Open jason022085 opened 2 years ago
If best_loss is nan in trial#1, then the best_loss_so_far will not update when best_loss is normal in the later trial
Code for reproducing the bug:
automodel = ak.TimeseriesForecaster( lookback=1, predict_from=1, predict_until=None, max_trials=max_trials, max_model_size = 10**8, tuner='bayesian', metrics = metrics, objective="val_loss", overwrite=True, directory = './', project_name = "DL") cb_list = [ keras.callbacks.CSVLogger("./history.csv", separator=',', append=True), keras.callbacks.TerminateOnNaN()] automodel.fit(x=x_train, y=y_train, validation_data = (x_val, y_val), batch_size=1, epochs=100, callbacks = cb_list)
Data used by the code (only show 5 features):
Bug Description
If best_loss is nan in trial#1, then the best_loss_so_far will not update when best_loss is normal in the later trial
Bug Reproduction
Code for reproducing the bug:
Data used by the code (only show 5 features):