
      "step": 1500
    },
    {
      "epoch": 3.05,
      "learning_rate": 7.085714285714286e-06,
      "loss": 0.0071,
      "step": 1525
    },
    {
      "epoch": 3.1,
      "learning_rate": 7.014285714285715e-06,
      "loss": 0.0043,
      "step": 1550
    },
    {
      "epoch": 3.15,
      "learning_rate": 6.942857142857144e-06,
      "loss": 0.0057,
      "step": 1575
    },
    {
      "epoch": 3.2,
      "learning_rate": 6.871428571428572e-06,
      "loss": 0.0077,
      "step": 1600
    },
    {
      "epoch": 3.25,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.006,
      "step": 1625
    },
    {
      "epoch": 3.3,
      "learning_rate": 6.728571428571429e-06,
      "loss": 0.0043,
      "step": 1650
    },
    {
      "epoch": 3.35,
      "learning_rate": 6.657142857142857e-06,
      "loss": 0.0058,
      "step": 1675
    },
    {
      "epoch": 3.4,
      "learning_rate": 6.585714285714286e-06,
      "loss": 0.0136,
      "step": 1700
    },
    {
      "epoch": 3.45,
      "learning_rate": 6.514285714285715e-06,
      "loss": 0.0061,
      "step": 1725
    },
    {
      "epoch": 3.5,
      "learning_rate": 6.442857142857143e-06,
      "loss": 0.0046,
      "step": 1750
    },
    {
      "epoch": 3.55,
      "learning_rate": 6.371428571428572e-06,
      "loss": 0.0049,
      "step": 1775
    },
    {
      "epoch": 3.6,
      "learning_rate": 6.300000000000001e-06,
      "loss": 0.0044,
      "step": 1800
    },
    {
      "epoch": 3.65,
      "learning_rate": 6.22857142857143e-06,
      "loss": 0.0069,
      "step": 1825
    },
    {
      "epoch": 3.7,
      "learning_rate": 6.157142857142858e-06,
      "loss": 0.0076,
      "step": 1850
    },
    {
      "epoch": 3.75,
      "learning_rate": 6.085714285714286e-06,
      "loss": 0.0071,
      "step": 1875
    },
    {
      "epoch": 3.8,
      "learning_rate": 6.014285714285715e-06,
      "loss": 0.0096,
      "step": 1900
    },
    {
      "epoch": 3.85,
      "learning_rate": 5.942857142857143e-06,
      "loss": 0.0061,
      "step": 1925
    },
    {
      "epoch": 3.9,
      "learning_rate": 5.871428571428572e-06,
      "loss": 0.0073,
      "step": 1950
    },
    {
      "epoch": 3.95,
      "learning_rate": 5.8e-06,
      "loss": 0.0047,
      "step": 1975
    },
    {
      "epoch": 4.0,
      "learning_rate": 5.7285714285714285e-06,
      "loss": 0.0066,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.014527006074786186,
      "eval_runtime": 771.2346,
      "eval_samples_per_second": 2.303,
      "eval_steps_per_second": 0.144,
      "eval_wer": 13.344594594594595,
      "step": 2000
    },
    {
      "epoch": 4.05,
      "learning_rate": 5.6571428571428576e-06,
      "loss": 0.0056,
      "step": 2025
    },
    {
      "epoch": 4.1,
      "learning_rate": 5.5857142857142866e-06,
      "loss": 0.0036,
      "step": 2050
    },
    {
      "epoch": 4.15,
      "learning_rate": 5.514285714285714e-06,
      "loss": 0.0035,
      "step": 2075
    },
    {
      "epoch": 4.2,
      "learning_rate": 5.442857142857143e-06,
      "loss": 0.0034,
      "step": 2100
    },
    {
      "epoch": 4.25,
      "learning_rate": 5.371428571428572e-06,
      "loss": 0.003,
      "step": 2125
    },
    {
      "epoch": 4.3,
      "learning_rate": 5.300000000000001e-06,
      "loss": 0.0045,
      "step": 2150
    },
    {
      "epoch": 4.35,
      "learning_rate": 5.22857142857143e-06,
      "loss": 0.0035,
      "step": 2175
    },
    {
      "epoch": 4.4,
      "learning_rate": 5.157142857142857e-06,
      "loss": 0.0056,
      "step": 2200
    },
    {
      "epoch": 4.45,
      "learning_rate": 5.085714285714286e-06,
      "loss": 0.0048,
      "step": 2225
    },
    {
      "epoch": 4.5,
      "learning_rate": 5.014285714285715e-06,
      "loss": 0.0054,
      "step": 2250
    },
    {
      "epoch": 4.55,
      "learning_rate": 4.9428571428571435e-06,
