{
  "best_metric": 0.6728349328041077,
  "best_model_checkpoint": "/scratch/skscla001/speech/results/whisper-medium-toigen-baseline-model/checkpoint-400",
  "epoch": 8.130081300813009,
  "eval_steps": 200,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2032520325203252,
      "grad_norm": 122.09156799316406,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 13.2126,
      "step": 25
    },
    {
      "epoch": 0.4065040650406504,
      "grad_norm": 96.64228057861328,
      "learning_rate": 9.000000000000001e-07,
      "loss": 10.8187,
      "step": 50
    },
    {
      "epoch": 0.6097560975609756,
      "grad_norm": 78.24544525146484,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 7.512,
      "step": 75
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 59.84244918823242,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 5.286,
      "step": 100
    },
    {
      "epoch": 1.016260162601626,
      "grad_norm": 56.45948028564453,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 4.2278,
      "step": 125
    },
    {
      "epoch": 1.2195121951219512,
      "grad_norm": 51.11392593383789,
      "learning_rate": 2.9e-06,
      "loss": 3.1606,
      "step": 150
    },
    {
      "epoch": 1.4227642276422765,
      "grad_norm": 66.8532485961914,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 2.877,
      "step": 175
    },
    {
      "epoch": 1.6260162601626016,
      "grad_norm": 49.620723724365234,
      "learning_rate": 3.900000000000001e-06,
      "loss": 2.8705,
      "step": 200
    },
    {
      "epoch": 1.6260162601626016,
      "eval_loss": 0.7697727084159851,
      "eval_runtime": 146.6109,
      "eval_samples_per_second": 1.501,
      "eval_steps_per_second": 0.75,
      "eval_wer": 0.5497317375154767,
      "step": 200
    },
    {
      "epoch": 1.8292682926829267,
      "grad_norm": 45.34678268432617,
      "learning_rate": 4.4e-06,
      "loss": 2.5243,
      "step": 225
    },
    {
      "epoch": 2.032520325203252,
      "grad_norm": 26.699161529541016,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 2.39,
      "step": 250
    },
    {
      "epoch": 2.2357723577235773,
      "grad_norm": 35.60199737548828,
      "learning_rate": 5.400000000000001e-06,
      "loss": 1.4524,
      "step": 275
    },
    {
      "epoch": 2.4390243902439024,
      "grad_norm": 44.11829376220703,
      "learning_rate": 5.9e-06,
      "loss": 1.6189,
      "step": 300
    },
    {
      "epoch": 2.642276422764228,
      "grad_norm": 41.32335662841797,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.4906,
      "step": 325
    },
    {
      "epoch": 2.845528455284553,
      "grad_norm": 33.91703796386719,
      "learning_rate": 6.9e-06,
      "loss": 1.7661,
      "step": 350
    },
    {
      "epoch": 3.048780487804878,
      "grad_norm": 18.920961380004883,
      "learning_rate": 7.4e-06,
      "loss": 1.3609,
      "step": 375
    },
    {
      "epoch": 3.252032520325203,
      "grad_norm": 43.83076095581055,
      "learning_rate": 7.9e-06,
      "loss": 0.75,
      "step": 400
    },
    {
      "epoch": 3.252032520325203,
      "eval_loss": 0.6728349328041077,
      "eval_runtime": 147.4314,
      "eval_samples_per_second": 1.492,
      "eval_steps_per_second": 0.746,
      "eval_wer": 0.4725546842756913,
      "step": 400
    },
    {
      "epoch": 3.4552845528455283,
      "grad_norm": 33.338050842285156,
      "learning_rate": 8.400000000000001e-06,
      "loss": 0.8486,
      "step": 425
    },
    {
      "epoch": 3.658536585365854,
      "grad_norm": 29.820608139038086,
      "learning_rate": 8.900000000000001e-06,
      "loss": 0.8751,
      "step": 450
    },
    {
      "epoch": 3.861788617886179,
      "grad_norm": 35.63396453857422,
      "learning_rate": 9.4e-06,
      "loss": 0.9388,
      "step": 475
    },
    {
      "epoch": 4.065040650406504,
      "grad_norm": 22.237375259399414,
      "learning_rate": 9.9e-06,
      "loss": 0.851,
      "step": 500
    },
    {
      "epoch": 4.2682926829268295,
      "grad_norm": 43.14656448364258,
      "learning_rate": 9.955555555555556e-06,
      "loss": 0.4389,
      "step": 525
    },
    {
      "epoch": 4.471544715447155,
      "grad_norm": 57.44211959838867,
      "learning_rate": 9.9e-06,
      "loss": 0.5182,
      "step": 550
