{
  "best_metric": 265.17816869643667,
  "best_model_checkpoint": "/kaggle/working/whisper-small-zh_chinese/checkpoint-100",
  "epoch": 3.225806451612903,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4032258064516129,
      "grad_norm": 21.932130813598633,
      "learning_rate": 4.600000000000001e-06,
      "loss": 3.5703,
      "step": 25
    },
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 21.00741958618164,
      "learning_rate": 9.600000000000001e-06,
      "loss": 3.4342,
      "step": 50
    },
    {
      "epoch": 0.8064516129032258,
      "eval_cer": 275.1465944970681,
      "eval_loss": 4.133521556854248,
      "eval_runtime": 108.8146,
      "eval_samples_per_second": 0.919,
      "eval_steps_per_second": 0.119,
      "step": 50
    },
    {
      "epoch": 1.2096774193548387,
      "grad_norm": 21.135292053222656,
      "learning_rate": 8.533333333333335e-06,
      "loss": 3.3497,
      "step": 75
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 21.045244216918945,
      "learning_rate": 6.866666666666667e-06,
      "loss": 3.0912,
      "step": 100
    },
    {
      "epoch": 1.6129032258064515,
      "eval_cer": 265.17816869643667,
      "eval_loss": 4.106583595275879,
      "eval_runtime": 97.0216,
      "eval_samples_per_second": 1.031,
      "eval_steps_per_second": 0.134,
      "step": 100
    },
    {
      "epoch": 2.0161290322580645,
      "grad_norm": 20.702259063720703,
      "learning_rate": 5.2e-06,
      "loss": 3.1659,
      "step": 125
    },
    {
      "epoch": 2.4193548387096775,
      "grad_norm": 26.67952537536621,
      "learning_rate": 3.5333333333333335e-06,
      "loss": 2.7991,
      "step": 150
    },
    {
      "epoch": 2.4193548387096775,
      "eval_cer": 318.1326116373478,
      "eval_loss": 4.060230255126953,
      "eval_runtime": 102.4275,
      "eval_samples_per_second": 0.976,
      "eval_steps_per_second": 0.127,
      "step": 150
    },
    {
      "epoch": 2.8225806451612905,
      "grad_norm": 24.625123977661133,
      "learning_rate": 1.8666666666666669e-06,
      "loss": 2.8228,
      "step": 175
    },
    {
      "epoch": 3.225806451612903,
      "grad_norm": 17.782535552978516,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.6758,
      "step": 200
    },
    {
      "epoch": 3.225806451612903,
      "eval_cer": 736.0396932792061,
      "eval_loss": 4.034571170806885,
      "eval_runtime": 123.6186,
      "eval_samples_per_second": 0.809,
      "eval_steps_per_second": 0.105,
      "step": 200
    },
    {
      "epoch": 3.225806451612903,
      "step": 200,
      "total_flos": 1.2824839544832e+18,
      "train_loss": 3.1136483764648437,
      "train_runtime": 2250.2712,
      "train_samples_per_second": 1.422,
      "train_steps_per_second": 0.089
    }
  ],
  "logging_steps": 25,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2824839544832e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}