{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.263823064770932,
  "eval_steps": 1000,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01579778830963665,
      "grad_norm": 39.75217819213867,
      "learning_rate": 4.4e-07,
      "loss": 2.8325,
      "step": 25
    },
    {
      "epoch": 0.0315955766192733,
      "grad_norm": 29.480606079101562,
      "learning_rate": 9.400000000000001e-07,
      "loss": 2.6716,
      "step": 50
    },
    {
      "epoch": 0.04739336492890995,
      "grad_norm": 25.953859329223633,
      "learning_rate": 1.44e-06,
      "loss": 2.4993,
      "step": 75
    },
    {
      "epoch": 0.0631911532385466,
      "grad_norm": 22.231847763061523,
      "learning_rate": 1.94e-06,
      "loss": 2.231,
      "step": 100
    },
    {
      "epoch": 0.07898894154818326,
      "grad_norm": 22.015960693359375,
      "learning_rate": 2.4400000000000004e-06,
      "loss": 2.0333,
      "step": 125
    },
    {
      "epoch": 0.0947867298578199,
      "grad_norm": 20.71744728088379,
      "learning_rate": 2.9400000000000002e-06,
      "loss": 1.8308,
      "step": 150
    },
    {
      "epoch": 0.11058451816745656,
      "grad_norm": 21.350202560424805,
      "learning_rate": 3.44e-06,
      "loss": 1.74,
      "step": 175
    },
    {
      "epoch": 0.1263823064770932,
      "grad_norm": 19.41323471069336,
      "learning_rate": 3.94e-06,
      "loss": 1.6661,
      "step": 200
    },
    {
      "epoch": 0.14218009478672985,
      "grad_norm": 19.41071891784668,
      "learning_rate": 4.440000000000001e-06,
      "loss": 1.5797,
      "step": 225
    },
    {
      "epoch": 0.1579778830963665,
      "grad_norm": 20.96115493774414,
      "learning_rate": 4.94e-06,
      "loss": 1.5021,
      "step": 250
    },
    {
      "epoch": 0.17377567140600317,
      "grad_norm": 19.24570083618164,
      "learning_rate": 5.4400000000000004e-06,
      "loss": 1.4673,
      "step": 275
    },
    {
      "epoch": 0.1895734597156398,
      "grad_norm": 18.830514907836914,
      "learning_rate": 5.94e-06,
      "loss": 1.4059,
      "step": 300
    },
    {
      "epoch": 0.20537124802527645,
      "grad_norm": 19.78591537475586,
      "learning_rate": 6.440000000000001e-06,
      "loss": 1.386,
      "step": 325
    },
    {
      "epoch": 0.2211690363349131,
      "grad_norm": 19.39731788635254,
      "learning_rate": 6.9400000000000005e-06,
      "loss": 1.3143,
      "step": 350
    },
    {
      "epoch": 0.23696682464454977,
      "grad_norm": 20.41983985900879,
      "learning_rate": 7.440000000000001e-06,
      "loss": 1.3208,
      "step": 375
    },
    {
      "epoch": 0.2527646129541864,
      "grad_norm": 19.726163864135742,
      "learning_rate": 7.94e-06,
      "loss": 1.2967,
      "step": 400
    },
    {
      "epoch": 0.2685624012638231,
      "grad_norm": 19.085514068603516,
      "learning_rate": 8.44e-06,
      "loss": 1.2114,
      "step": 425
    },
    {
      "epoch": 0.2843601895734597,
      "grad_norm": 17.482362747192383,
      "learning_rate": 8.94e-06,
      "loss": 1.2181,
      "step": 450
    },
    {
      "epoch": 0.3001579778830964,
      "grad_norm": 20.98807716369629,
      "learning_rate": 9.440000000000001e-06,
      "loss": 1.1581,
      "step": 475
    },
    {
      "epoch": 0.315955766192733,
      "grad_norm": 17.159069061279297,
      "learning_rate": 9.940000000000001e-06,
      "loss": 1.1218,
      "step": 500
    },
    {
      "epoch": 0.33175355450236965,
      "grad_norm": 16.87204933166504,
      "learning_rate": 9.853333333333334e-06,
      "loss": 1.1329,
      "step": 525
    },
    {
      "epoch": 0.34755134281200634,