    },
    {
      "epoch": 4.67479674796748,
      "grad_norm": 17.215864181518555,
      "learning_rate": 9.844444444444446e-06,
      "loss": 0.5018,
      "step": 575
    },
    {
      "epoch": 4.878048780487805,
      "grad_norm": 32.25491714477539,
      "learning_rate": 9.78888888888889e-06,
      "loss": 0.5272,
      "step": 600
    },
    {
      "epoch": 4.878048780487805,
      "eval_loss": 0.6985701322555542,
      "eval_runtime": 144.0545,
      "eval_samples_per_second": 1.527,
      "eval_steps_per_second": 0.764,
      "eval_wer": 0.4246801485761453,
      "step": 600
    },
    {
      "epoch": 5.08130081300813,
      "grad_norm": 15.851240158081055,
      "learning_rate": 9.733333333333334e-06,
      "loss": 0.4361,
      "step": 625
    },
    {
      "epoch": 5.284552845528455,
      "grad_norm": 17.774499893188477,
      "learning_rate": 9.677777777777778e-06,
      "loss": 0.2879,
      "step": 650
    },
    {
      "epoch": 5.487804878048781,
      "grad_norm": 19.017724990844727,
      "learning_rate": 9.622222222222222e-06,
      "loss": 0.3209,
      "step": 675
    },
    {
      "epoch": 5.691056910569106,
      "grad_norm": 14.00346565246582,
      "learning_rate": 9.566666666666668e-06,
      "loss": 0.2401,
      "step": 700
    },
    {
      "epoch": 5.894308943089431,
      "grad_norm": 14.700714111328125,
      "learning_rate": 9.511111111111112e-06,
      "loss": 0.2945,
      "step": 725
    },
    {
      "epoch": 6.097560975609756,
      "grad_norm": 15.902238845825195,
      "learning_rate": 9.455555555555557e-06,
      "loss": 0.2563,
      "step": 750
    },
    {
      "epoch": 6.300813008130081,
      "grad_norm": 17.665119171142578,
      "learning_rate": 9.4e-06,
      "loss": 0.1743,
      "step": 775
    },
    {
      "epoch": 6.504065040650406,
      "grad_norm": 30.66339111328125,
      "learning_rate": 9.344444444444446e-06,
      "loss": 0.1709,
      "step": 800
    },
    {
      "epoch": 6.504065040650406,
      "eval_loss": 0.7418065667152405,
      "eval_runtime": 146.4489,
      "eval_samples_per_second": 1.502,
      "eval_steps_per_second": 0.751,
      "eval_wer": 0.48741229880313663,
      "step": 800
    },
    {
      "epoch": 6.7073170731707314,
      "grad_norm": 13.78768539428711,
      "learning_rate": 9.28888888888889e-06,
      "loss": 0.2121,
      "step": 825
    },
    {
      "epoch": 6.9105691056910565,
      "grad_norm": 10.950778007507324,
      "learning_rate": 9.233333333333334e-06,
      "loss": 0.2024,
      "step": 850
    },
    {
      "epoch": 7.1138211382113825,
      "grad_norm": 24.484088897705078,
      "learning_rate": 9.17777777777778e-06,
      "loss": 0.1545,
      "step": 875
    },
    {
      "epoch": 7.317073170731708,
      "grad_norm": 20.098196029663086,
      "learning_rate": 9.122222222222223e-06,
      "loss": 0.1218,
      "step": 900
    },
    {
      "epoch": 7.520325203252033,
      "grad_norm": 2.7319154739379883,
      "learning_rate": 9.066666666666667e-06,
      "loss": 0.1161,
      "step": 925
    },
    {
      "epoch": 7.723577235772358,
      "grad_norm": 15.211636543273926,
      "learning_rate": 9.011111111111111e-06,
      "loss": 0.152,
      "step": 950
    },
    {
      "epoch": 7.926829268292683,
      "grad_norm": 12.316400527954102,
      "learning_rate": 8.955555555555555e-06,
      "loss": 0.0987,
      "step": 975
    },
    {
      "epoch": 8.130081300813009,
      "grad_norm": 1.9946662187576294,
      "learning_rate": 8.900000000000001e-06,
      "loss": 0.1112,
      "step": 1000
    },
    {
      "epoch": 8.130081300813009,
      "eval_loss": 0.7826012372970581,
      "eval_runtime": 144.7013,
      "eval_samples_per_second": 1.52,
      "eval_steps_per_second": 0.76,
      "eval_wer": 0.42302930251754023,
      "step": 1000
    },
    {
      "epoch": 8.130081300813009,
      "step": 1000,
      "total_flos": 8.16483926016e+18,
      "train_loss": 1.8041932809352874,
      "train_runtime": 2738.8323,
      "train_samples_per_second": 14.605,
      "train_steps_per_second": 1.826
    }
  ],
  "logging_steps": 25,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 41,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.16483926016e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}