{
  "best_global_step": 4000,
  "best_metric": 37.39491327019262,
  "best_model_checkpoint": "./whisper-medium-ru-lora/checkpoint-4000",
  "epoch": 0.30328303889604974,
  "eval_steps": 1000,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0075820759724012435,
      "grad_norm": 2.145202398300171,
      "learning_rate": 9.900000000000002e-06,
      "loss": 0.651605224609375,
      "step": 100
    },
    {
      "epoch": 0.015164151944802487,
      "grad_norm": 1.6405466794967651,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 0.38233642578125,
      "step": 200
    },
    {
      "epoch": 0.02274622791720373,
      "grad_norm": 4.584617614746094,
      "learning_rate": 2.9900000000000002e-05,
      "loss": 0.15616183280944823,
      "step": 300
    },
    {
      "epoch": 0.030328303889604974,
      "grad_norm": 1.5751986503601074,
      "learning_rate": 3.99e-05,
      "loss": 0.1865867042541504,
      "step": 400
    },
    {
      "epoch": 0.03791037986200622,
      "grad_norm": 2.414318561553955,
      "learning_rate": 4.99e-05,
      "loss": 0.17033681869506836,
      "step": 500
    },
    {
      "epoch": 0.04549245583440746,
      "grad_norm": 2.5033624172210693,
      "learning_rate": 4.858571428571429e-05,
      "loss": 0.15961559295654296,
      "step": 600
    },
    {
      "epoch": 0.053074531806808704,
      "grad_norm": 2.129359245300293,
      "learning_rate": 4.715714285714286e-05,
      "loss": 0.16227605819702148,
      "step": 700
    },
    {
      "epoch": 0.06065660777920995,
      "grad_norm": 0.5429865717887878,
      "learning_rate": 4.572857142857143e-05,
      "loss": 0.17982370376586915,
      "step": 800
    },
    {
      "epoch": 0.06823868375161118,
      "grad_norm": 0.09488433599472046,
      "learning_rate": 4.43e-05,
      "loss": 0.15608755111694336,
      "step": 900
    },
    {
      "epoch": 0.07582075972401243,
      "grad_norm": 1.4993505477905273,
      "learning_rate": 4.287142857142857e-05,
      "loss": 0.15827343940734864,
      "step": 1000
    },
    {
      "epoch": 0.07582075972401243,
      "eval_loss": 0.1047014594078064,
      "eval_runtime": 1260.1346,
      "eval_samples_per_second": 0.794,
      "eval_steps_per_second": 0.397,
      "eval_wer": 38.26753219112483,
      "step": 1000
    },
    {
      "epoch": 0.08340283569641367,
      "grad_norm": 0.5261468291282654,
      "learning_rate": 4.1442857142857146e-05,
      "loss": 0.1773993492126465,
      "step": 1100
    },
    {
      "epoch": 0.09098491166881492,
      "grad_norm": 3.5084214210510254,
      "learning_rate": 4.001428571428571e-05,
      "loss": 0.13967780113220216,
      "step": 1200
    },
    {
      "epoch": 0.09856698764121616,
      "grad_norm": 2.6616625785827637,
      "learning_rate": 3.8585714285714287e-05,
      "loss": 0.1545235538482666,
      "step": 1300
    },
    {
      "epoch": 0.10614906361361741,
      "grad_norm": 2.668151378631592,
      "learning_rate": 3.715714285714286e-05,
      "loss": 0.15973119735717772,
      "step": 1400
    },
    {
      "epoch": 0.11373113958601865,
      "grad_norm": 0.329638808965683,
      "learning_rate": 3.572857142857143e-05,
      "loss": 0.12528255462646484,
      "step": 1500
    },
    {
      "epoch": 0.1213132155584199,
      "grad_norm": 0.5731531381607056,
      "learning_rate": 3.430000000000001e-05,
      "loss": 0.12541525840759277,
      "step": 1600
    },
    {
      "epoch": 0.12889529153082113,
      "grad_norm": 1.0524909496307373,
      "learning_rate": 3.2871428571428574e-05,
      "loss": 0.14487401962280275,
      "step": 1700
    },
    {
      "epoch": 0.13647736750322237,
      "grad_norm": 0.17586998641490936,
      "learning_rate": 3.144285714285715e-05,
      "loss": 0.11433093070983887,
      "step": 1800
    },
    {
      "epoch": 0.14405944347562363,
      "grad_norm": 1.013460636138916,
      "learning_rate": 3.0014285714285717e-05,
      "loss": 0.15009353637695313,
      "step": 1900
    },
    {
      "epoch": 0.15164151944802487,
      "grad_norm": 1.2082782983779907,
      "learning_rate": 2.8585714285714287e-05,
      "loss": 0.15209393501281737,
      "step": 2000
    },
    {
      "epoch": 0.15164151944802487,
      "eval_loss": 0.09539687633514404,
      "eval_runtime": 1270.093,
      "eval_samples_per_second": 0.787,
      "eval_steps_per_second": 0.394,
      "eval_wer": 37.83122273065872,
      "step": 2000
    },
    {
      "epoch": 0.1592235954204261,
      "grad_norm": 0.7301309108734131,
      "learning_rate": 2.7157142857142858e-05,
      "loss": 0.12468180656433106,
      "step": 2100
    },
    {
      "epoch": 0.16680567139282734,
      "grad_norm": 1.471038579940796,
      "learning_rate": 2.572857142857143e-05,
      "loss": 0.13947233200073242,
      "step": 2200
    },
    {
      "epoch": 0.1743877473652286,
      "grad_norm": 3.3145599365234375,
      "learning_rate": 2.43e-05,
      "loss": 0.15013423919677735,
      "step": 2300
    },
    {
      "epoch": 0.18196982333762984,
      "grad_norm": 1.1346559524536133,
      "learning_rate": 2.287142857142857e-05,
      "loss": 0.13823192596435546,
      "step": 2400
    },
    {
      "epoch": 0.18955189931003108,
      "grad_norm": 0.8875208497047424,
      "learning_rate": 2.1442857142857145e-05,
      "loss": 0.13282781600952148,
      "step": 2500
    },
    {
      "epoch": 0.19713397528243232,
      "grad_norm": 1.3990944623947144,
      "learning_rate": 2.0014285714285715e-05,
      "loss": 0.15458744049072265,
      "step": 2600
    },
    {
      "epoch": 0.20471605125483358,
      "grad_norm": 4.13588809967041,
      "learning_rate": 1.858571428571429e-05,
      "loss": 0.1336074447631836,
      "step": 2700
    },
    {
      "epoch": 0.21229812722723482,
      "grad_norm": 3.2681021690368652,
      "learning_rate": 1.715714285714286e-05,
      "loss": 0.14435559272766113,
      "step": 2800
    },
    {
      "epoch": 0.21988020319963605,
      "grad_norm": 2.823951244354248,
      "learning_rate": 1.572857142857143e-05,
      "loss": 0.13421536445617677,
      "step": 2900
    },
    {
      "epoch": 0.2274622791720373,
      "grad_norm": 1.4937087297439575,
      "learning_rate": 1.43e-05,
      "loss": 0.12853222846984863,
      "step": 3000
    },
    {
      "epoch": 0.2274622791720373,
      "eval_loss": 0.09113000333309174,
      "eval_runtime": 1257.6368,
      "eval_samples_per_second": 0.795,
      "eval_steps_per_second": 0.398,
      "eval_wer": 37.639672235819944,
      "step": 3000
    },
    {
      "epoch": 0.23504435514443855,
      "grad_norm": 0.5249112844467163,
      "learning_rate": 1.2871428571428574e-05,
      "loss": 0.1645351791381836,
      "step": 3100
    },
    {
      "epoch": 0.2426264311168398,
      "grad_norm": 4.014407634735107,
      "learning_rate": 1.1442857142857144e-05,
      "loss": 0.14470401763916016,
      "step": 3200
    },
    {
      "epoch": 0.25020850708924103,
      "grad_norm": 0.6329492330551147,
      "learning_rate": 1.0014285714285716e-05,
      "loss": 0.12239849090576171,
      "step": 3300
    },
    {
      "epoch": 0.25779058306164226,
      "grad_norm": 2.205402135848999,
      "learning_rate": 8.585714285714286e-06,
      "loss": 0.15601092338562011,
      "step": 3400
    },
    {
      "epoch": 0.2653726590340435,
      "grad_norm": 3.0992422103881836,
      "learning_rate": 7.1571428571428584e-06,
      "loss": 0.1359235954284668,
      "step": 3500
    },
    {
      "epoch": 0.27295473500644474,
      "grad_norm": 1.166153073310852,
      "learning_rate": 5.728571428571429e-06,
      "loss": 0.1488318347930908,
      "step": 3600
    },
    {
      "epoch": 0.28053681097884603,
      "grad_norm": 0.10292654484510422,
      "learning_rate": 4.2999999999999995e-06,
      "loss": 0.1741475486755371,
      "step": 3700
    },
    {
      "epoch": 0.28811888695124727,
      "grad_norm": 0.1904854029417038,
      "learning_rate": 2.8714285714285713e-06,
      "loss": 0.12981878280639647,
      "step": 3800
    },
    {
      "epoch": 0.2957009629236485,
      "grad_norm": 1.543544888496399,
      "learning_rate": 1.4428571428571429e-06,
      "loss": 0.16215293884277343,
      "step": 3900
    },
    {
      "epoch": 0.30328303889604974,
      "grad_norm": 1.1929818391799927,
      "learning_rate": 1.4285714285714288e-08,
      "loss": 0.14198240280151367,
      "step": 4000
    },
    {
      "epoch": 0.30328303889604974,
      "eval_loss": 0.08855394273996353,
      "eval_runtime": 1257.4555,
      "eval_samples_per_second": 0.795,
      "eval_steps_per_second": 0.398,
      "eval_wer": 37.39491327019262,
      "step": 4000
    }
  ],
  "logging_steps": 100,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.38227197952e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}