{
  "best_metric": 0.43837225437164307,
  "best_model_checkpoint": "/scratch/skscla001/speech/results/mms-1b-bigcgen-male-10hrs-model/checkpoint-1900",
  "epoch": 3.560371517027864,
  "eval_steps": 100,
  "global_step": 2300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15479876160990713,
      "grad_norm": 5.460351943969727,
      "learning_rate": 0.00028799999999999995,
      "loss": 12.1631,
      "step": 100
    },
    {
      "epoch": 0.15479876160990713,
      "eval_loss": 1.2138845920562744,
      "eval_runtime": 30.7834,
      "eval_samples_per_second": 14.326,
      "eval_steps_per_second": 3.606,
      "eval_wer": 0.8800192353931233,
      "step": 100
    },
    {
      "epoch": 0.30959752321981426,
      "grad_norm": 9.577868461608887,
      "learning_rate": 0.00029850622406639004,
      "loss": 1.7593,
      "step": 200
    },
    {
      "epoch": 0.30959752321981426,
      "eval_loss": 0.6127354502677917,
      "eval_runtime": 30.6448,
      "eval_samples_per_second": 14.391,
      "eval_steps_per_second": 3.622,
      "eval_wer": 0.5688867516229863,
      "step": 200
    },
    {
      "epoch": 0.46439628482972134,
      "grad_norm": 3.2317442893981934,
      "learning_rate": 0.00029696576763485477,
      "loss": 1.6361,
      "step": 300
    },
    {
      "epoch": 0.46439628482972134,
      "eval_loss": 0.592118501663208,
      "eval_runtime": 30.6328,
      "eval_samples_per_second": 14.396,
      "eval_steps_per_second": 3.624,
      "eval_wer": 0.5732147150757394,
      "step": 300
    },
    {
      "epoch": 0.6191950464396285,
      "grad_norm": 2.212291955947876,
      "learning_rate": 0.0002954097510373444,
      "loss": 1.6146,
      "step": 400
    },
    {
      "epoch": 0.6191950464396285,
      "eval_loss": 0.5587197542190552,
      "eval_runtime": 30.5318,
      "eval_samples_per_second": 14.444,
      "eval_steps_per_second": 3.636,
      "eval_wer": 0.5547006491945179,
      "step": 400
    },
    {
      "epoch": 0.7739938080495357,
      "grad_norm": 36.353111267089844,
      "learning_rate": 0.000293853734439834,
      "loss": 1.3783,
      "step": 500
    },
    {
      "epoch": 0.7739938080495357,
      "eval_loss": 0.5519681572914124,
      "eval_runtime": 30.9645,
      "eval_samples_per_second": 14.242,
      "eval_steps_per_second": 3.585,
      "eval_wer": 0.5313777350324598,
      "step": 500
    },
    {
      "epoch": 0.9287925696594427,
      "grad_norm": 10.191967010498047,
      "learning_rate": 0.0002922977178423236,
      "loss": 1.36,
      "step": 600
    },
    {
      "epoch": 0.9287925696594427,
      "eval_loss": 0.5443902611732483,
      "eval_runtime": 30.4904,
      "eval_samples_per_second": 14.464,
      "eval_steps_per_second": 3.64,
      "eval_wer": 0.5277710988218322,
      "step": 600
    },
    {
      "epoch": 1.08359133126935,
      "grad_norm": 2.354079246520996,
      "learning_rate": 0.00029074170124481326,
      "loss": 1.3447,
      "step": 700
    },
    {
      "epoch": 1.08359133126935,
      "eval_loss": 0.5393995046615601,
      "eval_runtime": 30.4654,
      "eval_samples_per_second": 14.475,
      "eval_steps_per_second": 3.643,
      "eval_wer": 0.5126232267371964,
      "step": 700
    },
    {
      "epoch": 1.238390092879257,
      "grad_norm": 22.778234481811523,
      "learning_rate": 0.0002891856846473029,
      "loss": 1.3265,
      "step": 800
    },
    {
      "epoch": 1.238390092879257,
      "eval_loss": 0.5084973573684692,
      "eval_runtime": 30.5735,
