C comments

Results 18 comments of

Unable to reproduce the best result (F1: 0.58) on Weibo datasets?

@LeeSureman Pls. Look forward to your reply.

冒昧請問一下這樣是有在訓練嗎?如果有，為何GPU資源沒有使用到呢?

您可以先看看win上的torch能不能用cuda https://stackoverflow.com/questions/48152674/how-to-check-if-pytorch-is-using-the-gpu 再看看参数传的对不对（main里面的arg print打印靠前。也就是说print之后可能也有arg变化）

Minus sign in front of leaky relu

Hi @sh0416 , could you give a modification of the code?

My deepspeed code is very slow

👀

Is this model only works for English texts. Long texts will be truncated to at most 512 tokens? [E5: Text Embeddings by Weakly-Supervised Contrastive Pre-training]

So looking forward to the release of multilingual E5!! 👀

[Question] Implementation details of image regression loss

👀

I couldn't find any measure of query difficulty in the Spider dataset

👀

Run multiple trials on a single GPU

👀

Incorrect batch progress saved in checkpoint at every_n_train_steps

Same problem. Hope to see an appropriate solution.