{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.828854314002829,
  "eval_steps": 1000,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03536067892503536,
      "grad_norm": 30.994422912597656,
      "learning_rate": 4.6000000000000004e-07,
      "loss": 2.5424,
      "step": 25
    },
    {
      "epoch": 0.07072135785007072,
      "grad_norm": 28.130775451660156,
      "learning_rate": 9.600000000000001e-07,
      "loss": 2.3297,
      "step": 50
    },
    {
      "epoch": 0.10608203677510608,
      "grad_norm": 23.87168312072754,
      "learning_rate": 1.46e-06,
      "loss": 2.0791,
      "step": 75
    },
    {
      "epoch": 0.14144271570014144,
      "grad_norm": 22.275480270385742,
      "learning_rate": 1.9600000000000003e-06,
      "loss": 1.8166,
      "step": 100
    },
    {
      "epoch": 0.1768033946251768,
      "grad_norm": 20.288251876831055,
      "learning_rate": 2.46e-06,
      "loss": 1.6861,
      "step": 125
    },
    {
      "epoch": 0.21216407355021216,
      "grad_norm": 19.130552291870117,
      "learning_rate": 2.96e-06,
      "loss": 1.5617,
      "step": 150
    },
    {
      "epoch": 0.24752475247524752,
      "grad_norm": 19.718809127807617,
      "learning_rate": 3.46e-06,
      "loss": 1.4696,
      "step": 175
    },
    {
      "epoch": 0.2828854314002829,
      "grad_norm": 19.25800132751465,
      "learning_rate": 3.96e-06,
      "loss": 1.4243,
      "step": 200
    },
    {
      "epoch": 0.31824611032531824,
      "grad_norm": 17.486873626708984,
      "learning_rate": 4.4600000000000005e-06,
      "loss": 1.3264,
      "step": 225
    },
    {
      "epoch": 0.3536067892503536,
      "grad_norm": 17.029237747192383,
      "learning_rate": 4.960000000000001e-06,
      "loss": 1.2738,
      "step": 250
    },
    {
      "epoch": 0.38896746817538896,
      "grad_norm": 18.300344467163086,
      "learning_rate": 5.460000000000001e-06,
      "loss": 1.188,
      "step": 275
    },
    {
      "epoch": 0.4243281471004243,
      "grad_norm": 18.427331924438477,
      "learning_rate": 5.9600000000000005e-06,
      "loss": 1.1332,
      "step": 300
    },
    {
      "epoch": 0.4596888260254597,
      "grad_norm": 17.452590942382812,
      "learning_rate": 6.460000000000001e-06,
      "loss": 1.1342,
      "step": 325
    },
    {
      "epoch": 0.49504950495049505,
      "grad_norm": 17.23073387145996,
      "learning_rate": 6.96e-06,
      "loss": 1.0711,
      "step": 350
    },
    {
      "epoch": 0.5304101838755304,
      "grad_norm": 17.96349334716797,
      "learning_rate": 7.4600000000000006e-06,
      "loss": 0.9895,
      "step": 375
    },
    {
      "epoch": 0.5657708628005658,
      "grad_norm": 18.00710105895996,
      "learning_rate": 7.960000000000002e-06,
      "loss": 0.9815,
      "step": 400
    },
    {
      "epoch": 0.6011315417256011,
      "grad_norm": 14.980706214904785,
      "learning_rate": 8.46e-06,
      "loss": 0.9336,
      "step": 425
    },
    {
      "epoch": 0.6364922206506365,
      "grad_norm": 17.89024543762207,
      "learning_rate": 8.96e-06,
      "loss": 0.9098,
      "step": 450
    },
    {
      "epoch": 0.6718528995756718,
      "grad_norm": 16.27644157409668,
      "learning_rate": 9.460000000000001e-06,
      "loss": 0.8745,
      "step": 475
    },
    {
      "epoch": 0.7072135785007072,
      "grad_norm": 16.346195220947266,
      "learning_rate": 9.960000000000001e-06,
      "loss": 0.8709,
      "step": 500
    },
    {
      "epoch": 0.7425742574257426,
      "grad_norm": 15.123006820678711,
      "learning_rate": 9.846666666666668e-06,
      "loss": 0.8402,
      "step": 525
    },
    {