      "loss": 0.0034,
      "step": 2275
    },
    {
      "epoch": 4.6,
      "learning_rate": 4.871428571428572e-06,
      "loss": 0.0042,
      "step": 2300
    },
    {
      "epoch": 4.65,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.0032,
      "step": 2325
    },
    {
      "epoch": 4.7,
      "learning_rate": 4.728571428571429e-06,
      "loss": 0.0027,
      "step": 2350
    },
    {
      "epoch": 4.75,
      "learning_rate": 4.657142857142857e-06,
      "loss": 0.0039,
      "step": 2375
    },
    {
      "epoch": 4.8,
      "learning_rate": 4.585714285714286e-06,
      "loss": 0.006,
      "step": 2400
    },
    {
      "epoch": 4.85,
      "learning_rate": 4.514285714285714e-06,
      "loss": 0.0037,
      "step": 2425
    },
    {
      "epoch": 4.9,
      "learning_rate": 4.442857142857143e-06,
      "loss": 0.0033,
      "step": 2450
    },
    {
      "epoch": 4.95,
      "learning_rate": 4.371428571428572e-06,
      "loss": 0.0055,
      "step": 2475
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.3e-06,
      "loss": 0.0046,
      "step": 2500
    },
    {
      "epoch": 5.05,
      "learning_rate": 4.228571428571429e-06,
      "loss": 0.0023,
      "step": 2525
    },
    {
      "epoch": 5.1,
      "learning_rate": 4.1571428571428575e-06,
      "loss": 0.001,
      "step": 2550
    },
    {
      "epoch": 5.15,
      "learning_rate": 4.0857142857142865e-06,
      "loss": 0.0025,
      "step": 2575
    },
    {
      "epoch": 5.2,
      "learning_rate": 4.014285714285715e-06,
      "loss": 0.0028,
      "step": 2600
    },
    {
      "epoch": 5.25,
      "learning_rate": 3.942857142857143e-06,
      "loss": 0.0026,
      "step": 2625
    },
    {
      "epoch": 5.3,
      "learning_rate": 3.871428571428572e-06,
      "loss": 0.0027,
      "step": 2650
    },
    {
      "epoch": 5.35,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0017,
      "step": 2675
    },
    {
      "epoch": 5.4,
      "learning_rate": 3.7285714285714286e-06,
      "loss": 0.0041,
      "step": 2700
    },
    {
      "epoch": 5.45,
      "learning_rate": 3.6571428571428576e-06,
      "loss": 0.0033,
      "step": 2725
    },
    {
      "epoch": 5.5,
      "learning_rate": 3.5857142857142862e-06,
      "loss": 0.0027,
      "step": 2750
    },
    {
      "epoch": 5.55,
      "learning_rate": 3.5142857142857144e-06,
      "loss": 0.0025,
      "step": 2775
    },
    {
      "epoch": 5.6,
      "learning_rate": 3.4428571428571434e-06,
      "loss": 0.0021,
      "step": 2800
    },
    {
      "epoch": 5.65,
      "learning_rate": 3.3714285714285716e-06,
      "loss": 0.0016,
      "step": 2825
    },
    {
      "epoch": 5.7,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0028,
      "step": 2850
    },
    {
      "epoch": 5.75,
      "learning_rate": 3.2285714285714288e-06,
      "loss": 0.0025,
      "step": 2875
    },
    {
      "epoch": 5.8,
      "learning_rate": 3.1571428571428573e-06,
      "loss": 0.0019,
      "step": 2900
    },
    {
      "epoch": 5.85,
      "learning_rate": 3.085714285714286e-06,
      "loss": 0.0032,
      "step": 2925
    },
    {
      "epoch": 5.9,
      "learning_rate": 3.0142857142857145e-06,
      "loss": 0.0037,
      "step": 2950
    },
    {
      "epoch": 5.95,
      "learning_rate": 2.9428571428571427e-06,
      "loss": 0.0036,
      "step": 2975
    },
    {
      "epoch": 6.0,
      "learning_rate": 2.8714285714285717e-06,
      "loss": 0.0033,
      "step": 3000
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.011934439651668072,
      "eval_runtime": 771.6234,
      "eval_samples_per_second": 2.302,
      "eval_steps_per_second": 0.144,
      "eval_wer": 27.47747747747748,
      "step": 3000
    }
  ],
  "max_steps": 4000,
  "num_train_epochs": 8,
  "total_flos": 2.035951155265536e+20,
  "trial_name": null,
  "trial_params": null
}