      "eval_samples_per_second": 14.424,
      "eval_steps_per_second": 3.631,
      "eval_wer": 0.5027650877614811,
      "step": 800
    },
    {
      "epoch": 1.3931888544891642,
      "grad_norm": 1.102784276008606,
      "learning_rate": 0.00028762966804979253,
      "loss": 1.2625,
      "step": 900
    },
    {
      "epoch": 1.3931888544891642,
      "eval_loss": 0.4822230637073517,
      "eval_runtime": 30.9,
      "eval_samples_per_second": 14.272,
      "eval_steps_per_second": 3.592,
      "eval_wer": 0.5008415484491464,
      "step": 900
    },
    {
      "epoch": 1.5479876160990713,
      "grad_norm": 28.76813316345215,
      "learning_rate": 0.00028607365145228217,
      "loss": 1.2793,
      "step": 1000
    },
    {
      "epoch": 1.5479876160990713,
      "eval_loss": 0.5092038512229919,
      "eval_runtime": 30.5673,
      "eval_samples_per_second": 14.427,
      "eval_steps_per_second": 3.631,
      "eval_wer": 0.5037268574176484,
      "step": 1000
    },
    {
      "epoch": 1.7027863777089784,
      "grad_norm": 2.1807544231414795,
      "learning_rate": 0.00028453319502074685,
      "loss": 1.266,
      "step": 1100
    },
    {
      "epoch": 1.7027863777089784,
      "eval_loss": 0.4713282585144043,
      "eval_runtime": 30.5711,
      "eval_samples_per_second": 14.425,
      "eval_steps_per_second": 3.631,
      "eval_wer": 0.49579225775426783,
      "step": 1100
    },
    {
      "epoch": 1.8575851393188856,
      "grad_norm": 1.2101130485534668,
      "learning_rate": 0.0002829771784232365,
      "loss": 1.2451,
      "step": 1200
    },
    {
      "epoch": 1.8575851393188856,
      "eval_loss": 0.45441821217536926,
      "eval_runtime": 30.4675,
      "eval_samples_per_second": 14.474,
      "eval_steps_per_second": 3.643,
      "eval_wer": 0.4779995191151719,
      "step": 1200
    },
    {
      "epoch": 2.0123839009287927,
      "grad_norm": 5.769093036651611,
      "learning_rate": 0.0002814211618257261,
      "loss": 1.3066,
      "step": 1300
    },
    {
      "epoch": 2.0123839009287927,
      "eval_loss": 0.4491290748119354,
      "eval_runtime": 30.9343,
      "eval_samples_per_second": 14.256,
      "eval_steps_per_second": 3.588,
      "eval_wer": 0.47367155566241886,
      "step": 1300
    },
    {
      "epoch": 2.1671826625387,
      "grad_norm": 10.747196197509766,
      "learning_rate": 0.00027986514522821576,
      "loss": 1.2102,
      "step": 1400
    },
    {
      "epoch": 2.1671826625387,
      "eval_loss": 0.4510246217250824,
      "eval_runtime": 30.8465,
      "eval_samples_per_second": 14.297,
      "eval_steps_per_second": 3.598,
      "eval_wer": 0.4784804039432556,
      "step": 1400
    },
    {
      "epoch": 2.321981424148607,
      "grad_norm": 1.3166229724884033,
      "learning_rate": 0.0002783091286307054,
      "loss": 1.2384,
      "step": 1500
    },
    {
      "epoch": 2.321981424148607,
      "eval_loss": 0.4534485936164856,
      "eval_runtime": 30.6292,
      "eval_samples_per_second": 14.398,
      "eval_steps_per_second": 3.624,
      "eval_wer": 0.47559509497475355,
      "step": 1500
    },
    {
      "epoch": 2.476780185758514,
      "grad_norm": 1.1447139978408813,
      "learning_rate": 0.00027675311203319503,
      "loss": 1.2143,
      "step": 1600
    },
    {
      "epoch": 2.476780185758514,
      "eval_loss": 0.4538140892982483,
      "eval_runtime": 30.689,
      "eval_samples_per_second": 14.37,
      "eval_steps_per_second": 3.617,
