cc360 issues

Repositories
Issues
Comments

Results 3 issues of


                                            cc360

请问能否提供数据来源，想了解数据的背景和含义？

There are 39000 words in my vocab.txt, but the model vocab_size is set to 50000. In this case, how does the embedded weight of 50000 * 768 output correspond to my 39000 words, is simply the first 39000? thanks

Why is my training rusult (log loss) is always 0

Creating validation dataset of 0.01 of training for adaptive regularization -- Epoch 1 Training MSE: nan -- Epoch 2 Training MSE: nan -- Epoch 3 Training MSE: nan -- Epoch...