{
  "best_metric": 17.98756798756799,
  "best_model_checkpoint": "./whisper-small-vivos/checkpoint-3000",
  "epoch": 4.11522633744856,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 4.6000000000000004e-07,
      "loss": 3.0428,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.600000000000001e-07,
      "loss": 2.6303,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.46e-06,
      "loss": 2.0752,
      "step": 75
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9600000000000003e-06,
      "loss": 1.5733,
      "step": 100
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.46e-06,
      "loss": 1.1017,
      "step": 125
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.96e-06,
      "loss": 0.9,
      "step": 150
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.46e-06,
      "loss": 0.7899,
      "step": 175
    },
    {
      "epoch": 0.27,
      "learning_rate": 3.96e-06,
      "loss": 0.6859,
      "step": 200
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.4600000000000005e-06,
      "loss": 0.6151,
      "step": 225
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.960000000000001e-06,
      "loss": 0.539,
      "step": 250
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.460000000000001e-06,
      "loss": 0.37,
      "step": 275
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.9600000000000005e-06,
      "loss": 0.3106,
      "step": 300
    },
    {
      "epoch": 0.45,
      "learning_rate": 6.460000000000001e-06,
      "loss": 0.2854,
      "step": 325
    },
    {
      "epoch": 0.48,
      "learning_rate": 6.96e-06,
      "loss": 0.2651,
      "step": 350
    },
    {
      "epoch": 0.51,
      "learning_rate": 7.4600000000000006e-06,
      "loss": 0.2473,
      "step": 375
    },
    {
      "epoch": 0.55,
      "learning_rate": 7.960000000000002e-06,
      "loss": 0.2256,
      "step": 400
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.46e-06,
      "loss": 0.2195,
      "step": 425
    },
    {
      "epoch": 0.62,
      "learning_rate": 8.96e-06,
      "loss": 0.2266,
      "step": 450
    },
    {
      "epoch": 0.65,
      "learning_rate": 9.460000000000001e-06,
      "loss": 0.216,
      "step": 475
    },
    {
      "epoch": 0.69,
      "learning_rate": 9.960000000000001e-06,
      "loss": 0.2294,
      "step": 500
    },
    {
      "epoch": 0.72,
      "learning_rate": 1e-05,
      "loss": 0.1918,
      "step": 525
    },
    {
      "epoch": 0.75,
      "learning_rate": 1e-05,
      "loss": 0.2152,
      "step": 550
    },
    {
      "epoch": 0.79,
      "learning_rate": 1e-05,
      "loss": 0.187,
      "step": 575
    },
    {
      "epoch": 0.82,
      "learning_rate": 1e-05,
      "loss": 0.1756,
      "step": 600
    },
    {
      "epoch": 0.86,
      "learning_rate": 1e-05,
      "loss": 0.1862,
      "step": 625
    },
    {
      "epoch": 0.89,
      "learning_rate": 1e-05,
      "loss": 0.1744,
      "step": 650
    },
    {
      "epoch": 0.93,
      "learning_rate": 1e-05,
      "loss": 0.1764,
      "step": 675
    },
    {
      "epoch": 0.96,
      "learning_rate": 1e-05,
      "loss": 0.1662,
      "step": 700
    },
    {
      "epoch": 0.99,
      "learning_rate": 1e-05,
      "loss": 0.1788,
      "step": 725
    },
    {
      "epoch": 1.03,
      "learning_rate": 1e-05,
      "loss": 0.1472,
      "step": 750
    },
    {
      "epoch": 1.06,
      "learning_rate": 1e-05,
