min_alpha=0.00025, min_count=1, dm=1, epoch=max_epochs, workers=multiprocessing.cpu_count()) model.build_vocab([x for x in tqdm_notebook(tagged_data)]) for epoch in tqdm_notebook(range(max_epochs)): model.train(tagged_data, total_examples=model.corpus_count, epochs=model.iter) # decrease the learning rate model.alpha -= 0.0002 # fix the learning rate, no decay model.min_alpha = model.alpha model.save("d2v.model") print("Model Saved") # In[376]: tagged_data = pd.DataFrame( TaggedDocument(words=word_tokenize(i.lower()), tags=[str(_d)]) for i, _d in zip(classic_raw.values.ravel(), encoded_label_classic)) # In[377]: y_train, X_train = vec_for_learning(model, tagged_data) # In[378]: