Junkang Wu
Junkang Wu
我修改这个参数没有效果，请问train_neg_sample_args['sample_num']这个参数有在什么位置被调用吗？我查询代码文件没找到具体位置。
Thanks a lot, I understand your idea now!
@rusty1s By the way, I find it difficult to compute `alpha` and `beta` at the same time. If I filter `index` via `edge_type`, that is I focus on the subgraph...
- cool, In `#Compute beta based on cur_index` for relational type `i`, by using `torch.where` to fill the values into the specific indices in order to form a complete matrix....
Thanks a lot, I will have a try. It seems that indeed a bit tricky to compute.
Thank a lot for your patience. I have tried a trick and address it. The main idea is to control the index in order to using softmax function. We just...
> > Thank a lot for your patience. I have tried a trick and address it. The main idea is to control the index in order to using softmax function....
> Just to record some information about this error. datasets==2.14.5, transformers==4.36.2, pyarrow==10.0.0 will need this copy(copied the "exact_match" directory from evaluate module to ./lm-evaluation-harness/) but latter I encountered : `lib/python3.8/site-packages/evaluate/module.py",...
> Hi, even though I am not an author I think I can still answer your questions: > > * You can find the answers to this question on page...
@angelahzyuan Your configuration for the training epochs appears to be somewhat disorganized. Within your `configs/config_iter1.yaml` file, I observe the `num_train_epochs` parameter is set to 3, yet in conversation you mentioned...