      "epoch": 0.7779349363507779,
      "grad_norm": 16.96986961364746,
      "learning_rate": 9.68e-06,
      "loss": 0.8082,
      "step": 550
    },
    {
      "epoch": 0.8132956152758133,
      "grad_norm": 16.53630256652832,
      "learning_rate": 9.513333333333334e-06,
      "loss": 0.7627,
      "step": 575
    },
    {
      "epoch": 0.8486562942008486,
      "grad_norm": 16.62044906616211,
      "learning_rate": 9.346666666666666e-06,
      "loss": 0.7566,
      "step": 600
    },
    {
      "epoch": 0.884016973125884,
      "grad_norm": 14.903979301452637,
      "learning_rate": 9.180000000000002e-06,
      "loss": 0.7467,
      "step": 625
    },
    {
      "epoch": 0.9193776520509194,
      "grad_norm": 13.78823184967041,
      "learning_rate": 9.013333333333334e-06,
      "loss": 0.7248,
      "step": 650
    },
    {
      "epoch": 0.9547383309759547,
      "grad_norm": 15.028746604919434,
      "learning_rate": 8.846666666666668e-06,
      "loss": 0.7335,
      "step": 675
    },
    {
      "epoch": 0.9900990099009901,
      "grad_norm": 15.316567420959473,
      "learning_rate": 8.68e-06,
      "loss": 0.6937,
      "step": 700
    },
    {
      "epoch": 1.0254596888260255,
      "grad_norm": 14.481536865234375,
      "learning_rate": 8.513333333333335e-06,
      "loss": 0.6605,
      "step": 725
    },
    {
      "epoch": 1.0608203677510608,
      "grad_norm": 13.36230754852295,
      "learning_rate": 8.346666666666668e-06,
      "loss": 0.6326,
      "step": 750
    },
    {
      "epoch": 1.0961810466760962,
      "grad_norm": 15.339876174926758,
      "learning_rate": 8.18e-06,
      "loss": 0.5874,
      "step": 775
    },
    {
      "epoch": 1.1315417256011315,
      "grad_norm": 13.94893741607666,
      "learning_rate": 8.013333333333333e-06,
      "loss": 0.6046,
      "step": 800
    },
    {
      "epoch": 1.166902404526167,
      "grad_norm": 13.017638206481934,
      "learning_rate": 7.846666666666667e-06,
      "loss": 0.6161,
      "step": 825
    },
    {
      "epoch": 1.2022630834512023,
      "grad_norm": 13.231209754943848,
      "learning_rate": 7.680000000000001e-06,
      "loss": 0.5698,
      "step": 850
    },
    {
      "epoch": 1.2376237623762376,
      "grad_norm": 12.817441940307617,
      "learning_rate": 7.513333333333334e-06,
      "loss": 0.5713,
      "step": 875
    },
    {
      "epoch": 1.272984441301273,
      "grad_norm": 13.46290397644043,
      "learning_rate": 7.346666666666668e-06,
      "loss": 0.5654,
      "step": 900
    },
    {
      "epoch": 1.3083451202263083,
      "grad_norm": 14.10335922241211,
      "learning_rate": 7.180000000000001e-06,
      "loss": 0.573,
      "step": 925
    },
    {
      "epoch": 1.3437057991513437,
      "grad_norm": 13.611617088317871,
      "learning_rate": 7.0133333333333345e-06,
      "loss": 0.5811,
      "step": 950
    },
    {
      "epoch": 1.379066478076379,
      "grad_norm": 14.193683624267578,
      "learning_rate": 6.846666666666667e-06,
      "loss": 0.553,
      "step": 975
    },
    {
      "epoch": 1.4144271570014144,
      "grad_norm": 11.151966094970703,
      "learning_rate": 6.680000000000001e-06,
      "loss": 0.5465,
      "step": 1000
    },
    {
      "epoch": 1.4144271570014144,
      "eval_loss": 0.6222829222679138,
      "eval_runtime": 620.3275,
      "eval_samples_per_second": 8.674,
      "eval_steps_per_second": 0.543,
      "eval_wer": 0.47019762217185573,
      "step": 1000
    },
    {
      "epoch": 1.4497878359264498,
      "grad_norm": 14.845292091369629,
      "learning_rate": 6.513333333333333e-06,
      "loss": 0.5215,
      "step": 1025
    },
    {
