{
  "best_global_step": 500,
  "best_metric": 1.0,
  "best_model_checkpoint": "/home/jupyter-wb344850/chichewa-asr/models/checkpoints/mms-1b-all-chichewa-1h/checkpoint-500",
  "epoch": 500.0,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.25,
      "grad_norm": NaN,
      "learning_rate": 4.8e-05,
      "loss": 70.277255859375,
      "step": 25
    },
    {
      "epoch": 12.5,
      "grad_norm": NaN,
      "learning_rate": 9.800000000000001e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 18.75,
      "grad_norm": NaN,
      "learning_rate": 0.000148,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 25.0,
      "grad_norm": NaN,
      "learning_rate": 0.00019800000000000002,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 31.25,
      "grad_norm": NaN,
      "learning_rate": 0.000248,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 37.5,
      "grad_norm": NaN,
      "learning_rate": 0.000298,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 43.75,
      "grad_norm": NaN,
      "learning_rate": 0.000348,
      "loss": 0.0,
      "step": 175
    },
    {
      "epoch": 50.0,
      "grad_norm": NaN,
      "learning_rate": 0.000398,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 56.25,
      "grad_norm": NaN,
      "learning_rate": 0.000448,
      "loss": 0.0,
      "step": 225
    },
    {
      "epoch": 62.5,
      "grad_norm": NaN,
      "learning_rate": 0.000498,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 68.75,
      "grad_norm": NaN,
      "learning_rate": 0.0005480000000000001,
      "loss": 0.0,
      "step": 275
    },
    {
      "epoch": 75.0,
      "grad_norm": NaN,
      "learning_rate": 0.000598,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 81.25,
      "grad_norm": NaN,
      "learning_rate": 0.000648,
      "loss": 0.0,
      "step": 325
    },
    {
      "epoch": 87.5,
      "grad_norm": NaN,
      "learning_rate": 0.0006979999999999999,
      "loss": 0.0,
      "step": 350
    },
    {
      "epoch": 93.75,
      "grad_norm": NaN,
      "learning_rate": 0.000748,
      "loss": 0.0,
      "step": 375
    },
    {
      "epoch": 100.0,
      "grad_norm": NaN,
      "learning_rate": 0.0007980000000000001,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 106.25,
      "grad_norm": NaN,
      "learning_rate": 0.000848,
      "loss": 0.0,
      "step": 425
    },
    {
      "epoch": 112.5,
      "grad_norm": NaN,
      "learning_rate": 0.000898,
      "loss": 0.0,
      "step": 450
    },
    {
      "epoch": 118.75,
      "grad_norm": NaN,
      "learning_rate": 0.000948,
      "loss": 0.0,
      "step": 475
    },
    {
      "epoch": 125.0,
      "grad_norm": NaN,
      "learning_rate": 0.000998,
      "loss": 0.0,
      "step": 500
    },
    {
      "epoch": 125.0,
      "eval_loss": NaN,
      "eval_runtime": 1.3702,
      "eval_samples_per_second": 24.815,
      "eval_steps_per_second": 2.19,
      "eval_wer": 1.0,
      "step": 500
    },
    {
      "epoch": 131.25,
      "grad_norm": NaN,
      "learning_rate": 0.0009946666666666667,
      "loss": 0.0,
      "step": 525
    },
    {
      "epoch": 137.5,
      "grad_norm": NaN,
      "learning_rate": 0.0009891111111111112,
      "loss": 0.0,
      "step": 550
    },
    {
      "epoch": 143.75,
      "grad_norm": NaN,
      "learning_rate": 0.0009835555555555554,
      "loss": 0.0,
      "step": 575
    },
    {
      "epoch": 150.0,
      "grad_norm": NaN,
      "learning_rate": 0.000978,
      "loss": 0.0,
      "step": 600
    },
    {
      "epoch": 156.25,
      "grad_norm": NaN,
      "learning_rate": 0.0009724444444444445,
      "loss": 0.0,
      "step": 625
    },
    {
      "epoch": 162.5,
      "grad_norm": NaN,
      "learning_rate": 0.0009668888888888889,
      "loss": 0.0,
      "step": 650
    },
    {
      "epoch": 168.75,
      "grad_norm": NaN,
      "learning_rate": 0.0009613333333333334,
      "loss": 0.0,
      "step": 675
    },
    {
      "epoch": 175.0,
      "grad_norm": NaN,
      "learning_rate": 0.0009557777777777777,
      "loss": 0.0,
      "step": 700
    },
    {
      "epoch": 181.25,
      "grad_norm": NaN,
      "learning_rate": 0.0009502222222222222,
      "loss": 0.0,
      "step": 725
    },
    {
      "epoch": 187.5,
      "grad_norm": NaN,
      "learning_rate": 0.0009446666666666667,
      "loss": 0.0,
      "step": 750
    },
    {
      "epoch": 193.75,
      "grad_norm": NaN,
      "learning_rate": 0.0009391111111111112,
      "loss": 0.0,
      "step": 775
    },
    {
      "epoch": 200.0,
      "grad_norm": NaN,
      "learning_rate": 0.0009335555555555556,
      "loss": 0.0,
      "step": 800
    },
    {
      "epoch": 206.25,
      "grad_norm": NaN,
      "learning_rate": 0.0009280000000000001,
      "loss": 0.0,
      "step": 825
    },
    {
      "epoch": 212.5,
      "grad_norm": NaN,
      "learning_rate": 0.0009224444444444444,
      "loss": 0.0,
      "step": 850
    },
    {
      "epoch": 218.75,
      "grad_norm": NaN,
      "learning_rate": 0.0009168888888888889,
      "loss": 0.0,
      "step": 875
    },
    {
      "epoch": 225.0,
      "grad_norm": NaN,
      "learning_rate": 0.0009113333333333333,
      "loss": 0.0,
      "step": 900
    },
    {
      "epoch": 231.25,
      "grad_norm": NaN,
      "learning_rate": 0.0009057777777777778,
      "loss": 0.0,
      "step": 925
    },
    {
      "epoch": 237.5,
      "grad_norm": NaN,
      "learning_rate": 0.0009002222222222223,
      "loss": 0.0,
      "step": 950
    },
    {
      "epoch": 243.75,
      "grad_norm": NaN,
      "learning_rate": 0.0008946666666666668,
      "loss": 0.0,
      "step": 975
    },
    {
      "epoch": 250.0,
      "grad_norm": NaN,
      "learning_rate": 0.0008891111111111111,
      "loss": 0.0,
      "step": 1000
    },
    {
      "epoch": 250.0,
      "eval_loss": NaN,
      "eval_runtime": 1.3849,
      "eval_samples_per_second": 24.551,
      "eval_steps_per_second": 2.166,
      "eval_wer": 1.0,
      "step": 1000
    },
    {
      "epoch": 256.25,
      "grad_norm": NaN,
      "learning_rate": 0.0008835555555555555,
      "loss": 0.0,
      "step": 1025
    },
    {
      "epoch": 262.5,
      "grad_norm": NaN,
      "learning_rate": 0.000878,
      "loss": 0.0,
      "step": 1050
    },
    {
      "epoch": 268.75,
      "grad_norm": NaN,
      "learning_rate": 0.0008724444444444445,
      "loss": 0.0,
      "step": 1075
    },
    {
      "epoch": 275.0,
      "grad_norm": NaN,
      "learning_rate": 0.0008668888888888889,
      "loss": 0.0,
      "step": 1100
    },
    {
      "epoch": 281.25,
      "grad_norm": NaN,
      "learning_rate": 0.0008613333333333333,
      "loss": 0.0,
      "step": 1125
    },
    {
      "epoch": 287.5,
      "grad_norm": NaN,
      "learning_rate": 0.0008557777777777778,
      "loss": 0.0,
      "step": 1150
    },
    {
      "epoch": 293.75,
      "grad_norm": NaN,
      "learning_rate": 0.0008502222222222223,
      "loss": 0.0,
      "step": 1175
    },
    {
      "epoch": 300.0,
      "grad_norm": NaN,
      "learning_rate": 0.0008446666666666667,
      "loss": 0.0,
      "step": 1200
    },
    {
      "epoch": 306.25,
      "grad_norm": NaN,
      "learning_rate": 0.0008391111111111111,
      "loss": 0.0,
      "step": 1225
    },
    {
      "epoch": 312.5,
      "grad_norm": NaN,
      "learning_rate": 0.0008335555555555556,
      "loss": 0.0,
      "step": 1250
    },
    {
      "epoch": 318.75,
      "grad_norm": NaN,
      "learning_rate": 0.000828,
      "loss": 0.0,
      "step": 1275
    },
    {
      "epoch": 325.0,
      "grad_norm": NaN,
      "learning_rate": 0.0008224444444444444,
      "loss": 0.0,
      "step": 1300
    },
    {
      "epoch": 331.25,
      "grad_norm": NaN,
      "learning_rate": 0.0008168888888888889,
      "loss": 0.0,
      "step": 1325
    },
    {
      "epoch": 337.5,
      "grad_norm": NaN,
      "learning_rate": 0.0008113333333333334,
      "loss": 0.0,
      "step": 1350
    },
    {
      "epoch": 343.75,
      "grad_norm": NaN,
      "learning_rate": 0.0008057777777777779,
      "loss": 0.0,
      "step": 1375
    },
    {
      "epoch": 350.0,
      "grad_norm": NaN,
      "learning_rate": 0.0008002222222222221,
