{
  "best_metric": 0.167043074965477,
  "best_model_checkpoint": "output/Belle-whisper-large-v3-zh/checkpoint-100",
  "epoch": 2.9767441860465116,
  "eval_steps": 20,
  "global_step": 144,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4134366925064599,
      "grad_norm": 0.04502945393323898,
      "learning_rate": 0.0005,
      "loss": 0.277,
      "step": 20
    },
    {
      "epoch": 0.4134366925064599,
      "eval_loss": 0.25681591033935547,
      "eval_runtime": 47.889,
      "eval_samples_per_second": 3.466,
      "eval_steps_per_second": 0.439,
      "step": 20
    },
    {
      "epoch": 0.8268733850129198,
      "grad_norm": 0.1879778802394867,
      "learning_rate": 0.00041935483870967743,
      "loss": 0.2475,
      "step": 40
    },
    {
      "epoch": 0.8268733850129198,
      "eval_loss": 0.21537519991397858,
      "eval_runtime": 48.2573,
      "eval_samples_per_second": 3.44,
      "eval_steps_per_second": 0.435,
      "step": 40
    },
    {
      "epoch": 1.2403100775193798,
      "grad_norm": 0.4223547577857971,
      "learning_rate": 0.00033870967741935485,
      "loss": 0.1717,
      "step": 60
    },
    {
      "epoch": 1.2403100775193798,
      "eval_loss": 0.1794934719800949,
      "eval_runtime": 48.6009,
      "eval_samples_per_second": 3.416,
      "eval_steps_per_second": 0.432,
      "step": 60
    },
    {
      "epoch": 1.65374677002584,
      "grad_norm": 0.10938454419374466,
      "learning_rate": 0.00025806451612903227,
      "loss": 0.1786,
      "step": 80
    },
    {
      "epoch": 1.65374677002584,
      "eval_loss": 0.17136096954345703,
      "eval_runtime": 48.6822,
      "eval_samples_per_second": 3.41,
      "eval_steps_per_second": 0.431,
      "step": 80
    },
    {
      "epoch": 2.0671834625322996,
      "grad_norm": 0.1453220695257187,
      "learning_rate": 0.0001774193548387097,
      "loss": 0.1176,
      "step": 100
    },
    {
      "epoch": 2.0671834625322996,
      "eval_loss": 0.167043074965477,
      "eval_runtime": 48.823,
      "eval_samples_per_second": 3.4,
      "eval_steps_per_second": 0.43,
      "step": 100
    },
    {
      "epoch": 2.4806201550387597,
      "grad_norm": 0.244968444108963,
      "learning_rate": 9.67741935483871e-05,
      "loss": 0.1099,
      "step": 120
    },
    {
      "epoch": 2.4806201550387597,
      "eval_loss": 0.16719281673431396,
      "eval_runtime": 48.7477,
      "eval_samples_per_second": 3.405,
      "eval_steps_per_second": 0.431,
      "step": 120
    },
    {
      "epoch": 2.8940568475452197,
      "grad_norm": 0.16983452439308167,
      "learning_rate": 1.6129032258064517e-05,
      "loss": 0.0745,
      "step": 140
    },
    {
      "epoch": 2.8940568475452197,
      "eval_loss": 0.1675640493631363,
      "eval_runtime": 48.7651,
      "eval_samples_per_second": 3.404,
      "eval_steps_per_second": 0.431,
      "step": 140
    },
    {
      "epoch": 2.9767441860465116,
      "step": 144,
      "total_flos": 3.971337953476608e+18,
      "train_loss": 0.16459152557783657,
      "train_runtime": 1933.6363,
      "train_samples_per_second": 0.6,
      "train_steps_per_second": 0.074
    }
  ],
  "logging_steps": 20,
  "max_steps": 144,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.971337953476608e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}