      "epoch": 1.4851485148514851,
      "grad_norm": 14.059162139892578,
      "learning_rate": 6.346666666666668e-06,
      "loss": 0.5362,
      "step": 1050
    },
    {
      "epoch": 1.5205091937765205,
      "grad_norm": 12.1607027053833,
      "learning_rate": 6.18e-06,
      "loss": 0.5198,
      "step": 1075
    },
    {
      "epoch": 1.5558698727015559,
      "grad_norm": 14.104994773864746,
      "learning_rate": 6.013333333333335e-06,
      "loss": 0.522,
      "step": 1100
    },
    {
      "epoch": 1.5912305516265912,
      "grad_norm": 14.609585762023926,
      "learning_rate": 5.846666666666667e-06,
      "loss": 0.5456,
      "step": 1125
    },
    {
      "epoch": 1.6265912305516266,
      "grad_norm": 13.004403114318848,
      "learning_rate": 5.68e-06,
      "loss": 0.5216,
      "step": 1150
    },
    {
      "epoch": 1.661951909476662,
      "grad_norm": 13.968815803527832,
      "learning_rate": 5.513333333333334e-06,
      "loss": 0.5101,
      "step": 1175
    },
    {
      "epoch": 1.6973125884016973,
      "grad_norm": 12.793135643005371,
      "learning_rate": 5.346666666666667e-06,
      "loss": 0.5054,
      "step": 1200
    },
    {
      "epoch": 1.7326732673267327,
      "grad_norm": 12.969812393188477,
      "learning_rate": 5.18e-06,
      "loss": 0.5078,
      "step": 1225
    },
    {
      "epoch": 1.768033946251768,
      "grad_norm": 12.749104499816895,
      "learning_rate": 5.013333333333333e-06,
      "loss": 0.4944,
      "step": 1250
    },
    {
      "epoch": 1.8033946251768034,
      "grad_norm": 13.452000617980957,
      "learning_rate": 4.846666666666667e-06,
      "loss": 0.5047,
      "step": 1275
    },
    {
      "epoch": 1.8387553041018387,
      "grad_norm": 13.211859703063965,
      "learning_rate": 4.680000000000001e-06,
      "loss": 0.5024,
      "step": 1300
    },
    {
      "epoch": 1.874115983026874,
      "grad_norm": 12.375421524047852,
      "learning_rate": 4.513333333333333e-06,
      "loss": 0.4817,
      "step": 1325
    },
    {
      "epoch": 1.9094766619519095,
      "grad_norm": 13.229231834411621,
      "learning_rate": 4.346666666666667e-06,
      "loss": 0.47,
      "step": 1350
    },
    {
      "epoch": 1.9448373408769448,
      "grad_norm": 11.967358589172363,
      "learning_rate": 4.18e-06,
      "loss": 0.4717,
      "step": 1375
    },
    {
      "epoch": 1.9801980198019802,
      "grad_norm": 13.194028854370117,
      "learning_rate": 4.013333333333334e-06,
      "loss": 0.4871,
      "step": 1400
    },
    {
      "epoch": 2.0155586987270158,
      "grad_norm": 10.578360557556152,
      "learning_rate": 3.8466666666666665e-06,
      "loss": 0.4601,
      "step": 1425
    },
    {
      "epoch": 2.050919377652051,
      "grad_norm": 10.83725357055664,
      "learning_rate": 3.6800000000000003e-06,
      "loss": 0.4081,
      "step": 1450
    },
    {
      "epoch": 2.0862800565770865,
      "grad_norm": 11.61172866821289,
      "learning_rate": 3.5133333333333337e-06,
      "loss": 0.4086,
      "step": 1475
    },
    {
      "epoch": 2.1216407355021216,
      "grad_norm": 13.022510528564453,
      "learning_rate": 3.346666666666667e-06,
      "loss": 0.3962,
      "step": 1500
    },
    {
      "epoch": 2.157001414427157,
      "grad_norm": 11.560221672058105,
      "learning_rate": 3.1800000000000005e-06,
      "loss": 0.4214,
      "step": 1525
    },
    {
      "epoch": 2.1923620933521923,
      "grad_norm": 11.080381393432617,
      "learning_rate": 3.013333333333334e-06,
      "loss": 0.3891,
      "step": 1550
    },
    {
      "epoch": 2.227722772277228,
      "grad_norm": 11.685514450073242,
