{
  "best_metric": 53.939393939393945,
  "best_model_checkpoint": "./whisper-small-az/checkpoint-1000",
  "epoch": 250.0,
  "eval_steps": 1000,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.25,
      "grad_norm": 14.350049018859863,
      "learning_rate": 4.4e-07,
      "loss": 1.3755,
      "step": 25
    },
    {
      "epoch": 12.5,
      "grad_norm": 9.423840522766113,
      "learning_rate": 9.400000000000001e-07,
      "loss": 1.0989,
      "step": 50
    },
    {
      "epoch": 18.75,
      "grad_norm": 6.209718704223633,
      "learning_rate": 1.44e-06,
      "loss": 0.6302,
      "step": 75
    },
    {
      "epoch": 25.0,
      "grad_norm": 3.1120553016662598,
      "learning_rate": 1.94e-06,
      "loss": 0.2227,
      "step": 100
    },
    {
      "epoch": 31.25,
      "grad_norm": 0.41890719532966614,
      "learning_rate": 2.4400000000000004e-06,
      "loss": 0.0443,
      "step": 125
    },
    {
      "epoch": 37.5,
      "grad_norm": 0.14954017102718353,
      "learning_rate": 2.9400000000000002e-06,
      "loss": 0.0097,
      "step": 150
    },
    {
      "epoch": 43.75,
      "grad_norm": 0.08068686723709106,
      "learning_rate": 3.44e-06,
      "loss": 0.0046,
      "step": 175
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.0662764459848404,
      "learning_rate": 3.94e-06,
      "loss": 0.003,
      "step": 200
    },
    {
      "epoch": 56.25,
      "grad_norm": 0.04160891845822334,
      "learning_rate": 4.440000000000001e-06,
      "loss": 0.0021,
      "step": 225
    },
    {
      "epoch": 62.5,
      "grad_norm": 0.031241776421666145,
      "learning_rate": 4.94e-06,
      "loss": 0.0016,
      "step": 250
    },
    {
      "epoch": 68.75,
      "grad_norm": 0.02429639920592308,
      "learning_rate": 5.4400000000000004e-06,
      "loss": 0.0012,
      "step": 275
    },
    {
      "epoch": 75.0,
      "grad_norm": 0.024689121171832085,
      "learning_rate": 5.94e-06,
      "loss": 0.001,
      "step": 300
    },
    {
      "epoch": 81.25,
      "grad_norm": 0.014733972027897835,
      "learning_rate": 6.440000000000001e-06,
      "loss": 0.0008,
      "step": 325
    },
    {
      "epoch": 87.5,
      "grad_norm": 0.012692940421402454,
      "learning_rate": 6.9400000000000005e-06,
      "loss": 0.0007,
      "step": 350
    },
    {
      "epoch": 93.75,
      "grad_norm": 0.0114270756021142,
      "learning_rate": 7.440000000000001e-06,
      "loss": 0.0006,
      "step": 375
    },
    {
      "epoch": 100.0,
      "grad_norm": 0.009990418329834938,
      "learning_rate": 7.94e-06,
      "loss": 0.0005,
      "step": 400
    },
    {
      "epoch": 106.25,
      "grad_norm": 0.007662411779165268,
      "learning_rate": 8.44e-06,
      "loss": 0.0004,
      "step": 425
    },
    {
      "epoch": 112.5,
      "grad_norm": 0.006897376384586096,
      "learning_rate": 8.94e-06,
      "loss": 0.0004,
      "step": 450
    },
    {
      "epoch": 118.75,
      "grad_norm": 0.0064265248365700245,
      "learning_rate": 9.440000000000001e-06,
      "loss": 0.0003,
      "step": 475
    },
    {
      "epoch": 125.0,
      "grad_norm": 0.00633584288880229,
      "learning_rate": 9.940000000000001e-06,
      "loss": 0.0003,
      "step": 500
    },
    {
      "epoch": 131.25,
      "grad_norm": 0.005206201691180468,
      "learning_rate": 9.937142857142858e-06,
      "loss": 0.0002,
      "step": 525
    },
    {
      "epoch": 137.5,
      "grad_norm": 0.00430842163041234,
      "learning_rate": 9.865714285714285e-06,
      "loss": 0.0002,
      "step": 550
    },
    {
      "epoch": 143.75,
      "grad_norm": 0.004347742069512606,
      "learning_rate": 9.794285714285714e-06,
      "loss": 0.0002,
      "step": 575
    },
    {
      "epoch": 150.0,
      "grad_norm": 0.004352904390543699,
      "learning_rate": 9.722857142857143e-06,
      "loss": 0.0002,
      "step": 600
    },
    {
      "epoch": 156.25,
      "grad_norm": 0.0033592204563319683,
      "learning_rate": 9.651428571428572e-06,
      "loss": 0.0002,
      "step": 625
    },
    {
      "epoch": 162.5,
      "grad_norm": 0.003341004019603133,
      "learning_rate": 9.58e-06,
      "loss": 0.0002,
      "step": 650
    },
    {
      "epoch": 168.75,
      "grad_norm": 0.0031617768108844757,
      "learning_rate": 9.508571428571429e-06,
      "loss": 0.0001,
      "step": 675
    },
    {
      "epoch": 175.0,
      "grad_norm": 0.003022307762876153,
      "learning_rate": 9.437142857142858e-06,
      "loss": 0.0001,
      "step": 700
    },
    {
      "epoch": 181.25,
      "grad_norm": 0.0027644785586744547,
      "learning_rate": 9.365714285714287e-06,
      "loss": 0.0001,
      "step": 725
    },
    {
      "epoch": 187.5,
      "grad_norm": 0.002608550013974309,
      "learning_rate": 9.294285714285714e-06,
      "loss": 0.0001,
      "step": 750
    },
    {
      "epoch": 193.75,
      "grad_norm": 0.002360701095312834,
      "learning_rate": 9.222857142857143e-06,
      "loss": 0.0001,
      "step": 775
    },
    {
      "epoch": 200.0,
      "grad_norm": 0.0027755298651754856,
      "learning_rate": 9.151428571428572e-06,
      "loss": 0.0001,
      "step": 800
    },
    {
      "epoch": 206.25,
      "grad_norm": 0.0021338986698538065,
      "learning_rate": 9.080000000000001e-06,
      "loss": 0.0001,
      "step": 825
    },
    {
      "epoch": 212.5,
      "grad_norm": 0.002221581991761923,
      "learning_rate": 9.00857142857143e-06,
      "loss": 0.0001,
      "step": 850
    },
    {
      "epoch": 218.75,
      "grad_norm": 0.0020208328496664762,
      "learning_rate": 8.937142857142857e-06,
      "loss": 0.0001,
      "step": 875
    },
    {
      "epoch": 225.0,
      "grad_norm": 0.002234733197838068,
      "learning_rate": 8.865714285714287e-06,
      "loss": 0.0001,
      "step": 900
    },
    {
      "epoch": 231.25,
      "grad_norm": 0.0017689570086076856,
      "learning_rate": 8.794285714285716e-06,
      "loss": 0.0001,
      "step": 925
    },
    {
      "epoch": 237.5,
      "grad_norm": 0.001749723101966083,
      "learning_rate": 8.722857142857145e-06,
      "loss": 0.0001,
      "step": 950
    },
    {
      "epoch": 243.75,
      "grad_norm": 0.0018199320184066892,
      "learning_rate": 8.651428571428572e-06,
      "loss": 0.0001,
      "step": 975
    },
    {
      "epoch": 250.0,
      "grad_norm": 0.0018287795828655362,
      "learning_rate": 8.580000000000001e-06,
      "loss": 0.0001,
      "step": 1000
    },
    {
      "epoch": 250.0,
      "eval_loss": 1.053104043006897,
      "eval_runtime": 10.8714,
      "eval_samples_per_second": 2.024,
      "eval_steps_per_second": 0.276,
      "eval_wer": 53.939393939393945,
      "step": 1000
    }
  ],
  "logging_steps": 25,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1000,
  "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": 4.25663465472e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}