      "grad_norm": 17.013330459594727,
      "learning_rate": 9.686666666666668e-06,
      "loss": 1.0566,
      "step": 550
    },
    {
      "epoch": 0.36334913112164297,
      "grad_norm": 16.366235733032227,
      "learning_rate": 9.52e-06,
      "loss": 1.0501,
      "step": 575
    },
    {
      "epoch": 0.3791469194312796,
      "grad_norm": 16.095335006713867,
      "learning_rate": 9.353333333333334e-06,
      "loss": 1.0634,
      "step": 600
    },
    {
      "epoch": 0.3949447077409163,
      "grad_norm": 18.551029205322266,
      "learning_rate": 9.186666666666666e-06,
      "loss": 1.0138,
      "step": 625
    },
    {
      "epoch": 0.4107424960505529,
      "grad_norm": 15.467816352844238,
      "learning_rate": 9.020000000000002e-06,
      "loss": 1.0199,
      "step": 650
    },
    {
      "epoch": 0.4265402843601896,
      "grad_norm": 18.306955337524414,
      "learning_rate": 8.853333333333334e-06,
      "loss": 1.0209,
      "step": 675
    },
    {
      "epoch": 0.4423380726698262,
      "grad_norm": 16.152812957763672,
      "learning_rate": 8.686666666666668e-06,
      "loss": 0.9889,
      "step": 700
    },
    {
      "epoch": 0.45813586097946285,
      "grad_norm": 16.533315658569336,
      "learning_rate": 8.52e-06,
      "loss": 0.9622,
      "step": 725
    },
    {
      "epoch": 0.47393364928909953,
      "grad_norm": 16.151216506958008,
      "learning_rate": 8.353333333333335e-06,
      "loss": 0.9555,
      "step": 750
    },
    {
      "epoch": 0.48973143759873616,
      "grad_norm": 16.503087997436523,
      "learning_rate": 8.186666666666667e-06,
      "loss": 0.9833,
      "step": 775
    },
    {
      "epoch": 0.5055292259083728,
      "grad_norm": 18.59416961669922,
      "learning_rate": 8.020000000000001e-06,
      "loss": 0.9451,
      "step": 800
    },
    {
      "epoch": 0.5213270142180095,
      "grad_norm": 17.992612838745117,
      "learning_rate": 7.853333333333333e-06,
      "loss": 0.9003,
      "step": 825
    },
    {
      "epoch": 0.5371248025276462,
      "grad_norm": 16.3101806640625,
      "learning_rate": 7.686666666666667e-06,
      "loss": 0.9197,
      "step": 850
    },
    {
      "epoch": 0.5529225908372828,
      "grad_norm": 17.981529235839844,
      "learning_rate": 7.520000000000001e-06,
      "loss": 0.8954,
      "step": 875
    },
    {
      "epoch": 0.5687203791469194,
      "grad_norm": 15.544134140014648,
      "learning_rate": 7.353333333333334e-06,
      "loss": 0.9083,
      "step": 900
    },
    {
      "epoch": 0.584518167456556,
      "grad_norm": 16.51857566833496,
      "learning_rate": 7.186666666666668e-06,
      "loss": 0.87,
      "step": 925
    },
    {
      "epoch": 0.6003159557661928,
      "grad_norm": 15.2325439453125,
      "learning_rate": 7.0200000000000006e-06,
      "loss": 0.8907,
      "step": 950
    },
    {
      "epoch": 0.6161137440758294,
      "grad_norm": 15.995855331420898,
      "learning_rate": 6.853333333333334e-06,
      "loss": 0.9026,
      "step": 975
    },
    {
      "epoch": 0.631911532385466,
      "grad_norm": 16.089975357055664,
      "learning_rate": 6.6866666666666665e-06,
      "loss": 0.86,
      "step": 1000
    },
    {
      "epoch": 0.631911532385466,
      "eval_loss": 0.9047765135765076,
      "eval_runtime": 642.0774,
      "eval_samples_per_second": 6.076,
      "eval_steps_per_second": 0.38,
      "eval_wer": 0.5978218873756399,
      "step": 1000
    },
    {
      "epoch": 0.6477093206951027,
      "grad_norm": 15.475512504577637,
      "learning_rate": 6.520000000000001e-06,
      "loss": 0.8655,
      "step": 1025
    },
    {
      "epoch": 0.6635071090047393,
      "grad_norm": 17.087614059448242,
      "learning_rate": 6.353333333333333e-06,
      "loss": 0.8498,
      "step": 1050
    },
    {
      "epoch": 0.6793048973143759,
      "grad_norm": 15.394526481628418,
      "learning_rate": 6.186666666666668e-06,
      "loss": 0.8618,
      "step": 1075
    },
    {
      "epoch": 0.6951026856240127,
      "grad_norm": 16.02501106262207,
      "learning_rate": 6.02e-06,
      "loss": 0.8323,
      "step": 1100
    },
    {
      "epoch": 0.7109004739336493,
      "grad_norm": 16.395601272583008,
      "learning_rate": 5.853333333333335e-06,
      "loss": 0.8695,
      "step": 1125
    },
    {
      "epoch": 0.7266982622432859,
      "grad_norm": 14.254459381103516,
      "learning_rate": 5.686666666666667e-06,
      "loss": 0.8349,
      "step": 1150
    },
    {
      "epoch": 0.7424960505529226,
      "grad_norm": 14.784615516662598,
      "learning_rate": 5.5200000000000005e-06,
      "loss": 0.83,
      "step": 1175
    },
    {
      "epoch": 0.7582938388625592,
      "grad_norm": 14.301170349121094,
      "learning_rate": 5.3533333333333335e-06,
      "loss": 0.8208,
      "step": 1200
    },
    {
      "epoch": 0.7740916271721959,
      "grad_norm": 15.711307525634766,
      "learning_rate": 5.186666666666667e-06,
      "loss": 0.834,
      "step": 1225
    },
    {
      "epoch": 0.7898894154818326,
      "grad_norm": 16.111242294311523,
      "learning_rate": 5.02e-06,
      "loss": 0.8367,
      "step": 1250
    },
    {
      "epoch": 0.8056872037914692,
      "grad_norm": 14.488164901733398,
      "learning_rate": 4.853333333333334e-06,
      "loss": 0.8206,
      "step": 1275
    },
    {
      "epoch": 0.8214849921011058,
      "grad_norm": 15.93684196472168,
      "learning_rate": 4.686666666666667e-06,
      "loss": 0.7844,
      "step": 1300
    },
    {
      "epoch": 0.8372827804107424,
      "grad_norm": 15.021976470947266,
      "learning_rate": 4.520000000000001e-06,
      "loss": 0.8104,
      "step": 1325
    },
    {
      "epoch": 0.8530805687203792,
      "grad_norm": 17.250614166259766,
      "learning_rate": 4.353333333333334e-06,
      "loss": 0.8138,
      "step": 1350
    },
    {
      "epoch": 0.8688783570300158,
      "grad_norm": 17.35563087463379,
      "learning_rate": 4.1866666666666675e-06,
      "loss": 0.7968,
      "step": 1375
    },
    {
      "epoch": 0.8846761453396524,
      "grad_norm": 16.59588623046875,
      "learning_rate": 4.0200000000000005e-06,
      "loss": 0.7904,
      "step": 1400
    },
    {
      "epoch": 0.9004739336492891,
      "grad_norm": 14.530390739440918,
      "learning_rate": 3.853333333333334e-06,
      "loss": 0.7922,
      "step": 1425
    },
    {
      "epoch": 0.9162717219589257,
      "grad_norm": 16.025850296020508,
      "learning_rate": 3.686666666666667e-06,
      "loss": 0.7811,
      "step": 1450
    },
    {
      "epoch": 0.9320695102685624,
      "grad_norm": 16.774017333984375,
      "learning_rate": 3.52e-06,
      "loss": 0.8197,
      "step": 1475
    },
    {
      "epoch": 0.9478672985781991,
      "grad_norm": 16.73988914489746,
      "learning_rate": 3.3533333333333336e-06,
      "loss": 0.7817,
      "step": 1500
    },
    {
      "epoch": 0.9636650868878357,
      "grad_norm": 16.070240020751953,
      "learning_rate": 3.186666666666667e-06,
      "loss": 0.7592,
      "step": 1525
    },
    {
      "epoch": 0.9794628751974723,
      "grad_norm": 15.3619966506958,
      "learning_rate": 3.0200000000000003e-06,
      "loss": 0.7874,
      "step": 1550
    },
    {
      "epoch": 0.995260663507109,
