David Herel

I have the same problem. Attack recipe that I used is the following: `!textattack attack --recipe bert-attack --num-examples 1000 --model bert-base-uncased-mr --dataset-from-huggingface rotten_tomatoes --dataset-split test`

Same issue here.

Yeah, I think it was something similar to you. I did not play with lr, warmup and dropout, so maybe more extensive hyperparams search will get us the results?

I have same issue as @KisuYang.

Thank you for the reply! I have read and followed instructions in the FWM-README.md and I am using exactly same commands. I have also attached my log file, which is...

Thank you for the tips. However, even when I try to increase the number of epochs to 1600, I can still not get below 4.26 loss on valid. I am...

I have posted my log of eval.py, which I have run on trained PTB model. This PTB model achieves reported test perplexity after training however as I wrote eval.py aka...