      "loss": 0.1381,
      "step": 775
    },
    {
      "epoch": 1.1,
      "learning_rate": 1e-05,
      "loss": 0.1277,
      "step": 800
    },
    {
      "epoch": 1.13,
      "learning_rate": 1e-05,
      "loss": 0.13,
      "step": 825
    },
    {
      "epoch": 1.17,
      "learning_rate": 1e-05,
      "loss": 0.1309,
      "step": 850
    },
    {
      "epoch": 1.2,
      "learning_rate": 1e-05,
      "loss": 0.1279,
      "step": 875
    },
    {
      "epoch": 1.23,
      "learning_rate": 1e-05,
      "loss": 0.1221,
      "step": 900
    },
    {
      "epoch": 1.27,
      "learning_rate": 1e-05,
      "loss": 0.1263,
      "step": 925
    },
    {
      "epoch": 1.3,
      "learning_rate": 1e-05,
      "loss": 0.122,
      "step": 950
    },
    {
      "epoch": 1.34,
      "learning_rate": 1e-05,
      "loss": 0.1251,
      "step": 975
    },
    {
      "epoch": 1.37,
      "learning_rate": 1e-05,
      "loss": 0.1276,
      "step": 1000
    },
    {
      "epoch": 1.37,
      "eval_cer": 8.6875591223948,
      "eval_loss": 0.21370840072631836,
      "eval_runtime": 393.7923,
      "eval_samples_per_second": 1.93,
      "eval_steps_per_second": 0.122,
      "eval_wer": 20.616420616420616,
      "step": 1000
    },
    {
      "epoch": 1.41,
      "learning_rate": 1e-05,
      "loss": 0.1184,
      "step": 1025
    },
    {
      "epoch": 1.44,
      "learning_rate": 1e-05,
      "loss": 0.125,
      "step": 1050
    },
    {
      "epoch": 1.47,
      "learning_rate": 1e-05,
      "loss": 0.1163,
      "step": 1075
    },
    {
      "epoch": 1.51,
      "learning_rate": 1e-05,
      "loss": 0.1263,
      "step": 1100
    },
    {
      "epoch": 1.54,
      "learning_rate": 1e-05,
      "loss": 0.1129,
      "step": 1125
    },
    {
      "epoch": 1.58,
      "learning_rate": 1e-05,
      "loss": 0.1199,
      "step": 1150
    },
    {
      "epoch": 1.61,
      "learning_rate": 1e-05,
      "loss": 0.1231,
      "step": 1175
    },
    {
      "epoch": 1.65,
      "learning_rate": 1e-05,
      "loss": 0.1195,
      "step": 1200
    },
    {
      "epoch": 1.68,
      "learning_rate": 1e-05,
      "loss": 0.1145,
      "step": 1225
    },
    {
      "epoch": 1.71,
      "learning_rate": 1e-05,
      "loss": 0.1115,
      "step": 1250
    },
    {
      "epoch": 1.75,
      "learning_rate": 1e-05,
      "loss": 0.117,
      "step": 1275
    },
    {
      "epoch": 1.78,
      "learning_rate": 1e-05,
      "loss": 0.1089,
      "step": 1300
    },
    {
      "epoch": 1.82,
      "learning_rate": 1e-05,
      "loss": 0.1143,
      "step": 1325
    },
    {
      "epoch": 1.85,
      "learning_rate": 1e-05,
      "loss": 0.1195,
      "step": 1350
    },
    {
      "epoch": 1.89,
      "learning_rate": 1e-05,
      "loss": 0.1137,
      "step": 1375
    },
    {
      "epoch": 1.92,
      "learning_rate": 1e-05,
      "loss": 0.1142,
      "step": 1400
    },
    {
      "epoch": 1.95,
      "learning_rate": 1e-05,
      "loss": 0.1022,
      "step": 1425
    },
    {
      "epoch": 1.99,
      "learning_rate": 1e-05,
      "loss": 0.1,
      "step": 1450
    },
    {
      "epoch": 2.02,
      "learning_rate": 1e-05,
      "loss": 0.0854,
      "step": 1475
    },
    {
      "epoch": 2.06,
      "learning_rate": 1e-05,
      "loss": 0.0707,
      "step": 1500
    },
    {
      "epoch": 2.09,
      "learning_rate": 1e-05,
      "loss": 0.0702,
      "step": 1525