      "learning_rate": 2.8466666666666672e-06,
      "loss": 0.4066,
      "step": 1575
    },
    {
      "epoch": 2.263083451202263,
      "grad_norm": 10.105015754699707,
      "learning_rate": 2.68e-06,
      "loss": 0.4023,
      "step": 1600
    },
    {
      "epoch": 2.298444130127298,
      "grad_norm": 10.330554008483887,
      "learning_rate": 2.5133333333333336e-06,
      "loss": 0.3896,
      "step": 1625
    },
    {
      "epoch": 2.333804809052334,
      "grad_norm": 12.053783416748047,
      "learning_rate": 2.346666666666667e-06,
      "loss": 0.4,
      "step": 1650
    },
    {
      "epoch": 2.3691654879773694,
      "grad_norm": 11.276220321655273,
      "learning_rate": 2.1800000000000003e-06,
      "loss": 0.3984,
      "step": 1675
    },
    {
      "epoch": 2.4045261669024045,
      "grad_norm": 13.366302490234375,
      "learning_rate": 2.0133333333333337e-06,
      "loss": 0.3986,
      "step": 1700
    },
    {
      "epoch": 2.4398868458274396,
      "grad_norm": 10.583386421203613,
      "learning_rate": 1.8466666666666668e-06,
      "loss": 0.4013,
      "step": 1725
    },
    {
      "epoch": 2.4752475247524752,
      "grad_norm": 11.777633666992188,
      "learning_rate": 1.6800000000000002e-06,
      "loss": 0.4076,
      "step": 1750
    },
    {
      "epoch": 2.510608203677511,
      "grad_norm": 12.717354774475098,
      "learning_rate": 1.5133333333333334e-06,
      "loss": 0.3901,
      "step": 1775
    },
    {
      "epoch": 2.545968882602546,
      "grad_norm": 10.099494934082031,
      "learning_rate": 1.3466666666666668e-06,
      "loss": 0.3914,
      "step": 1800
    },
    {
      "epoch": 2.581329561527581,
      "grad_norm": 12.377460479736328,
      "learning_rate": 1.1800000000000001e-06,
      "loss": 0.3904,
      "step": 1825
    },
    {
      "epoch": 2.6166902404526167,
      "grad_norm": 11.621073722839355,
      "learning_rate": 1.0133333333333333e-06,
      "loss": 0.3865,
      "step": 1850
    },
    {
      "epoch": 2.6520509193776522,
      "grad_norm": 12.402543067932129,
      "learning_rate": 8.466666666666668e-07,
      "loss": 0.3993,
      "step": 1875
    },
    {
      "epoch": 2.6874115983026874,
      "grad_norm": 12.710662841796875,
      "learning_rate": 6.800000000000001e-07,
      "loss": 0.3892,
      "step": 1900
    },
    {
      "epoch": 2.7227722772277225,
      "grad_norm": 11.998794555664062,
      "learning_rate": 5.133333333333334e-07,
      "loss": 0.3725,
      "step": 1925
    },
    {
      "epoch": 2.758132956152758,
      "grad_norm": 11.460661888122559,
      "learning_rate": 3.466666666666667e-07,
      "loss": 0.3947,
      "step": 1950
    },
    {
      "epoch": 2.7934936350777937,
      "grad_norm": 10.511993408203125,
      "learning_rate": 1.8e-07,
      "loss": 0.3839,
      "step": 1975
    },
    {
      "epoch": 2.828854314002829,
      "grad_norm": 11.295842170715332,
      "learning_rate": 1.3333333333333334e-08,
      "loss": 0.3781,
      "step": 2000
    },
    {
      "epoch": 2.828854314002829,
      "eval_loss": 0.5415101647377014,
      "eval_runtime": 593.481,
      "eval_samples_per_second": 9.067,
      "eval_steps_per_second": 0.568,
      "eval_wer": 0.4117459938764961,
      "step": 2000
    },
    {
      "epoch": 2.828854314002829,
      "step": 2000,
      "total_flos": 4.14935339433984e+18,
      "train_loss": 0.729869236946106,
      "train_runtime": 7273.2114,
      "train_samples_per_second": 8.799,
      "train_steps_per_second": 0.275
    }
  ],
  "logging_steps": 25,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 4.14935339433984e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}