      "grad_norm": 15.880134582519531,
      "learning_rate": 2.8533333333333337e-06,
      "loss": 0.7664,
      "step": 1575
    },
    {
      "epoch": 1.0110584518167456,
      "grad_norm": 14.766377449035645,
      "learning_rate": 2.686666666666667e-06,
      "loss": 0.7161,
      "step": 1600
    },
    {
      "epoch": 1.0268562401263823,
      "grad_norm": 14.066420555114746,
      "learning_rate": 2.52e-06,
      "loss": 0.698,
      "step": 1625
    },
    {
      "epoch": 1.042654028436019,
      "grad_norm": 15.264778137207031,
      "learning_rate": 2.3533333333333334e-06,
      "loss": 0.6944,
      "step": 1650
    },
    {
      "epoch": 1.0584518167456556,
      "grad_norm": 15.829083442687988,
      "learning_rate": 2.1866666666666668e-06,
      "loss": 0.6755,
      "step": 1675
    },
    {
      "epoch": 1.0742496050552923,
      "grad_norm": 16.2938289642334,
      "learning_rate": 2.02e-06,
      "loss": 0.7162,
      "step": 1700
    },
    {
      "epoch": 1.0900473933649288,
      "grad_norm": 14.18964672088623,
      "learning_rate": 1.8533333333333333e-06,
      "loss": 0.6773,
      "step": 1725
    },
    {
      "epoch": 1.1058451816745656,
      "grad_norm": 13.311141967773438,
      "learning_rate": 1.6866666666666667e-06,
      "loss": 0.6835,
      "step": 1750
    },
    {
      "epoch": 1.1216429699842023,
      "grad_norm": 13.857542991638184,
      "learning_rate": 1.52e-06,
      "loss": 0.6995,
      "step": 1775
    },
    {
      "epoch": 1.1374407582938388,
      "grad_norm": 14.40538501739502,
      "learning_rate": 1.3533333333333334e-06,
      "loss": 0.705,
      "step": 1800
    },
    {
      "epoch": 1.1532385466034756,
      "grad_norm": 14.70490837097168,
      "learning_rate": 1.1866666666666668e-06,
      "loss": 0.6889,
      "step": 1825
    },
    {
      "epoch": 1.169036334913112,
      "grad_norm": 15.341684341430664,
      "learning_rate": 1.02e-06,
      "loss": 0.6935,
      "step": 1850
    },
    {
      "epoch": 1.1848341232227488,
      "grad_norm": 15.82376766204834,
      "learning_rate": 8.533333333333334e-07,
      "loss": 0.6972,
      "step": 1875
    },
    {
      "epoch": 1.2006319115323856,
      "grad_norm": 15.344350814819336,
      "learning_rate": 6.866666666666667e-07,
      "loss": 0.6755,
      "step": 1900
    },
    {
      "epoch": 1.216429699842022,
      "grad_norm": 14.48157787322998,
      "learning_rate": 5.2e-07,
      "loss": 0.6746,
      "step": 1925
    },
    {
      "epoch": 1.2322274881516588,
      "grad_norm": 15.609822273254395,
      "learning_rate": 3.533333333333334e-07,
      "loss": 0.7027,
      "step": 1950
    },
    {
      "epoch": 1.2480252764612954,
      "grad_norm": 14.66109848022461,
      "learning_rate": 1.866666666666667e-07,
      "loss": 0.7034,
      "step": 1975
    },
    {
      "epoch": 1.263823064770932,
      "grad_norm": 14.325251579284668,
      "learning_rate": 2e-08,
      "loss": 0.6944,
      "step": 2000
    },
    {
      "epoch": 1.263823064770932,
      "eval_loss": 0.8038402795791626,
      "eval_runtime": 452.3801,
      "eval_samples_per_second": 8.623,
      "eval_steps_per_second": 0.539,
      "eval_wer": 0.5420651019028301,
      "step": 2000
    },
    {
      "epoch": 1.263823064770932,
      "step": 2000,
      "total_flos": 4.15103975424e+18,
      "train_loss": 1.0420200901031493,
      "train_runtime": 9413.1109,
      "train_samples_per_second": 6.799,
      "train_steps_per_second": 0.212
    }
  ],
  "logging_steps": 25,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 4.15103975424e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}