    },
    {
      "epoch": 2.13,
      "learning_rate": 1e-05,
      "loss": 0.0647,
      "step": 1550
    },
    {
      "epoch": 2.16,
      "learning_rate": 1e-05,
      "loss": 0.0713,
      "step": 1575
    },
    {
      "epoch": 2.19,
      "learning_rate": 1e-05,
      "loss": 0.0627,
      "step": 1600
    },
    {
      "epoch": 2.23,
      "learning_rate": 1e-05,
      "loss": 0.0678,
      "step": 1625
    },
    {
      "epoch": 2.26,
      "learning_rate": 1e-05,
      "loss": 0.0667,
      "step": 1650
    },
    {
      "epoch": 2.3,
      "learning_rate": 1e-05,
      "loss": 0.0795,
      "step": 1675
    },
    {
      "epoch": 2.33,
      "learning_rate": 1e-05,
      "loss": 0.0608,
      "step": 1700
    },
    {
      "epoch": 2.37,
      "learning_rate": 1e-05,
      "loss": 0.0642,
      "step": 1725
    },
    {
      "epoch": 2.4,
      "learning_rate": 1e-05,
      "loss": 0.0684,
      "step": 1750
    },
    {
      "epoch": 2.43,
      "learning_rate": 1e-05,
      "loss": 0.0676,
      "step": 1775
    },
    {
      "epoch": 2.47,
      "learning_rate": 1e-05,
      "loss": 0.0743,
      "step": 1800
    },
    {
      "epoch": 2.5,
      "learning_rate": 1e-05,
      "loss": 0.0713,
      "step": 1825
    },
    {
      "epoch": 2.54,
      "learning_rate": 1e-05,
      "loss": 0.062,
      "step": 1850
    },
    {
      "epoch": 2.57,
      "learning_rate": 1e-05,
      "loss": 0.0678,
      "step": 1875
    },
    {
      "epoch": 2.61,
      "learning_rate": 1e-05,
      "loss": 0.0668,
      "step": 1900
    },
    {
      "epoch": 2.64,
      "learning_rate": 1e-05,
      "loss": 0.0739,
      "step": 1925
    },
    {
      "epoch": 2.67,
      "learning_rate": 1e-05,
      "loss": 0.0672,
      "step": 1950
    },
    {
      "epoch": 2.71,
      "learning_rate": 1e-05,
      "loss": 0.0653,
      "step": 1975
    },
    {
      "epoch": 2.74,
      "learning_rate": 1e-05,
      "loss": 0.0696,
      "step": 2000
    },
    {
      "epoch": 2.74,
      "eval_cer": 7.509688444051142,
      "eval_loss": 0.217300683259964,
      "eval_runtime": 392.9774,
      "eval_samples_per_second": 1.934,
      "eval_steps_per_second": 0.122,
      "eval_wer": 19.08831908831909,
      "step": 2000
    },
    {
      "epoch": 2.78,
      "learning_rate": 1e-05,
      "loss": 0.0816,
      "step": 2025
    },
    {
      "epoch": 2.81,
      "learning_rate": 1e-05,
      "loss": 0.0796,
      "step": 2050
    },
    {
      "epoch": 2.85,
      "learning_rate": 1e-05,
      "loss": 0.0721,
      "step": 2075
    },
    {
      "epoch": 2.88,
      "learning_rate": 1e-05,
      "loss": 0.0716,
      "step": 2100
    },
    {
      "epoch": 2.91,
      "learning_rate": 1e-05,
      "loss": 0.0659,
      "step": 2125
    },
    {
      "epoch": 2.95,
      "learning_rate": 1e-05,
      "loss": 0.0644,
      "step": 2150
    },
    {
      "epoch": 2.98,
      "learning_rate": 1e-05,
      "loss": 0.0653,
      "step": 2175
    },
    {
      "epoch": 3.02,
      "learning_rate": 1e-05,
      "loss": 0.0558,
      "step": 2200
    },
    {
      "epoch": 3.05,
      "learning_rate": 1e-05,
      "loss": 0.043,
      "step": 2225
    },
    {
      "epoch": 3.09,
      "learning_rate": 1e-05,
      "loss": 0.047,
      "step": 2250
    },
    {
      "epoch": 3.12,
      "learning_rate": 1e-05,
      "loss": 0.0355,
      "step": 2275
    },
    {
