luoyangen

loss nan occurs

1

I trained bert-han on ag-news following instructs, loss became nan after 45600 step. 

gpu out of memory

8

I just ran the example NMT, the data used was automatic downloaded by prepare_data.py while using gpu(GTX 850M, 2G gpu mem), only after 5 iterations, then ran out of memory....

train failed, attributeError: __exit__

5

while using the command adagram-train input output, it comes to a error that in the learn.py line 30 with ThreadPool(processes=n_workers) as pool: attributeError: __exit__ i am wondering if it's my...

embedding evaluate dataset

1

Hi, where can i find the dataset for embedding evaluation~ thx!

add metadata in save and load procedure