      "loss": 0.0,
      "step": 1400
    },
    {
      "epoch": 356.25,
      "grad_norm": NaN,
      "learning_rate": 0.0007946666666666666,
      "loss": 0.0,
      "step": 1425
    },
    {
      "epoch": 362.5,
      "grad_norm": NaN,
      "learning_rate": 0.0007891111111111111,
      "loss": 0.0,
      "step": 1450
    },
    {
      "epoch": 368.75,
      "grad_norm": NaN,
      "learning_rate": 0.0007835555555555556,
      "loss": 0.0,
      "step": 1475
    },
    {
      "epoch": 375.0,
      "grad_norm": NaN,
      "learning_rate": 0.000778,
      "loss": 0.0,
      "step": 1500
    },
    {
      "epoch": 375.0,
      "eval_loss": NaN,
      "eval_runtime": 1.3509,
      "eval_samples_per_second": 25.168,
      "eval_steps_per_second": 2.221,
      "eval_wer": 1.0,
      "step": 1500
    },
    {
      "epoch": 381.25,
      "grad_norm": NaN,
      "learning_rate": 0.0007724444444444445,
      "loss": 0.0,
      "step": 1525
    },
    {
      "epoch": 387.5,
      "grad_norm": NaN,
      "learning_rate": 0.0007668888888888889,
      "loss": 0.0,
      "step": 1550
    },
    {
      "epoch": 393.75,
      "grad_norm": NaN,
      "learning_rate": 0.0007613333333333334,
      "loss": 0.0,
      "step": 1575
    },
    {
      "epoch": 400.0,
      "grad_norm": NaN,
      "learning_rate": 0.0007557777777777777,
      "loss": 0.0,
      "step": 1600
    },
    {
      "epoch": 406.25,
      "grad_norm": NaN,
      "learning_rate": 0.0007502222222222222,
      "loss": 0.0,
      "step": 1625
    },
    {
      "epoch": 412.5,
      "grad_norm": NaN,
      "learning_rate": 0.0007446666666666667,
      "loss": 0.0,
      "step": 1650
    },
    {
      "epoch": 418.75,
      "grad_norm": NaN,
      "learning_rate": 0.0007391111111111112,
      "loss": 0.0,
      "step": 1675
    },
    {
      "epoch": 425.0,
      "grad_norm": NaN,
      "learning_rate": 0.0007335555555555555,
      "loss": 0.0,
      "step": 1700
    },
    {
      "epoch": 431.25,
      "grad_norm": NaN,
      "learning_rate": 0.000728,
      "loss": 0.0,
      "step": 1725
    },
    {
      "epoch": 437.5,
      "grad_norm": NaN,
      "learning_rate": 0.0007224444444444445,
      "loss": 0.0,
      "step": 1750
    },
    {
      "epoch": 443.75,
      "grad_norm": NaN,
      "learning_rate": 0.0007168888888888889,
      "loss": 0.0,
      "step": 1775
    },
    {
      "epoch": 450.0,
      "grad_norm": NaN,
      "learning_rate": 0.0007113333333333333,
      "loss": 0.0,
      "step": 1800
    },
    {
      "epoch": 456.25,
      "grad_norm": NaN,
      "learning_rate": 0.0007057777777777777,
      "loss": 0.0,
      "step": 1825
    },
    {
      "epoch": 462.5,
      "grad_norm": NaN,
      "learning_rate": 0.0007002222222222222,
      "loss": 0.0,
      "step": 1850
    },
    {
      "epoch": 468.75,
      "grad_norm": NaN,
      "learning_rate": 0.0006946666666666667,
      "loss": 0.0,
      "step": 1875
    },
    {
      "epoch": 475.0,
      "grad_norm": NaN,
      "learning_rate": 0.0006891111111111112,
      "loss": 0.0,
      "step": 1900
    },
    {
      "epoch": 481.25,
      "grad_norm": NaN,
      "learning_rate": 0.0006835555555555556,
      "loss": 0.0,
      "step": 1925
    },
    {
      "epoch": 487.5,
      "grad_norm": NaN,
      "learning_rate": 0.0006780000000000001,
      "loss": 0.0,
      "step": 1950
    },
    {
      "epoch": 493.75,
      "grad_norm": NaN,
      "learning_rate": 0.0006724444444444444,
      "loss": 0.0,
      "step": 1975
    },
    {
      "epoch": 500.0,
      "grad_norm": NaN,
      "learning_rate": 0.0006668888888888888,
      "loss": 0.0,
      "step": 2000
    },
    {
      "epoch": 500.0,
      "eval_loss": NaN,
      "eval_runtime": 1.4369,
      "eval_samples_per_second": 23.662,
      "eval_steps_per_second": 2.088,
      "eval_wer": 1.0,
      "step": 2000
    }
  ],
  "logging_steps": 25,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1250,
  "save_steps": 500,
  "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": 2.9793100083132944e+20,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}