      "epoch": 3.16,
      "learning_rate": 1e-05,
      "loss": 0.033,
      "step": 2300
    },
    {
      "epoch": 3.19,
      "learning_rate": 1e-05,
      "loss": 0.0357,
      "step": 2325
    },
    {
      "epoch": 3.22,
      "learning_rate": 1e-05,
      "loss": 0.0364,
      "step": 2350
    },
    {
      "epoch": 3.26,
      "learning_rate": 1e-05,
      "loss": 0.0425,
      "step": 2375
    },
    {
      "epoch": 3.29,
      "learning_rate": 1e-05,
      "loss": 0.0398,
      "step": 2400
    },
    {
      "epoch": 3.33,
      "learning_rate": 1e-05,
      "loss": 0.0376,
      "step": 2425
    },
    {
      "epoch": 3.36,
      "learning_rate": 1e-05,
      "loss": 0.0413,
      "step": 2450
    },
    {
      "epoch": 3.4,
      "learning_rate": 1e-05,
      "loss": 0.0374,
      "step": 2475
    },
    {
      "epoch": 3.43,
      "learning_rate": 1e-05,
      "loss": 0.0383,
      "step": 2500
    },
    {
      "epoch": 3.46,
      "learning_rate": 1e-05,
      "loss": 0.0381,
      "step": 2525
    },
    {
      "epoch": 3.5,
      "learning_rate": 1e-05,
      "loss": 0.0466,
      "step": 2550
    },
    {
      "epoch": 3.53,
      "learning_rate": 1e-05,
      "loss": 0.04,
      "step": 2575
    },
    {
      "epoch": 3.57,
      "learning_rate": 1e-05,
      "loss": 0.0452,
      "step": 2600
    },
    {
      "epoch": 3.6,
      "learning_rate": 1e-05,
      "loss": 0.0393,
      "step": 2625
    },
    {
      "epoch": 3.64,
      "learning_rate": 1e-05,
      "loss": 0.0461,
      "step": 2650
    },
    {
      "epoch": 3.67,
      "learning_rate": 1e-05,
      "loss": 0.0403,
      "step": 2675
    },
    {
      "epoch": 3.7,
      "learning_rate": 1e-05,
      "loss": 0.0489,
      "step": 2700
    },
    {
      "epoch": 3.74,
      "learning_rate": 1e-05,
      "loss": 0.0418,
      "step": 2725
    },
    {
      "epoch": 3.77,
      "learning_rate": 1e-05,
      "loss": 0.0389,
      "step": 2750
    },
    {
      "epoch": 3.81,
      "learning_rate": 1e-05,
      "loss": 0.041,
      "step": 2775
    },
    {
      "epoch": 3.84,
      "learning_rate": 1e-05,
      "loss": 0.0394,
      "step": 2800
    },
    {
      "epoch": 3.88,
      "learning_rate": 1e-05,
      "loss": 0.0485,
      "step": 2825
    },
    {
      "epoch": 3.91,
      "learning_rate": 1e-05,
      "loss": 0.0416,
      "step": 2850
    },
    {
      "epoch": 3.94,
      "learning_rate": 1e-05,
      "loss": 0.0501,
      "step": 2875
    },
    {
      "epoch": 3.98,
      "learning_rate": 1e-05,
      "loss": 0.0393,
      "step": 2900
    },
    {
      "epoch": 4.01,
      "learning_rate": 1e-05,
      "loss": 0.0306,
      "step": 2925
    },
    {
      "epoch": 4.05,
      "learning_rate": 1e-05,
      "loss": 0.0265,
      "step": 2950
    },
    {
      "epoch": 4.08,
      "learning_rate": 1e-05,
      "loss": 0.0223,
      "step": 2975
    },
    {
      "epoch": 4.12,
      "learning_rate": 1e-05,
      "loss": 0.0215,
      "step": 3000
    },
    {
      "epoch": 4.12,
      "eval_cer": 7.079429983827164,
      "eval_loss": 0.24198034405708313,
      "eval_runtime": 393.3959,
      "eval_samples_per_second": 1.932,
      "eval_steps_per_second": 0.122,
      "eval_wer": 17.98756798756799,
      "step": 3000
    }
  ],
  "max_steps": 4000,
  "num_train_epochs": 6,
  "total_flos": 1.384748184895488e+19,
  "trial_name": null,
  "trial_params": null
}