{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.623629719853836,
  "eval_steps": 100,
  "global_step": 1900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.243605359317905,
      "grad_norm": 33.11063766479492,
      "learning_rate": 4.8844282238442824e-05,
      "loss": 10.7343,
      "step": 100
    },
    {
      "epoch": 0.243605359317905,
      "eval_loss": 4.385446548461914,
      "eval_runtime": 206.0799,
      "eval_samples_per_second": 7.992,
      "eval_steps_per_second": 1.0,
      "eval_wer": 1.0,
      "step": 100
    },
    {
      "epoch": 0.48721071863581,
      "grad_norm": 2.508547067642212,
      "learning_rate": 4.762773722627738e-05,
      "loss": 3.1325,
      "step": 200
    },
    {
      "epoch": 0.48721071863581,
      "eval_loss": 2.1581695079803467,
      "eval_runtime": 206.4525,
      "eval_samples_per_second": 7.978,
      "eval_steps_per_second": 0.998,
      "eval_wer": 0.9690996270644646,
      "step": 200
    },
    {
      "epoch": 0.730816077953715,
      "grad_norm": 1.2504737377166748,
      "learning_rate": 4.641119221411192e-05,
      "loss": 1.6166,
      "step": 300
    },
    {
      "epoch": 0.730816077953715,
      "eval_loss": 1.1347323656082153,
      "eval_runtime": 206.3117,
      "eval_samples_per_second": 7.983,
      "eval_steps_per_second": 0.998,
      "eval_wer": 0.7188184455099745,
      "step": 300
    },
    {
      "epoch": 0.97442143727162,
      "grad_norm": 1.3984403610229492,
      "learning_rate": 4.520681265206813e-05,
      "loss": 1.1808,
      "step": 400
    },
    {
      "epoch": 0.97442143727162,
      "eval_loss": 0.9792075157165527,
      "eval_runtime": 206.2345,
      "eval_samples_per_second": 7.986,
      "eval_steps_per_second": 0.999,
      "eval_wer": 0.6746581424258569,
      "step": 400
    },
    {
      "epoch": 1.2168087697929355,
      "grad_norm": 10.769020080566406,
      "learning_rate": 4.3990267639902676e-05,
      "loss": 1.0459,
      "step": 500
    },
    {
      "epoch": 1.2168087697929355,
      "eval_loss": 0.9049620032310486,
      "eval_runtime": 208.2322,
      "eval_samples_per_second": 7.909,
      "eval_steps_per_second": 0.989,
      "eval_wer": 0.6494405966968567,
      "step": 500
    },
    {
      "epoch": 1.4604141291108403,
      "grad_norm": 0.8941505551338196,
      "learning_rate": 4.277372262773723e-05,
      "loss": 1.0317,
      "step": 600
    },
    {
      "epoch": 1.4604141291108403,
      "eval_loss": 0.8543379306793213,
      "eval_runtime": 205.6459,
      "eval_samples_per_second": 8.009,
      "eval_steps_per_second": 1.002,
      "eval_wer": 0.6338128218788848,
      "step": 600
    },
    {
      "epoch": 1.7040194884287454,
      "grad_norm": 0.9768113493919373,
      "learning_rate": 4.1569343065693435e-05,
      "loss": 0.9836,
      "step": 700
    },
    {
      "epoch": 1.7040194884287454,
      "eval_loss": 0.8191400766372681,
      "eval_runtime": 207.1525,
      "eval_samples_per_second": 7.951,
      "eval_steps_per_second": 0.994,
      "eval_wer": 0.6251701888356124,
      "step": 700
    },
    {
      "epoch": 1.9476248477466505,
      "grad_norm": 0.9090480208396912,
      "learning_rate": 4.035279805352798e-05,
      "loss": 0.9567,
      "step": 800
    },
    {
      "epoch": 1.9476248477466505,
      "eval_loss": 0.7955169081687927,
      "eval_runtime": 206.8205,
      "eval_samples_per_second": 7.963,
      "eval_steps_per_second": 0.996,
      "eval_wer": 0.6124430237376428,
      "step": 800
    },
    {
      "epoch": 2.1900121802679657,
      "grad_norm": 0.6563196778297424,
      "learning_rate": 3.913625304136253e-05,
      "loss": 0.9354,
      "step": 900
    },
    {
      "epoch": 2.1900121802679657,
      "eval_loss": 0.7705180644989014,
      "eval_runtime": 206.4429,
      "eval_samples_per_second": 7.978,
      "eval_steps_per_second": 0.998,
      "eval_wer": 0.6046291363286569,
      "step": 900
    },
    {
      "epoch": 2.433617539585871,
      "grad_norm": 0.8123560547828674,
      "learning_rate": 3.791970802919708e-05,
      "loss": 0.9037,
      "step": 1000
    },
    {
      "epoch": 2.433617539585871,
      "eval_loss": 0.75263512134552,
      "eval_runtime": 206.6571,
      "eval_samples_per_second": 7.97,
      "eval_steps_per_second": 0.997,
      "eval_wer": 0.5982359557213047,
      "step": 1000
    },
    {
      "epoch": 2.677222898903776,
      "grad_norm": 0.8349791169166565,
      "learning_rate": 3.6703163017031634e-05,
      "loss": 0.901,
      "step": 1100
    },
    {
      "epoch": 2.677222898903776,
      "eval_loss": 0.7370020747184753,
      "eval_runtime": 207.9183,
      "eval_samples_per_second": 7.921,
      "eval_steps_per_second": 0.991,
      "eval_wer": 0.5959865032853845,
      "step": 1100
    },
    {
      "epoch": 2.9208282582216807,
      "grad_norm": 2.0188732147216797,
      "learning_rate": 3.549878345498784e-05,
      "loss": 0.8888,
      "step": 1200
    },
    {
      "epoch": 2.9208282582216807,
      "eval_loss": 0.7251046895980835,
      "eval_runtime": 208.4027,
      "eval_samples_per_second": 7.903,
      "eval_steps_per_second": 0.988,
      "eval_wer": 0.58781743917599,
      "step": 1200
    },
    {
      "epoch": 3.1632155907429964,
      "grad_norm": 0.4746805429458618,
      "learning_rate": 3.4282238442822386e-05,
      "loss": 0.8686,
      "step": 1300
    },
    {
      "epoch": 3.1632155907429964,
      "eval_loss": 0.7125080823898315,
      "eval_runtime": 206.121,
      "eval_samples_per_second": 7.99,
      "eval_steps_per_second": 0.999,
      "eval_wer": 0.5834369265376191,
      "step": 1300
    },
    {
      "epoch": 3.4068209500609012,
      "grad_norm": 1.0152044296264648,
      "learning_rate": 3.306569343065693e-05,
      "loss": 0.8681,
      "step": 1400
    },
    {
      "epoch": 3.4068209500609012,
      "eval_loss": 0.7029690742492676,
      "eval_runtime": 206.1729,
      "eval_samples_per_second": 7.988,
      "eval_steps_per_second": 0.999,
      "eval_wer": 0.577043745930267,
      "step": 1400
    },
    {
      "epoch": 3.6504263093788065,
      "grad_norm": 0.5681760907173157,
      "learning_rate": 3.1849148418491486e-05,
      "loss": 0.8428,
      "step": 1500
    },
    {
      "epoch": 3.6504263093788065,
      "eval_loss": 0.6939159035682678,
      "eval_runtime": 206.9126,
      "eval_samples_per_second": 7.96,
      "eval_steps_per_second": 0.996,
      "eval_wer": 0.572900017758835,
      "step": 1500
    },
    {
      "epoch": 3.8940316686967114,
      "grad_norm": 0.535625159740448,
      "learning_rate": 3.064476885644769e-05,
      "loss": 0.8372,
      "step": 1600
    },
    {
      "epoch": 3.8940316686967114,
      "eval_loss": 0.6848719716072083,
      "eval_runtime": 206.7992,
      "eval_samples_per_second": 7.964,
      "eval_steps_per_second": 0.996,
      "eval_wer": 0.5706505653229148,
      "step": 1600
    },
    {
      "epoch": 4.136419001218027,
      "grad_norm": 1.2212234735488892,
      "learning_rate": 2.942822384428224e-05,
      "loss": 0.8388,
      "step": 1700
    },
    {
      "epoch": 4.136419001218027,
      "eval_loss": 0.6779345870018005,
      "eval_runtime": 206.7198,
      "eval_samples_per_second": 7.967,
      "eval_steps_per_second": 0.997,
      "eval_wer": 0.5667436216184218,
      "step": 1700
    },
    {
      "epoch": 4.3800243605359315,
      "grad_norm": 0.515786349773407,
      "learning_rate": 2.8211678832116788e-05,
      "loss": 0.8222,
      "step": 1800
    },
    {
      "epoch": 4.3800243605359315,
      "eval_loss": 0.6726759672164917,
      "eval_runtime": 206.3937,
      "eval_samples_per_second": 7.98,
      "eval_steps_per_second": 0.998,
      "eval_wer": 0.5620671283963772,
      "step": 1800
    },
    {
      "epoch": 4.623629719853836,
      "grad_norm": 2.3206946849823,
      "learning_rate": 2.699513381995134e-05,
      "loss": 0.8289,
      "step": 1900
    },
    {
      "epoch": 4.623629719853836,
      "eval_loss": 0.6664962768554688,
      "eval_runtime": 206.3925,
      "eval_samples_per_second": 7.98,
      "eval_steps_per_second": 0.998,
      "eval_wer": 0.5570354584739241,
      "step": 1900
    }
  ],
  "logging_steps": 100,
  "max_steps": 4110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6671378469235286e+19,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}