{
  "best_metric": 6.2487983080176885,
  "best_model_checkpoint": "./whisper-small-accented-zh/checkpoint-1000",
  "epoch": 1.639344262295082,
  "eval_steps": 1000,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.040983606557377046,
      "grad_norm": 12.423908233642578,
      "learning_rate": 4.4e-07,
      "loss": 0.8187,
      "step": 25
    },
    {
      "epoch": 0.08196721311475409,
      "grad_norm": 8.58937931060791,
      "learning_rate": 9.400000000000001e-07,
      "loss": 0.7215,
      "step": 50
    },
    {
      "epoch": 0.12295081967213115,
      "grad_norm": 7.652582168579102,
      "learning_rate": 1.44e-06,
      "loss": 0.5298,
      "step": 75
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 6.042815208435059,
      "learning_rate": 1.94e-06,
      "loss": 0.2638,
      "step": 100
    },
    {
      "epoch": 0.20491803278688525,
      "grad_norm": 5.032693386077881,
      "learning_rate": 2.4400000000000004e-06,
      "loss": 0.2174,
      "step": 125
    },
    {
      "epoch": 0.2459016393442623,
      "grad_norm": 4.777662754058838,
      "learning_rate": 2.9400000000000002e-06,
      "loss": 0.2203,
      "step": 150
    },
    {
      "epoch": 0.28688524590163933,
      "grad_norm": 5.7645978927612305,
      "learning_rate": 3.44e-06,
      "loss": 0.2071,
      "step": 175
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 4.543417930603027,
      "learning_rate": 3.94e-06,
      "loss": 0.198,
      "step": 200
    },
    {
      "epoch": 0.36885245901639346,
      "grad_norm": 4.255733489990234,
      "learning_rate": 4.440000000000001e-06,
      "loss": 0.1925,
      "step": 225
    },
    {
      "epoch": 0.4098360655737705,
      "grad_norm": 3.3336269855499268,
      "learning_rate": 4.94e-06,
      "loss": 0.1919,
      "step": 250
    },
    {
      "epoch": 0.45081967213114754,
      "grad_norm": 4.648979663848877,
      "learning_rate": 5.4400000000000004e-06,
      "loss": 0.1738,
      "step": 275
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 5.091792106628418,
      "learning_rate": 5.94e-06,
      "loss": 0.1663,
      "step": 300
    },
    {
      "epoch": 0.5327868852459017,
      "grad_norm": 3.3704090118408203,
      "learning_rate": 6.440000000000001e-06,
      "loss": 0.1866,
      "step": 325
    },
    {
      "epoch": 0.5737704918032787,
      "grad_norm": 3.840672254562378,
      "learning_rate": 6.9400000000000005e-06,
      "loss": 0.1843,
      "step": 350
    },
    {
      "epoch": 0.6147540983606558,
      "grad_norm": 5.291604995727539,
      "learning_rate": 7.440000000000001e-06,
      "loss": 0.1823,
      "step": 375
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 4.463294506072998,
      "learning_rate": 7.94e-06,
      "loss": 0.1646,
      "step": 400
    },
    {
      "epoch": 0.6967213114754098,
      "grad_norm": 5.233398914337158,
      "learning_rate": 8.44e-06,
      "loss": 0.1759,
      "step": 425
    },
    {
      "epoch": 0.7377049180327869,
      "grad_norm": 4.283503532409668,
      "learning_rate": 8.94e-06,
      "loss": 0.1638,
      "step": 450
    },
    {
      "epoch": 0.7786885245901639,
      "grad_norm": 4.230199337005615,
      "learning_rate": 9.440000000000001e-06,
      "loss": 0.164,
      "step": 475
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 4.199690341949463,
      "learning_rate": 9.940000000000001e-06,
      "loss": 0.1609,
      "step": 500
    },
    {
      "epoch": 0.860655737704918,
      "grad_norm": 3.917048215866089,
      "learning_rate": 9.834586466165415e-06,
      "loss": 0.1542,
      "step": 525
    },
    {
      "epoch": 0.9016393442622951,
