训练期间损失没有减少（Word2Vec、Gensim）

哪些情况会造成损失model.get_latest_training_loss()每个时期都会增加？

用于训练的代码：

class EpochSaver(CallbackAny2Vec):
    '''Callback to save model after each epoch and show training parameters '''

    def __init__(self, savedir):
        self.savedir = savedir
        self.epoch = 0

        os.makedirs(self.savedir, exist_ok=True)

    def on_epoch_end(self, model):
        savepath = os.path.join(self.savedir, "model_neg{}_epoch.gz".format(self.epoch))
        model.save(savepath)
        print(
            "Epoch saved: {}".format(self.epoch + 1),
            "Start next epoch ... ", sep="\n"
            )
        if os.path.isfile(os.path.join(self.savedir, "model_neg{}_epoch.gz".format(self.epoch - 1))):
            print("Previous model deleted ")
            os.remove(os.path.join(self.savedir, "model_neg{}_epoch.gz".format(self.epoch - 1))) 
        self.epoch += 1
        print("Model loss:", model.get_latest_training_loss())

    def train():

        ### Initialize model ###
        print("Start training Word2Vec model")

        workers = multiprocessing.cpu_count()/2

        model = Word2Vec(
            DocIter(),
            size=300, alpha=0.03, min_alpha=0.00025, iter=20,
            min_count=10, hs=0, negative=10, workers=workers,
            window=10, callbacks=[EpochSaver("./checkpoints")], 
            compute_loss=True
    )     

Output:

历元（1 到 20）的损失：

Model loss: 745896.8125
Model loss: 1403872.0
Model loss: 2022238.875
Model loss: 2552509.0
Model loss: 3065454.0
Model loss: 3549122.0
Model loss: 4096209.75
Model loss: 4615430.0
Model loss: 5103492.5
Model loss: 5570137.5
Model loss: 5955891.0
Model loss: 6395258.0
Model loss: 6845765.0
Model loss: 7260698.5
Model loss: 7712688.0
Model loss: 8144109.5
Model loss: 8542560.0
Model loss: 8903244.0
Model loss: 9280568.0
Model loss: 9676936.0

我究竟做错了什么？

语言 阿拉伯语。 作为 DocIter 的输入 - 带有标记的列表。

在 gensim 3.6.0 之前，报告的损失值可能不是很明智，仅将每次调用的计数重置为train()，而不是每个内部纪元。此问题即将进行一些修复：

https://github.com/RaRe-Technologies/gensim/pull/2135

与此同时，不同之处之前的值和最新的值之间可能更有意义。在这种情况下，您的数据表明第一个时期的总损失为 745896，而最后一个时期的损失总数为 (9676936-9280568=) 396,368 – 这可能表明了所希望的进展。