      "eval_wer": 0.473431113248377,
      "step": 1600
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 1.3231621980667114,
      "learning_rate": 0.0002751970954356846,
      "loss": 1.0998,
      "step": 1700
    },
    {
      "epoch": 2.6315789473684212,
      "eval_loss": 0.44723573327064514,
      "eval_runtime": 31.1806,
      "eval_samples_per_second": 14.143,
      "eval_steps_per_second": 3.56,
      "eval_wer": 0.4683818225534984,
      "step": 1700
    },
    {
      "epoch": 2.7863777089783284,
      "grad_norm": 2.1241629123687744,
      "learning_rate": 0.00027364107883817425,
      "loss": 1.0608,
      "step": 1800
    },
    {
      "epoch": 2.7863777089783284,
      "eval_loss": 0.4533312916755676,
      "eval_runtime": 31.1676,
      "eval_samples_per_second": 14.149,
      "eval_steps_per_second": 3.561,
      "eval_wer": 0.461649434960327,
      "step": 1800
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 1.158493161201477,
      "learning_rate": 0.0002720850622406639,
      "loss": 1.1756,
      "step": 1900
    },
    {
      "epoch": 2.9411764705882355,
      "eval_loss": 0.43837225437164307,
      "eval_runtime": 31.1732,
      "eval_samples_per_second": 14.147,
      "eval_steps_per_second": 3.561,
      "eval_wer": 0.46140899254628515,
      "step": 1900
    },
    {
      "epoch": 3.0959752321981426,
      "grad_norm": 1.2850475311279297,
      "learning_rate": 0.0002705290456431535,
      "loss": 1.0873,
      "step": 2000
    },
    {
      "epoch": 3.0959752321981426,
      "eval_loss": 0.4458366930484772,
      "eval_runtime": 31.0493,
      "eval_samples_per_second": 14.203,
      "eval_steps_per_second": 3.575,
      "eval_wer": 0.46381341668670356,
      "step": 2000
    },
    {
      "epoch": 3.2507739938080498,
      "grad_norm": 0.9354444146156311,
      "learning_rate": 0.00026897302904564316,
      "loss": 1.0788,
      "step": 2100
    },
    {
      "epoch": 3.2507739938080498,
      "eval_loss": 0.44000744819641113,
      "eval_runtime": 31.515,
      "eval_samples_per_second": 13.993,
      "eval_steps_per_second": 3.522,
      "eval_wer": 0.45732147150757396,
      "step": 2100
    },
    {
      "epoch": 3.405572755417957,
      "grad_norm": 2.473445177078247,
      "learning_rate": 0.0002674170124481328,
      "loss": 1.1188,
      "step": 2200
    },
    {
      "epoch": 3.405572755417957,
      "eval_loss": 0.44116678833961487,
      "eval_runtime": 31.1851,
      "eval_samples_per_second": 14.141,
      "eval_steps_per_second": 3.559,
      "eval_wer": 0.4650156287569127,
      "step": 2200
    },
    {
      "epoch": 3.560371517027864,
      "grad_norm": 5.2535858154296875,
      "learning_rate": 0.0002658609958506224,
      "loss": 1.2589,
      "step": 2300
    },
    {
      "epoch": 3.560371517027864,
      "eval_loss": 0.44131311774253845,
      "eval_runtime": 30.9569,
      "eval_samples_per_second": 14.246,
      "eval_steps_per_second": 3.586,
      "eval_wer": 0.4553979321952392,
      "step": 2300
    },
    {
      "epoch": 3.560371517027864,
      "step": 2300,
      "total_flos": 1.198392334375229e+19,
      "train_loss": 1.7602186650815217,
      "train_runtime": 3322.857,
      "train_samples_per_second": 46.641,
      "train_steps_per_second": 5.832
    }
  ],
  "logging_steps": 100,
  "max_steps": 19380,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 400,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.198392334375229e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}