      "grad_norm": 4.927728652954102,
      "learning_rate": 9.646616541353384e-06,
      "loss": 0.1598,
      "step": 550
    },
    {
      "epoch": 0.9426229508196722,
      "grad_norm": 4.517211437225342,
      "learning_rate": 9.458646616541354e-06,
      "loss": 0.1662,
      "step": 575
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 3.689638376235962,
      "learning_rate": 9.270676691729324e-06,
      "loss": 0.1572,
      "step": 600
    },
    {
      "epoch": 1.0245901639344261,
      "grad_norm": 2.320606231689453,
      "learning_rate": 9.082706766917295e-06,
      "loss": 0.1245,
      "step": 625
    },
    {
      "epoch": 1.0655737704918034,
      "grad_norm": 3.2085626125335693,
      "learning_rate": 8.894736842105264e-06,
      "loss": 0.0852,
      "step": 650
    },
    {
      "epoch": 1.1065573770491803,
      "grad_norm": 3.1523311138153076,
      "learning_rate": 8.706766917293234e-06,
      "loss": 0.0875,
      "step": 675
    },
    {
      "epoch": 1.1475409836065573,
      "grad_norm": 3.194944143295288,
      "learning_rate": 8.518796992481204e-06,
      "loss": 0.0893,
      "step": 700
    },
    {
      "epoch": 1.1885245901639343,
      "grad_norm": 3.3109562397003174,
      "learning_rate": 8.330827067669175e-06,
      "loss": 0.0834,
      "step": 725
    },
    {
      "epoch": 1.2295081967213115,
      "grad_norm": 3.2149627208709717,
      "learning_rate": 8.142857142857143e-06,
      "loss": 0.0823,
      "step": 750
    },
    {
      "epoch": 1.2704918032786885,
      "grad_norm": 3.485633134841919,
      "learning_rate": 7.954887218045114e-06,
      "loss": 0.0786,
      "step": 775
    },
    {
      "epoch": 1.3114754098360657,
      "grad_norm": 3.9137911796569824,
      "learning_rate": 7.766917293233084e-06,
      "loss": 0.0899,
      "step": 800
    },
    {
      "epoch": 1.3524590163934427,
      "grad_norm": 3.738978385925293,
      "learning_rate": 7.578947368421054e-06,
      "loss": 0.0779,
      "step": 825
    },
    {
      "epoch": 1.3934426229508197,
      "grad_norm": 3.3302817344665527,
      "learning_rate": 7.390977443609023e-06,
      "loss": 0.0887,
      "step": 850
    },
    {
      "epoch": 1.4344262295081966,
      "grad_norm": 2.2804222106933594,
      "learning_rate": 7.203007518796993e-06,
      "loss": 0.0847,
      "step": 875
    },
    {
      "epoch": 1.4754098360655736,
      "grad_norm": 4.204668998718262,
      "learning_rate": 7.015037593984964e-06,
      "loss": 0.0951,
      "step": 900
    },
    {
      "epoch": 1.5163934426229508,
      "grad_norm": 3.1958775520324707,
      "learning_rate": 6.827067669172933e-06,
      "loss": 0.0973,
      "step": 925
    },
    {
      "epoch": 1.5573770491803278,
      "grad_norm": 3.041691303253174,
      "learning_rate": 6.639097744360903e-06,
      "loss": 0.0851,
      "step": 950
    },
    {
      "epoch": 1.598360655737705,
      "grad_norm": 3.4011526107788086,
      "learning_rate": 6.4511278195488724e-06,
      "loss": 0.0925,
      "step": 975
    },
    {
      "epoch": 1.639344262295082,
      "grad_norm": 3.0124940872192383,
      "learning_rate": 6.263157894736842e-06,
      "loss": 0.0727,
      "step": 1000
    },
    {
      "epoch": 1.639344262295082,
      "eval_loss": 0.15620099008083344,
      "eval_runtime": 878.7882,
      "eval_samples_per_second": 2.774,
      "eval_steps_per_second": 0.174,
      "eval_wer": 6.2487983080176885,
      "step": 1000
    }
  ],
  "logging_steps": 25,
  "max_steps": 1830,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.61419196571648e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}